diff --git a/polly/www/example_manual_matmul.html b/polly/www/example_manual_matmul.html
index 7e352a26802a..2636e1d60989 100644
--- a/polly/www/example_manual_matmul.html
+++ b/polly/www/example_manual_matmul.html
@@ -110,7 +110,7 @@ view-scops-only:
 <pre>
 [...]
 Printing analysis 'Polly - Create polyhedral description of Scops' for region:
-'%1 =&gt;&nbsp;%17' in function 'init_array':
+'for.cond =&gt; for.end19' in function 'init_array':
    Context:
    { [] }
    Statements {
@@ -135,7 +135,7 @@ Printing analysis 'Polly - Create polyhedral description of Scops' for region:
    }
 [...]
 Printing analysis 'Polly - Create polyhedral description of Scops' for region:
-'%1 =&gt;&nbsp;%17' in function 'main':
+'for.cond =&gt; for.end30' in function 'main':
    Context:
    { [] }
    Statements {
@@ -178,7 +178,7 @@ Printing analysis 'Polly - Create polyhedral description of Scops' for region:
 <li><h4>Show the dependences for the SCoPs</h4>
 <pre class="code">opt -basicaa -polly-dependences -analyze matmul.preopt.ll</pre>
 <pre>Printing analysis 'Polly - Calculate dependences for SCoP' for region:
-'for.cond =&gt; for.end28' in function 'init_array':
+'for.cond =&gt; for.end19' in function 'init_array':
    Must dependences:
        {  }
    May dependences:
@@ -188,7 +188,7 @@ Printing analysis 'Polly - Create polyhedral description of Scops' for region:
    May no source:
        {  }
 Printing analysis 'Polly - Calculate dependences for SCoP' for region:
-'for.cond =&gt; for.end48' in function 'main':
+'for.cond =&gt; for.end30' in function 'main':
    Must dependences:
        {  Stmt_4[i0, i1] -&gt; Stmt_6[i0, i1, 0]&nbsp;:
               i0 &gt;= 0 and i0 &lt;= 1023 and i1 &gt;= 0 and i1 &lt;= 1023;
@@ -221,8 +221,8 @@ Printing analysis 'Polly - Calculate dependences for SCoP' for region:
 Polly can export the polyhedral representation in so called jscop files. Jscop
 files contain the polyhedral representation stored in a JSON file.
 <pre class="code">opt -basicaa -polly-export-jscop matmul.preopt.ll</pre>
-<pre>Writing SCoP 'for.cond =&gt; for.end28' in function 'init_array' to './init_array___%for.cond---%for.end28.jscop'.
-Writing SCoP 'for.cond =&gt; for.end48' in function 'main' to './main___%for.cond---%for.end48.jscop'.
+<pre>Writing SCoP 'for.cond =&gt; for.end19' in function 'init_array' to './init_array___%for.cond---%for.end19.jscop'.
+Writing SCoP 'for.cond =&gt; for.end30' in function 'main' to './main___%for.cond---%for.end30.jscop'.
 </pre></li>
 
 <li><h4>Import the changed jscop files and print the updated SCoP structure
@@ -268,7 +268,7 @@ opt matmul.preopt.ll -basicaa \
 </pre>
 <pre>
 [...]
-Reading JScop '%1 =&gt; %17' in function 'main' from './main___%1---%17.jscop.interchanged'.
+Reading JScop 'for.cond =&gt; for.end30' in function 'main' from './main___%for.cond---%for.end30.jscop.interchanged+tiled'.
 [...]
 main():
 for (c2=0;c2&lt;=1535;c2++) {
@@ -295,7 +295,7 @@ opt matmul.preopt.ll -basicaa \
 </pre>
 <pre>
 [...]
-Reading JScop '%1 =&gt; %17' in function 'main' from './main___%1---%17.jscop.interchanged+tiled'.
+Reading JScop 'for.cond =&gt; for.end30' in function 'main' from './main___%for.cond---%for.end30.jscop.interchanged+tiled'.
 [...]
 main():
 for (c2=0;c2&lt;=1535;c2++) {
@@ -329,7 +329,7 @@ opt matmul.preopt.ll -basicaa \
 
 <pre>
 [...]
-Reading JScop '%1 =&gt; %17' in function 'main' from './main___%1---%17.jscop.interchanged+tiled+vector'.
+Reading JScop 'for.cond =&gt; for.end30' in function 'main' from './main___%for.cond---%for.end30.jscop.interchanged+tiled+vector'.
 [...]
 main():
 for (c2=0;c2&lt;=1535;c2++) {
@@ -369,11 +369,11 @@ opt -basicaa \
     -polly-codegen matmul.preopt.ll \
    | opt -O3 &gt; matmul.polly.interchanged.ll</pre>
 <pre>
-Reading JScop '%1 =&gt; %19' in function 'init_array' from
-    './init_array___%1---%19.jscop.interchanged'.
+Reading JScop 'for.cond =&gt; for.end19' in function 'init_array' from
+    './init_array___%for.cond---%for.end19.jscop.interchanged'.
 File could not be read: No such file or directory
-Reading JScop '%1 =&gt; %17' in function 'main' from
-    './main___%1---%17.jscop.interchanged'.
+Reading JScop 'for.cond =&gt; for.end30' in function 'main' from
+    './main___%for.cond---%for.end30.jscop.interchanged'.
 </pre>
 <pre class="code">
 opt -basicaa \
@@ -381,11 +381,11 @@ opt -basicaa \
     -polly-codegen matmul.preopt.ll \
    | opt -O3 &gt; matmul.polly.interchanged+tiled.ll</pre>
 <pre>
-Reading JScop '%1 =&gt; %19' in function 'init_array' from
-    './init_array___%1---%19.jscop.interchanged+tiled'.
+Reading JScop 'for.cond =&gt; for.end19' in function 'init_array' from
+    './init_array___%for.cond---%for.end19.jscop.interchanged+tiled'.
 File could not be read: No such file or directory
-Reading JScop '%1 =&gt; %17' in function 'main' from
-    './main___%1---%17.jscop.interchanged+tiled'.
+Reading JScop 'for.cond =&gt; for.end30' in function 'main' from
+    './main___%for.cond---%for.end30.jscop.interchanged+tiled'.
 </pre>
 <pre class="code">
 opt -basicaa \
@@ -393,11 +393,11 @@ opt -basicaa \
     -polly-codegen -polly-vectorizer=polly matmul.preopt.ll \
    | opt -O3 &gt; matmul.polly.interchanged+tiled+vector.ll</pre>
 <pre>
-Reading JScop '%1 =&gt; %19' in function 'init_array' from
-    './init_array___%1---%19.jscop.interchanged+tiled+vector'.
+Reading JScop 'for.cond =&gt; for.end19' in function 'init_array' from
+    './init_array___%for.cond---%for.end19.jscop.interchanged+tiled+vector'.
 File could not be read: No such file or directory
-Reading JScop '%1 =&gt; %17' in function 'main' from
-    './main___%1---%17.jscop.interchanged+tiled+vector'.
+Reading JScop 'for.cond =&gt; for.end30' in function 'main' from
+    './main___%for.cond---%for.end30.jscop.interchanged+tiled+vector'.
 </pre>
 <pre class="code">
 opt -basicaa \
@@ -405,11 +405,11 @@ opt -basicaa \
     -polly-codegen -polly-vectorizer=polly -enable-polly-openmp matmul.preopt.ll \
   | opt -O3 &gt; matmul.polly.interchanged+tiled+openmp.ll</pre>
 <pre>
-Reading JScop '%1 =&gt; %19' in function 'init_array' from
-    './init_array___%1---%19.jscop.interchanged+tiled+vector'.
+Reading JScop 'for.cond =&gt; for.end19' in function 'init_array' from
+    './init_array___%for.cond---%for.end19.jscop.interchanged+tiled+vector'.
 File could not be read: No such file or directory
-Reading JScop '%1 =&gt; %17' in function 'main' from
-    './main___%1---%17.jscop.interchanged+tiled+vector'.
+Reading JScop 'for.cond =&gt; for.end30' in function 'main' from
+    './main___%for.cond---%for.end30.jscop.interchanged+tiled+vector'.
 </pre>
 
 <li><h4>Create the executables</h4>
diff --git a/polly/www/experiments/matmul/init_array___%1---%19.jscop b/polly/www/experiments/matmul/init_array___%1---%19.jscop
deleted file mode 100644
index c7f9bb8c87ae..000000000000
--- a/polly/www/experiments/matmul/init_array___%1---%19.jscop
+++ /dev/null
@@ -1,21 +0,0 @@
-{
-   "context" : "{ [] }",
-   "name" : "%1 => %19",
-   "statements" : [
-      {
-         "accesses" : [
-            {
-               "kind" : "write",
-               "relation" : "{ Stmt_5[i0, i1] -> MemRef_A[1536i0 + i1] }"
-            },
-            {
-               "kind" : "write",
-               "relation" : "{ Stmt_5[i0, i1] -> MemRef_B[1536i0 + i1] }"
-            }
-         ],
-         "domain" : "{ Stmt_5[i0, i1] : i0 >= 0 and i0 <= 1535 and i1 >= 0 and i1 <= 1535 }",
-         "name" : "Stmt_5",
-         "schedule" : "{ Stmt_5[i0, i1] -> scattering[0, i0, 0, i1, 0] }"
-      }
-   ]
-}
diff --git a/polly/www/experiments/matmul/init_array___%for.cond---%for.end19.jscop b/polly/www/experiments/matmul/init_array___%for.cond---%for.end19.jscop
new file mode 100644
index 000000000000..dfd10935988a
--- /dev/null
+++ b/polly/www/experiments/matmul/init_array___%for.cond---%for.end19.jscop
@@ -0,0 +1,21 @@
+{
+   "context" : "{  :  }",
+   "name" : "for.cond => for.end19",
+   "statements" : [
+      {
+         "accesses" : [
+            {
+               "kind" : "write",
+               "relation" : "{ Stmt_for_body3[i0, i1] -> MemRef_A[1536i0 + i1] }"
+            },
+            {
+               "kind" : "write",
+               "relation" : "{ Stmt_for_body3[i0, i1] -> MemRef_B[1536i0 + i1] }"
+            }
+         ],
+         "domain" : "{ Stmt_for_body3[i0, i1] : i0 >= 0 and i0 <= 1535 and i1 >= 0 and i1 <= 1535 }",
+         "name" : "Stmt_for_body3",
+         "schedule" : "{ Stmt_for_body3[i0, i1] -> scattering[0, i0, 0, i1, 0] }"
+      }
+   ]
+}
diff --git a/polly/www/experiments/matmul/main___%1---%17.jscop b/polly/www/experiments/matmul/main___%1---%17.jscop
deleted file mode 100644
index c37839525add..000000000000
--- a/polly/www/experiments/matmul/main___%1---%17.jscop
+++ /dev/null
@@ -1,40 +0,0 @@
-{
-   "context" : "{  :  }",
-   "name" : "%1 => %17",
-   "statements" : [
-      {
-         "accesses" : [
-            {
-               "kind" : "write",
-               "relation" : "{ Stmt_4[i0, i1] -> MemRef_C[1536i0 + i1] }"
-            }
-         ],
-         "domain" : "{ Stmt_4[i0, i1] : i0 >= 0 and i0 <= 1535 and i1 >= 0 and i1 <= 1535 }",
-         "name" : "Stmt_4",
-         "schedule" : "{ Stmt_4[i0, i1] -> scattering[0, i0, 0, i1, 0, 0, 0] }"
-      },
-      {
-         "accesses" : [
-            {
-               "kind" : "read",
-               "relation" : "{ Stmt_6[i0, i1, i2] -> MemRef_C[1536i0 + i1] }"
-            },
-            {
-               "kind" : "read",
-               "relation" : "{ Stmt_6[i0, i1, i2] -> MemRef_A[1536i0 + i2] }"
-            },
-            {
-               "kind" : "read",
-               "relation" : "{ Stmt_6[i0, i1, i2] -> MemRef_B[i1 + 1536i2] }"
-            },
-            {
-               "kind" : "write",
-               "relation" : "{ Stmt_6[i0, i1, i2] -> MemRef_C[1536i0 + i1] }"
-            }
-         ],
-         "domain" : "{ Stmt_6[i0, i1, i2] : i0 >= 0 and i0 <= 1535 and i1 >= 0 and i1 <= 1535 and i2 >= 0 and i2 <= 1535 }",
-         "name" : "Stmt_6",
-         "schedule" : "{ Stmt_6[i0, i1, i2] -> scattering[0, i0, 0, i1, 1, i2, 0] }"
-      }
-   ]
-}
diff --git a/polly/www/experiments/matmul/main___%for.cond---%for.end30.jscop b/polly/www/experiments/matmul/main___%for.cond---%for.end30.jscop
new file mode 100644
index 000000000000..4d6e463a7dbc
--- /dev/null
+++ b/polly/www/experiments/matmul/main___%for.cond---%for.end30.jscop
@@ -0,0 +1,40 @@
+{
+   "context" : "{  :  }",
+   "name" : "for.cond => for.end30",
+   "statements" : [
+      {
+         "accesses" : [
+            {
+               "kind" : "write",
+               "relation" : "{ Stmt_for_body3[i0, i1] -> MemRef_C[1536i0 + i1] }"
+            }
+         ],
+         "domain" : "{ Stmt_for_body3[i0, i1] : i0 >= 0 and i0 <= 1535 and i1 >= 0 and i1 <= 1535 }",
+         "name" : "Stmt_for_body3",
+         "schedule" : "{ Stmt_for_body3[i0, i1] -> scattering[0, i0, 0, i1, 0, 0, 0] }"
+      },
+      {
+         "accesses" : [
+            {
+               "kind" : "read",
+               "relation" : "{ Stmt_for_body8[i0, i1, i2] -> MemRef_C[1536i0 + i1] }"
+            },
+            {
+               "kind" : "read",
+               "relation" : "{ Stmt_for_body8[i0, i1, i2] -> MemRef_A[1536i0 + i2] }"
+            },
+            {
+               "kind" : "read",
+               "relation" : "{ Stmt_for_body8[i0, i1, i2] -> MemRef_B[i1 + 1536i2] }"
+            },
+            {
+               "kind" : "write",
+               "relation" : "{ Stmt_for_body8[i0, i1, i2] -> MemRef_C[1536i0 + i1] }"
+            }
+         ],
+         "domain" : "{ Stmt_for_body8[i0, i1, i2] : i0 >= 0 and i0 <= 1535 and i1 >= 0 and i1 <= 1535 and i2 >= 0 and i2 <= 1535 }",
+         "name" : "Stmt_for_body8",
+         "schedule" : "{ Stmt_for_body8[i0, i1, i2] -> scattering[0, i0, 0, i1, 1, i2, 0] }"
+      }
+   ]
+}
diff --git a/polly/www/experiments/matmul/main___%1---%17.jscop.interchanged b/polly/www/experiments/matmul/main___%for.cond---%for.end30.jscop.interchanged
similarity index 100%
rename from polly/www/experiments/matmul/main___%1---%17.jscop.interchanged
rename to polly/www/experiments/matmul/main___%for.cond---%for.end30.jscop.interchanged
diff --git a/polly/www/experiments/matmul/main___%1---%17.jscop.interchanged+tiled b/polly/www/experiments/matmul/main___%for.cond---%for.end30.jscop.interchanged+tiled
similarity index 100%
rename from polly/www/experiments/matmul/main___%1---%17.jscop.interchanged+tiled
rename to polly/www/experiments/matmul/main___%for.cond---%for.end30.jscop.interchanged+tiled
diff --git a/polly/www/experiments/matmul/main___%1---%17.jscop.interchanged+tiled+vector b/polly/www/experiments/matmul/main___%for.cond---%for.end30.jscop.interchanged+tiled+vector
similarity index 100%
rename from polly/www/experiments/matmul/main___%1---%17.jscop.interchanged+tiled+vector
rename to polly/www/experiments/matmul/main___%for.cond---%for.end30.jscop.interchanged+tiled+vector
diff --git a/polly/www/experiments/matmul/matmul.normalopt.exe b/polly/www/experiments/matmul/matmul.normalopt.exe
index 73b94752d8ed..cdb9e67af454 100755
Binary files a/polly/www/experiments/matmul/matmul.normalopt.exe and b/polly/www/experiments/matmul/matmul.normalopt.exe differ
diff --git a/polly/www/experiments/matmul/matmul.normalopt.ll b/polly/www/experiments/matmul/matmul.normalopt.ll
index 182ed9aa2218..ba792c29f701 100644
Binary files a/polly/www/experiments/matmul/matmul.normalopt.ll and b/polly/www/experiments/matmul/matmul.normalopt.ll differ
diff --git a/polly/www/experiments/matmul/matmul.normalopt.s b/polly/www/experiments/matmul/matmul.normalopt.s
index f10f64411824..079af702a14f 100644
--- a/polly/www/experiments/matmul/matmul.normalopt.s
+++ b/polly/www/experiments/matmul/matmul.normalopt.s
@@ -2,74 +2,112 @@
 	.section	.rodata.cst8,"aM",@progbits,8
 	.align	8
 .LCPI0_0:
-	.quad	4602678819172646912     # double 5.000000e-01
+	.quad	4602678819172646912     # double 0.5
 	.text
 	.globl	init_array
 	.align	16, 0x90
 	.type	init_array,@function
 init_array:                             # @init_array
-# BB#0:
-	xorl	%eax, %eax
-	movsd	.LCPI0_0(%rip), %xmm0
-	movq	%rax, %rcx
+	.cfi_startproc
+# BB#0:                                 # %entry
+	pushq	%rbp
+.Ltmp2:
+	.cfi_def_cfa_offset 16
+.Ltmp3:
+	.cfi_offset %rbp, -16
+	movq	%rsp, %rbp
+.Ltmp4:
+	.cfi_def_cfa_register %rbp
+	xorl	%r8d, %r8d
+	vmovsd	.LCPI0_0(%rip), %xmm0
 	.align	16, 0x90
-.LBB0_1:                                # %.preheader
+.LBB0_1:                                # %for.cond1.preheader
                                         # =>This Loop Header: Depth=1
                                         #     Child Loop BB0_2 Depth 2
-	movq	$-1536, %rdx            # imm = 0xFFFFFFFFFFFFFA00
-	xorl	%esi, %esi
+	xorl	%ecx, %ecx
 	.align	16, 0x90
-.LBB0_2:                                #   Parent Loop BB0_1 Depth=1
+.LBB0_2:                                # %for.body3
+                                        #   Parent Loop BB0_1 Depth=1
                                         # =>  This Inner Loop Header: Depth=2
-	movl	%esi, %edi
-	sarl	$31, %edi
-	shrl	$22, %edi
-	addl	%esi, %edi
-	andl	$-1024, %edi            # imm = 0xFFFFFFFFFFFFFC00
-	negl	%edi
-	leal	1(%rsi,%rdi), %edi
-	cvtsi2sd	%edi, %xmm1
-	mulsd	%xmm0, %xmm1
-	cvtsd2ss	%xmm1, %xmm1
-	movss	%xmm1, A+6144(%rax,%rdx,4)
-	movss	%xmm1, B+6144(%rax,%rdx,4)
-	addl	%ecx, %esi
-	incq	%rdx
+	movl	%ecx, %edx
+	imull	%r8d, %edx
+	movl	%edx, %esi
+	sarl	$31, %esi
+	shrl	$22, %esi
+	addl	%edx, %esi
+	andl	$-1024, %esi            # imm = 0xFFFFFFFFFFFFFC00
+	negl	%esi
+	movq	%r8, %rax
+	shlq	$11, %rax
+	leal	1(%rdx,%rsi), %edi
+	leaq	(%rax,%rax,2), %rsi
+	leaq	1(%rcx), %rdx
+	cmpq	$1536, %rdx             # imm = 0x600
+	vcvtsi2sdl	%edi, %xmm0, %xmm1
+	vmulsd	%xmm0, %xmm1, %xmm1
+	vcvtsd2ss	%xmm1, %xmm1, %xmm1
+	vmovss	%xmm1, A(%rsi,%rcx,4)
+	vmovss	%xmm1, B(%rsi,%rcx,4)
+	movq	%rdx, %rcx
 	jne	.LBB0_2
-# BB#3:                                 #   in Loop: Header=BB0_1 Depth=1
-	addq	$6144, %rax             # imm = 0x1800
-	incq	%rcx
-	cmpq	$1536, %rcx             # imm = 0x600
+# BB#3:                                 # %for.inc17
+                                        #   in Loop: Header=BB0_1 Depth=1
+	incq	%r8
+	cmpq	$1536, %r8              # imm = 0x600
 	jne	.LBB0_1
-# BB#4:
+# BB#4:                                 # %for.end19
+	popq	%rbp
 	ret
-.Ltmp0:
-	.size	init_array, .Ltmp0-init_array
+.Ltmp5:
+	.size	init_array, .Ltmp5-init_array
+	.cfi_endproc
 
 	.globl	print_array
 	.align	16, 0x90
 	.type	print_array,@function
 print_array:                            # @print_array
-# BB#0:
+	.cfi_startproc
+# BB#0:                                 # %entry
+	pushq	%rbp
+.Ltmp9:
+	.cfi_def_cfa_offset 16
+.Ltmp10:
+	.cfi_offset %rbp, -16
+	movq	%rsp, %rbp
+.Ltmp11:
+	.cfi_def_cfa_register %rbp
+	pushq	%r15
 	pushq	%r14
+	pushq	%r12
 	pushq	%rbx
-	pushq	%rax
-	movq	$-9437184, %rbx         # imm = 0xFFFFFFFFFF700000
+.Ltmp12:
+	.cfi_offset %rbx, -48
+.Ltmp13:
+	.cfi_offset %r12, -40
+.Ltmp14:
+	.cfi_offset %r14, -32
+.Ltmp15:
+	.cfi_offset %r15, -24
+	xorl	%r14d, %r14d
+	movl	$C, %r15d
 	.align	16, 0x90
-.LBB1_1:                                # %.preheader
+.LBB1_1:                                # %for.cond1.preheader
                                         # =>This Loop Header: Depth=1
                                         #     Child Loop BB1_2 Depth 2
-	xorl	%r14d, %r14d
-	movq	stdout(%rip), %rdi
+	movq	stdout(%rip), %rax
+	movq	%r15, %r12
+	xorl	%ebx, %ebx
 	.align	16, 0x90
-.LBB1_2:                                #   Parent Loop BB1_1 Depth=1
+.LBB1_2:                                # %for.body3
+                                        #   Parent Loop BB1_1 Depth=1
                                         # =>  This Inner Loop Header: Depth=2
-	movss	C+9437184(%rbx,%r14,4), %xmm0
-	cvtss2sd	%xmm0, %xmm0
+	vmovss	(%r12), %xmm0
+	vcvtss2sd	%xmm0, %xmm0, %xmm0
+	movq	%rax, %rdi
 	movl	$.L.str, %esi
 	movb	$1, %al
 	callq	fprintf
-	movslq	%r14d, %rax
+	movslq	%ebx, %rax
 	imulq	$1717986919, %rax, %rcx # imm = 0x66666667
 	movq	%rcx, %rdx
 	shrq	$63, %rdx
@@ -79,113 +117,146 @@ print_array:                            # @print_array
 	subl	%ecx, %eax
 	cmpl	$79, %eax
 	jne	.LBB1_4
-# BB#3:                                 #   in Loop: Header=BB1_2 Depth=2
+# BB#3:                                 # %if.then
+                                        #   in Loop: Header=BB1_2 Depth=2
 	movq	stdout(%rip), %rsi
 	movl	$10, %edi
 	callq	fputc
-.LBB1_4:                                #   in Loop: Header=BB1_2 Depth=2
-	incq	%r14
-	movq	stdout(%rip), %rsi
-	cmpq	$1536, %r14             # imm = 0x600
-	movq	%rsi, %rdi
+.LBB1_4:                                # %for.inc
+                                        #   in Loop: Header=BB1_2 Depth=2
+	addq	$4, %r12
+	incq	%rbx
+	movq	stdout(%rip), %rax
+	cmpq	$1536, %rbx             # imm = 0x600
 	jne	.LBB1_2
-# BB#5:                                 #   in Loop: Header=BB1_1 Depth=1
+# BB#5:                                 # %for.end
+                                        #   in Loop: Header=BB1_1 Depth=1
 	movl	$10, %edi
+	movq	%rax, %rsi
 	callq	fputc
-	addq	$6144, %rbx             # imm = 0x1800
+	addq	$6144, %r15             # imm = 0x1800
+	incq	%r14
+	cmpq	$1536, %r14             # imm = 0x600
 	jne	.LBB1_1
-# BB#6:
-	addq	$8, %rsp
+# BB#6:                                 # %for.end12
 	popq	%rbx
+	popq	%r12
 	popq	%r14
+	popq	%r15
+	popq	%rbp
 	ret
-.Ltmp1:
-	.size	print_array, .Ltmp1-print_array
+.Ltmp16:
+	.size	print_array, .Ltmp16-print_array
+	.cfi_endproc
 
 	.section	.rodata.cst8,"aM",@progbits,8
 	.align	8
 .LCPI2_0:
-	.quad	4602678819172646912     # double 5.000000e-01
+	.quad	4602678819172646912     # double 0.5
 	.text
 	.globl	main
 	.align	16, 0x90
 	.type	main,@function
 main:                                   # @main
-# BB#0:
-	xorl	%eax, %eax
-	movsd	.LCPI2_0(%rip), %xmm0
-	movq	%rax, %rcx
+	.cfi_startproc
+# BB#0:                                 # %entry
+	pushq	%rbp
+.Ltmp19:
+	.cfi_def_cfa_offset 16
+.Ltmp20:
+	.cfi_offset %rbp, -16
+	movq	%rsp, %rbp
+.Ltmp21:
+	.cfi_def_cfa_register %rbp
+	xorl	%r8d, %r8d
+	vmovsd	.LCPI2_0(%rip), %xmm0
 	.align	16, 0x90
-.LBB2_1:                                # %.preheader.i
+.LBB2_1:                                # %for.cond1.preheader.i
                                         # =>This Loop Header: Depth=1
                                         #     Child Loop BB2_2 Depth 2
-	movq	$-1536, %rdx            # imm = 0xFFFFFFFFFFFFFA00
-	xorl	%esi, %esi
-	.align	16, 0x90
-.LBB2_2:                                #   Parent Loop BB2_1 Depth=1
-                                        # =>  This Inner Loop Header: Depth=2
-	movl	%esi, %edi
-	sarl	$31, %edi
-	shrl	$22, %edi
-	addl	%esi, %edi
-	andl	$-1024, %edi            # imm = 0xFFFFFFFFFFFFFC00
-	negl	%edi
-	leal	1(%rsi,%rdi), %edi
-	cvtsi2sd	%edi, %xmm1
-	mulsd	%xmm0, %xmm1
-	cvtsd2ss	%xmm1, %xmm1
-	movss	%xmm1, A+6144(%rax,%rdx,4)
-	movss	%xmm1, B+6144(%rax,%rdx,4)
-	addl	%ecx, %esi
-	incq	%rdx
-	jne	.LBB2_2
-# BB#3:                                 #   in Loop: Header=BB2_1 Depth=1
-	addq	$6144, %rax             # imm = 0x1800
-	incq	%rcx
-	xorl	%edx, %edx
-	cmpq	$1536, %rcx             # imm = 0x600
-	jne	.LBB2_1
-	.align	16, 0x90
-.LBB2_4:                                # %.preheader
-                                        # =>This Loop Header: Depth=1
-                                        #     Child Loop BB2_5 Depth 2
-                                        #       Child Loop BB2_6 Depth 3
-	xorl	%eax, %eax
 	xorl	%ecx, %ecx
 	.align	16, 0x90
-.LBB2_5:                                #   Parent Loop BB2_4 Depth=1
-                                        # =>  This Loop Header: Depth=2
-                                        #       Child Loop BB2_6 Depth 3
-	movl	$0, C(%rcx,%rdx)
-	leaq	B(%rcx), %rsi
-	pxor	%xmm0, %xmm0
-	movq	%rax, %rdi
+.LBB2_2:                                # %for.body3.i
+                                        #   Parent Loop BB2_1 Depth=1
+                                        # =>  This Inner Loop Header: Depth=2
+	movl	%ecx, %edx
+	imull	%r8d, %edx
+	movl	%edx, %esi
+	sarl	$31, %esi
+	shrl	$22, %esi
+	addl	%edx, %esi
+	andl	$-1024, %esi            # imm = 0xFFFFFFFFFFFFFC00
+	negl	%esi
+	movq	%r8, %rax
+	shlq	$11, %rax
+	leal	1(%rdx,%rsi), %edi
+	leaq	(%rax,%rax,2), %rsi
+	leaq	1(%rcx), %rdx
+	cmpq	$1536, %rdx             # imm = 0x600
+	vcvtsi2sdl	%edi, %xmm0, %xmm1
+	vmulsd	%xmm0, %xmm1, %xmm1
+	vcvtsd2ss	%xmm1, %xmm1, %xmm1
+	vmovss	%xmm1, A(%rsi,%rcx,4)
+	vmovss	%xmm1, B(%rsi,%rcx,4)
+	movq	%rdx, %rcx
+	jne	.LBB2_2
+# BB#3:                                 # %for.inc17.i
+                                        #   in Loop: Header=BB2_1 Depth=1
+	incq	%r8
+	cmpq	$1536, %r8              # imm = 0x600
+	jne	.LBB2_1
+# BB#4:
+	xorl	%r8d, %r8d
+	movl	$A, %r9d
 	.align	16, 0x90
-.LBB2_6:                                #   Parent Loop BB2_4 Depth=1
-                                        #     Parent Loop BB2_5 Depth=2
+.LBB2_5:                                # %for.cond1.preheader
+                                        # =>This Loop Header: Depth=1
+                                        #     Child Loop BB2_6 Depth 2
+                                        #       Child Loop BB2_7 Depth 3
+	leaq	(%r8,%r8,2), %rdx
+	shlq	$11, %rdx
+	leaq	C(%rdx), %rsi
+	xorl	%edi, %edi
+	.align	16, 0x90
+.LBB2_6:                                # %for.body3
+                                        #   Parent Loop BB2_5 Depth=1
+                                        # =>  This Loop Header: Depth=2
+                                        #       Child Loop BB2_7 Depth 3
+	movl	$0, (%rsi)
+	vxorps	%xmm0, %xmm0, %xmm0
+	movq	$-9437184, %rax         # imm = 0xFFFFFFFFFF700000
+	movq	%r9, %rcx
+	.align	16, 0x90
+.LBB2_7:                                # %for.body8
+                                        #   Parent Loop BB2_5 Depth=1
+                                        #     Parent Loop BB2_6 Depth=2
                                         # =>    This Inner Loop Header: Depth=3
-	movss	A(%rdx,%rdi,4), %xmm1
-	mulss	(%rsi), %xmm1
-	addss	%xmm1, %xmm0
-	addq	$6144, %rsi             # imm = 0x1800
+	vmovss	(%rcx), %xmm1
+	vmulss	B+9437184(%rax,%rdi,4), %xmm1, %xmm1
+	vaddss	%xmm1, %xmm0, %xmm0
+	addq	$4, %rcx
+	addq	$6144, %rax             # imm = 0x1800
+	jne	.LBB2_7
+# BB#8:                                 # %for.inc25
+                                        #   in Loop: Header=BB2_6 Depth=2
+	vmovss	%xmm0, (%rsi)
+	leaq	C+4(%rdx,%rdi,4), %rsi
 	incq	%rdi
 	cmpq	$1536, %rdi             # imm = 0x600
 	jne	.LBB2_6
-# BB#7:                                 #   in Loop: Header=BB2_5 Depth=2
-	movss	%xmm0, C(%rcx,%rdx)
-	addq	$4, %rcx
-	cmpq	$6144, %rcx             # imm = 0x1800
+# BB#9:                                 # %for.inc28
+                                        #   in Loop: Header=BB2_5 Depth=1
+	addq	$6144, %r9              # imm = 0x1800
+	incq	%r8
+	cmpq	$1536, %r8              # imm = 0x600
 	jne	.LBB2_5
-# BB#8:                                 # %init_array.exit
-                                        #   in Loop: Header=BB2_4 Depth=1
-	addq	$6144, %rdx             # imm = 0x1800
-	cmpq	$9437184, %rdx          # imm = 0x900000
-	jne	.LBB2_4
-# BB#9:
+# BB#10:                                # %for.end30
 	xorl	%eax, %eax
+	popq	%rbp
 	ret
-.Ltmp2:
-	.size	main, .Ltmp2-main
+.Ltmp22:
+	.size	main, .Ltmp22-main
+	.cfi_endproc
 
 	.type	A,@object               # @A
 	.comm	A,9437184,16
diff --git a/polly/www/experiments/matmul/matmul.polly.interchanged+tiled+vector+openmp.exe b/polly/www/experiments/matmul/matmul.polly.interchanged+tiled+vector+openmp.exe
index 7a2e6de61388..feb24366d730 100755
Binary files a/polly/www/experiments/matmul/matmul.polly.interchanged+tiled+vector+openmp.exe and b/polly/www/experiments/matmul/matmul.polly.interchanged+tiled+vector+openmp.exe differ
diff --git a/polly/www/experiments/matmul/matmul.polly.interchanged+tiled+vector+openmp.ll b/polly/www/experiments/matmul/matmul.polly.interchanged+tiled+vector+openmp.ll
index 710f706f68e8..593794ef380b 100644
Binary files a/polly/www/experiments/matmul/matmul.polly.interchanged+tiled+vector+openmp.ll and b/polly/www/experiments/matmul/matmul.polly.interchanged+tiled+vector+openmp.ll differ
diff --git a/polly/www/experiments/matmul/matmul.polly.interchanged+tiled+vector+openmp.s b/polly/www/experiments/matmul/matmul.polly.interchanged+tiled+vector+openmp.s
index 04dc0656c068..ca87de11704e 100644
--- a/polly/www/experiments/matmul/matmul.polly.interchanged+tiled+vector+openmp.s
+++ b/polly/www/experiments/matmul/matmul.polly.interchanged+tiled+vector+openmp.s
@@ -1,55 +1,166 @@
 	.file	"matmul.polly.interchanged+tiled+vector+openmp.ll"
+	.section	.rodata.cst8,"aM",@progbits,8
+	.align	8
+.LCPI0_0:
+	.quad	4602678819172646912     # double 0.5
 	.text
 	.globl	init_array
 	.align	16, 0x90
 	.type	init_array,@function
 init_array:                             # @init_array
-# BB#0:                                 # %pollyBB
+	.cfi_startproc
+# BB#0:                                 # %entry
+	pushq	%rbp
+.Ltmp3:
+	.cfi_def_cfa_offset 16
+.Ltmp4:
+	.cfi_offset %rbp, -16
+	movq	%rsp, %rbp
+.Ltmp5:
+	.cfi_def_cfa_register %rbp
+	pushq	%r15
+	pushq	%r14
 	pushq	%rbx
-	subq	$16, %rsp
-	movq	$A, (%rsp)
-	movq	$B, 8(%rsp)
+	subq	$24, %rsp
+.Ltmp6:
+	.cfi_offset %rbx, -40
+.Ltmp7:
+	.cfi_offset %r14, -32
+.Ltmp8:
+	.cfi_offset %r15, -24
+	leaq	-32(%rbp), %rsi
 	movl	$init_array.omp_subfn, %edi
-	leaq	(%rsp), %rbx
 	xorl	%edx, %edx
 	xorl	%ecx, %ecx
 	movl	$1536, %r8d             # imm = 0x600
 	movl	$1, %r9d
-	movq	%rbx, %rsi
 	callq	GOMP_parallel_loop_runtime_start
-	movq	%rbx, %rdi
-	callq	init_array.omp_subfn
+	leaq	-40(%rbp), %rdi
+	leaq	-48(%rbp), %rsi
+	callq	GOMP_loop_runtime_next
+	testb	%al, %al
+	je	.LBB0_4
+# BB#1:
+	leaq	-40(%rbp), %r14
+	leaq	-48(%rbp), %r15
+	vmovsd	.LCPI0_0(%rip), %xmm1
+	.align	16, 0x90
+.LBB0_2:                                # %omp.loadIVBounds.i
+                                        # =>This Loop Header: Depth=1
+                                        #     Child Loop BB0_8 Depth 2
+                                        #       Child Loop BB0_5 Depth 3
+	movq	-48(%rbp), %r8
+	leaq	-1(%r8), %rcx
+	movq	-40(%rbp), %rax
+	cmpq	%rcx, %rax
+	jg	.LBB0_3
+# BB#7:                                 # %polly.loop_preheader4.preheader.i
+                                        #   in Loop: Header=BB0_2 Depth=1
+	addq	$-2, %r8
+	.align	16, 0x90
+.LBB0_8:                                # %polly.loop_preheader4.i
+                                        #   Parent Loop BB0_2 Depth=1
+                                        # =>  This Loop Header: Depth=2
+                                        #       Child Loop BB0_5 Depth 3
+	xorl	%edx, %edx
+	.align	16, 0x90
+.LBB0_5:                                # %polly.loop_header3.i
+                                        #   Parent Loop BB0_2 Depth=1
+                                        #     Parent Loop BB0_8 Depth=2
+                                        # =>    This Inner Loop Header: Depth=3
+	movl	%edx, %esi
+	imull	%eax, %esi
+	movl	%esi, %edi
+	sarl	$31, %edi
+	shrl	$22, %edi
+	addl	%esi, %edi
+	andl	$-1024, %edi            # imm = 0xFFFFFFFFFFFFFC00
+	negl	%edi
+	movq	%rax, %rcx
+	shlq	$11, %rcx
+	leal	1(%rsi,%rdi), %ebx
+	leaq	(%rcx,%rcx,2), %rdi
+	leaq	1(%rdx), %rsi
+	cmpq	$1536, %rsi             # imm = 0x600
+	vcvtsi2sdl	%ebx, %xmm0, %xmm0
+	vmulsd	%xmm1, %xmm0, %xmm0
+	vcvtsd2ss	%xmm0, %xmm0, %xmm0
+	vmovss	%xmm0, A(%rdi,%rdx,4)
+	vmovss	%xmm0, B(%rdi,%rdx,4)
+	movq	%rsi, %rdx
+	jne	.LBB0_5
+# BB#6:                                 # %polly.loop_exit5.i
+                                        #   in Loop: Header=BB0_8 Depth=2
+	cmpq	%r8, %rax
+	leaq	1(%rax), %rax
+	jle	.LBB0_8
+.LBB0_3:                                # %omp.checkNext.backedge.i
+                                        #   in Loop: Header=BB0_2 Depth=1
+	movq	%r14, %rdi
+	movq	%r15, %rsi
+	callq	GOMP_loop_runtime_next
+	vmovsd	.LCPI0_0(%rip), %xmm1
+	testb	%al, %al
+	jne	.LBB0_2
+.LBB0_4:                                # %init_array.omp_subfn.exit
+	callq	GOMP_loop_end_nowait
 	callq	GOMP_parallel_end
-	addq	$16, %rsp
+	addq	$24, %rsp
 	popq	%rbx
+	popq	%r14
+	popq	%r15
+	popq	%rbp
 	ret
-.Ltmp0:
-	.size	init_array, .Ltmp0-init_array
+.Ltmp9:
+	.size	init_array, .Ltmp9-init_array
+	.cfi_endproc
 
 	.globl	print_array
 	.align	16, 0x90
 	.type	print_array,@function
 print_array:                            # @print_array
-# BB#0:
+	.cfi_startproc
+# BB#0:                                 # %entry
+	pushq	%rbp
+.Ltmp13:
+	.cfi_def_cfa_offset 16
+.Ltmp14:
+	.cfi_offset %rbp, -16
+	movq	%rsp, %rbp
+.Ltmp15:
+	.cfi_def_cfa_register %rbp
+	pushq	%r15
 	pushq	%r14
+	pushq	%r12
 	pushq	%rbx
-	pushq	%rax
-	movq	$-9437184, %rbx         # imm = 0xFFFFFFFFFF700000
+.Ltmp16:
+	.cfi_offset %rbx, -48
+.Ltmp17:
+	.cfi_offset %r12, -40
+.Ltmp18:
+	.cfi_offset %r14, -32
+.Ltmp19:
+	.cfi_offset %r15, -24
+	xorl	%r14d, %r14d
+	movl	$C, %r15d
 	.align	16, 0x90
-.LBB1_1:                                # %.preheader
+.LBB1_1:                                # %for.cond1.preheader
                                         # =>This Loop Header: Depth=1
                                         #     Child Loop BB1_2 Depth 2
-	xorl	%r14d, %r14d
-	movq	stdout(%rip), %rdi
+	movq	stdout(%rip), %rax
+	movq	%r15, %r12
+	xorl	%ebx, %ebx
 	.align	16, 0x90
-.LBB1_2:                                #   Parent Loop BB1_1 Depth=1
+.LBB1_2:                                # %for.body3
+                                        #   Parent Loop BB1_1 Depth=1
                                         # =>  This Inner Loop Header: Depth=2
-	movss	C+9437184(%rbx,%r14,4), %xmm0
-	cvtss2sd	%xmm0, %xmm0
+	vmovss	(%r12), %xmm0
+	vcvtss2sd	%xmm0, %xmm0, %xmm0
+	movq	%rax, %rdi
 	movl	$.L.str, %esi
 	movb	$1, %al
 	callq	fprintf
-	movslq	%r14d, %rax
+	movslq	%ebx, %rax
 	imulq	$1717986919, %rax, %rcx # imm = 0x66666667
 	movq	%rcx, %rdx
 	shrq	$63, %rdx
@@ -59,127 +170,135 @@ print_array:                            # @print_array
 	subl	%ecx, %eax
 	cmpl	$79, %eax
 	jne	.LBB1_4
-# BB#3:                                 #   in Loop: Header=BB1_2 Depth=2
+# BB#3:                                 # %if.then
+                                        #   in Loop: Header=BB1_2 Depth=2
 	movq	stdout(%rip), %rsi
 	movl	$10, %edi
 	callq	fputc
-.LBB1_4:                                #   in Loop: Header=BB1_2 Depth=2
-	incq	%r14
-	movq	stdout(%rip), %rsi
-	cmpq	$1536, %r14             # imm = 0x600
-	movq	%rsi, %rdi
+.LBB1_4:                                # %for.inc
+                                        #   in Loop: Header=BB1_2 Depth=2
+	addq	$4, %r12
+	incq	%rbx
+	movq	stdout(%rip), %rax
+	cmpq	$1536, %rbx             # imm = 0x600
 	jne	.LBB1_2
-# BB#5:                                 #   in Loop: Header=BB1_1 Depth=1
+# BB#5:                                 # %for.end
+                                        #   in Loop: Header=BB1_1 Depth=1
 	movl	$10, %edi
+	movq	%rax, %rsi
 	callq	fputc
-	addq	$6144, %rbx             # imm = 0x1800
+	addq	$6144, %r15             # imm = 0x1800
+	incq	%r14
+	cmpq	$1536, %r14             # imm = 0x600
 	jne	.LBB1_1
-# BB#6:
-	addq	$8, %rsp
+# BB#6:                                 # %for.end12
 	popq	%rbx
+	popq	%r12
 	popq	%r14
+	popq	%r15
+	popq	%rbp
 	ret
-.Ltmp1:
-	.size	print_array, .Ltmp1-print_array
+.Ltmp20:
+	.size	print_array, .Ltmp20-print_array
+	.cfi_endproc
 
 	.globl	main
 	.align	16, 0x90
 	.type	main,@function
 main:                                   # @main
-# BB#0:                                 # %pollyBB
+	.cfi_startproc
+# BB#0:                                 # %entry
 	pushq	%rbp
+.Ltmp24:
+	.cfi_def_cfa_offset 16
+.Ltmp25:
+	.cfi_offset %rbp, -16
 	movq	%rsp, %rbp
+.Ltmp26:
+	.cfi_def_cfa_register %rbp
 	pushq	%r15
 	pushq	%r14
 	pushq	%r13
 	pushq	%r12
 	pushq	%rbx
-	subq	$56, %rsp
-	movq	$A, -72(%rbp)
-	movq	$B, -64(%rbp)
-	movl	$init_array.omp_subfn, %edi
-	leaq	-72(%rbp), %rbx
-	movq	%rbx, %rsi
-	xorl	%edx, %edx
-	xorl	%ecx, %ecx
-	movl	$1536, %r8d             # imm = 0x600
-	movl	$1, %r9d
-	callq	GOMP_parallel_loop_runtime_start
-	movq	%rbx, %rdi
-	callq	init_array.omp_subfn
-	callq	GOMP_parallel_end
+	subq	$24, %rsp
+.Ltmp27:
+	.cfi_offset %rbx, -56
+.Ltmp28:
+	.cfi_offset %r12, -48
+.Ltmp29:
+	.cfi_offset %r13, -40
+.Ltmp30:
+	.cfi_offset %r14, -32
+.Ltmp31:
+	.cfi_offset %r15, -24
+	callq	init_array
+	leaq	-48(%rbp), %rsi
 	movl	$main.omp_subfn, %edi
-	leaq	-96(%rbp), %rsi
-	movq	$C, -96(%rbp)
-	movq	$A, -88(%rbp)
-	movq	$B, -80(%rbp)
 	xorl	%edx, %edx
 	xorl	%ecx, %ecx
 	movl	$1536, %r8d             # imm = 0x600
 	movl	$1, %r9d
 	callq	GOMP_parallel_loop_runtime_start
-	leaq	-48(%rbp), %rdi
-	leaq	-56(%rbp), %rsi
+	leaq	-56(%rbp), %rdi
+	leaq	-64(%rbp), %rsi
 	callq	GOMP_loop_runtime_next
-	testb	$1, %al
-	je	.LBB2_6
+	testb	%al, %al
+	je	.LBB2_4
 # BB#1:
-	leaq	-48(%rbp), %rbx
 	leaq	-56(%rbp), %r14
+	leaq	-64(%rbp), %r15
 	.align	16, 0x90
-.LBB2_3:                                # %omp.loadIVBounds.i
+.LBB2_2:                                # %omp.loadIVBounds.i
                                         # =>This Loop Header: Depth=1
-                                        #     Child Loop BB2_5 Depth 2
-	movq	-56(%rbp), %r15
-	decq	%r15
-	movq	-48(%rbp), %r12
-	cmpq	%r15, %r12
-	jg	.LBB2_2
-# BB#4:                                 # %polly.loop_header2.preheader.lr.ph.i
-                                        #   in Loop: Header=BB2_3 Depth=1
-	leaq	(%r12,%r12,2), %rax
-	shlq	$11, %rax
-	leaq	C(%rax), %r13
+                                        #     Child Loop BB2_6 Depth 2
+	movq	-64(%rbp), %r12
+	leaq	-1(%r12), %rcx
+	movq	-56(%rbp), %rax
+	cmpq	%rcx, %rax
+	jg	.LBB2_3
+# BB#5:                                 # %polly.loop_preheader4.preheader.i
+                                        #   in Loop: Header=BB2_2 Depth=1
+	addq	$-2, %r12
+	leaq	(%rax,%rax,2), %rcx
+	leaq	-1(%rax), %r13
+	shlq	$11, %rcx
+	leaq	C(%rcx), %rbx
 	.align	16, 0x90
-.LBB2_5:                                # %polly.loop_header2.preheader.i
-                                        #   Parent Loop BB2_3 Depth=1
+.LBB2_6:                                # %polly.loop_preheader4.i
+                                        #   Parent Loop BB2_2 Depth=1
                                         # =>  This Inner Loop Header: Depth=2
-	movq	%r13, %rdi
+	movq	%rbx, %rdi
 	xorl	%esi, %esi
 	movl	$6144, %edx             # imm = 0x1800
 	callq	memset
-	addq	$6144, %r13             # imm = 0x1800
-	incq	%r12
-	cmpq	%r15, %r12
-	jle	.LBB2_5
-.LBB2_2:                                # %omp.checkNext.loopexit.i
-                                        #   in Loop: Header=BB2_3 Depth=1
-	movq	%rbx, %rdi
-	movq	%r14, %rsi
+	addq	$6144, %rbx             # imm = 0x1800
+	incq	%r13
+	cmpq	%r12, %r13
+	jle	.LBB2_6
+.LBB2_3:                                # %omp.checkNext.backedge.i
+                                        #   in Loop: Header=BB2_2 Depth=1
+	movq	%r14, %rdi
+	movq	%r15, %rsi
 	callq	GOMP_loop_runtime_next
-	testb	$1, %al
-	jne	.LBB2_3
-.LBB2_6:                                # %main.omp_subfn.exit
+	testb	%al, %al
+	jne	.LBB2_2
+.LBB2_4:                                # %main.omp_subfn.exit
 	callq	GOMP_loop_end_nowait
 	callq	GOMP_parallel_end
-	movq	%rsp, %rax
-	leaq	-32(%rax), %rbx
+	leaq	-48(%rbp), %rbx
 	movl	$main.omp_subfn1, %edi
+	movq	%rbx, %rsi
+	xorl	%edx, %edx
 	xorl	%ecx, %ecx
 	movl	$1536, %r8d             # imm = 0x600
 	movl	$64, %r9d
-	movq	%rbx, %rsp
-	movq	$C, -32(%rax)
-	movq	$A, -24(%rax)
-	movq	$B, -16(%rax)
-	movq	%rbx, %rsi
-	xorl	%edx, %edx
 	callq	GOMP_parallel_loop_runtime_start
 	movq	%rbx, %rdi
 	callq	main.omp_subfn1
 	callq	GOMP_parallel_end
 	xorl	%eax, %eax
-	leaq	-40(%rbp), %rsp
+	addq	$24, %rsp
 	popq	%rbx
 	popq	%r12
 	popq	%r13
@@ -187,418 +306,192 @@ main:                                   # @main
 	popq	%r15
 	popq	%rbp
 	ret
-.Ltmp2:
-	.size	main, .Ltmp2-main
+.Ltmp32:
+	.size	main, .Ltmp32-main
+	.cfi_endproc
 
 	.section	.rodata.cst8,"aM",@progbits,8
 	.align	8
 .LCPI3_0:
-	.quad	4602678819172646912     # double 5.000000e-01
+	.quad	4602678819172646912     # double 0.5
 	.text
 	.align	16, 0x90
 	.type	init_array.omp_subfn,@function
 init_array.omp_subfn:                   # @init_array.omp_subfn
-.Leh_func_begin3:
-.Ltmp6:
 	.cfi_startproc
 # BB#0:                                 # %omp.setup
-	pushq	%r14
-.Ltmp7:
+	pushq	%rbp
+.Ltmp36:
 	.cfi_def_cfa_offset 16
+.Ltmp37:
+	.cfi_offset %rbp, -16
+	movq	%rsp, %rbp
+.Ltmp38:
+	.cfi_def_cfa_register %rbp
+	pushq	%r15
+	pushq	%r14
 	pushq	%rbx
-.Ltmp8:
-	.cfi_def_cfa_offset 24
 	subq	$24, %rsp
-.Ltmp9:
-	.cfi_def_cfa_offset 48
-.Ltmp10:
-	.cfi_offset 3, -24
-.Ltmp11:
-	.cfi_offset 14, -16
-	leaq	16(%rsp), %rdi
-	leaq	8(%rsp), %rsi
+.Ltmp39:
+	.cfi_offset %rbx, -40
+.Ltmp40:
+	.cfi_offset %r14, -32
+.Ltmp41:
+	.cfi_offset %r15, -24
+	leaq	-32(%rbp), %rdi
+	leaq	-40(%rbp), %rsi
 	callq	GOMP_loop_runtime_next
-	testb	$1, %al
-	je	.LBB3_2
+	testb	%al, %al
+	je	.LBB3_4
 # BB#1:
-	leaq	16(%rsp), %rbx
-	leaq	8(%rsp), %r14
-	jmp	.LBB3_4
-.LBB3_2:                                # %omp.exit
+	leaq	-32(%rbp), %r14
+	leaq	-40(%rbp), %r15
+	vmovsd	.LCPI3_0(%rip), %xmm1
+	.align	16, 0x90
+.LBB3_2:                                # %omp.loadIVBounds
+                                        # =>This Loop Header: Depth=1
+                                        #     Child Loop BB3_8 Depth 2
+                                        #       Child Loop BB3_5 Depth 3
+	movq	-40(%rbp), %r8
+	leaq	-1(%r8), %rcx
+	movq	-32(%rbp), %rax
+	cmpq	%rcx, %rax
+	jg	.LBB3_3
+# BB#7:                                 # %polly.loop_preheader4.preheader
+                                        #   in Loop: Header=BB3_2 Depth=1
+	addq	$-2, %r8
+	.align	16, 0x90
+.LBB3_8:                                # %polly.loop_preheader4
+                                        #   Parent Loop BB3_2 Depth=1
+                                        # =>  This Loop Header: Depth=2
+                                        #       Child Loop BB3_5 Depth 3
+	xorl	%edx, %edx
+	.align	16, 0x90
+.LBB3_5:                                # %polly.loop_header3
+                                        #   Parent Loop BB3_2 Depth=1
+                                        #     Parent Loop BB3_8 Depth=2
+                                        # =>    This Inner Loop Header: Depth=3
+	movl	%edx, %esi
+	imull	%eax, %esi
+	movl	%esi, %edi
+	sarl	$31, %edi
+	shrl	$22, %edi
+	addl	%esi, %edi
+	andl	$-1024, %edi            # imm = 0xFFFFFFFFFFFFFC00
+	negl	%edi
+	movq	%rax, %rcx
+	shlq	$11, %rcx
+	leal	1(%rsi,%rdi), %ebx
+	leaq	(%rcx,%rcx,2), %rdi
+	leaq	1(%rdx), %rsi
+	cmpq	$1536, %rsi             # imm = 0x600
+	vcvtsi2sdl	%ebx, %xmm0, %xmm0
+	vmulsd	%xmm1, %xmm0, %xmm0
+	vcvtsd2ss	%xmm0, %xmm0, %xmm0
+	vmovss	%xmm0, A(%rdi,%rdx,4)
+	vmovss	%xmm0, B(%rdi,%rdx,4)
+	movq	%rsi, %rdx
+	jne	.LBB3_5
+# BB#6:                                 # %polly.loop_exit5
+                                        #   in Loop: Header=BB3_8 Depth=2
+	cmpq	%r8, %rax
+	leaq	1(%rax), %rax
+	jle	.LBB3_8
+.LBB3_3:                                # %omp.checkNext.backedge
+                                        #   in Loop: Header=BB3_2 Depth=1
+	movq	%r14, %rdi
+	movq	%r15, %rsi
+	callq	GOMP_loop_runtime_next
+	vmovsd	.LCPI3_0(%rip), %xmm1
+	testb	%al, %al
+	jne	.LBB3_2
+.LBB3_4:                                # %omp.exit
 	callq	GOMP_loop_end_nowait
 	addq	$24, %rsp
 	popq	%rbx
 	popq	%r14
+	popq	%r15
+	popq	%rbp
 	ret
-	.align	16, 0x90
-.LBB3_3:                                # %omp.checkNext.loopexit
-                                        #   in Loop: Header=BB3_4 Depth=1
-	movq	%rbx, %rdi
-	movq	%r14, %rsi
-	callq	GOMP_loop_runtime_next
-	testb	$1, %al
-	je	.LBB3_2
-.LBB3_4:                                # %omp.loadIVBounds
-                                        # =>This Loop Header: Depth=1
-                                        #     Child Loop BB3_7 Depth 2
-                                        #       Child Loop BB3_8 Depth 3
-	movq	8(%rsp), %rax
-	decq	%rax
-	movq	16(%rsp), %rcx
-	cmpq	%rax, %rcx
-	jg	.LBB3_3
-# BB#5:                                 # %polly.loop_header2.preheader.lr.ph
-                                        #   in Loop: Header=BB3_4 Depth=1
-	movq	%rcx, %rdx
-	shlq	$11, %rdx
-	leaq	(%rdx,%rdx,2), %rdx
-	jmp	.LBB3_7
-	.align	16, 0x90
-.LBB3_6:                                # %polly.loop_header.loopexit
-                                        #   in Loop: Header=BB3_7 Depth=2
-	addq	$6144, %rdx             # imm = 0x1800
-	incq	%rcx
-	cmpq	%rax, %rcx
-	jg	.LBB3_3
-.LBB3_7:                                # %polly.loop_header2.preheader
-                                        #   Parent Loop BB3_4 Depth=1
-                                        # =>  This Loop Header: Depth=2
-                                        #       Child Loop BB3_8 Depth 3
-	movq	$-1536, %rsi            # imm = 0xFFFFFFFFFFFFFA00
-	xorl	%edi, %edi
-	.align	16, 0x90
-.LBB3_8:                                # %polly.loop_body3
-                                        #   Parent Loop BB3_4 Depth=1
-                                        #     Parent Loop BB3_7 Depth=2
-                                        # =>    This Inner Loop Header: Depth=3
-	movl	%edi, %r8d
-	sarl	$31, %r8d
-	shrl	$22, %r8d
-	addl	%edi, %r8d
-	andl	$-1024, %r8d            # imm = 0xFFFFFFFFFFFFFC00
-	negl	%r8d
-	leal	1(%rdi,%r8), %r8d
-	cvtsi2sd	%r8d, %xmm0
-	mulsd	.LCPI3_0(%rip), %xmm0
-	cvtsd2ss	%xmm0, %xmm0
-	movss	%xmm0, A+6144(%rdx,%rsi,4)
-	movss	%xmm0, B+6144(%rdx,%rsi,4)
-	addl	%ecx, %edi
-	incq	%rsi
-	jne	.LBB3_8
-	jmp	.LBB3_6
-.Ltmp12:
-	.size	init_array.omp_subfn, .Ltmp12-init_array.omp_subfn
-.Ltmp13:
+.Ltmp42:
+	.size	init_array.omp_subfn, .Ltmp42-init_array.omp_subfn
 	.cfi_endproc
-.Leh_func_end3:
 
 	.align	16, 0x90
 	.type	main.omp_subfn,@function
 main.omp_subfn:                         # @main.omp_subfn
-.Leh_func_begin4:
-.Ltmp20:
-	.cfi_startproc
-# BB#0:                                 # %omp.setup
-	pushq	%r15
-.Ltmp21:
-	.cfi_def_cfa_offset 16
-	pushq	%r14
-.Ltmp22:
-	.cfi_def_cfa_offset 24
-	pushq	%r13
-.Ltmp23:
-	.cfi_def_cfa_offset 32
-	pushq	%r12
-.Ltmp24:
-	.cfi_def_cfa_offset 40
-	pushq	%rbx
-.Ltmp25:
-	.cfi_def_cfa_offset 48
-	subq	$16, %rsp
-.Ltmp26:
-	.cfi_def_cfa_offset 64
-.Ltmp27:
-	.cfi_offset 3, -48
-.Ltmp28:
-	.cfi_offset 12, -40
-.Ltmp29:
-	.cfi_offset 13, -32
-.Ltmp30:
-	.cfi_offset 14, -24
-.Ltmp31:
-	.cfi_offset 15, -16
-	leaq	8(%rsp), %rdi
-	leaq	(%rsp), %rsi
-	callq	GOMP_loop_runtime_next
-	testb	$1, %al
-	je	.LBB4_2
-# BB#1:
-	leaq	8(%rsp), %rbx
-	leaq	(%rsp), %r14
-	jmp	.LBB4_4
-.LBB4_2:                                # %omp.exit
-	callq	GOMP_loop_end_nowait
-	addq	$16, %rsp
-	popq	%rbx
-	popq	%r12
-	popq	%r13
-	popq	%r14
-	popq	%r15
-	ret
-	.align	16, 0x90
-.LBB4_3:                                # %omp.checkNext.loopexit
-                                        #   in Loop: Header=BB4_4 Depth=1
-	movq	%rbx, %rdi
-	movq	%r14, %rsi
-	callq	GOMP_loop_runtime_next
-	testb	$1, %al
-	je	.LBB4_2
-.LBB4_4:                                # %omp.loadIVBounds
-                                        # =>This Loop Header: Depth=1
-                                        #     Child Loop BB4_6 Depth 2
-	movq	(%rsp), %r15
-	decq	%r15
-	movq	8(%rsp), %r12
-	cmpq	%r15, %r12
-	jg	.LBB4_3
-# BB#5:                                 # %polly.loop_header2.preheader.lr.ph
-                                        #   in Loop: Header=BB4_4 Depth=1
-	leaq	(%r12,%r12,2), %rax
-	shlq	$11, %rax
-	leaq	C(%rax), %r13
-	.align	16, 0x90
-.LBB4_6:                                # %polly.loop_header2.preheader
-                                        #   Parent Loop BB4_4 Depth=1
-                                        # =>  This Inner Loop Header: Depth=2
-	movq	%r13, %rdi
-	xorl	%esi, %esi
-	movl	$6144, %edx             # imm = 0x1800
-	callq	memset
-	addq	$6144, %r13             # imm = 0x1800
-	incq	%r12
-	cmpq	%r15, %r12
-	jle	.LBB4_6
-	jmp	.LBB4_3
-.Ltmp32:
-	.size	main.omp_subfn, .Ltmp32-main.omp_subfn
-.Ltmp33:
-	.cfi_endproc
-.Leh_func_end4:
-
-	.align	16, 0x90
-	.type	main.omp_subfn1,@function
-main.omp_subfn1:                        # @main.omp_subfn1
-.Leh_func_begin5:
-.Ltmp41:
 	.cfi_startproc
 # BB#0:                                 # %omp.setup
 	pushq	%rbp
-.Ltmp42:
-	.cfi_def_cfa_offset 16
-	pushq	%r15
-.Ltmp43:
-	.cfi_def_cfa_offset 24
-	pushq	%r14
-.Ltmp44:
-	.cfi_def_cfa_offset 32
-	pushq	%r13
-.Ltmp45:
-	.cfi_def_cfa_offset 40
-	pushq	%r12
 .Ltmp46:
-	.cfi_def_cfa_offset 48
-	pushq	%rbx
+	.cfi_def_cfa_offset 16
 .Ltmp47:
-	.cfi_def_cfa_offset 56
-	subq	$40, %rsp
+	.cfi_offset %rbp, -16
+	movq	%rsp, %rbp
 .Ltmp48:
-	.cfi_def_cfa_offset 96
+	.cfi_def_cfa_register %rbp
+	pushq	%r15
+	pushq	%r14
+	pushq	%r13
+	pushq	%r12
+	pushq	%rbx
+	subq	$24, %rsp
 .Ltmp49:
-	.cfi_offset 3, -56
+	.cfi_offset %rbx, -56
 .Ltmp50:
-	.cfi_offset 12, -48
+	.cfi_offset %r12, -48
 .Ltmp51:
-	.cfi_offset 13, -40
+	.cfi_offset %r13, -40
 .Ltmp52:
-	.cfi_offset 14, -32
+	.cfi_offset %r14, -32
 .Ltmp53:
-	.cfi_offset 15, -24
-.Ltmp54:
-	.cfi_offset 6, -16
-	leaq	32(%rsp), %rdi
-	leaq	24(%rsp), %rsi
-	jmp	.LBB5_1
-	.align	16, 0x90
-.LBB5_4:                                # %omp.loadIVBounds
-                                        #   in Loop: Header=BB5_1 Depth=1
-	movq	24(%rsp), %rax
-	decq	%rax
-	movq	%rax, (%rsp)            # 8-byte Spill
-	movq	32(%rsp), %rcx
-	cmpq	%rax, %rcx
-	jg	.LBB5_3
-# BB#5:                                 # %polly.loop_header2.preheader.lr.ph
-                                        #   in Loop: Header=BB5_1 Depth=1
-	leaq	(%rcx,%rcx,2), %rax
-	movq	%rcx, %rdx
-	shlq	$9, %rdx
-	leaq	(%rdx,%rdx,2), %rdx
-	movq	%rdx, 16(%rsp)          # 8-byte Spill
-	shlq	$11, %rax
-	leaq	A(%rax), %rax
-	movq	%rax, 8(%rsp)           # 8-byte Spill
-	jmp	.LBB5_7
-	.align	16, 0x90
-.LBB5_6:                                # %polly.loop_header.loopexit
-                                        #   in Loop: Header=BB5_7 Depth=2
-	addq	$98304, 16(%rsp)        # 8-byte Folded Spill
-                                        # imm = 0x18000
-	addq	$393216, 8(%rsp)        # 8-byte Folded Spill
-                                        # imm = 0x60000
-	addq	$64, %rcx
-	cmpq	(%rsp), %rcx            # 8-byte Folded Reload
-	jg	.LBB5_3
-.LBB5_7:                                # %polly.loop_header2.preheader
-                                        #   Parent Loop BB5_1 Depth=1
-                                        # =>  This Loop Header: Depth=2
-                                        #       Child Loop BB5_9 Depth 3
-                                        #         Child Loop BB5_11 Depth 4
-                                        #           Child Loop BB5_14 Depth 5
-                                        #             Child Loop BB5_18 Depth 6
-                                        #               Child Loop BB5_19 Depth 7
-	leaq	63(%rcx), %rax
-	xorl	%edx, %edx
-	jmp	.LBB5_9
-	.align	16, 0x90
-.LBB5_8:                                # %polly.loop_header2.loopexit
-                                        #   in Loop: Header=BB5_9 Depth=3
-	addq	$64, %rdx
-	cmpq	$1536, %rdx             # imm = 0x600
-	je	.LBB5_6
-.LBB5_9:                                # %polly.loop_header7.preheader
-                                        #   Parent Loop BB5_1 Depth=1
-                                        #     Parent Loop BB5_7 Depth=2
-                                        # =>    This Loop Header: Depth=3
-                                        #         Child Loop BB5_11 Depth 4
-                                        #           Child Loop BB5_14 Depth 5
-                                        #             Child Loop BB5_18 Depth 6
-                                        #               Child Loop BB5_19 Depth 7
-	movq	16(%rsp), %rsi          # 8-byte Reload
-	leaq	(%rsi,%rdx), %rsi
-	leaq	63(%rdx), %rdi
-	xorl	%r8d, %r8d
-	movq	8(%rsp), %r9            # 8-byte Reload
-	movq	%rdx, %r10
-	jmp	.LBB5_11
-	.align	16, 0x90
-.LBB5_10:                               # %polly.loop_header7.loopexit
-                                        #   in Loop: Header=BB5_11 Depth=4
-	addq	$256, %r9               # imm = 0x100
-	addq	$98304, %r10            # imm = 0x18000
-	addq	$64, %r8
-	cmpq	$1536, %r8              # imm = 0x600
-	je	.LBB5_8
-.LBB5_11:                               # %polly.loop_body8
-                                        #   Parent Loop BB5_1 Depth=1
-                                        #     Parent Loop BB5_7 Depth=2
-                                        #       Parent Loop BB5_9 Depth=3
-                                        # =>      This Loop Header: Depth=4
-                                        #           Child Loop BB5_14 Depth 5
-                                        #             Child Loop BB5_18 Depth 6
-                                        #               Child Loop BB5_19 Depth 7
-	movabsq	$9223372036854775744, %r11 # imm = 0x7FFFFFFFFFFFFFC0
-	cmpq	%r11, %rcx
-	jg	.LBB5_10
-# BB#12:                                # %polly.loop_body13.lr.ph
-                                        #   in Loop: Header=BB5_11 Depth=4
-	leaq	63(%r8), %r11
-	movq	%rcx, %rbx
-	movq	%rsi, %r14
-	movq	%r9, %r15
-	jmp	.LBB5_14
-	.align	16, 0x90
-.LBB5_13:                               # %polly.loop_header12.loopexit
-                                        #   in Loop: Header=BB5_14 Depth=5
-	addq	$1536, %r14             # imm = 0x600
-	addq	$6144, %r15             # imm = 0x1800
-	incq	%rbx
-	cmpq	%rax, %rbx
-	jg	.LBB5_10
-.LBB5_14:                               # %polly.loop_body13
-                                        #   Parent Loop BB5_1 Depth=1
-                                        #     Parent Loop BB5_7 Depth=2
-                                        #       Parent Loop BB5_9 Depth=3
-                                        #         Parent Loop BB5_11 Depth=4
-                                        # =>        This Loop Header: Depth=5
-                                        #             Child Loop BB5_18 Depth 6
-                                        #               Child Loop BB5_19 Depth 7
-	cmpq	%r11, %r8
-	jg	.LBB5_13
-# BB#15:                                # %polly.loop_body13
-                                        #   in Loop: Header=BB5_14 Depth=5
-	cmpq	%rdi, %rdx
-	jg	.LBB5_13
-# BB#16:                                # %polly.loop_body23.lr.ph.preheader
-                                        #   in Loop: Header=BB5_14 Depth=5
-	xorl	%r12d, %r12d
-	movq	%r10, %r13
-	jmp	.LBB5_18
-	.align	16, 0x90
-.LBB5_17:                               # %polly.loop_header17.loopexit
-                                        #   in Loop: Header=BB5_18 Depth=6
-	addq	$1536, %r13             # imm = 0x600
-	incq	%r12
-	cmpq	$64, %r12
-	je	.LBB5_13
-.LBB5_18:                               # %polly.loop_body23.lr.ph
-                                        #   Parent Loop BB5_1 Depth=1
-                                        #     Parent Loop BB5_7 Depth=2
-                                        #       Parent Loop BB5_9 Depth=3
-                                        #         Parent Loop BB5_11 Depth=4
-                                        #           Parent Loop BB5_14 Depth=5
-                                        # =>          This Loop Header: Depth=6
-                                        #               Child Loop BB5_19 Depth 7
-	movss	(%r15,%r12,4), %xmm0
-	pshufd	$0, %xmm0, %xmm0        # xmm0 = xmm0[0,0,0,0]
-	xorl	%ebp, %ebp
-	.align	16, 0x90
-.LBB5_19:                               # %polly.loop_body23
-                                        #   Parent Loop BB5_1 Depth=1
-                                        #     Parent Loop BB5_7 Depth=2
-                                        #       Parent Loop BB5_9 Depth=3
-                                        #         Parent Loop BB5_11 Depth=4
-                                        #           Parent Loop BB5_14 Depth=5
-                                        #             Parent Loop BB5_18 Depth=6
-                                        # =>            This Inner Loop Header: Depth=7
-	movaps	B(%rbp,%r13,4), %xmm1
-	mulps	%xmm0, %xmm1
-	addps	C(%rbp,%r14,4), %xmm1
-	movaps	%xmm1, C(%rbp,%r14,4)
-	addq	$16, %rbp
-	cmpq	$256, %rbp              # imm = 0x100
-	jne	.LBB5_19
-	jmp	.LBB5_17
-.LBB5_3:                                # %omp.checkNext.loopexit
-                                        #   in Loop: Header=BB5_1 Depth=1
-	leaq	32(%rsp), %rax
-	movq	%rax, %rdi
-	leaq	24(%rsp), %rax
-	movq	%rax, %rsi
-.LBB5_1:                                # %omp.setup
-                                        # =>This Loop Header: Depth=1
-                                        #     Child Loop BB5_7 Depth 2
-                                        #       Child Loop BB5_9 Depth 3
-                                        #         Child Loop BB5_11 Depth 4
-                                        #           Child Loop BB5_14 Depth 5
-                                        #             Child Loop BB5_18 Depth 6
-                                        #               Child Loop BB5_19 Depth 7
+	.cfi_offset %r15, -24
+	leaq	-48(%rbp), %rdi
+	leaq	-56(%rbp), %rsi
 	callq	GOMP_loop_runtime_next
-	testb	$1, %al
-	jne	.LBB5_4
-# BB#2:                                 # %omp.exit
+	testb	%al, %al
+	je	.LBB4_4
+# BB#1:
+	leaq	-48(%rbp), %r14
+	leaq	-56(%rbp), %r15
+	.align	16, 0x90
+.LBB4_2:                                # %omp.loadIVBounds
+                                        # =>This Loop Header: Depth=1
+                                        #     Child Loop BB4_6 Depth 2
+	movq	-56(%rbp), %r12
+	leaq	-1(%r12), %rcx
+	movq	-48(%rbp), %rax
+	cmpq	%rcx, %rax
+	jg	.LBB4_3
+# BB#5:                                 # %polly.loop_preheader4.preheader
+                                        #   in Loop: Header=BB4_2 Depth=1
+	addq	$-2, %r12
+	leaq	(%rax,%rax,2), %rcx
+	leaq	-1(%rax), %r13
+	shlq	$11, %rcx
+	leaq	C(%rcx), %rbx
+	.align	16, 0x90
+.LBB4_6:                                # %polly.loop_preheader4
+                                        #   Parent Loop BB4_2 Depth=1
+                                        # =>  This Inner Loop Header: Depth=2
+	movq	%rbx, %rdi
+	xorl	%esi, %esi
+	movl	$6144, %edx             # imm = 0x1800
+	callq	memset
+	addq	$6144, %rbx             # imm = 0x1800
+	incq	%r13
+	cmpq	%r12, %r13
+	jle	.LBB4_6
+.LBB4_3:                                # %omp.checkNext.backedge
+                                        #   in Loop: Header=BB4_2 Depth=1
+	movq	%r14, %rdi
+	movq	%r15, %rsi
+	callq	GOMP_loop_runtime_next
+	testb	%al, %al
+	jne	.LBB4_2
+.LBB4_4:                                # %omp.exit
 	callq	GOMP_loop_end_nowait
-	addq	$40, %rsp
+	addq	$24, %rsp
 	popq	%rbx
 	popq	%r12
 	popq	%r13
@@ -606,11 +499,244 @@ main.omp_subfn1:                        # @main.omp_subfn1
 	popq	%r15
 	popq	%rbp
 	ret
-.Ltmp55:
-	.size	main.omp_subfn1, .Ltmp55-main.omp_subfn1
-.Ltmp56:
+.Ltmp54:
+	.size	main.omp_subfn, .Ltmp54-main.omp_subfn
+	.cfi_endproc
+
+	.align	16, 0x90
+	.type	main.omp_subfn1,@function
+main.omp_subfn1:                        # @main.omp_subfn1
+	.cfi_startproc
+# BB#0:                                 # %omp.setup
+	pushq	%rbp
+.Ltmp58:
+	.cfi_def_cfa_offset 16
+.Ltmp59:
+	.cfi_offset %rbp, -16
+	movq	%rsp, %rbp
+.Ltmp60:
+	.cfi_def_cfa_register %rbp
+	pushq	%r15
+	pushq	%r14
+	pushq	%r13
+	pushq	%r12
+	pushq	%rbx
+	subq	$72, %rsp
+.Ltmp61:
+	.cfi_offset %rbx, -56
+.Ltmp62:
+	.cfi_offset %r12, -48
+.Ltmp63:
+	.cfi_offset %r13, -40
+.Ltmp64:
+	.cfi_offset %r14, -32
+.Ltmp65:
+	.cfi_offset %r15, -24
+	jmp	.LBB5_1
+	.align	16, 0x90
+.LBB5_2:                                # %omp.loadIVBounds
+                                        #   in Loop: Header=BB5_1 Depth=1
+	movq	-56(%rbp), %rax
+	movq	%rax, -112(%rbp)        # 8-byte Spill
+	leaq	-1(%rax), %rax
+	movq	-48(%rbp), %rcx
+	cmpq	%rax, %rcx
+	jg	.LBB5_1
+# BB#3:                                 # %polly.loop_preheader4.preheader
+                                        #   in Loop: Header=BB5_1 Depth=1
+	leaq	-1(%rcx), %rax
+	movq	%rax, -88(%rbp)         # 8-byte Spill
+	addq	$-65, -112(%rbp)        # 8-byte Folded Spill
+	movq	%rcx, %rax
+	shlq	$9, %rax
+	leaq	(%rax,%rax,2), %rax
+	leaq	C+16(,%rax,4), %rax
+	movq	%rax, -104(%rbp)        # 8-byte Spill
+	.align	16, 0x90
+.LBB5_7:                                # %polly.loop_preheader4
+                                        #   Parent Loop BB5_1 Depth=1
+                                        # =>  This Loop Header: Depth=2
+                                        #       Child Loop BB5_8 Depth 3
+                                        #         Child Loop BB5_9 Depth 4
+                                        #           Child Loop BB5_12 Depth 5
+                                        #             Child Loop BB5_17 Depth 6
+                                        #               Child Loop BB5_18 Depth 7
+                                        #           Child Loop BB5_14 Depth 5
+	movq	%rcx, -72(%rbp)         # 8-byte Spill
+	leaq	62(%rcx), %rdi
+	xorl	%edx, %edx
+	.align	16, 0x90
+.LBB5_8:                                # %polly.loop_preheader11
+                                        #   Parent Loop BB5_1 Depth=1
+                                        #     Parent Loop BB5_7 Depth=2
+                                        # =>    This Loop Header: Depth=3
+                                        #         Child Loop BB5_9 Depth 4
+                                        #           Child Loop BB5_12 Depth 5
+                                        #             Child Loop BB5_17 Depth 6
+                                        #               Child Loop BB5_18 Depth 7
+                                        #           Child Loop BB5_14 Depth 5
+	movq	%rdx, -96(%rbp)         # 8-byte Spill
+	leaq	-4(%rdx), %rcx
+	movq	%rdx, %rax
+	decq	%rax
+	cmovsq	%rcx, %rax
+	movq	%rax, %r14
+	sarq	$63, %r14
+	shrq	$62, %r14
+	addq	%rax, %r14
+	andq	$-4, %r14
+	movq	%rdx, %rax
+	orq	$63, %rax
+	leaq	-4(%rax), %rdx
+	movq	-104(%rbp), %rcx        # 8-byte Reload
+	leaq	(%rcx,%r14,4), %rcx
+	movq	%rcx, -80(%rbp)         # 8-byte Spill
+	leaq	B+16(,%r14,4), %rbx
+	leaq	4(%r14), %rcx
+	movq	%rcx, -64(%rbp)         # 8-byte Spill
+	xorl	%r11d, %r11d
+	.align	16, 0x90
+.LBB5_9:                                # %polly.loop_header10
+                                        #   Parent Loop BB5_1 Depth=1
+                                        #     Parent Loop BB5_7 Depth=2
+                                        #       Parent Loop BB5_8 Depth=3
+                                        # =>      This Loop Header: Depth=4
+                                        #           Child Loop BB5_12 Depth 5
+                                        #             Child Loop BB5_17 Depth 6
+                                        #               Child Loop BB5_18 Depth 7
+                                        #           Child Loop BB5_14 Depth 5
+	movabsq	$9223372036854775744, %rcx # imm = 0x7FFFFFFFFFFFFFC0
+	cmpq	%rcx, -72(%rbp)         # 8-byte Folded Reload
+	jg	.LBB5_15
+# BB#10:                                # %polly.loop_header17.preheader
+                                        #   in Loop: Header=BB5_9 Depth=4
+	movq	%r11, %r15
+	orq	$63, %r15
+	cmpq	%r15, %r11
+	movq	-88(%rbp), %rcx         # 8-byte Reload
+	jle	.LBB5_11
+	.align	16, 0x90
+.LBB5_14:                               # %polly.loop_exit28.us
+                                        #   Parent Loop BB5_1 Depth=1
+                                        #     Parent Loop BB5_7 Depth=2
+                                        #       Parent Loop BB5_8 Depth=3
+                                        #         Parent Loop BB5_9 Depth=4
+                                        # =>        This Inner Loop Header: Depth=5
+	incq	%rcx
+	cmpq	%rdi, %rcx
+	jle	.LBB5_14
+	jmp	.LBB5_15
+	.align	16, 0x90
+.LBB5_11:                               #   in Loop: Header=BB5_9 Depth=4
+	decq	%r15
+	movq	-80(%rbp), %r13         # 8-byte Reload
+	movq	-72(%rbp), %rcx         # 8-byte Reload
+	.align	16, 0x90
+.LBB5_12:                               # %polly.loop_header26.preheader
+                                        #   Parent Loop BB5_1 Depth=1
+                                        #     Parent Loop BB5_7 Depth=2
+                                        #       Parent Loop BB5_8 Depth=3
+                                        #         Parent Loop BB5_9 Depth=4
+                                        # =>        This Loop Header: Depth=5
+                                        #             Child Loop BB5_17 Depth 6
+                                        #               Child Loop BB5_18 Depth 7
+	cmpq	%rax, -64(%rbp)         # 8-byte Folded Reload
+	movq	%rbx, %r12
+	movq	%r11, %r8
+	jg	.LBB5_13
+	.align	16, 0x90
+.LBB5_17:                               # %polly.loop_header35.preheader
+                                        #   Parent Loop BB5_1 Depth=1
+                                        #     Parent Loop BB5_7 Depth=2
+                                        #       Parent Loop BB5_8 Depth=3
+                                        #         Parent Loop BB5_9 Depth=4
+                                        #           Parent Loop BB5_12 Depth=5
+                                        # =>          This Loop Header: Depth=6
+                                        #               Child Loop BB5_18 Depth 7
+	leaq	(%rcx,%rcx,2), %rsi
+	shlq	$11, %rsi
+	vbroadcastss	A(%rsi,%r8,4), %xmm0
+	movq	%r13, %r9
+	movq	%r12, %r10
+	movq	%r14, %rsi
+.LBB5_18:                               # %polly.loop_header35
+                                        #   Parent Loop BB5_1 Depth=1
+                                        #     Parent Loop BB5_7 Depth=2
+                                        #       Parent Loop BB5_8 Depth=3
+                                        #         Parent Loop BB5_9 Depth=4
+                                        #           Parent Loop BB5_12 Depth=5
+                                        #             Parent Loop BB5_17 Depth=6
+                                        # =>            This Inner Loop Header: Depth=7
+	vmulps	(%r10), %xmm0, %xmm1
+	vaddps	(%r9), %xmm1, %xmm1
+	vmovaps	%xmm1, (%r9)
+	addq	$16, %r9
+	addq	$16, %r10
+	addq	$4, %rsi
+	cmpq	%rdx, %rsi
+	jle	.LBB5_18
+# BB#16:                                # %polly.loop_exit37
+                                        #   in Loop: Header=BB5_17 Depth=6
+	addq	$6144, %r12             # imm = 0x1800
+	cmpq	%r15, %r8
+	leaq	1(%r8), %r8
+	jle	.LBB5_17
+	.align	16, 0x90
+.LBB5_13:                               # %polly.loop_exit28
+                                        #   in Loop: Header=BB5_12 Depth=5
+	addq	$6144, %r13             # imm = 0x1800
+	cmpq	%rdi, %rcx
+	leaq	1(%rcx), %rcx
+	jle	.LBB5_12
+	.align	16, 0x90
+.LBB5_15:                               # %polly.loop_exit19
+                                        #   in Loop: Header=BB5_9 Depth=4
+	addq	$393216, %rbx           # imm = 0x60000
+	cmpq	$1472, %r11             # imm = 0x5C0
+	leaq	64(%r11), %r11
+	jl	.LBB5_9
+# BB#5:                                 # %polly.loop_exit12
+                                        #   in Loop: Header=BB5_8 Depth=3
+	movq	-96(%rbp), %rdx         # 8-byte Reload
+	cmpq	$1472, %rdx             # imm = 0x5C0
+	leaq	64(%rdx), %rdx
+	jl	.LBB5_8
+# BB#6:                                 # %polly.loop_exit5
+                                        #   in Loop: Header=BB5_7 Depth=2
+	addq	$64, -88(%rbp)          # 8-byte Folded Spill
+	addq	$393216, -104(%rbp)     # 8-byte Folded Spill
+                                        # imm = 0x60000
+	movq	-72(%rbp), %rcx         # 8-byte Reload
+	cmpq	-112(%rbp), %rcx        # 8-byte Folded Reload
+	leaq	64(%rcx), %rcx
+	jle	.LBB5_7
+.LBB5_1:                                # %omp.setup
+                                        # =>This Loop Header: Depth=1
+                                        #     Child Loop BB5_7 Depth 2
+                                        #       Child Loop BB5_8 Depth 3
+                                        #         Child Loop BB5_9 Depth 4
+                                        #           Child Loop BB5_12 Depth 5
+                                        #             Child Loop BB5_17 Depth 6
+                                        #               Child Loop BB5_18 Depth 7
+                                        #           Child Loop BB5_14 Depth 5
+	leaq	-48(%rbp), %rdi
+	leaq	-56(%rbp), %rsi
+	callq	GOMP_loop_runtime_next
+	testb	%al, %al
+	jne	.LBB5_2
+# BB#4:                                 # %omp.exit
+	callq	GOMP_loop_end_nowait
+	addq	$72, %rsp
+	popq	%rbx
+	popq	%r12
+	popq	%r13
+	popq	%r14
+	popq	%r15
+	popq	%rbp
+	ret
+.Ltmp66:
+	.size	main.omp_subfn1, .Ltmp66-main.omp_subfn1
 	.cfi_endproc
-.Leh_func_end5:
 
 	.type	A,@object               # @A
 	.comm	A,9437184,16
diff --git a/polly/www/experiments/matmul/matmul.polly.interchanged+tiled+vector.exe b/polly/www/experiments/matmul/matmul.polly.interchanged+tiled+vector.exe
index fac17e216859..36b788ea9ac3 100755
Binary files a/polly/www/experiments/matmul/matmul.polly.interchanged+tiled+vector.exe and b/polly/www/experiments/matmul/matmul.polly.interchanged+tiled+vector.exe differ
diff --git a/polly/www/experiments/matmul/matmul.polly.interchanged+tiled+vector.ll b/polly/www/experiments/matmul/matmul.polly.interchanged+tiled+vector.ll
index 7217bc92c804..9d1f9ad098f9 100644
Binary files a/polly/www/experiments/matmul/matmul.polly.interchanged+tiled+vector.ll and b/polly/www/experiments/matmul/matmul.polly.interchanged+tiled+vector.ll differ
diff --git a/polly/www/experiments/matmul/matmul.polly.interchanged+tiled+vector.s b/polly/www/experiments/matmul/matmul.polly.interchanged+tiled+vector.s
index a1d6f0bf9b04..485d230bc398 100644
--- a/polly/www/experiments/matmul/matmul.polly.interchanged+tiled+vector.s
+++ b/polly/www/experiments/matmul/matmul.polly.interchanged+tiled+vector.s
@@ -2,76 +2,112 @@
 	.section	.rodata.cst8,"aM",@progbits,8
 	.align	8
 .LCPI0_0:
-	.quad	4602678819172646912     # double 5.000000e-01
+	.quad	4602678819172646912     # double 0.5
 	.text
 	.globl	init_array
 	.align	16, 0x90
 	.type	init_array,@function
 init_array:                             # @init_array
-# BB#0:                                 # %pollyBB
-	xorl	%eax, %eax
-	movsd	.LCPI0_0(%rip), %xmm0
-	movq	%rax, %rcx
+	.cfi_startproc
+# BB#0:                                 # %entry
+	pushq	%rbp
+.Ltmp2:
+	.cfi_def_cfa_offset 16
+.Ltmp3:
+	.cfi_offset %rbp, -16
+	movq	%rsp, %rbp
+.Ltmp4:
+	.cfi_def_cfa_register %rbp
+	xorl	%r8d, %r8d
+	vmovsd	.LCPI0_0(%rip), %xmm0
 	.align	16, 0x90
-.LBB0_2:                                # %polly.loop_header1.preheader
+.LBB0_1:                                # %polly.loop_preheader3
                                         # =>This Loop Header: Depth=1
-                                        #     Child Loop BB0_3 Depth 2
-	movq	$-1536, %rdx            # imm = 0xFFFFFFFFFFFFFA00
-	xorl	%esi, %esi
+                                        #     Child Loop BB0_2 Depth 2
+	xorl	%ecx, %ecx
 	.align	16, 0x90
-.LBB0_3:                                # %polly.loop_body2
-                                        #   Parent Loop BB0_2 Depth=1
+.LBB0_2:                                # %polly.loop_header2
+                                        #   Parent Loop BB0_1 Depth=1
                                         # =>  This Inner Loop Header: Depth=2
-	movl	%esi, %edi
-	sarl	$31, %edi
-	shrl	$22, %edi
-	addl	%esi, %edi
-	andl	$-1024, %edi            # imm = 0xFFFFFFFFFFFFFC00
-	negl	%edi
-	leal	1(%rsi,%rdi), %edi
-	cvtsi2sd	%edi, %xmm1
-	mulsd	%xmm0, %xmm1
-	cvtsd2ss	%xmm1, %xmm1
-	movss	%xmm1, A+6144(%rax,%rdx,4)
-	movss	%xmm1, B+6144(%rax,%rdx,4)
-	addl	%ecx, %esi
-	incq	%rdx
-	jne	.LBB0_3
-# BB#1:                                 # %polly.loop_header.loopexit
-                                        #   in Loop: Header=BB0_2 Depth=1
-	addq	$6144, %rax             # imm = 0x1800
-	incq	%rcx
-	cmpq	$1536, %rcx             # imm = 0x600
+	movl	%ecx, %edx
+	imull	%r8d, %edx
+	movl	%edx, %esi
+	sarl	$31, %esi
+	shrl	$22, %esi
+	addl	%edx, %esi
+	andl	$-1024, %esi            # imm = 0xFFFFFFFFFFFFFC00
+	negl	%esi
+	movq	%r8, %rax
+	shlq	$11, %rax
+	leal	1(%rdx,%rsi), %edi
+	leaq	(%rax,%rax,2), %rsi
+	leaq	1(%rcx), %rdx
+	cmpq	$1536, %rdx             # imm = 0x600
+	vcvtsi2sdl	%edi, %xmm0, %xmm1
+	vmulsd	%xmm0, %xmm1, %xmm1
+	vcvtsd2ss	%xmm1, %xmm1, %xmm1
+	vmovss	%xmm1, A(%rsi,%rcx,4)
+	vmovss	%xmm1, B(%rsi,%rcx,4)
+	movq	%rdx, %rcx
 	jne	.LBB0_2
-# BB#4:                                 # %polly.after_loop
+# BB#3:                                 # %polly.loop_exit4
+                                        #   in Loop: Header=BB0_1 Depth=1
+	incq	%r8
+	cmpq	$1536, %r8              # imm = 0x600
+	jne	.LBB0_1
+# BB#4:                                 # %polly.loop_exit
+	popq	%rbp
 	ret
-.Ltmp0:
-	.size	init_array, .Ltmp0-init_array
+.Ltmp5:
+	.size	init_array, .Ltmp5-init_array
+	.cfi_endproc
 
 	.globl	print_array
 	.align	16, 0x90
 	.type	print_array,@function
 print_array:                            # @print_array
-# BB#0:
+	.cfi_startproc
+# BB#0:                                 # %entry
+	pushq	%rbp
+.Ltmp9:
+	.cfi_def_cfa_offset 16
+.Ltmp10:
+	.cfi_offset %rbp, -16
+	movq	%rsp, %rbp
+.Ltmp11:
+	.cfi_def_cfa_register %rbp
+	pushq	%r15
 	pushq	%r14
+	pushq	%r12
 	pushq	%rbx
-	pushq	%rax
-	movq	$-9437184, %rbx         # imm = 0xFFFFFFFFFF700000
+.Ltmp12:
+	.cfi_offset %rbx, -48
+.Ltmp13:
+	.cfi_offset %r12, -40
+.Ltmp14:
+	.cfi_offset %r14, -32
+.Ltmp15:
+	.cfi_offset %r15, -24
+	xorl	%r14d, %r14d
+	movl	$C, %r15d
 	.align	16, 0x90
-.LBB1_1:                                # %.preheader
+.LBB1_1:                                # %for.cond1.preheader
                                         # =>This Loop Header: Depth=1
                                         #     Child Loop BB1_2 Depth 2
-	xorl	%r14d, %r14d
-	movq	stdout(%rip), %rdi
+	movq	stdout(%rip), %rax
+	movq	%r15, %r12
+	xorl	%ebx, %ebx
 	.align	16, 0x90
-.LBB1_2:                                #   Parent Loop BB1_1 Depth=1
+.LBB1_2:                                # %for.body3
+                                        #   Parent Loop BB1_1 Depth=1
                                         # =>  This Inner Loop Header: Depth=2
-	movss	C+9437184(%rbx,%r14,4), %xmm0
-	cvtss2sd	%xmm0, %xmm0
+	vmovss	(%r12), %xmm0
+	vcvtss2sd	%xmm0, %xmm0, %xmm0
+	movq	%rax, %rdi
 	movl	$.L.str, %esi
 	movb	$1, %al
 	callq	fprintf
-	movslq	%r14d, %rax
+	movslq	%ebx, %rax
 	imulq	$1717986919, %rax, %rcx # imm = 0x66666667
 	movq	%rcx, %rdx
 	shrq	$63, %rdx
@@ -81,217 +117,258 @@ print_array:                            # @print_array
 	subl	%ecx, %eax
 	cmpl	$79, %eax
 	jne	.LBB1_4
-# BB#3:                                 #   in Loop: Header=BB1_2 Depth=2
+# BB#3:                                 # %if.then
+                                        #   in Loop: Header=BB1_2 Depth=2
 	movq	stdout(%rip), %rsi
 	movl	$10, %edi
 	callq	fputc
-.LBB1_4:                                #   in Loop: Header=BB1_2 Depth=2
-	incq	%r14
-	movq	stdout(%rip), %rsi
-	cmpq	$1536, %r14             # imm = 0x600
-	movq	%rsi, %rdi
+.LBB1_4:                                # %for.inc
+                                        #   in Loop: Header=BB1_2 Depth=2
+	addq	$4, %r12
+	incq	%rbx
+	movq	stdout(%rip), %rax
+	cmpq	$1536, %rbx             # imm = 0x600
 	jne	.LBB1_2
-# BB#5:                                 #   in Loop: Header=BB1_1 Depth=1
+# BB#5:                                 # %for.end
+                                        #   in Loop: Header=BB1_1 Depth=1
 	movl	$10, %edi
+	movq	%rax, %rsi
 	callq	fputc
-	addq	$6144, %rbx             # imm = 0x1800
+	addq	$6144, %r15             # imm = 0x1800
+	incq	%r14
+	cmpq	$1536, %r14             # imm = 0x600
 	jne	.LBB1_1
-# BB#6:
-	addq	$8, %rsp
+# BB#6:                                 # %for.end12
 	popq	%rbx
+	popq	%r12
 	popq	%r14
+	popq	%r15
+	popq	%rbp
 	ret
-.Ltmp1:
-	.size	print_array, .Ltmp1-print_array
+.Ltmp16:
+	.size	print_array, .Ltmp16-print_array
+	.cfi_endproc
 
 	.section	.rodata.cst8,"aM",@progbits,8
 	.align	8
 .LCPI2_0:
-	.quad	4602678819172646912     # double 5.000000e-01
+	.quad	4602678819172646912     # double 0.5
 	.text
 	.globl	main
 	.align	16, 0x90
 	.type	main,@function
 main:                                   # @main
-# BB#0:                                 # %pollyBB
+	.cfi_startproc
+# BB#0:                                 # %entry
 	pushq	%rbp
+.Ltmp20:
+	.cfi_def_cfa_offset 16
+.Ltmp21:
+	.cfi_offset %rbp, -16
+	movq	%rsp, %rbp
+.Ltmp22:
+	.cfi_def_cfa_register %rbp
 	pushq	%r15
 	pushq	%r14
 	pushq	%r13
 	pushq	%r12
 	pushq	%rbx
-	subq	$24, %rsp
-	xorl	%eax, %eax
-	movsd	.LCPI2_0(%rip), %xmm0
-	movq	%rax, %rcx
+	subq	$56, %rsp
+.Ltmp23:
+	.cfi_offset %rbx, -56
+.Ltmp24:
+	.cfi_offset %r12, -48
+.Ltmp25:
+	.cfi_offset %r13, -40
+.Ltmp26:
+	.cfi_offset %r14, -32
+.Ltmp27:
+	.cfi_offset %r15, -24
+	xorl	%ebx, %ebx
+	vmovsd	.LCPI2_0(%rip), %xmm0
 	.align	16, 0x90
-.LBB2_1:                                # %polly.loop_header1.preheader.i
+.LBB2_1:                                # %polly.loop_preheader3.i
                                         # =>This Loop Header: Depth=1
                                         #     Child Loop BB2_2 Depth 2
-	movq	$-1536, %rdx            # imm = 0xFFFFFFFFFFFFFA00
-	xorl	%esi, %esi
+	xorl	%ecx, %ecx
 	.align	16, 0x90
-.LBB2_2:                                # %polly.loop_body2.i
+.LBB2_2:                                # %polly.loop_header2.i
                                         #   Parent Loop BB2_1 Depth=1
                                         # =>  This Inner Loop Header: Depth=2
-	movl	%esi, %edi
-	sarl	$31, %edi
-	shrl	$22, %edi
-	addl	%esi, %edi
-	andl	$-1024, %edi            # imm = 0xFFFFFFFFFFFFFC00
-	negl	%edi
-	leal	1(%rsi,%rdi), %edi
-	cvtsi2sd	%edi, %xmm1
-	mulsd	%xmm0, %xmm1
-	cvtsd2ss	%xmm1, %xmm1
-	movss	%xmm1, A+6144(%rax,%rdx,4)
-	movss	%xmm1, B+6144(%rax,%rdx,4)
-	addl	%ecx, %esi
-	incq	%rdx
+	movl	%ecx, %edx
+	imull	%ebx, %edx
+	movl	%edx, %esi
+	sarl	$31, %esi
+	shrl	$22, %esi
+	addl	%edx, %esi
+	andl	$-1024, %esi            # imm = 0xFFFFFFFFFFFFFC00
+	negl	%esi
+	movq	%rbx, %rax
+	shlq	$11, %rax
+	leal	1(%rdx,%rsi), %edi
+	leaq	(%rax,%rax,2), %rsi
+	leaq	1(%rcx), %rdx
+	cmpq	$1536, %rdx             # imm = 0x600
+	vcvtsi2sdl	%edi, %xmm0, %xmm1
+	vmulsd	%xmm0, %xmm1, %xmm1
+	vcvtsd2ss	%xmm1, %xmm1, %xmm1
+	vmovss	%xmm1, A(%rsi,%rcx,4)
+	vmovss	%xmm1, B(%rsi,%rcx,4)
+	movq	%rdx, %rcx
 	jne	.LBB2_2
-# BB#3:                                 # %polly.loop_header.loopexit.i
+# BB#3:                                 # %polly.loop_exit4.i
                                         #   in Loop: Header=BB2_1 Depth=1
-	addq	$6144, %rax             # imm = 0x1800
-	incq	%rcx
-	cmpq	$1536, %rcx             # imm = 0x600
+	incq	%rbx
+	cmpq	$1536, %rbx             # imm = 0x600
 	jne	.LBB2_1
-# BB#4:                                 # %polly.loop_header.preheader
+# BB#4:                                 # %polly.loop_preheader3.preheader
 	movl	$C, %edi
 	xorl	%esi, %esi
 	movl	$9437184, %edx          # imm = 0x900000
 	callq	memset
-	xorl	%eax, %eax
-	movq	%rax, 16(%rsp)          # 8-byte Spill
-	movq	%rax, (%rsp)            # 8-byte Spill
-	jmp	.LBB2_6
+	xorl	%esi, %esi
+	movl	$C+16, %eax
+	movq	%rax, -88(%rbp)         # 8-byte Spill
 	.align	16, 0x90
-.LBB2_5:                                # %polly.loop_header7.loopexit
-                                        #   in Loop: Header=BB2_6 Depth=1
-	addq	$393216, (%rsp)         # 8-byte Folded Spill
-                                        # imm = 0x60000
-	movq	16(%rsp), %rax          # 8-byte Reload
-	addq	$64, %rax
-	movq	%rax, 16(%rsp)          # 8-byte Spill
-	cmpq	$1536, %rax             # imm = 0x600
-	je	.LBB2_7
-.LBB2_6:                                # %polly.loop_header12.preheader
+.LBB2_5:                                # %polly.loop_preheader17
                                         # =>This Loop Header: Depth=1
-                                        #     Child Loop BB2_9 Depth 2
-                                        #       Child Loop BB2_11 Depth 3
-                                        #         Child Loop BB2_14 Depth 4
-                                        #           Child Loop BB2_18 Depth 5
-                                        #             Child Loop BB2_19 Depth 6
-	movq	16(%rsp), %rax          # 8-byte Reload
-	leaq	63(%rax), %rax
-	movq	(%rsp), %rcx            # 8-byte Reload
-	leaq	A(%rcx), %rdx
-	movq	%rdx, 8(%rsp)           # 8-byte Spill
+                                        #     Child Loop BB2_15 Depth 2
+                                        #       Child Loop BB2_8 Depth 3
+                                        #         Child Loop BB2_11 Depth 4
+                                        #           Child Loop BB2_17 Depth 5
+                                        #             Child Loop BB2_18 Depth 6
+	movq	%rsi, -56(%rbp)         # 8-byte Spill
+	movq	%rsi, %rax
+	orq	$63, %rax
+	movq	%rax, -72(%rbp)         # 8-byte Spill
+	leaq	-1(%rax), %rax
+	movq	%rax, -48(%rbp)         # 8-byte Spill
 	xorl	%edx, %edx
-	jmp	.LBB2_9
 	.align	16, 0x90
-.LBB2_8:                                # %polly.loop_header12.loopexit
-                                        #   in Loop: Header=BB2_9 Depth=2
-	addq	$256, %rcx              # imm = 0x100
-	addq	$64, %rdx
-	cmpq	$1536, %rdx             # imm = 0x600
-	je	.LBB2_5
-.LBB2_9:                                # %polly.loop_header17.preheader
-                                        #   Parent Loop BB2_6 Depth=1
+.LBB2_15:                               # %polly.loop_preheader24
+                                        #   Parent Loop BB2_5 Depth=1
                                         # =>  This Loop Header: Depth=2
-                                        #       Child Loop BB2_11 Depth 3
-                                        #         Child Loop BB2_14 Depth 4
-                                        #           Child Loop BB2_18 Depth 5
-                                        #             Child Loop BB2_19 Depth 6
-	leaq	63(%rdx), %rsi
-	xorl	%edi, %edi
-	movq	8(%rsp), %r8            # 8-byte Reload
-	movq	%rdx, %r9
-	jmp	.LBB2_11
+                                        #       Child Loop BB2_8 Depth 3
+                                        #         Child Loop BB2_11 Depth 4
+                                        #           Child Loop BB2_17 Depth 5
+                                        #             Child Loop BB2_18 Depth 6
+	movq	%rdx, -80(%rbp)         # 8-byte Spill
+	leaq	-4(%rdx), %rcx
+	movq	%rdx, %rax
+	decq	%rax
+	cmovsq	%rcx, %rax
+	movq	%rax, %r15
+	sarq	$63, %r15
+	shrq	$62, %r15
+	addq	%rax, %r15
+	andq	$-4, %r15
+	movq	%rdx, %r13
+	orq	$63, %r13
+	leaq	-4(%r13), %rdx
+	xorl	%r10d, %r10d
+	movq	-88(%rbp), %rax         # 8-byte Reload
+	leaq	(%rax,%r15,4), %rax
+	movq	%rax, -64(%rbp)         # 8-byte Spill
+	leaq	B+16(,%r15,4), %rbx
+	leaq	4(%r15), %r12
 	.align	16, 0x90
-.LBB2_10:                               # %polly.loop_header17.loopexit
-                                        #   in Loop: Header=BB2_11 Depth=3
-	addq	$256, %r8               # imm = 0x100
-	addq	$98304, %r9             # imm = 0x18000
-	addq	$64, %rdi
-	cmpq	$1536, %rdi             # imm = 0x600
-	je	.LBB2_8
-.LBB2_11:                               # %polly.loop_body18
-                                        #   Parent Loop BB2_6 Depth=1
-                                        #     Parent Loop BB2_9 Depth=2
+.LBB2_8:                                # %polly.loop_header23
+                                        #   Parent Loop BB2_5 Depth=1
+                                        #     Parent Loop BB2_15 Depth=2
                                         # =>    This Loop Header: Depth=3
-                                        #         Child Loop BB2_14 Depth 4
-                                        #           Child Loop BB2_18 Depth 5
-                                        #             Child Loop BB2_19 Depth 6
-	cmpq	%rax, 16(%rsp)          # 8-byte Folded Reload
-	jg	.LBB2_10
-# BB#12:                                # %polly.loop_body23.lr.ph
-                                        #   in Loop: Header=BB2_11 Depth=3
-	leaq	63(%rdi), %r10
-	xorl	%r11d, %r11d
-	jmp	.LBB2_14
+                                        #         Child Loop BB2_11 Depth 4
+                                        #           Child Loop BB2_17 Depth 5
+                                        #             Child Loop BB2_18 Depth 6
+	cmpq	-72(%rbp), %rsi         # 8-byte Folded Reload
+	jg	.LBB2_13
+# BB#9:                                 # %polly.loop_header30.preheader
+                                        #   in Loop: Header=BB2_8 Depth=3
+	movq	%r10, %rax
+	orq	$63, %rax
+	cmpq	%rax, %r10
+	jg	.LBB2_13
+# BB#10:                                #   in Loop: Header=BB2_8 Depth=3
+	decq	%rax
+	movq	-64(%rbp), %r14         # 8-byte Reload
+	movq	-56(%rbp), %r11         # 8-byte Reload
 	.align	16, 0x90
-.LBB2_13:                               # %polly.loop_header22.loopexit
-                                        #   in Loop: Header=BB2_14 Depth=4
-	addq	$6144, %r11             # imm = 0x1800
-	cmpq	$393216, %r11           # imm = 0x60000
-	je	.LBB2_10
-.LBB2_14:                               # %polly.loop_body23
-                                        #   Parent Loop BB2_6 Depth=1
-                                        #     Parent Loop BB2_9 Depth=2
-                                        #       Parent Loop BB2_11 Depth=3
+.LBB2_11:                               # %polly.loop_header37.preheader
+                                        #   Parent Loop BB2_5 Depth=1
+                                        #     Parent Loop BB2_15 Depth=2
+                                        #       Parent Loop BB2_8 Depth=3
                                         # =>      This Loop Header: Depth=4
-                                        #           Child Loop BB2_18 Depth 5
-                                        #             Child Loop BB2_19 Depth 6
-	cmpq	%r10, %rdi
-	jg	.LBB2_13
-# BB#15:                                # %polly.loop_body23
-                                        #   in Loop: Header=BB2_14 Depth=4
-	cmpq	%rsi, %rdx
-	jg	.LBB2_13
-# BB#16:                                # %polly.loop_body33.lr.ph.preheader
-                                        #   in Loop: Header=BB2_14 Depth=4
-	leaq	(%r8,%r11), %rbx
-	xorl	%r14d, %r14d
-	movq	%r9, %r15
-	movq	%r14, %r12
-	jmp	.LBB2_18
+                                        #           Child Loop BB2_17 Depth 5
+                                        #             Child Loop BB2_18 Depth 6
+	cmpq	%r13, %r12
+	movq	%rbx, %r8
+	movq	%r10, %rsi
+	jg	.LBB2_12
 	.align	16, 0x90
-.LBB2_17:                               # %polly.loop_header27.loopexit
-                                        #   in Loop: Header=BB2_18 Depth=5
-	addq	$1536, %r15             # imm = 0x600
-	incq	%r12
-	cmpq	$64, %r12
-	je	.LBB2_13
-.LBB2_18:                               # %polly.loop_body33.lr.ph
-                                        #   Parent Loop BB2_6 Depth=1
-                                        #     Parent Loop BB2_9 Depth=2
-                                        #       Parent Loop BB2_11 Depth=3
-                                        #         Parent Loop BB2_14 Depth=4
+.LBB2_17:                               # %polly.loop_header46.preheader
+                                        #   Parent Loop BB2_5 Depth=1
+                                        #     Parent Loop BB2_15 Depth=2
+                                        #       Parent Loop BB2_8 Depth=3
+                                        #         Parent Loop BB2_11 Depth=4
                                         # =>        This Loop Header: Depth=5
-                                        #             Child Loop BB2_19 Depth 6
-	movss	(%rbx,%r12,4), %xmm0
-	pshufd	$0, %xmm0, %xmm0        # xmm0 = xmm0[0,0,0,0]
-	movq	%r14, %r13
-	.align	16, 0x90
-.LBB2_19:                               # %polly.loop_body33
-                                        #   Parent Loop BB2_6 Depth=1
-                                        #     Parent Loop BB2_9 Depth=2
-                                        #       Parent Loop BB2_11 Depth=3
-                                        #         Parent Loop BB2_14 Depth=4
-                                        #           Parent Loop BB2_18 Depth=5
+                                        #             Child Loop BB2_18 Depth 6
+	leaq	(%r11,%r11,2), %rcx
+	shlq	$11, %rcx
+	vbroadcastss	A(%rcx,%rsi,4), %xmm0
+	movq	%r14, %rdi
+	movq	%r8, %r9
+	movq	%r15, %rcx
+.LBB2_18:                               # %polly.loop_header46
+                                        #   Parent Loop BB2_5 Depth=1
+                                        #     Parent Loop BB2_15 Depth=2
+                                        #       Parent Loop BB2_8 Depth=3
+                                        #         Parent Loop BB2_11 Depth=4
+                                        #           Parent Loop BB2_17 Depth=5
                                         # =>          This Inner Loop Header: Depth=6
-	movaps	B(%r13,%r15,4), %xmm1
-	mulps	%xmm0, %xmm1
-	leaq	(%r11,%r13), %rbp
-	addps	C(%rcx,%rbp), %xmm1
-	movaps	%xmm1, C(%rcx,%rbp)
-	addq	$16, %r13
-	cmpq	$256, %r13              # imm = 0x100
-	jne	.LBB2_19
-	jmp	.LBB2_17
-.LBB2_7:                                # %polly.after_loop9
+	vmulps	(%r9), %xmm0, %xmm1
+	vaddps	(%rdi), %xmm1, %xmm1
+	vmovaps	%xmm1, (%rdi)
+	addq	$16, %rdi
+	addq	$16, %r9
+	addq	$4, %rcx
+	cmpq	%rdx, %rcx
+	jle	.LBB2_18
+# BB#16:                                # %polly.loop_exit48
+                                        #   in Loop: Header=BB2_17 Depth=5
+	addq	$6144, %r8              # imm = 0x1800
+	cmpq	%rax, %rsi
+	leaq	1(%rsi), %rsi
+	jle	.LBB2_17
+	.align	16, 0x90
+.LBB2_12:                               # %polly.loop_exit39
+                                        #   in Loop: Header=BB2_11 Depth=4
+	addq	$6144, %r14             # imm = 0x1800
+	cmpq	-48(%rbp), %r11         # 8-byte Folded Reload
+	leaq	1(%r11), %r11
+	jle	.LBB2_11
+	.align	16, 0x90
+.LBB2_13:                               # %polly.loop_exit32
+                                        #   in Loop: Header=BB2_8 Depth=3
+	addq	$393216, %rbx           # imm = 0x60000
+	cmpq	$1472, %r10             # imm = 0x5C0
+	leaq	64(%r10), %r10
+	movq	-56(%rbp), %rsi         # 8-byte Reload
+	jl	.LBB2_8
+# BB#14:                                # %polly.loop_exit25
+                                        #   in Loop: Header=BB2_15 Depth=2
+	movq	-80(%rbp), %rdx         # 8-byte Reload
+	cmpq	$1472, %rdx             # imm = 0x5C0
+	leaq	64(%rdx), %rdx
+	jl	.LBB2_15
+# BB#6:                                 # %polly.loop_exit18
+                                        #   in Loop: Header=BB2_5 Depth=1
+	addq	$393216, -88(%rbp)      # 8-byte Folded Spill
+                                        # imm = 0x60000
+	cmpq	$1472, %rsi             # imm = 0x5C0
+	leaq	64(%rsi), %rsi
+	jl	.LBB2_5
+# BB#7:                                 # %polly.loop_exit11
 	xorl	%eax, %eax
-	addq	$24, %rsp
+	addq	$56, %rsp
 	popq	%rbx
 	popq	%r12
 	popq	%r13
@@ -299,8 +376,9 @@ main:                                   # @main
 	popq	%r15
 	popq	%rbp
 	ret
-.Ltmp2:
-	.size	main, .Ltmp2-main
+.Ltmp28:
+	.size	main, .Ltmp28-main
+	.cfi_endproc
 
 	.type	A,@object               # @A
 	.comm	A,9437184,16
diff --git a/polly/www/experiments/matmul/matmul.polly.interchanged+tiled.exe b/polly/www/experiments/matmul/matmul.polly.interchanged+tiled.exe
index 4334522f4587..fbd8b128fd88 100755
Binary files a/polly/www/experiments/matmul/matmul.polly.interchanged+tiled.exe and b/polly/www/experiments/matmul/matmul.polly.interchanged+tiled.exe differ
diff --git a/polly/www/experiments/matmul/matmul.polly.interchanged+tiled.ll b/polly/www/experiments/matmul/matmul.polly.interchanged+tiled.ll
index fa301cfa5eb0..acdd95f3bc4c 100644
Binary files a/polly/www/experiments/matmul/matmul.polly.interchanged+tiled.ll and b/polly/www/experiments/matmul/matmul.polly.interchanged+tiled.ll differ
diff --git a/polly/www/experiments/matmul/matmul.polly.interchanged+tiled.s b/polly/www/experiments/matmul/matmul.polly.interchanged+tiled.s
index 0f86df25d357..f7ab7fdd59cc 100644
--- a/polly/www/experiments/matmul/matmul.polly.interchanged+tiled.s
+++ b/polly/www/experiments/matmul/matmul.polly.interchanged+tiled.s
@@ -2,76 +2,112 @@
 	.section	.rodata.cst8,"aM",@progbits,8
 	.align	8
 .LCPI0_0:
-	.quad	4602678819172646912     # double 5.000000e-01
+	.quad	4602678819172646912     # double 0.5
 	.text
 	.globl	init_array
 	.align	16, 0x90
 	.type	init_array,@function
 init_array:                             # @init_array
-# BB#0:                                 # %pollyBB
-	xorl	%eax, %eax
-	movsd	.LCPI0_0(%rip), %xmm0
-	movq	%rax, %rcx
+	.cfi_startproc
+# BB#0:                                 # %entry
+	pushq	%rbp
+.Ltmp2:
+	.cfi_def_cfa_offset 16
+.Ltmp3:
+	.cfi_offset %rbp, -16
+	movq	%rsp, %rbp
+.Ltmp4:
+	.cfi_def_cfa_register %rbp
+	xorl	%r8d, %r8d
+	vmovsd	.LCPI0_0(%rip), %xmm0
 	.align	16, 0x90
-.LBB0_2:                                # %polly.loop_header1.preheader
+.LBB0_1:                                # %polly.loop_preheader3
                                         # =>This Loop Header: Depth=1
-                                        #     Child Loop BB0_3 Depth 2
-	movq	$-1536, %rdx            # imm = 0xFFFFFFFFFFFFFA00
-	xorl	%esi, %esi
+                                        #     Child Loop BB0_2 Depth 2
+	xorl	%ecx, %ecx
 	.align	16, 0x90
-.LBB0_3:                                # %polly.loop_body2
-                                        #   Parent Loop BB0_2 Depth=1
+.LBB0_2:                                # %polly.loop_header2
+                                        #   Parent Loop BB0_1 Depth=1
                                         # =>  This Inner Loop Header: Depth=2
-	movl	%esi, %edi
-	sarl	$31, %edi
-	shrl	$22, %edi
-	addl	%esi, %edi
-	andl	$-1024, %edi            # imm = 0xFFFFFFFFFFFFFC00
-	negl	%edi
-	leal	1(%rsi,%rdi), %edi
-	cvtsi2sd	%edi, %xmm1
-	mulsd	%xmm0, %xmm1
-	cvtsd2ss	%xmm1, %xmm1
-	movss	%xmm1, A+6144(%rax,%rdx,4)
-	movss	%xmm1, B+6144(%rax,%rdx,4)
-	addl	%ecx, %esi
-	incq	%rdx
-	jne	.LBB0_3
-# BB#1:                                 # %polly.loop_header.loopexit
-                                        #   in Loop: Header=BB0_2 Depth=1
-	addq	$6144, %rax             # imm = 0x1800
-	incq	%rcx
-	cmpq	$1536, %rcx             # imm = 0x600
+	movl	%ecx, %edx
+	imull	%r8d, %edx
+	movl	%edx, %esi
+	sarl	$31, %esi
+	shrl	$22, %esi
+	addl	%edx, %esi
+	andl	$-1024, %esi            # imm = 0xFFFFFFFFFFFFFC00
+	negl	%esi
+	movq	%r8, %rax
+	shlq	$11, %rax
+	leal	1(%rdx,%rsi), %edi
+	leaq	(%rax,%rax,2), %rsi
+	leaq	1(%rcx), %rdx
+	cmpq	$1536, %rdx             # imm = 0x600
+	vcvtsi2sdl	%edi, %xmm0, %xmm1
+	vmulsd	%xmm0, %xmm1, %xmm1
+	vcvtsd2ss	%xmm1, %xmm1, %xmm1
+	vmovss	%xmm1, A(%rsi,%rcx,4)
+	vmovss	%xmm1, B(%rsi,%rcx,4)
+	movq	%rdx, %rcx
 	jne	.LBB0_2
-# BB#4:                                 # %polly.after_loop
+# BB#3:                                 # %polly.loop_exit4
+                                        #   in Loop: Header=BB0_1 Depth=1
+	incq	%r8
+	cmpq	$1536, %r8              # imm = 0x600
+	jne	.LBB0_1
+# BB#4:                                 # %polly.loop_exit
+	popq	%rbp
 	ret
-.Ltmp0:
-	.size	init_array, .Ltmp0-init_array
+.Ltmp5:
+	.size	init_array, .Ltmp5-init_array
+	.cfi_endproc
 
 	.globl	print_array
 	.align	16, 0x90
 	.type	print_array,@function
 print_array:                            # @print_array
-# BB#0:
+	.cfi_startproc
+# BB#0:                                 # %entry
+	pushq	%rbp
+.Ltmp9:
+	.cfi_def_cfa_offset 16
+.Ltmp10:
+	.cfi_offset %rbp, -16
+	movq	%rsp, %rbp
+.Ltmp11:
+	.cfi_def_cfa_register %rbp
+	pushq	%r15
 	pushq	%r14
+	pushq	%r12
 	pushq	%rbx
-	pushq	%rax
-	movq	$-9437184, %rbx         # imm = 0xFFFFFFFFFF700000
+.Ltmp12:
+	.cfi_offset %rbx, -48
+.Ltmp13:
+	.cfi_offset %r12, -40
+.Ltmp14:
+	.cfi_offset %r14, -32
+.Ltmp15:
+	.cfi_offset %r15, -24
+	xorl	%r14d, %r14d
+	movl	$C, %r15d
 	.align	16, 0x90
-.LBB1_1:                                # %.preheader
+.LBB1_1:                                # %for.cond1.preheader
                                         # =>This Loop Header: Depth=1
                                         #     Child Loop BB1_2 Depth 2
-	xorl	%r14d, %r14d
-	movq	stdout(%rip), %rdi
+	movq	stdout(%rip), %rax
+	movq	%r15, %r12
+	xorl	%ebx, %ebx
 	.align	16, 0x90
-.LBB1_2:                                #   Parent Loop BB1_1 Depth=1
+.LBB1_2:                                # %for.body3
+                                        #   Parent Loop BB1_1 Depth=1
                                         # =>  This Inner Loop Header: Depth=2
-	movss	C+9437184(%rbx,%r14,4), %xmm0
-	cvtss2sd	%xmm0, %xmm0
+	vmovss	(%r12), %xmm0
+	vcvtss2sd	%xmm0, %xmm0, %xmm0
+	movq	%rax, %rdi
 	movl	$.L.str, %esi
 	movb	$1, %al
 	callq	fprintf
-	movslq	%r14d, %rax
+	movslq	%ebx, %rax
 	imulq	$1717986919, %rax, %rcx # imm = 0x66666667
 	movq	%rcx, %rdx
 	shrq	$63, %rdx
@@ -81,222 +117,252 @@ print_array:                            # @print_array
 	subl	%ecx, %eax
 	cmpl	$79, %eax
 	jne	.LBB1_4
-# BB#3:                                 #   in Loop: Header=BB1_2 Depth=2
+# BB#3:                                 # %if.then
+                                        #   in Loop: Header=BB1_2 Depth=2
 	movq	stdout(%rip), %rsi
 	movl	$10, %edi
 	callq	fputc
-.LBB1_4:                                #   in Loop: Header=BB1_2 Depth=2
-	incq	%r14
-	movq	stdout(%rip), %rsi
-	cmpq	$1536, %r14             # imm = 0x600
-	movq	%rsi, %rdi
+.LBB1_4:                                # %for.inc
+                                        #   in Loop: Header=BB1_2 Depth=2
+	addq	$4, %r12
+	incq	%rbx
+	movq	stdout(%rip), %rax
+	cmpq	$1536, %rbx             # imm = 0x600
 	jne	.LBB1_2
-# BB#5:                                 #   in Loop: Header=BB1_1 Depth=1
+# BB#5:                                 # %for.end
+                                        #   in Loop: Header=BB1_1 Depth=1
 	movl	$10, %edi
+	movq	%rax, %rsi
 	callq	fputc
-	addq	$6144, %rbx             # imm = 0x1800
+	addq	$6144, %r15             # imm = 0x1800
+	incq	%r14
+	cmpq	$1536, %r14             # imm = 0x600
 	jne	.LBB1_1
-# BB#6:
-	addq	$8, %rsp
+# BB#6:                                 # %for.end12
 	popq	%rbx
+	popq	%r12
 	popq	%r14
+	popq	%r15
+	popq	%rbp
 	ret
-.Ltmp1:
-	.size	print_array, .Ltmp1-print_array
+.Ltmp16:
+	.size	print_array, .Ltmp16-print_array
+	.cfi_endproc
 
 	.section	.rodata.cst8,"aM",@progbits,8
 	.align	8
 .LCPI2_0:
-	.quad	4602678819172646912     # double 5.000000e-01
+	.quad	4602678819172646912     # double 0.5
 	.text
 	.globl	main
 	.align	16, 0x90
 	.type	main,@function
 main:                                   # @main
-# BB#0:                                 # %pollyBB
+	.cfi_startproc
+# BB#0:                                 # %entry
 	pushq	%rbp
+.Ltmp20:
+	.cfi_def_cfa_offset 16
+.Ltmp21:
+	.cfi_offset %rbp, -16
+	movq	%rsp, %rbp
+.Ltmp22:
+	.cfi_def_cfa_register %rbp
 	pushq	%r15
 	pushq	%r14
 	pushq	%r13
 	pushq	%r12
 	pushq	%rbx
-	subq	$40, %rsp
-	xorl	%eax, %eax
-	movsd	.LCPI2_0(%rip), %xmm0
-	movq	%rax, %rcx
+	subq	$56, %rsp
+.Ltmp23:
+	.cfi_offset %rbx, -56
+.Ltmp24:
+	.cfi_offset %r12, -48
+.Ltmp25:
+	.cfi_offset %r13, -40
+.Ltmp26:
+	.cfi_offset %r14, -32
+.Ltmp27:
+	.cfi_offset %r15, -24
+	xorl	%ebx, %ebx
+	vmovsd	.LCPI2_0(%rip), %xmm0
 	.align	16, 0x90
-.LBB2_1:                                # %polly.loop_header1.preheader.i
+.LBB2_1:                                # %polly.loop_preheader3.i
                                         # =>This Loop Header: Depth=1
                                         #     Child Loop BB2_2 Depth 2
-	movq	$-1536, %rdx            # imm = 0xFFFFFFFFFFFFFA00
-	xorl	%esi, %esi
+	xorl	%ecx, %ecx
 	.align	16, 0x90
-.LBB2_2:                                # %polly.loop_body2.i
+.LBB2_2:                                # %polly.loop_header2.i
                                         #   Parent Loop BB2_1 Depth=1
                                         # =>  This Inner Loop Header: Depth=2
-	movl	%esi, %edi
-	sarl	$31, %edi
-	shrl	$22, %edi
-	addl	%esi, %edi
-	andl	$-1024, %edi            # imm = 0xFFFFFFFFFFFFFC00
-	negl	%edi
-	leal	1(%rsi,%rdi), %edi
-	cvtsi2sd	%edi, %xmm1
-	mulsd	%xmm0, %xmm1
-	cvtsd2ss	%xmm1, %xmm1
-	movss	%xmm1, A+6144(%rax,%rdx,4)
-	movss	%xmm1, B+6144(%rax,%rdx,4)
-	addl	%ecx, %esi
-	incq	%rdx
+	movl	%ecx, %edx
+	imull	%ebx, %edx
+	movl	%edx, %esi
+	sarl	$31, %esi
+	shrl	$22, %esi
+	addl	%edx, %esi
+	andl	$-1024, %esi            # imm = 0xFFFFFFFFFFFFFC00
+	negl	%esi
+	movq	%rbx, %rax
+	shlq	$11, %rax
+	leal	1(%rdx,%rsi), %edi
+	leaq	(%rax,%rax,2), %rsi
+	leaq	1(%rcx), %rdx
+	cmpq	$1536, %rdx             # imm = 0x600
+	vcvtsi2sdl	%edi, %xmm0, %xmm1
+	vmulsd	%xmm0, %xmm1, %xmm1
+	vcvtsd2ss	%xmm1, %xmm1, %xmm1
+	vmovss	%xmm1, A(%rsi,%rcx,4)
+	vmovss	%xmm1, B(%rsi,%rcx,4)
+	movq	%rdx, %rcx
 	jne	.LBB2_2
-# BB#3:                                 # %polly.loop_header.loopexit.i
+# BB#3:                                 # %polly.loop_exit4.i
                                         #   in Loop: Header=BB2_1 Depth=1
-	addq	$6144, %rax             # imm = 0x1800
-	incq	%rcx
-	cmpq	$1536, %rcx             # imm = 0x600
+	incq	%rbx
+	cmpq	$1536, %rbx             # imm = 0x600
 	jne	.LBB2_1
-# BB#4:                                 # %polly.loop_header.preheader
-	movl	$C, %eax
-	movq	%rax, 8(%rsp)           # 8-byte Spill
+# BB#4:                                 # %polly.loop_preheader3.preheader
+	movl	$C, %ebx
+	movl	$C, %edi
 	xorl	%esi, %esi
 	movl	$9437184, %edx          # imm = 0x900000
-	movl	$C, %edi
 	callq	memset
-	movl	$A, %eax
-	movq	%rax, 16(%rsp)          # 8-byte Spill
-	movq	$0, 32(%rsp)            # 8-byte Folded Spill
-	jmp	.LBB2_6
-	.align	16, 0x90
-.LBB2_5:                                # %polly.loop_header7.loopexit
-                                        #   in Loop: Header=BB2_6 Depth=1
-	addq	$393216, 16(%rsp)       # 8-byte Folded Spill
-                                        # imm = 0x60000
-	addq	$393216, 8(%rsp)        # 8-byte Folded Spill
-                                        # imm = 0x60000
-	movq	32(%rsp), %rax          # 8-byte Reload
-	addq	$64, %rax
-	movq	%rax, 32(%rsp)          # 8-byte Spill
-	cmpq	$1536, %rax             # imm = 0x600
-	je	.LBB2_7
-.LBB2_6:                                # %polly.loop_header12.preheader
-                                        # =>This Loop Header: Depth=1
-                                        #     Child Loop BB2_9 Depth 2
-                                        #       Child Loop BB2_11 Depth 3
-                                        #         Child Loop BB2_14 Depth 4
-                                        #           Child Loop BB2_18 Depth 5
-                                        #             Child Loop BB2_19 Depth 6
-	movq	32(%rsp), %rax          # 8-byte Reload
-	leaq	63(%rax), %rax
-	movl	$B, %ecx
-	movq	%rcx, 24(%rsp)          # 8-byte Spill
-	xorl	%ecx, %ecx
-	movq	8(%rsp), %rdx           # 8-byte Reload
-	jmp	.LBB2_9
-	.align	16, 0x90
-.LBB2_8:                                # %polly.loop_header12.loopexit
-                                        #   in Loop: Header=BB2_9 Depth=2
-	addq	$256, %rdx              # imm = 0x100
-	addq	$256, 24(%rsp)          # 8-byte Folded Spill
-                                        # imm = 0x100
-	addq	$64, %rcx
-	cmpq	$1536, %rcx             # imm = 0x600
-	je	.LBB2_5
-.LBB2_9:                                # %polly.loop_header17.preheader
-                                        #   Parent Loop BB2_6 Depth=1
-                                        # =>  This Loop Header: Depth=2
-                                        #       Child Loop BB2_11 Depth 3
-                                        #         Child Loop BB2_14 Depth 4
-                                        #           Child Loop BB2_18 Depth 5
-                                        #             Child Loop BB2_19 Depth 6
-	leaq	63(%rcx), %rsi
-	xorl	%edi, %edi
-	movq	16(%rsp), %r8           # 8-byte Reload
-	movq	24(%rsp), %r9           # 8-byte Reload
-	jmp	.LBB2_11
-	.align	16, 0x90
-.LBB2_10:                               # %polly.loop_header17.loopexit
-                                        #   in Loop: Header=BB2_11 Depth=3
-	addq	$256, %r8               # imm = 0x100
-	addq	$393216, %r9            # imm = 0x60000
-	addq	$64, %rdi
-	cmpq	$1536, %rdi             # imm = 0x600
-	je	.LBB2_8
-.LBB2_11:                               # %polly.loop_body18
-                                        #   Parent Loop BB2_6 Depth=1
-                                        #     Parent Loop BB2_9 Depth=2
-                                        # =>    This Loop Header: Depth=3
-                                        #         Child Loop BB2_14 Depth 4
-                                        #           Child Loop BB2_18 Depth 5
-                                        #             Child Loop BB2_19 Depth 6
-	cmpq	%rax, 32(%rsp)          # 8-byte Folded Reload
-	jg	.LBB2_10
-# BB#12:                                # %polly.loop_body23.lr.ph
-                                        #   in Loop: Header=BB2_11 Depth=3
-	leaq	63(%rdi), %r10
-	xorl	%r11d, %r11d
-	jmp	.LBB2_14
-	.align	16, 0x90
-.LBB2_13:                               # %polly.loop_header22.loopexit
-                                        #   in Loop: Header=BB2_14 Depth=4
-	addq	$6144, %r11             # imm = 0x1800
-	cmpq	$393216, %r11           # imm = 0x60000
-	je	.LBB2_10
-.LBB2_14:                               # %polly.loop_body23
-                                        #   Parent Loop BB2_6 Depth=1
-                                        #     Parent Loop BB2_9 Depth=2
-                                        #       Parent Loop BB2_11 Depth=3
-                                        # =>      This Loop Header: Depth=4
-                                        #           Child Loop BB2_18 Depth 5
-                                        #             Child Loop BB2_19 Depth 6
-	cmpq	%r10, %rdi
-	jg	.LBB2_13
-# BB#15:                                # %polly.loop_body23
-                                        #   in Loop: Header=BB2_14 Depth=4
-	cmpq	%rsi, %rcx
-	jg	.LBB2_13
-# BB#16:                                # %polly.loop_body33.lr.ph.preheader
-                                        #   in Loop: Header=BB2_14 Depth=4
-	leaq	(%rdx,%r11), %rbx
-	leaq	(%r8,%r11), %r14
-	xorl	%r15d, %r15d
-	movq	%r9, %r12
-	movq	%r15, %r13
-	jmp	.LBB2_18
-	.align	16, 0x90
-.LBB2_17:                               # %polly.loop_header27.loopexit
-                                        #   in Loop: Header=BB2_18 Depth=5
-	addq	$6144, %r12             # imm = 0x1800
-	incq	%r13
-	cmpq	$64, %r13
-	je	.LBB2_13
-.LBB2_18:                               # %polly.loop_body33.lr.ph
-                                        #   Parent Loop BB2_6 Depth=1
-                                        #     Parent Loop BB2_9 Depth=2
-                                        #       Parent Loop BB2_11 Depth=3
-                                        #         Parent Loop BB2_14 Depth=4
-                                        # =>        This Loop Header: Depth=5
-                                        #             Child Loop BB2_19 Depth 6
-	movss	(%r14,%r13,4), %xmm0
-	movq	%r15, %rbp
-	.align	16, 0x90
-.LBB2_19:                               # %polly.loop_body33
-                                        #   Parent Loop BB2_6 Depth=1
-                                        #     Parent Loop BB2_9 Depth=2
-                                        #       Parent Loop BB2_11 Depth=3
-                                        #         Parent Loop BB2_14 Depth=4
-                                        #           Parent Loop BB2_18 Depth=5
-                                        # =>          This Inner Loop Header: Depth=6
-	movss	(%r12,%rbp,4), %xmm1
-	mulss	%xmm0, %xmm1
-	addss	(%rbx,%rbp,4), %xmm1
-	movss	%xmm1, (%rbx,%rbp,4)
-	incq	%rbp
-	cmpq	$64, %rbp
-	jne	.LBB2_19
-	jmp	.LBB2_17
-.LBB2_7:                                # %polly.after_loop9
 	xorl	%eax, %eax
-	addq	$40, %rsp
+	.align	16, 0x90
+.LBB2_5:                                # %polly.loop_preheader17
+                                        # =>This Loop Header: Depth=1
+                                        #     Child Loop BB2_15 Depth 2
+                                        #       Child Loop BB2_8 Depth 3
+                                        #         Child Loop BB2_11 Depth 4
+                                        #           Child Loop BB2_17 Depth 5
+                                        #             Child Loop BB2_18 Depth 6
+	movq	%rax, -56(%rbp)         # 8-byte Spill
+	movq	%rbx, -88(%rbp)         # 8-byte Spill
+	movq	%rax, %rcx
+	orq	$63, %rcx
+	movq	%rcx, -72(%rbp)         # 8-byte Spill
+	leaq	-1(%rcx), %rcx
+	movq	%rcx, -48(%rbp)         # 8-byte Spill
+	movq	$-1, %r15
+	movl	$B, %ecx
+	movq	%rbx, -64(%rbp)         # 8-byte Spill
+	xorl	%r12d, %r12d
+	.align	16, 0x90
+.LBB2_15:                               # %polly.loop_preheader24
+                                        #   Parent Loop BB2_5 Depth=1
+                                        # =>  This Loop Header: Depth=2
+                                        #       Child Loop BB2_8 Depth 3
+                                        #         Child Loop BB2_11 Depth 4
+                                        #           Child Loop BB2_17 Depth 5
+                                        #             Child Loop BB2_18 Depth 6
+	movq	%rcx, -80(%rbp)         # 8-byte Spill
+	movq	%r12, %r13
+	orq	$63, %r13
+	leaq	-1(%r13), %rbx
+	xorl	%r9d, %r9d
+	movq	%rcx, %rdx
+	.align	16, 0x90
+.LBB2_8:                                # %polly.loop_header23
+                                        #   Parent Loop BB2_5 Depth=1
+                                        #     Parent Loop BB2_15 Depth=2
+                                        # =>    This Loop Header: Depth=3
+                                        #         Child Loop BB2_11 Depth 4
+                                        #           Child Loop BB2_17 Depth 5
+                                        #             Child Loop BB2_18 Depth 6
+	cmpq	-72(%rbp), %rax         # 8-byte Folded Reload
+	jg	.LBB2_13
+# BB#9:                                 # %polly.loop_header30.preheader
+                                        #   in Loop: Header=BB2_8 Depth=3
+	movq	%r9, %rax
+	orq	$63, %rax
+	cmpq	%rax, %r9
+	jg	.LBB2_13
+# BB#10:                                #   in Loop: Header=BB2_8 Depth=3
+	decq	%rax
+	movq	-64(%rbp), %r10         # 8-byte Reload
+	movq	-56(%rbp), %r11         # 8-byte Reload
+	.align	16, 0x90
+.LBB2_11:                               # %polly.loop_header37.preheader
+                                        #   Parent Loop BB2_5 Depth=1
+                                        #     Parent Loop BB2_15 Depth=2
+                                        #       Parent Loop BB2_8 Depth=3
+                                        # =>      This Loop Header: Depth=4
+                                        #           Child Loop BB2_17 Depth 5
+                                        #             Child Loop BB2_18 Depth 6
+	cmpq	%r13, %r12
+	movq	%rdx, %r14
+	movq	%r9, %rcx
+	jg	.LBB2_12
+	.align	16, 0x90
+.LBB2_17:                               # %polly.loop_header46.preheader
+                                        #   Parent Loop BB2_5 Depth=1
+                                        #     Parent Loop BB2_15 Depth=2
+                                        #       Parent Loop BB2_8 Depth=3
+                                        #         Parent Loop BB2_11 Depth=4
+                                        # =>        This Loop Header: Depth=5
+                                        #             Child Loop BB2_18 Depth 6
+	leaq	(%r11,%r11,2), %rsi
+	shlq	$11, %rsi
+	vmovss	A(%rsi,%rcx,4), %xmm0
+	movq	%r10, %rdi
+	movq	%r14, %r8
+	movq	%r15, %rsi
+.LBB2_18:                               # %polly.loop_header46
+                                        #   Parent Loop BB2_5 Depth=1
+                                        #     Parent Loop BB2_15 Depth=2
+                                        #       Parent Loop BB2_8 Depth=3
+                                        #         Parent Loop BB2_11 Depth=4
+                                        #           Parent Loop BB2_17 Depth=5
+                                        # =>          This Inner Loop Header: Depth=6
+	vmulss	(%r8), %xmm0, %xmm1
+	vaddss	(%rdi), %xmm1, %xmm1
+	vmovss	%xmm1, (%rdi)
+	addq	$4, %rdi
+	addq	$4, %r8
+	incq	%rsi
+	cmpq	%rbx, %rsi
+	jle	.LBB2_18
+# BB#16:                                # %polly.loop_exit48
+                                        #   in Loop: Header=BB2_17 Depth=5
+	addq	$6144, %r14             # imm = 0x1800
+	cmpq	%rax, %rcx
+	leaq	1(%rcx), %rcx
+	jle	.LBB2_17
+	.align	16, 0x90
+.LBB2_12:                               # %polly.loop_exit39
+                                        #   in Loop: Header=BB2_11 Depth=4
+	addq	$6144, %r10             # imm = 0x1800
+	cmpq	-48(%rbp), %r11         # 8-byte Folded Reload
+	leaq	1(%r11), %r11
+	jle	.LBB2_11
+	.align	16, 0x90
+.LBB2_13:                               # %polly.loop_exit32
+                                        #   in Loop: Header=BB2_8 Depth=3
+	addq	$393216, %rdx           # imm = 0x60000
+	cmpq	$1472, %r9              # imm = 0x5C0
+	leaq	64(%r9), %r9
+	movq	-56(%rbp), %rax         # 8-byte Reload
+	jl	.LBB2_8
+# BB#14:                                # %polly.loop_exit25
+                                        #   in Loop: Header=BB2_15 Depth=2
+	addq	$256, -64(%rbp)         # 8-byte Folded Spill
+                                        # imm = 0x100
+	movq	-80(%rbp), %rcx         # 8-byte Reload
+	addq	$256, %rcx              # imm = 0x100
+	addq	$64, %r15
+	cmpq	$1472, %r12             # imm = 0x5C0
+	leaq	64(%r12), %r12
+	jl	.LBB2_15
+# BB#6:                                 # %polly.loop_exit18
+                                        #   in Loop: Header=BB2_5 Depth=1
+	movq	-88(%rbp), %rbx         # 8-byte Reload
+	addq	$393216, %rbx           # imm = 0x60000
+	cmpq	$1472, %rax             # imm = 0x5C0
+	leaq	64(%rax), %rax
+	jl	.LBB2_5
+# BB#7:                                 # %polly.loop_exit11
+	xorl	%eax, %eax
+	addq	$56, %rsp
 	popq	%rbx
 	popq	%r12
 	popq	%r13
@@ -304,8 +370,9 @@ main:                                   # @main
 	popq	%r15
 	popq	%rbp
 	ret
-.Ltmp2:
-	.size	main, .Ltmp2-main
+.Ltmp28:
+	.size	main, .Ltmp28-main
+	.cfi_endproc
 
 	.type	A,@object               # @A
 	.comm	A,9437184,16
diff --git a/polly/www/experiments/matmul/matmul.polly.interchanged.exe b/polly/www/experiments/matmul/matmul.polly.interchanged.exe
index cc125c4b2b1a..240c95a7f790 100755
Binary files a/polly/www/experiments/matmul/matmul.polly.interchanged.exe and b/polly/www/experiments/matmul/matmul.polly.interchanged.exe differ
diff --git a/polly/www/experiments/matmul/matmul.polly.interchanged.ll b/polly/www/experiments/matmul/matmul.polly.interchanged.ll
index c0a54bb64f45..52fbccc7ed5c 100644
Binary files a/polly/www/experiments/matmul/matmul.polly.interchanged.ll and b/polly/www/experiments/matmul/matmul.polly.interchanged.ll differ
diff --git a/polly/www/experiments/matmul/matmul.polly.interchanged.s b/polly/www/experiments/matmul/matmul.polly.interchanged.s
index 8bbc523f764e..a764da0b3f22 100644
--- a/polly/www/experiments/matmul/matmul.polly.interchanged.s
+++ b/polly/www/experiments/matmul/matmul.polly.interchanged.s
@@ -2,76 +2,112 @@
 	.section	.rodata.cst8,"aM",@progbits,8
 	.align	8
 .LCPI0_0:
-	.quad	4602678819172646912     # double 5.000000e-01
+	.quad	4602678819172646912     # double 0.5
 	.text
 	.globl	init_array
 	.align	16, 0x90
 	.type	init_array,@function
 init_array:                             # @init_array
-# BB#0:                                 # %pollyBB
-	xorl	%eax, %eax
-	movsd	.LCPI0_0(%rip), %xmm0
-	movq	%rax, %rcx
+	.cfi_startproc
+# BB#0:                                 # %entry
+	pushq	%rbp
+.Ltmp2:
+	.cfi_def_cfa_offset 16
+.Ltmp3:
+	.cfi_offset %rbp, -16
+	movq	%rsp, %rbp
+.Ltmp4:
+	.cfi_def_cfa_register %rbp
+	xorl	%r8d, %r8d
+	vmovsd	.LCPI0_0(%rip), %xmm0
 	.align	16, 0x90
-.LBB0_2:                                # %polly.loop_header1.preheader
+.LBB0_1:                                # %polly.loop_preheader3
                                         # =>This Loop Header: Depth=1
-                                        #     Child Loop BB0_3 Depth 2
-	movq	$-1536, %rdx            # imm = 0xFFFFFFFFFFFFFA00
-	xorl	%esi, %esi
+                                        #     Child Loop BB0_2 Depth 2
+	xorl	%ecx, %ecx
 	.align	16, 0x90
-.LBB0_3:                                # %polly.loop_body2
-                                        #   Parent Loop BB0_2 Depth=1
+.LBB0_2:                                # %polly.loop_header2
+                                        #   Parent Loop BB0_1 Depth=1
                                         # =>  This Inner Loop Header: Depth=2
-	movl	%esi, %edi
-	sarl	$31, %edi
-	shrl	$22, %edi
-	addl	%esi, %edi
-	andl	$-1024, %edi            # imm = 0xFFFFFFFFFFFFFC00
-	negl	%edi
-	leal	1(%rsi,%rdi), %edi
-	cvtsi2sd	%edi, %xmm1
-	mulsd	%xmm0, %xmm1
-	cvtsd2ss	%xmm1, %xmm1
-	movss	%xmm1, A+6144(%rax,%rdx,4)
-	movss	%xmm1, B+6144(%rax,%rdx,4)
-	addl	%ecx, %esi
-	incq	%rdx
-	jne	.LBB0_3
-# BB#1:                                 # %polly.loop_header.loopexit
-                                        #   in Loop: Header=BB0_2 Depth=1
-	addq	$6144, %rax             # imm = 0x1800
-	incq	%rcx
-	cmpq	$1536, %rcx             # imm = 0x600
+	movl	%ecx, %edx
+	imull	%r8d, %edx
+	movl	%edx, %esi
+	sarl	$31, %esi
+	shrl	$22, %esi
+	addl	%edx, %esi
+	andl	$-1024, %esi            # imm = 0xFFFFFFFFFFFFFC00
+	negl	%esi
+	movq	%r8, %rax
+	shlq	$11, %rax
+	leal	1(%rdx,%rsi), %edi
+	leaq	(%rax,%rax,2), %rsi
+	leaq	1(%rcx), %rdx
+	cmpq	$1536, %rdx             # imm = 0x600
+	vcvtsi2sdl	%edi, %xmm0, %xmm1
+	vmulsd	%xmm0, %xmm1, %xmm1
+	vcvtsd2ss	%xmm1, %xmm1, %xmm1
+	vmovss	%xmm1, A(%rsi,%rcx,4)
+	vmovss	%xmm1, B(%rsi,%rcx,4)
+	movq	%rdx, %rcx
 	jne	.LBB0_2
-# BB#4:                                 # %polly.after_loop
+# BB#3:                                 # %polly.loop_exit4
+                                        #   in Loop: Header=BB0_1 Depth=1
+	incq	%r8
+	cmpq	$1536, %r8              # imm = 0x600
+	jne	.LBB0_1
+# BB#4:                                 # %polly.loop_exit
+	popq	%rbp
 	ret
-.Ltmp0:
-	.size	init_array, .Ltmp0-init_array
+.Ltmp5:
+	.size	init_array, .Ltmp5-init_array
+	.cfi_endproc
 
 	.globl	print_array
 	.align	16, 0x90
 	.type	print_array,@function
 print_array:                            # @print_array
-# BB#0:
+	.cfi_startproc
+# BB#0:                                 # %entry
+	pushq	%rbp
+.Ltmp9:
+	.cfi_def_cfa_offset 16
+.Ltmp10:
+	.cfi_offset %rbp, -16
+	movq	%rsp, %rbp
+.Ltmp11:
+	.cfi_def_cfa_register %rbp
+	pushq	%r15
 	pushq	%r14
+	pushq	%r12
 	pushq	%rbx
-	pushq	%rax
-	movq	$-9437184, %rbx         # imm = 0xFFFFFFFFFF700000
+.Ltmp12:
+	.cfi_offset %rbx, -48
+.Ltmp13:
+	.cfi_offset %r12, -40
+.Ltmp14:
+	.cfi_offset %r14, -32
+.Ltmp15:
+	.cfi_offset %r15, -24
+	xorl	%r14d, %r14d
+	movl	$C, %r15d
 	.align	16, 0x90
-.LBB1_1:                                # %.preheader
+.LBB1_1:                                # %for.cond1.preheader
                                         # =>This Loop Header: Depth=1
                                         #     Child Loop BB1_2 Depth 2
-	xorl	%r14d, %r14d
-	movq	stdout(%rip), %rdi
+	movq	stdout(%rip), %rax
+	movq	%r15, %r12
+	xorl	%ebx, %ebx
 	.align	16, 0x90
-.LBB1_2:                                #   Parent Loop BB1_1 Depth=1
+.LBB1_2:                                # %for.body3
+                                        #   Parent Loop BB1_1 Depth=1
                                         # =>  This Inner Loop Header: Depth=2
-	movss	C+9437184(%rbx,%r14,4), %xmm0
-	cvtss2sd	%xmm0, %xmm0
+	vmovss	(%r12), %xmm0
+	vcvtss2sd	%xmm0, %xmm0, %xmm0
+	movq	%rax, %rdi
 	movl	$.L.str, %esi
 	movb	$1, %al
 	callq	fprintf
-	movslq	%r14d, %rax
+	movslq	%ebx, %rax
 	imulq	$1717986919, %rax, %rcx # imm = 0x66666667
 	movq	%rcx, %rdx
 	shrq	$63, %rdx
@@ -81,125 +117,158 @@ print_array:                            # @print_array
 	subl	%ecx, %eax
 	cmpl	$79, %eax
 	jne	.LBB1_4
-# BB#3:                                 #   in Loop: Header=BB1_2 Depth=2
+# BB#3:                                 # %if.then
+                                        #   in Loop: Header=BB1_2 Depth=2
 	movq	stdout(%rip), %rsi
 	movl	$10, %edi
 	callq	fputc
-.LBB1_4:                                #   in Loop: Header=BB1_2 Depth=2
-	incq	%r14
-	movq	stdout(%rip), %rsi
-	cmpq	$1536, %r14             # imm = 0x600
-	movq	%rsi, %rdi
+.LBB1_4:                                # %for.inc
+                                        #   in Loop: Header=BB1_2 Depth=2
+	addq	$4, %r12
+	incq	%rbx
+	movq	stdout(%rip), %rax
+	cmpq	$1536, %rbx             # imm = 0x600
 	jne	.LBB1_2
-# BB#5:                                 #   in Loop: Header=BB1_1 Depth=1
+# BB#5:                                 # %for.end
+                                        #   in Loop: Header=BB1_1 Depth=1
 	movl	$10, %edi
+	movq	%rax, %rsi
 	callq	fputc
-	addq	$6144, %rbx             # imm = 0x1800
+	addq	$6144, %r15             # imm = 0x1800
+	incq	%r14
+	cmpq	$1536, %r14             # imm = 0x600
 	jne	.LBB1_1
-# BB#6:
-	addq	$8, %rsp
+# BB#6:                                 # %for.end12
 	popq	%rbx
+	popq	%r12
 	popq	%r14
+	popq	%r15
+	popq	%rbp
 	ret
-.Ltmp1:
-	.size	print_array, .Ltmp1-print_array
+.Ltmp16:
+	.size	print_array, .Ltmp16-print_array
+	.cfi_endproc
 
 	.section	.rodata.cst8,"aM",@progbits,8
 	.align	8
 .LCPI2_0:
-	.quad	4602678819172646912     # double 5.000000e-01
+	.quad	4602678819172646912     # double 0.5
 	.text
 	.globl	main
 	.align	16, 0x90
 	.type	main,@function
 main:                                   # @main
-# BB#0:                                 # %pollyBB
-	pushq	%rax
-	xorl	%eax, %eax
-	movsd	.LCPI2_0(%rip), %xmm0
-	movq	%rax, %rcx
+	.cfi_startproc
+# BB#0:                                 # %entry
+	pushq	%rbp
+.Ltmp20:
+	.cfi_def_cfa_offset 16
+.Ltmp21:
+	.cfi_offset %rbp, -16
+	movq	%rsp, %rbp
+.Ltmp22:
+	.cfi_def_cfa_register %rbp
+	pushq	%r14
+	pushq	%rbx
+.Ltmp23:
+	.cfi_offset %rbx, -32
+.Ltmp24:
+	.cfi_offset %r14, -24
+	xorl	%ebx, %ebx
+	vmovsd	.LCPI2_0(%rip), %xmm0
 	.align	16, 0x90
-.LBB2_1:                                # %polly.loop_header1.preheader.i
+.LBB2_1:                                # %polly.loop_preheader3.i
                                         # =>This Loop Header: Depth=1
                                         #     Child Loop BB2_2 Depth 2
-	movq	$-1536, %rdx            # imm = 0xFFFFFFFFFFFFFA00
-	xorl	%esi, %esi
+	xorl	%ecx, %ecx
 	.align	16, 0x90
-.LBB2_2:                                # %polly.loop_body2.i
+.LBB2_2:                                # %polly.loop_header2.i
                                         #   Parent Loop BB2_1 Depth=1
                                         # =>  This Inner Loop Header: Depth=2
-	movl	%esi, %edi
-	sarl	$31, %edi
-	shrl	$22, %edi
-	addl	%esi, %edi
-	andl	$-1024, %edi            # imm = 0xFFFFFFFFFFFFFC00
-	negl	%edi
-	leal	1(%rsi,%rdi), %edi
-	cvtsi2sd	%edi, %xmm1
-	mulsd	%xmm0, %xmm1
-	cvtsd2ss	%xmm1, %xmm1
-	movss	%xmm1, A+6144(%rax,%rdx,4)
-	movss	%xmm1, B+6144(%rax,%rdx,4)
-	addl	%ecx, %esi
-	incq	%rdx
+	movl	%ecx, %edx
+	imull	%ebx, %edx
+	movl	%edx, %esi
+	sarl	$31, %esi
+	shrl	$22, %esi
+	addl	%edx, %esi
+	andl	$-1024, %esi            # imm = 0xFFFFFFFFFFFFFC00
+	negl	%esi
+	movq	%rbx, %rax
+	shlq	$11, %rax
+	leal	1(%rdx,%rsi), %edi
+	leaq	(%rax,%rax,2), %rsi
+	leaq	1(%rcx), %rdx
+	cmpq	$1536, %rdx             # imm = 0x600
+	vcvtsi2sdl	%edi, %xmm0, %xmm1
+	vmulsd	%xmm0, %xmm1, %xmm1
+	vcvtsd2ss	%xmm1, %xmm1, %xmm1
+	vmovss	%xmm1, A(%rsi,%rcx,4)
+	vmovss	%xmm1, B(%rsi,%rcx,4)
+	movq	%rdx, %rcx
 	jne	.LBB2_2
-# BB#3:                                 # %polly.loop_header.loopexit.i
+# BB#3:                                 # %polly.loop_exit4.i
                                         #   in Loop: Header=BB2_1 Depth=1
-	addq	$6144, %rax             # imm = 0x1800
-	incq	%rcx
-	cmpq	$1536, %rcx             # imm = 0x600
+	incq	%rbx
+	cmpq	$1536, %rbx             # imm = 0x600
 	jne	.LBB2_1
-# BB#4:                                 # %polly.loop_header.preheader
+# BB#4:                                 # %polly.loop_preheader3.preheader
+	movl	$C, %r14d
 	movl	$C, %edi
 	xorl	%esi, %esi
 	movl	$9437184, %edx          # imm = 0x900000
 	callq	memset
 	xorl	%eax, %eax
-	jmp	.LBB2_6
 	.align	16, 0x90
-.LBB2_5:                                # %polly.loop_header7.loopexit
-                                        #   in Loop: Header=BB2_6 Depth=1
-	addq	$6144, %rax             # imm = 0x1800
-	cmpq	$9437184, %rax          # imm = 0x900000
-	je	.LBB2_7
-.LBB2_6:                                # %polly.loop_header12.preheader
+.LBB2_5:                                # %polly.loop_preheader17
                                         # =>This Loop Header: Depth=1
-                                        #     Child Loop BB2_9 Depth 2
-                                        #       Child Loop BB2_10 Depth 3
-	leaq	A(%rax), %rcx
-	movq	$-9437184, %rdx         # imm = 0xFFFFFFFFFF700000
-	jmp	.LBB2_9
+                                        #     Child Loop BB2_10 Depth 2
+                                        #       Child Loop BB2_8 Depth 3
+	movl	$B, %ebx
+	xorl	%edx, %edx
 	.align	16, 0x90
-.LBB2_8:                                # %polly.loop_header12.loopexit
-                                        #   in Loop: Header=BB2_9 Depth=2
-	addq	$4, %rcx
-	addq	$6144, %rdx             # imm = 0x1800
-	je	.LBB2_5
-.LBB2_9:                                # %polly.loop_header17.preheader
-                                        #   Parent Loop BB2_6 Depth=1
+.LBB2_10:                               # %polly.loop_preheader24
+                                        #   Parent Loop BB2_5 Depth=1
                                         # =>  This Loop Header: Depth=2
-                                        #       Child Loop BB2_10 Depth 3
-	movss	(%rcx), %xmm0
-	xorl	%esi, %esi
+                                        #       Child Loop BB2_8 Depth 3
+	leaq	(%rax,%rax,2), %rcx
+	shlq	$11, %rcx
+	vmovss	A(%rcx,%rdx,4), %xmm0
+	movl	$1536, %esi             # imm = 0x600
+	movq	%r14, %rdi
+	movq	%rbx, %rcx
 	.align	16, 0x90
-.LBB2_10:                               # %polly.loop_body18
-                                        #   Parent Loop BB2_6 Depth=1
-                                        #     Parent Loop BB2_9 Depth=2
+.LBB2_8:                                # %polly.loop_header23
+                                        #   Parent Loop BB2_5 Depth=1
+                                        #     Parent Loop BB2_10 Depth=2
                                         # =>    This Inner Loop Header: Depth=3
-	movss	B+9437184(%rdx,%rsi,4), %xmm1
-	mulss	%xmm0, %xmm1
-	addss	C(%rax,%rsi,4), %xmm1
-	movss	%xmm1, C(%rax,%rsi,4)
-	incq	%rsi
-	cmpq	$1536, %rsi             # imm = 0x600
+	vmulss	(%rcx), %xmm0, %xmm1
+	vaddss	(%rdi), %xmm1, %xmm1
+	vmovss	%xmm1, (%rdi)
+	addq	$4, %rdi
+	addq	$4, %rcx
+	decq	%rsi
+	jne	.LBB2_8
+# BB#9:                                 # %polly.loop_exit25
+                                        #   in Loop: Header=BB2_10 Depth=2
+	addq	$6144, %rbx             # imm = 0x1800
+	incq	%rdx
+	cmpq	$1536, %rdx             # imm = 0x600
 	jne	.LBB2_10
-	jmp	.LBB2_8
-.LBB2_7:                                # %polly.after_loop9
+# BB#6:                                 # %polly.loop_exit18
+                                        #   in Loop: Header=BB2_5 Depth=1
+	addq	$6144, %r14             # imm = 0x1800
+	incq	%rax
+	cmpq	$1536, %rax             # imm = 0x600
+	jne	.LBB2_5
+# BB#7:                                 # %polly.loop_exit11
 	xorl	%eax, %eax
-	popq	%rdx
+	popq	%rbx
+	popq	%r14
+	popq	%rbp
 	ret
-.Ltmp2:
-	.size	main, .Ltmp2-main
+.Ltmp25:
+	.size	main, .Ltmp25-main
+	.cfi_endproc
 
 	.type	A,@object               # @A
 	.comm	A,9437184,16
diff --git a/polly/www/experiments/matmul/matmul.preopt.ll b/polly/www/experiments/matmul/matmul.preopt.ll
index 9287d7e141b0..3931716619bf 100644
--- a/polly/www/experiments/matmul/matmul.preopt.ll
+++ b/polly/www/experiments/matmul/matmul.preopt.ll
@@ -1,5 +1,5 @@
 ; ModuleID = 'matmul.s'
-target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
 
 %struct._IO_FILE = type { i32, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, %struct._IO_marker*, %struct._IO_FILE*, i32, i32, i64, i16, i8, [1 x i8], i8*, i64, i8*, i8*, i8*, i8*, i64, i32, [20 x i8] }
@@ -8,173 +8,179 @@ target triple = "x86_64-unknown-linux-gnu"
 @A = common global [1536 x [1536 x float]] zeroinitializer, align 16
 @B = common global [1536 x [1536 x float]] zeroinitializer, align 16
 @stdout = external global %struct._IO_FILE*
-@.str = private unnamed_addr constant [5 x i8] c"%lf \00"
+@.str = private unnamed_addr constant [5 x i8] c"%lf \00", align 1
 @C = common global [1536 x [1536 x float]] zeroinitializer, align 16
-@.str1 = private unnamed_addr constant [2 x i8] c"\0A\00"
+@.str1 = private unnamed_addr constant [2 x i8] c"\0A\00", align 1
 
-define void @init_array() nounwind {
-; <label>:0
-  br label %1
+; Function Attrs: nounwind uwtable
+define void @init_array() #0 {
+entry:
+  br label %for.cond
 
-; <label>:1                                       ; preds = %18, %0
-  %2 = phi i64 [ %indvar.next2, %18 ], [ 0, %0 ]
-  %exitcond5 = icmp ne i64 %2, 1536
-  br i1 %exitcond5, label %3, label %19
+for.cond:                                         ; preds = %for.inc17, %entry
+  %0 = phi i64 [ %indvar.next2, %for.inc17 ], [ 0, %entry ]
+  %exitcond3 = icmp ne i64 %0, 1536
+  br i1 %exitcond3, label %for.body, label %for.end19
 
-; <label>:3                                       ; preds = %1
-  br label %4
+for.body:                                         ; preds = %for.cond
+  br label %for.cond1
 
-; <label>:4                                       ; preds = %16, %3
-  %indvar = phi i64 [ %indvar.next, %16 ], [ 0, %3 ]
-  %scevgep4 = getelementptr [1536 x [1536 x float]]* @A, i64 0, i64 %2, i64 %indvar
-  %scevgep = getelementptr [1536 x [1536 x float]]* @B, i64 0, i64 %2, i64 %indvar
-  %tmp = mul i64 %2, %indvar
-  %tmp3 = trunc i64 %tmp to i32
+for.cond1:                                        ; preds = %for.inc, %for.body
+  %indvar = phi i64 [ %indvar.next, %for.inc ], [ 0, %for.body ]
+  %arrayidx6 = getelementptr [1536 x [1536 x float]]* @A, i64 0, i64 %0, i64 %indvar
+  %arrayidx16 = getelementptr [1536 x [1536 x float]]* @B, i64 0, i64 %0, i64 %indvar
+  %1 = mul i64 %0, %indvar
+  %mul = trunc i64 %1 to i32
   %exitcond = icmp ne i64 %indvar, 1536
-  br i1 %exitcond, label %5, label %17
+  br i1 %exitcond, label %for.body3, label %for.end
 
-; <label>:5                                       ; preds = %4
-  %6 = srem i32 %tmp3, 1024
-  %7 = add nsw i32 1, %6
-  %8 = sitofp i32 %7 to double
-  %9 = fdiv double %8, 2.000000e+00
-  %10 = fptrunc double %9 to float
-  store float %10, float* %scevgep4
-  %11 = srem i32 %tmp3, 1024
-  %12 = add nsw i32 1, %11
-  %13 = sitofp i32 %12 to double
-  %14 = fdiv double %13, 2.000000e+00
-  %15 = fptrunc double %14 to float
-  store float %15, float* %scevgep
-  br label %16
+for.body3:                                        ; preds = %for.cond1
+  %rem = srem i32 %mul, 1024
+  %add = add nsw i32 1, %rem
+  %conv = sitofp i32 %add to double
+  %div = fdiv double %conv, 2.000000e+00
+  %conv4 = fptrunc double %div to float
+  store float %conv4, float* %arrayidx6, align 4
+  %rem8 = srem i32 %mul, 1024
+  %add9 = add nsw i32 1, %rem8
+  %conv10 = sitofp i32 %add9 to double
+  %div11 = fdiv double %conv10, 2.000000e+00
+  %conv12 = fptrunc double %div11 to float
+  store float %conv12, float* %arrayidx16, align 4
+  br label %for.inc
 
-; <label>:16                                      ; preds = %5
+for.inc:                                          ; preds = %for.body3
   %indvar.next = add i64 %indvar, 1
-  br label %4
+  br label %for.cond1
 
-; <label>:17                                      ; preds = %4
-  br label %18
+for.end:                                          ; preds = %for.cond1
+  br label %for.inc17
 
-; <label>:18                                      ; preds = %17
-  %indvar.next2 = add i64 %2, 1
-  br label %1
+for.inc17:                                        ; preds = %for.end
+  %indvar.next2 = add i64 %0, 1
+  br label %for.cond
 
-; <label>:19                                      ; preds = %1
+for.end19:                                        ; preds = %for.cond
   ret void
 }
 
-define void @print_array() nounwind {
-; <label>:0
-  br label %1
+; Function Attrs: nounwind uwtable
+define void @print_array() #0 {
+entry:
+  br label %for.cond
 
-; <label>:1                                       ; preds = %19, %0
-  %indvar1 = phi i64 [ %indvar.next2, %19 ], [ 0, %0 ]
+for.cond:                                         ; preds = %for.inc10, %entry
+  %indvar1 = phi i64 [ %indvar.next2, %for.inc10 ], [ 0, %entry ]
   %exitcond3 = icmp ne i64 %indvar1, 1536
-  br i1 %exitcond3, label %2, label %20
+  br i1 %exitcond3, label %for.body, label %for.end12
 
-; <label>:2                                       ; preds = %1
-  br label %3
+for.body:                                         ; preds = %for.cond
+  br label %for.cond1
 
-; <label>:3                                       ; preds = %15, %2
-  %indvar = phi i64 [ %indvar.next, %15 ], [ 0, %2 ]
-  %scevgep = getelementptr [1536 x [1536 x float]]* @C, i64 0, i64 %indvar1, i64 %indvar
+for.cond1:                                        ; preds = %for.inc, %for.body
+  %indvar = phi i64 [ %indvar.next, %for.inc ], [ 0, %for.body ]
+  %arrayidx5 = getelementptr [1536 x [1536 x float]]* @C, i64 0, i64 %indvar1, i64 %indvar
   %j.0 = trunc i64 %indvar to i32
   %exitcond = icmp ne i64 %indvar, 1536
-  br i1 %exitcond, label %4, label %16
+  br i1 %exitcond, label %for.body3, label %for.end
 
-; <label>:4                                       ; preds = %3
-  %5 = load %struct._IO_FILE** @stdout, align 8
-  %6 = load float* %scevgep
-  %7 = fpext float %6 to double
-  %8 = call i32 (%struct._IO_FILE*, i8*, ...)* @fprintf(%struct._IO_FILE* %5, i8* getelementptr inbounds ([5 x i8]* @.str, i32 0, i32 0), double %7)
-  %9 = srem i32 %j.0, 80
-  %10 = icmp eq i32 %9, 79
-  br i1 %10, label %11, label %14
+for.body3:                                        ; preds = %for.cond1
+  %0 = load %struct._IO_FILE** @stdout, align 8
+  %1 = load float* %arrayidx5, align 4
+  %conv = fpext float %1 to double
+  %call = call i32 (%struct._IO_FILE*, i8*, ...)* @fprintf(%struct._IO_FILE* %0, i8* getelementptr inbounds ([5 x i8]* @.str, i32 0, i32 0), double %conv)
+  %rem = srem i32 %j.0, 80
+  %cmp6 = icmp eq i32 %rem, 79
+  br i1 %cmp6, label %if.then, label %if.end
 
-; <label>:11                                      ; preds = %4
-  %12 = load %struct._IO_FILE** @stdout, align 8
-  %13 = call i32 (%struct._IO_FILE*, i8*, ...)* @fprintf(%struct._IO_FILE* %12, i8* getelementptr inbounds ([2 x i8]* @.str1, i32 0, i32 0))
-  br label %14
+if.then:                                          ; preds = %for.body3
+  %2 = load %struct._IO_FILE** @stdout, align 8
+  %call8 = call i32 (%struct._IO_FILE*, i8*, ...)* @fprintf(%struct._IO_FILE* %2, i8* getelementptr inbounds ([2 x i8]* @.str1, i32 0, i32 0))
+  br label %if.end
 
-; <label>:14                                      ; preds = %11, %4
-  br label %15
+if.end:                                           ; preds = %if.then, %for.body3
+  br label %for.inc
 
-; <label>:15                                      ; preds = %14
+for.inc:                                          ; preds = %if.end
   %indvar.next = add i64 %indvar, 1
-  br label %3
+  br label %for.cond1
 
-; <label>:16                                      ; preds = %3
-  %17 = load %struct._IO_FILE** @stdout, align 8
-  %18 = call i32 (%struct._IO_FILE*, i8*, ...)* @fprintf(%struct._IO_FILE* %17, i8* getelementptr inbounds ([2 x i8]* @.str1, i32 0, i32 0))
-  br label %19
+for.end:                                          ; preds = %for.cond1
+  %3 = load %struct._IO_FILE** @stdout, align 8
+  %call9 = call i32 (%struct._IO_FILE*, i8*, ...)* @fprintf(%struct._IO_FILE* %3, i8* getelementptr inbounds ([2 x i8]* @.str1, i32 0, i32 0))
+  br label %for.inc10
 
-; <label>:19                                      ; preds = %16
+for.inc10:                                        ; preds = %for.end
   %indvar.next2 = add i64 %indvar1, 1
-  br label %1
+  br label %for.cond
 
-; <label>:20                                      ; preds = %1
+for.end12:                                        ; preds = %for.cond
   ret void
 }
 
-declare i32 @fprintf(%struct._IO_FILE*, i8*, ...)
+declare i32 @fprintf(%struct._IO_FILE*, i8*, ...) #1
 
-define i32 @main() nounwind {
-; <label>:0
+; Function Attrs: nounwind uwtable
+define i32 @main() #0 {
+entry:
   call void @init_array()
-  br label %1
+  br label %for.cond
 
-; <label>:1                                       ; preds = %16, %0
-  %indvar3 = phi i64 [ %indvar.next4, %16 ], [ 0, %0 ]
-  %exitcond9 = icmp ne i64 %indvar3, 1536
-  br i1 %exitcond9, label %2, label %17
+for.cond:                                         ; preds = %for.inc28, %entry
+  %indvar3 = phi i64 [ %indvar.next4, %for.inc28 ], [ 0, %entry ]
+  %exitcond6 = icmp ne i64 %indvar3, 1536
+  br i1 %exitcond6, label %for.body, label %for.end30
 
-; <label>:2                                       ; preds = %1
-  br label %3
+for.body:                                         ; preds = %for.cond
+  br label %for.cond1
 
-; <label>:3                                       ; preds = %14, %2
-  %indvar1 = phi i64 [ %indvar.next2, %14 ], [ 0, %2 ]
-  %scevgep8 = getelementptr [1536 x [1536 x float]]* @C, i64 0, i64 %indvar3, i64 %indvar1
-  %exitcond6 = icmp ne i64 %indvar1, 1536
-  br i1 %exitcond6, label %4, label %15
+for.cond1:                                        ; preds = %for.inc25, %for.body
+  %indvar1 = phi i64 [ %indvar.next2, %for.inc25 ], [ 0, %for.body ]
+  %arrayidx5 = getelementptr [1536 x [1536 x float]]* @C, i64 0, i64 %indvar3, i64 %indvar1
+  %exitcond5 = icmp ne i64 %indvar1, 1536
+  br i1 %exitcond5, label %for.body3, label %for.end27
 
-; <label>:4                                       ; preds = %3
-  store float 0.000000e+00, float* %scevgep8
-  br label %5
+for.body3:                                        ; preds = %for.cond1
+  store float 0.000000e+00, float* %arrayidx5, align 4
+  br label %for.cond6
 
-; <label>:5                                       ; preds = %12, %4
-  %indvar = phi i64 [ %indvar.next, %12 ], [ 0, %4 ]
-  %scevgep5 = getelementptr [1536 x [1536 x float]]* @A, i64 0, i64 %indvar3, i64 %indvar
-  %scevgep = getelementptr [1536 x [1536 x float]]* @B, i64 0, i64 %indvar, i64 %indvar1
+for.cond6:                                        ; preds = %for.inc, %for.body3
+  %indvar = phi i64 [ %indvar.next, %for.inc ], [ 0, %for.body3 ]
+  %arrayidx16 = getelementptr [1536 x [1536 x float]]* @A, i64 0, i64 %indvar3, i64 %indvar
+  %arrayidx20 = getelementptr [1536 x [1536 x float]]* @B, i64 0, i64 %indvar, i64 %indvar1
   %exitcond = icmp ne i64 %indvar, 1536
-  br i1 %exitcond, label %6, label %13
+  br i1 %exitcond, label %for.body8, label %for.end
 
-; <label>:6                                       ; preds = %5
-  %7 = load float* %scevgep8
-  %8 = load float* %scevgep5
-  %9 = load float* %scevgep
-  %10 = fmul float %8, %9
-  %11 = fadd float %7, %10
-  store float %11, float* %scevgep8
-  br label %12
+for.body8:                                        ; preds = %for.cond6
+  %0 = load float* %arrayidx5, align 4
+  %1 = load float* %arrayidx16, align 4
+  %2 = load float* %arrayidx20, align 4
+  %mul = fmul float %1, %2
+  %add = fadd float %0, %mul
+  store float %add, float* %arrayidx5, align 4
+  br label %for.inc
 
-; <label>:12                                      ; preds = %6
+for.inc:                                          ; preds = %for.body8
   %indvar.next = add i64 %indvar, 1
-  br label %5
+  br label %for.cond6
 
-; <label>:13                                      ; preds = %5
-  br label %14
+for.end:                                          ; preds = %for.cond6
+  br label %for.inc25
 
-; <label>:14                                      ; preds = %13
+for.inc25:                                        ; preds = %for.end
   %indvar.next2 = add i64 %indvar1, 1
-  br label %3
+  br label %for.cond1
 
-; <label>:15                                      ; preds = %3
-  br label %16
+for.end27:                                        ; preds = %for.cond1
+  br label %for.inc28
 
-; <label>:16                                      ; preds = %15
+for.inc28:                                        ; preds = %for.end27
   %indvar.next4 = add i64 %indvar3, 1
-  br label %1
+  br label %for.cond
 
-; <label>:17                                      ; preds = %1
+for.end30:                                        ; preds = %for.cond
   ret i32 0
 }
+
+attributes #0 = { nounwind uwtable "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf"="true" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "unsafe-fp-math"="false" "use-soft-float"="false" }
+attributes #1 = { "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf"="true" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "unsafe-fp-math"="false" "use-soft-float"="false" }
diff --git a/polly/www/experiments/matmul/matmul.s b/polly/www/experiments/matmul/matmul.s
index bec9d2a7504e..22ea57b16878 100644
--- a/polly/www/experiments/matmul/matmul.s
+++ b/polly/www/experiments/matmul/matmul.s
@@ -1,5 +1,5 @@
 ; ModuleID = 'matmul.c'
-target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
 
 %struct._IO_FILE = type { i32, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, i8*, %struct._IO_marker*, %struct._IO_FILE*, i32, i32, i64, i16, i8, [1 x i8], i8*, i64, i8*, i8*, i8*, i8*, i64, i32, [20 x i8] }
@@ -8,248 +8,257 @@ target triple = "x86_64-unknown-linux-gnu"
 @A = common global [1536 x [1536 x float]] zeroinitializer, align 16
 @B = common global [1536 x [1536 x float]] zeroinitializer, align 16
 @stdout = external global %struct._IO_FILE*
-@.str = private unnamed_addr constant [5 x i8] c"%lf \00"
+@.str = private unnamed_addr constant [5 x i8] c"%lf \00", align 1
 @C = common global [1536 x [1536 x float]] zeroinitializer, align 16
-@.str1 = private unnamed_addr constant [2 x i8] c"\0A\00"
+@.str1 = private unnamed_addr constant [2 x i8] c"\0A\00", align 1
 
-define void @init_array() nounwind {
+; Function Attrs: nounwind uwtable
+define void @init_array() #0 {
+entry:
   %i = alloca i32, align 4
   %j = alloca i32, align 4
   store i32 0, i32* %i, align 4
-  br label %1
+  br label %for.cond
 
-; <label>:1                                       ; preds = %41, %0
-  %2 = load i32* %i, align 4
-  %3 = icmp slt i32 %2, 1536
-  br i1 %3, label %4, label %44
+for.cond:                                         ; preds = %for.inc17, %entry
+  %0 = load i32* %i, align 4
+  %cmp = icmp slt i32 %0, 1536
+  br i1 %cmp, label %for.body, label %for.end19
 
-; <label>:4                                       ; preds = %1
+for.body:                                         ; preds = %for.cond
   store i32 0, i32* %j, align 4
-  br label %5
+  br label %for.cond1
 
-; <label>:5                                       ; preds = %37, %4
-  %6 = load i32* %j, align 4
-  %7 = icmp slt i32 %6, 1536
-  br i1 %7, label %8, label %40
+for.cond1:                                        ; preds = %for.inc, %for.body
+  %1 = load i32* %j, align 4
+  %cmp2 = icmp slt i32 %1, 1536
+  br i1 %cmp2, label %for.body3, label %for.end
 
-; <label>:8                                       ; preds = %5
+for.body3:                                        ; preds = %for.cond1
+  %2 = load i32* %i, align 4
+  %3 = load i32* %j, align 4
+  %mul = mul nsw i32 %2, %3
+  %rem = srem i32 %mul, 1024
+  %add = add nsw i32 1, %rem
+  %conv = sitofp i32 %add to double
+  %div = fdiv double %conv, 2.000000e+00
+  %conv4 = fptrunc double %div to float
+  %4 = load i32* %j, align 4
+  %idxprom = sext i32 %4 to i64
+  %5 = load i32* %i, align 4
+  %idxprom5 = sext i32 %5 to i64
+  %arrayidx = getelementptr inbounds [1536 x [1536 x float]]* @A, i32 0, i64 %idxprom5
+  %arrayidx6 = getelementptr inbounds [1536 x float]* %arrayidx, i32 0, i64 %idxprom
+  store float %conv4, float* %arrayidx6, align 4
+  %6 = load i32* %i, align 4
+  %7 = load i32* %j, align 4
+  %mul7 = mul nsw i32 %6, %7
+  %rem8 = srem i32 %mul7, 1024
+  %add9 = add nsw i32 1, %rem8
+  %conv10 = sitofp i32 %add9 to double
+  %div11 = fdiv double %conv10, 2.000000e+00
+  %conv12 = fptrunc double %div11 to float
+  %8 = load i32* %j, align 4
+  %idxprom13 = sext i32 %8 to i64
   %9 = load i32* %i, align 4
+  %idxprom14 = sext i32 %9 to i64
+  %arrayidx15 = getelementptr inbounds [1536 x [1536 x float]]* @B, i32 0, i64 %idxprom14
+  %arrayidx16 = getelementptr inbounds [1536 x float]* %arrayidx15, i32 0, i64 %idxprom13
+  store float %conv12, float* %arrayidx16, align 4
+  br label %for.inc
+
+for.inc:                                          ; preds = %for.body3
   %10 = load i32* %j, align 4
-  %11 = mul nsw i32 %9, %10
-  %12 = srem i32 %11, 1024
-  %13 = add nsw i32 1, %12
-  %14 = sitofp i32 %13 to double
-  %15 = fdiv double %14, 2.000000e+00
-  %16 = fptrunc double %15 to float
-  %17 = load i32* %j, align 4
-  %18 = sext i32 %17 to i64
-  %19 = load i32* %i, align 4
-  %20 = sext i32 %19 to i64
-  %21 = getelementptr inbounds [1536 x [1536 x float]]* @A, i32 0, i64 %20
-  %22 = getelementptr inbounds [1536 x float]* %21, i32 0, i64 %18
-  store float %16, float* %22
-  %23 = load i32* %i, align 4
-  %24 = load i32* %j, align 4
-  %25 = mul nsw i32 %23, %24
-  %26 = srem i32 %25, 1024
-  %27 = add nsw i32 1, %26
-  %28 = sitofp i32 %27 to double
-  %29 = fdiv double %28, 2.000000e+00
-  %30 = fptrunc double %29 to float
-  %31 = load i32* %j, align 4
-  %32 = sext i32 %31 to i64
-  %33 = load i32* %i, align 4
-  %34 = sext i32 %33 to i64
-  %35 = getelementptr inbounds [1536 x [1536 x float]]* @B, i32 0, i64 %34
-  %36 = getelementptr inbounds [1536 x float]* %35, i32 0, i64 %32
-  store float %30, float* %36
-  br label %37
+  %inc = add nsw i32 %10, 1
+  store i32 %inc, i32* %j, align 4
+  br label %for.cond1
 
-; <label>:37                                      ; preds = %8
-  %38 = load i32* %j, align 4
-  %39 = add nsw i32 %38, 1
-  store i32 %39, i32* %j, align 4
-  br label %5
+for.end:                                          ; preds = %for.cond1
+  br label %for.inc17
 
-; <label>:40                                      ; preds = %5
-  br label %41
+for.inc17:                                        ; preds = %for.end
+  %11 = load i32* %i, align 4
+  %inc18 = add nsw i32 %11, 1
+  store i32 %inc18, i32* %i, align 4
+  br label %for.cond
 
-; <label>:41                                      ; preds = %40
-  %42 = load i32* %i, align 4
-  %43 = add nsw i32 %42, 1
-  store i32 %43, i32* %i, align 4
-  br label %1
-
-; <label>:44                                      ; preds = %1
+for.end19:                                        ; preds = %for.cond
   ret void
 }
 
-define void @print_array() nounwind {
+; Function Attrs: nounwind uwtable
+define void @print_array() #0 {
+entry:
   %i = alloca i32, align 4
   %j = alloca i32, align 4
   store i32 0, i32* %i, align 4
-  br label %1
+  br label %for.cond
 
-; <label>:1                                       ; preds = %32, %0
-  %2 = load i32* %i, align 4
-  %3 = icmp slt i32 %2, 1536
-  br i1 %3, label %4, label %35
+for.cond:                                         ; preds = %for.inc10, %entry
+  %0 = load i32* %i, align 4
+  %cmp = icmp slt i32 %0, 1536
+  br i1 %cmp, label %for.body, label %for.end12
 
-; <label>:4                                       ; preds = %1
+for.body:                                         ; preds = %for.cond
   store i32 0, i32* %j, align 4
-  br label %5
+  br label %for.cond1
 
-; <label>:5                                       ; preds = %26, %4
+for.cond1:                                        ; preds = %for.inc, %for.body
+  %1 = load i32* %j, align 4
+  %cmp2 = icmp slt i32 %1, 1536
+  br i1 %cmp2, label %for.body3, label %for.end
+
+for.body3:                                        ; preds = %for.cond1
+  %2 = load %struct._IO_FILE** @stdout, align 8
+  %3 = load i32* %j, align 4
+  %idxprom = sext i32 %3 to i64
+  %4 = load i32* %i, align 4
+  %idxprom4 = sext i32 %4 to i64
+  %arrayidx = getelementptr inbounds [1536 x [1536 x float]]* @C, i32 0, i64 %idxprom4
+  %arrayidx5 = getelementptr inbounds [1536 x float]* %arrayidx, i32 0, i64 %idxprom
+  %5 = load float* %arrayidx5, align 4
+  %conv = fpext float %5 to double
+  %call = call i32 (%struct._IO_FILE*, i8*, ...)* @fprintf(%struct._IO_FILE* %2, i8* getelementptr inbounds ([5 x i8]* @.str, i32 0, i32 0), double %conv)
   %6 = load i32* %j, align 4
-  %7 = icmp slt i32 %6, 1536
-  br i1 %7, label %8, label %29
+  %rem = srem i32 %6, 80
+  %cmp6 = icmp eq i32 %rem, 79
+  br i1 %cmp6, label %if.then, label %if.end
 
-; <label>:8                                       ; preds = %5
+if.then:                                          ; preds = %for.body3
+  %7 = load %struct._IO_FILE** @stdout, align 8
+  %call8 = call i32 (%struct._IO_FILE*, i8*, ...)* @fprintf(%struct._IO_FILE* %7, i8* getelementptr inbounds ([2 x i8]* @.str1, i32 0, i32 0))
+  br label %if.end
+
+if.end:                                           ; preds = %if.then, %for.body3
+  br label %for.inc
+
+for.inc:                                          ; preds = %if.end
+  %8 = load i32* %j, align 4
+  %inc = add nsw i32 %8, 1
+  store i32 %inc, i32* %j, align 4
+  br label %for.cond1
+
+for.end:                                          ; preds = %for.cond1
   %9 = load %struct._IO_FILE** @stdout, align 8
-  %10 = load i32* %j, align 4
-  %11 = sext i32 %10 to i64
-  %12 = load i32* %i, align 4
-  %13 = sext i32 %12 to i64
-  %14 = getelementptr inbounds [1536 x [1536 x float]]* @C, i32 0, i64 %13
-  %15 = getelementptr inbounds [1536 x float]* %14, i32 0, i64 %11
-  %16 = load float* %15
-  %17 = fpext float %16 to double
-  %18 = call i32 (%struct._IO_FILE*, i8*, ...)* @fprintf(%struct._IO_FILE* %9, i8* getelementptr inbounds ([5 x i8]* @.str, i32 0, i32 0), double %17)
-  %19 = load i32* %j, align 4
-  %20 = srem i32 %19, 80
-  %21 = icmp eq i32 %20, 79
-  br i1 %21, label %22, label %25
+  %call9 = call i32 (%struct._IO_FILE*, i8*, ...)* @fprintf(%struct._IO_FILE* %9, i8* getelementptr inbounds ([2 x i8]* @.str1, i32 0, i32 0))
+  br label %for.inc10
 
-; <label>:22                                      ; preds = %8
-  %23 = load %struct._IO_FILE** @stdout, align 8
-  %24 = call i32 (%struct._IO_FILE*, i8*, ...)* @fprintf(%struct._IO_FILE* %23, i8* getelementptr inbounds ([2 x i8]* @.str1, i32 0, i32 0))
-  br label %25
+for.inc10:                                        ; preds = %for.end
+  %10 = load i32* %i, align 4
+  %inc11 = add nsw i32 %10, 1
+  store i32 %inc11, i32* %i, align 4
+  br label %for.cond
 
-; <label>:25                                      ; preds = %22, %8
-  br label %26
-
-; <label>:26                                      ; preds = %25
-  %27 = load i32* %j, align 4
-  %28 = add nsw i32 %27, 1
-  store i32 %28, i32* %j, align 4
-  br label %5
-
-; <label>:29                                      ; preds = %5
-  %30 = load %struct._IO_FILE** @stdout, align 8
-  %31 = call i32 (%struct._IO_FILE*, i8*, ...)* @fprintf(%struct._IO_FILE* %30, i8* getelementptr inbounds ([2 x i8]* @.str1, i32 0, i32 0))
-  br label %32
-
-; <label>:32                                      ; preds = %29
-  %33 = load i32* %i, align 4
-  %34 = add nsw i32 %33, 1
-  store i32 %34, i32* %i, align 4
-  br label %1
-
-; <label>:35                                      ; preds = %1
+for.end12:                                        ; preds = %for.cond
   ret void
 }
 
-declare i32 @fprintf(%struct._IO_FILE*, i8*, ...)
+declare i32 @fprintf(%struct._IO_FILE*, i8*, ...) #1
 
-define i32 @main() nounwind {
-  %1 = alloca i32, align 4
+; Function Attrs: nounwind uwtable
+define i32 @main() #0 {
+entry:
+  %retval = alloca i32, align 4
   %i = alloca i32, align 4
   %j = alloca i32, align 4
   %k = alloca i32, align 4
   %t_start = alloca double, align 8
   %t_end = alloca double, align 8
-  store i32 0, i32* %1
+  store i32 0, i32* %retval
   call void @init_array()
   store i32 0, i32* %i, align 4
-  br label %2
+  br label %for.cond
 
-; <label>:2                                       ; preds = %57, %0
-  %3 = load i32* %i, align 4
-  %4 = icmp slt i32 %3, 1536
-  br i1 %4, label %5, label %60
+for.cond:                                         ; preds = %for.inc28, %entry
+  %0 = load i32* %i, align 4
+  %cmp = icmp slt i32 %0, 1536
+  br i1 %cmp, label %for.body, label %for.end30
 
-; <label>:5                                       ; preds = %2
+for.body:                                         ; preds = %for.cond
   store i32 0, i32* %j, align 4
-  br label %6
+  br label %for.cond1
 
-; <label>:6                                       ; preds = %53, %5
-  %7 = load i32* %j, align 4
-  %8 = icmp slt i32 %7, 1536
-  br i1 %8, label %9, label %56
+for.cond1:                                        ; preds = %for.inc25, %for.body
+  %1 = load i32* %j, align 4
+  %cmp2 = icmp slt i32 %1, 1536
+  br i1 %cmp2, label %for.body3, label %for.end27
 
-; <label>:9                                       ; preds = %6
-  %10 = load i32* %j, align 4
-  %11 = sext i32 %10 to i64
-  %12 = load i32* %i, align 4
-  %13 = sext i32 %12 to i64
-  %14 = getelementptr inbounds [1536 x [1536 x float]]* @C, i32 0, i64 %13
-  %15 = getelementptr inbounds [1536 x float]* %14, i32 0, i64 %11
-  store float 0.000000e+00, float* %15
+for.body3:                                        ; preds = %for.cond1
+  %2 = load i32* %j, align 4
+  %idxprom = sext i32 %2 to i64
+  %3 = load i32* %i, align 4
+  %idxprom4 = sext i32 %3 to i64
+  %arrayidx = getelementptr inbounds [1536 x [1536 x float]]* @C, i32 0, i64 %idxprom4
+  %arrayidx5 = getelementptr inbounds [1536 x float]* %arrayidx, i32 0, i64 %idxprom
+  store float 0.000000e+00, float* %arrayidx5, align 4
   store i32 0, i32* %k, align 4
-  br label %16
+  br label %for.cond6
 
-; <label>:16                                      ; preds = %49, %9
-  %17 = load i32* %k, align 4
-  %18 = icmp slt i32 %17, 1536
-  br i1 %18, label %19, label %52
+for.cond6:                                        ; preds = %for.inc, %for.body3
+  %4 = load i32* %k, align 4
+  %cmp7 = icmp slt i32 %4, 1536
+  br i1 %cmp7, label %for.body8, label %for.end
 
-; <label>:19                                      ; preds = %16
-  %20 = load i32* %j, align 4
-  %21 = sext i32 %20 to i64
-  %22 = load i32* %i, align 4
-  %23 = sext i32 %22 to i64
-  %24 = getelementptr inbounds [1536 x [1536 x float]]* @C, i32 0, i64 %23
-  %25 = getelementptr inbounds [1536 x float]* %24, i32 0, i64 %21
-  %26 = load float* %25
-  %27 = load i32* %k, align 4
-  %28 = sext i32 %27 to i64
-  %29 = load i32* %i, align 4
-  %30 = sext i32 %29 to i64
-  %31 = getelementptr inbounds [1536 x [1536 x float]]* @A, i32 0, i64 %30
-  %32 = getelementptr inbounds [1536 x float]* %31, i32 0, i64 %28
-  %33 = load float* %32
-  %34 = load i32* %j, align 4
-  %35 = sext i32 %34 to i64
-  %36 = load i32* %k, align 4
-  %37 = sext i32 %36 to i64
-  %38 = getelementptr inbounds [1536 x [1536 x float]]* @B, i32 0, i64 %37
-  %39 = getelementptr inbounds [1536 x float]* %38, i32 0, i64 %35
-  %40 = load float* %39
-  %41 = fmul float %33, %40
-  %42 = fadd float %26, %41
-  %43 = load i32* %j, align 4
-  %44 = sext i32 %43 to i64
-  %45 = load i32* %i, align 4
-  %46 = sext i32 %45 to i64
-  %47 = getelementptr inbounds [1536 x [1536 x float]]* @C, i32 0, i64 %46
-  %48 = getelementptr inbounds [1536 x float]* %47, i32 0, i64 %44
-  store float %42, float* %48
-  br label %49
+for.body8:                                        ; preds = %for.cond6
+  %5 = load i32* %j, align 4
+  %idxprom9 = sext i32 %5 to i64
+  %6 = load i32* %i, align 4
+  %idxprom10 = sext i32 %6 to i64
+  %arrayidx11 = getelementptr inbounds [1536 x [1536 x float]]* @C, i32 0, i64 %idxprom10
+  %arrayidx12 = getelementptr inbounds [1536 x float]* %arrayidx11, i32 0, i64 %idxprom9
+  %7 = load float* %arrayidx12, align 4
+  %8 = load i32* %k, align 4
+  %idxprom13 = sext i32 %8 to i64
+  %9 = load i32* %i, align 4
+  %idxprom14 = sext i32 %9 to i64
+  %arrayidx15 = getelementptr inbounds [1536 x [1536 x float]]* @A, i32 0, i64 %idxprom14
+  %arrayidx16 = getelementptr inbounds [1536 x float]* %arrayidx15, i32 0, i64 %idxprom13
+  %10 = load float* %arrayidx16, align 4
+  %11 = load i32* %j, align 4
+  %idxprom17 = sext i32 %11 to i64
+  %12 = load i32* %k, align 4
+  %idxprom18 = sext i32 %12 to i64
+  %arrayidx19 = getelementptr inbounds [1536 x [1536 x float]]* @B, i32 0, i64 %idxprom18
+  %arrayidx20 = getelementptr inbounds [1536 x float]* %arrayidx19, i32 0, i64 %idxprom17
+  %13 = load float* %arrayidx20, align 4
+  %mul = fmul float %10, %13
+  %add = fadd float %7, %mul
+  %14 = load i32* %j, align 4
+  %idxprom21 = sext i32 %14 to i64
+  %15 = load i32* %i, align 4
+  %idxprom22 = sext i32 %15 to i64
+  %arrayidx23 = getelementptr inbounds [1536 x [1536 x float]]* @C, i32 0, i64 %idxprom22
+  %arrayidx24 = getelementptr inbounds [1536 x float]* %arrayidx23, i32 0, i64 %idxprom21
+  store float %add, float* %arrayidx24, align 4
+  br label %for.inc
 
-; <label>:49                                      ; preds = %19
-  %50 = load i32* %k, align 4
-  %51 = add nsw i32 %50, 1
-  store i32 %51, i32* %k, align 4
-  br label %16
+for.inc:                                          ; preds = %for.body8
+  %16 = load i32* %k, align 4
+  %inc = add nsw i32 %16, 1
+  store i32 %inc, i32* %k, align 4
+  br label %for.cond6
 
-; <label>:52                                      ; preds = %16
-  br label %53
+for.end:                                          ; preds = %for.cond6
+  br label %for.inc25
 
-; <label>:53                                      ; preds = %52
-  %54 = load i32* %j, align 4
-  %55 = add nsw i32 %54, 1
-  store i32 %55, i32* %j, align 4
-  br label %6
+for.inc25:                                        ; preds = %for.end
+  %17 = load i32* %j, align 4
+  %inc26 = add nsw i32 %17, 1
+  store i32 %inc26, i32* %j, align 4
+  br label %for.cond1
 
-; <label>:56                                      ; preds = %6
-  br label %57
+for.end27:                                        ; preds = %for.cond1
+  br label %for.inc28
 
-; <label>:57                                      ; preds = %56
-  %58 = load i32* %i, align 4
-  %59 = add nsw i32 %58, 1
-  store i32 %59, i32* %i, align 4
-  br label %2
+for.inc28:                                        ; preds = %for.end27
+  %18 = load i32* %i, align 4
+  %inc29 = add nsw i32 %18, 1
+  store i32 %inc29, i32* %i, align 4
+  br label %for.cond
 
-; <label>:60                                      ; preds = %2
+for.end30:                                        ; preds = %for.cond
   ret i32 0
 }
+
+attributes #0 = { nounwind uwtable "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf"="true" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "unsafe-fp-math"="false" "use-soft-float"="false" }
+attributes #1 = { "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf"="true" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "unsafe-fp-math"="false" "use-soft-float"="false" }
diff --git a/polly/www/experiments/matmul/scops.init_array.dot b/polly/www/experiments/matmul/scops.init_array.dot
index 1b3f09284f92..10a0add0a617 100644
--- a/polly/www/experiments/matmul/scops.init_array.dot
+++ b/polly/www/experiments/matmul/scops.init_array.dot
@@ -1,47 +1,47 @@
 digraph "Scop Graph for 'init_array' function" {
 	label="Scop Graph for 'init_array' function";
 
-	Node0x26ade30 [shape=record,label="{%0:\l\l  br label %1\l}"];
-	Node0x26ade30 -> Node0x26acdd0;
-	Node0x26acdd0 [shape=record,label="{%1:\l\l  %2 = phi i64 [ %indvar.next2, %18 ], [ 0, %0 ]\l  %exitcond5 = icmp ne i64 %2, 1536\l  br i1 %exitcond5, label %3, label %19\l}"];
-	Node0x26acdd0 -> Node0x26acdf0;
-	Node0x26acdd0 -> Node0x26adce0;
-	Node0x26acdf0 [shape=record,label="{%3:\l\l  br label %4\l}"];
-	Node0x26acdf0 -> Node0x26addc0;
-	Node0x26addc0 [shape=record,label="{%4:\l\l  %indvar = phi i64 [ %indvar.next, %16 ], [ 0, %3 ]\l  %scevgep4 = getelementptr [1536 x [1536 x float]]* @A, i64 0, i64 %2, i64 %indvar\l  %scevgep = getelementptr [1536 x [1536 x float]]* @B, i64 0, i64 %2, i64 %indvar\l  %tmp = mul i64 %2, %indvar\l  %tmp3 = trunc i64 %tmp to i32\l  %exitcond = icmp ne i64 %indvar, 1536\l  br i1 %exitcond, label %5, label %17\l}"];
-	Node0x26addc0 -> Node0x26ace70;
-	Node0x26addc0 -> Node0x26ad010;
-	Node0x26ace70 [shape=record,label="{%5:\l\l  %6 = srem i32 %tmp3, 1024\l  %7 = add nsw i32 1, %6\l  %8 = sitofp i32 %7 to double\l  %9 = fdiv double %8, 2.000000e+00\l  %10 = fptrunc double %9 to float\l  store float %10, float* %scevgep4\l  %11 = srem i32 %tmp3, 1024\l  %12 = add nsw i32 1, %11\l  %13 = sitofp i32 %12 to double\l  %14 = fdiv double %13, 2.000000e+00\l  %15 = fptrunc double %14 to float\l  store float %15, float* %scevgep\l  br label %16\l}"];
-	Node0x26ace70 -> Node0x26ace90;
-	Node0x26ace90 [shape=record,label="{%16:\l\l  %indvar.next = add i64 %indvar, 1\l  br label %4\l}"];
-	Node0x26ace90 -> Node0x26addc0[constraint=false];
-	Node0x26ad010 [shape=record,label="{%17:\l\l  br label %18\l}"];
-	Node0x26ad010 -> Node0x26ad6c0;
-	Node0x26ad6c0 [shape=record,label="{%18:\l\l  %indvar.next2 = add i64 %2, 1\l  br label %1\l}"];
-	Node0x26ad6c0 -> Node0x26acdd0[constraint=false];
-	Node0x26adce0 [shape=record,label="{%19:\l\l  ret void\l}"];
+	Node0x17d4370 [shape=record,label="{entry:\l  br label %for.cond\l}"];
+	Node0x17d4370 -> Node0x17da5d0;
+	Node0x17da5d0 [shape=record,label="{for.cond:                                         \l  %0 = phi i64 [ %indvar.next2, %for.inc17 ], [ 0, %entry ]\l  %exitcond3 = icmp ne i64 %0, 1536\l  br i1 %exitcond3, label %for.body, label %for.end19\l}"];
+	Node0x17da5d0 -> Node0x17da5f0;
+	Node0x17da5d0 -> Node0x17da650;
+	Node0x17da5f0 [shape=record,label="{for.body:                                         \l  br label %for.cond1\l}"];
+	Node0x17da5f0 -> Node0x17da900;
+	Node0x17da900 [shape=record,label="{for.cond1:                                        \l  %indvar = phi i64 [ %indvar.next, %for.inc ], [ 0, %for.body ]\l  %arrayidx6 = getelementptr [1536 x [1536 x float]]* @A, i64 0, i64 %0, i64 %indvar\l  %arrayidx16 = getelementptr [1536 x [1536 x float]]* @B, i64 0, i64 %0, i64 %indvar\l  %1 = mul i64 %0, %indvar\l  %mul = trunc i64 %1 to i32\l  %exitcond = icmp ne i64 %indvar, 1536\l  br i1 %exitcond, label %for.body3, label %for.end\l}"];
+	Node0x17da900 -> Node0x17da670;
+	Node0x17da900 -> Node0x17da9a0;
+	Node0x17da670 [shape=record,label="{for.body3:                                        \l  %rem = srem i32 %mul, 1024\l  %add = add nsw i32 1, %rem\l  %conv = sitofp i32 %add to double\l  %div = fdiv double %conv, 2.000000e+00\l  %conv4 = fptrunc double %div to float\l  store float %conv4, float* %arrayidx6, align 4\l  %rem8 = srem i32 %mul, 1024\l  %add9 = add nsw i32 1, %rem8\l  %conv10 = sitofp i32 %add9 to double\l  %div11 = fdiv double %conv10, 2.000000e+00\l  %conv12 = fptrunc double %div11 to float\l  store float %conv12, float* %arrayidx16, align 4\l  br label %for.inc\l}"];
+	Node0x17da670 -> Node0x17da8e0;
+	Node0x17da8e0 [shape=record,label="{for.inc:                                          \l  %indvar.next = add i64 %indvar, 1\l  br label %for.cond1\l}"];
+	Node0x17da8e0 -> Node0x17da900[constraint=false];
+	Node0x17da9a0 [shape=record,label="{for.end:                                          \l  br label %for.inc17\l}"];
+	Node0x17da9a0 -> Node0x17d9e70;
+	Node0x17d9e70 [shape=record,label="{for.inc17:                                        \l  %indvar.next2 = add i64 %0, 1\l  br label %for.cond\l}"];
+	Node0x17d9e70 -> Node0x17da5d0[constraint=false];
+	Node0x17da650 [shape=record,label="{for.end19:                                        \l  ret void\l}"];
 	colorscheme = "paired12"
-        subgraph cluster_0x26a94c0 {
+        subgraph cluster_0x17d3a30 {
           label = "";
           style = solid;
           color = 1
-          subgraph cluster_0x26aa4e0 {
+          subgraph cluster_0x17d4ec0 {
             label = "";
             style = filled;
-            color = 3            subgraph cluster_0x26a9780 {
+            color = 3            subgraph cluster_0x17d4180 {
               label = "";
               style = solid;
               color = 5
-              Node0x26addc0;
-              Node0x26ace70;
-              Node0x26ace90;
+              Node0x17da900;
+              Node0x17da670;
+              Node0x17da8e0;
             }
-            Node0x26acdd0;
-            Node0x26acdf0;
-            Node0x26ad010;
-            Node0x26ad6c0;
+            Node0x17da5d0;
+            Node0x17da5f0;
+            Node0x17da9a0;
+            Node0x17d9e70;
           }
-          Node0x26ade30;
-          Node0x26adce0;
+          Node0x17d4370;
+          Node0x17da650;
         }
 }
diff --git a/polly/www/experiments/matmul/scops.init_array.dot.png b/polly/www/experiments/matmul/scops.init_array.dot.png
index ee04e8b70180..48a9f38946a9 100644
Binary files a/polly/www/experiments/matmul/scops.init_array.dot.png and b/polly/www/experiments/matmul/scops.init_array.dot.png differ
diff --git a/polly/www/experiments/matmul/scops.main.dot b/polly/www/experiments/matmul/scops.main.dot
index 0459c48fb50a..2a1fc50cf726 100644
--- a/polly/www/experiments/matmul/scops.main.dot
+++ b/polly/www/experiments/matmul/scops.main.dot
@@ -1,65 +1,65 @@
 digraph "Scop Graph for 'main' function" {
 	label="Scop Graph for 'main' function";
 
-	Node0x26ace10 [shape=record,label="{%0:\l\l  call void @init_array()\l  br label %1\l}"];
-	Node0x26ace10 -> Node0x26acd60;
-	Node0x26acd60 [shape=record,label="{%1:\l\l  %indvar3 = phi i64 [ %indvar.next4, %16 ], [ 0, %0 ]\l  %exitcond9 = icmp ne i64 %indvar3, 1536\l  br i1 %exitcond9, label %2, label %17\l}"];
-	Node0x26acd60 -> Node0x26acd80;
-	Node0x26acd60 -> Node0x26af2e0;
-	Node0x26acd80 [shape=record,label="{%2:\l\l  br label %3\l}"];
-	Node0x26acd80 -> Node0x26aee80;
-	Node0x26aee80 [shape=record,label="{%3:\l\l  %indvar1 = phi i64 [ %indvar.next2, %14 ], [ 0, %2 ]\l  %scevgep8 = getelementptr [1536 x [1536 x float]]* @C, i64 0, i64 %indvar3, i64 %indvar1\l  %exitcond6 = icmp ne i64 %indvar1, 1536\l  br i1 %exitcond6, label %4, label %15\l}"];
-	Node0x26aee80 -> Node0x26aeea0;
-	Node0x26aee80 -> Node0x26aeec0;
-	Node0x26aeea0 [shape=record,label="{%4:\l\l  store float 0.000000e+00, float* %scevgep8\l  br label %5\l}"];
-	Node0x26aeea0 -> Node0x26aced0;
-	Node0x26aced0 [shape=record,label="{%5:\l\l  %indvar = phi i64 [ %indvar.next, %12 ], [ 0, %4 ]\l  %scevgep5 = getelementptr [1536 x [1536 x float]]* @A, i64 0, i64 %indvar3, i64 %indvar\l  %scevgep = getelementptr [1536 x [1536 x float]]* @B, i64 0, i64 %indvar, i64 %indvar1\l  %exitcond = icmp ne i64 %indvar, 1536\l  br i1 %exitcond, label %6, label %13\l}"];
-	Node0x26aced0 -> Node0x26ace60;
-	Node0x26aced0 -> Node0x26af5e0;
-	Node0x26ace60 [shape=record,label="{%6:\l\l  %7 = load float* %scevgep8\l  %8 = load float* %scevgep5\l  %9 = load float* %scevgep\l  %10 = fmul float %8, %9\l  %11 = fadd float %7, %10\l  store float %11, float* %scevgep8\l  br label %12\l}"];
-	Node0x26ace60 -> Node0x26af640;
-	Node0x26af640 [shape=record,label="{%12:\l\l  %indvar.next = add i64 %indvar, 1\l  br label %5\l}"];
-	Node0x26af640 -> Node0x26aced0[constraint=false];
-	Node0x26af5e0 [shape=record,label="{%13:\l\l  br label %14\l}"];
-	Node0x26af5e0 -> Node0x26af6e0;
-	Node0x26af6e0 [shape=record,label="{%14:\l\l  %indvar.next2 = add i64 %indvar1, 1\l  br label %3\l}"];
-	Node0x26af6e0 -> Node0x26aee80[constraint=false];
-	Node0x26aeec0 [shape=record,label="{%15:\l\l  br label %16\l}"];
-	Node0x26aeec0 -> Node0x26af740;
-	Node0x26af740 [shape=record,label="{%16:\l\l  %indvar.next4 = add i64 %indvar3, 1\l  br label %1\l}"];
-	Node0x26af740 -> Node0x26acd60[constraint=false];
-	Node0x26af2e0 [shape=record,label="{%17:\l\l  ret i32 0\l}"];
+	Node0x17d21a0 [shape=record,label="{entry:\l  call void @init_array()\l  br label %for.cond\l}"];
+	Node0x17d21a0 -> Node0x17d2020;
+	Node0x17d2020 [shape=record,label="{for.cond:                                         \l  %indvar3 = phi i64 [ %indvar.next4, %for.inc28 ], [ 0, %entry ]\l  %exitcond6 = icmp ne i64 %indvar3, 1536\l  br i1 %exitcond6, label %for.body, label %for.end30\l}"];
+	Node0x17d2020 -> Node0x17d3950;
+	Node0x17d2020 -> Node0x17da500;
+	Node0x17d3950 [shape=record,label="{for.body:                                         \l  br label %for.cond1\l}"];
+	Node0x17d3950 -> Node0x17da760;
+	Node0x17da760 [shape=record,label="{for.cond1:                                        \l  %indvar1 = phi i64 [ %indvar.next2, %for.inc25 ], [ 0, %for.body ]\l  %arrayidx5 = getelementptr [1536 x [1536 x float]]* @C, i64 0, i64 %indvar3, i64 %indvar1\l  %exitcond5 = icmp ne i64 %indvar1, 1536\l  br i1 %exitcond5, label %for.body3, label %for.end27\l}"];
+	Node0x17da760 -> Node0x17db1e0;
+	Node0x17da760 -> Node0x17db250;
+	Node0x17db1e0 [shape=record,label="{for.body3:                                        \l  store float 0.000000e+00, float* %arrayidx5, align 4\l  br label %for.cond6\l}"];
+	Node0x17db1e0 -> Node0x17da740;
+	Node0x17da740 [shape=record,label="{for.cond6:                                        \l  %indvar = phi i64 [ %indvar.next, %for.inc ], [ 0, %for.body3 ]\l  %arrayidx16 = getelementptr [1536 x [1536 x float]]* @A, i64 0, i64 %indvar3, i64 %indvar\l  %arrayidx20 = getelementptr [1536 x [1536 x float]]* @B, i64 0, i64 %indvar, i64 %indvar1\l  %exitcond = icmp ne i64 %indvar, 1536\l  br i1 %exitcond, label %for.body8, label %for.end\l}"];
+	Node0x17da740 -> Node0x17da5a0;
+	Node0x17da740 -> Node0x17da800;
+	Node0x17da5a0 [shape=record,label="{for.body8:                                        \l  %0 = load float* %arrayidx5, align 4\l  %1 = load float* %arrayidx16, align 4\l  %2 = load float* %arrayidx20, align 4\l  %mul = fmul float %1, %2\l  %add = fadd float %0, %mul\l  store float %add, float* %arrayidx5, align 4\l  br label %for.inc\l}"];
+	Node0x17da5a0 -> Node0x17da5c0;
+	Node0x17da5c0 [shape=record,label="{for.inc:                                          \l  %indvar.next = add i64 %indvar, 1\l  br label %for.cond6\l}"];
+	Node0x17da5c0 -> Node0x17da740[constraint=false];
+	Node0x17da800 [shape=record,label="{for.end:                                          \l  br label %for.inc25\l}"];
+	Node0x17da800 -> Node0x17dae20;
+	Node0x17dae20 [shape=record,label="{for.inc25:                                        \l  %indvar.next2 = add i64 %indvar1, 1\l  br label %for.cond1\l}"];
+	Node0x17dae20 -> Node0x17da760[constraint=false];
+	Node0x17db250 [shape=record,label="{for.end27:                                        \l  br label %for.inc28\l}"];
+	Node0x17db250 -> Node0x17dae80;
+	Node0x17dae80 [shape=record,label="{for.inc28:                                        \l  %indvar.next4 = add i64 %indvar3, 1\l  br label %for.cond\l}"];
+	Node0x17dae80 -> Node0x17d2020[constraint=false];
+	Node0x17da500 [shape=record,label="{for.end30:                                        \l  ret i32 0\l}"];
 	colorscheme = "paired12"
-        subgraph cluster_0x26a8b20 {
+        subgraph cluster_0x17d3f30 {
           label = "";
           style = solid;
           color = 1
-          subgraph cluster_0x26a9220 {
+          subgraph cluster_0x17d38d0 {
             label = "";
             style = filled;
-            color = 3            subgraph cluster_0x26ad500 {
+            color = 3            subgraph cluster_0x17d3850 {
               label = "";
               style = solid;
               color = 5
-              subgraph cluster_0x26ad480 {
+              subgraph cluster_0x17d37d0 {
                 label = "";
                 style = solid;
                 color = 7
-                Node0x26aced0;
-                Node0x26ace60;
-                Node0x26af640;
+                Node0x17da740;
+                Node0x17da5a0;
+                Node0x17da5c0;
               }
-              Node0x26aee80;
-              Node0x26aeea0;
-              Node0x26af5e0;
-              Node0x26af6e0;
+              Node0x17da760;
+              Node0x17db1e0;
+              Node0x17da800;
+              Node0x17dae20;
             }
-            Node0x26acd60;
-            Node0x26acd80;
-            Node0x26aeec0;
-            Node0x26af740;
+            Node0x17d2020;
+            Node0x17d3950;
+            Node0x17db250;
+            Node0x17dae80;
           }
-          Node0x26ace10;
-          Node0x26af2e0;
+          Node0x17d21a0;
+          Node0x17da500;
         }
 }
diff --git a/polly/www/experiments/matmul/scops.main.dot.png b/polly/www/experiments/matmul/scops.main.dot.png
index 404d5f19f389..4e73701a08d7 100644
Binary files a/polly/www/experiments/matmul/scops.main.dot.png and b/polly/www/experiments/matmul/scops.main.dot.png differ
diff --git a/polly/www/experiments/matmul/scops.print_array.dot b/polly/www/experiments/matmul/scops.print_array.dot
index 6aafb40d6663..59f02e769100 100644
--- a/polly/www/experiments/matmul/scops.print_array.dot
+++ b/polly/www/experiments/matmul/scops.print_array.dot
@@ -1,60 +1,60 @@
 digraph "Scop Graph for 'print_array' function" {
 	label="Scop Graph for 'print_array' function";
 
-	Node0x26ac9a0 [shape=record,label="{%0:\l\l  br label %1\l}"];
-	Node0x26ac9a0 -> Node0x26acd00;
-	Node0x26acd00 [shape=record,label="{%1:\l\l  %indvar1 = phi i64 [ %indvar.next2, %19 ], [ 0, %0 ]\l  %exitcond3 = icmp ne i64 %indvar1, 1536\l  br i1 %exitcond3, label %2, label %20\l}"];
-	Node0x26acd00 -> Node0x26a8ac0;
-	Node0x26acd00 -> Node0x26ac9c0;
-	Node0x26a8ac0 [shape=record,label="{%2:\l\l  br label %3\l}"];
-	Node0x26a8ac0 -> Node0x26ad940;
-	Node0x26ad940 [shape=record,label="{%3:\l\l  %indvar = phi i64 [ %indvar.next, %15 ], [ 0, %2 ]\l  %scevgep = getelementptr [1536 x [1536 x float]]* @C, i64 0, i64 %indvar1, i64 %indvar\l  %j.0 = trunc i64 %indvar to i32\l  %exitcond = icmp ne i64 %indvar, 1536\l  br i1 %exitcond, label %4, label %16\l}"];
-	Node0x26ad940 -> Node0x26acde0;
-	Node0x26ad940 -> Node0x26ad9e0;
-	Node0x26acde0 [shape=record,label="{%4:\l\l  %5 = load %struct._IO_FILE** @stdout, align 8\l  %6 = load float* %scevgep\l  %7 = fpext float %6 to double\l  %8 = call i32 (%struct._IO_FILE*, i8*, ...)* @fprintf(%struct._IO_FILE* %5, i8* getelementptr inbounds ([5 x i8]* @.str, i32 0, i32 0), double %7)\l  %9 = srem i32 %j.0, 80\l  %10 = icmp eq i32 %9, 79\l  br i1 %10, label %11, label %14\l}"];
-	Node0x26acde0 -> Node0x26ada40;
-	Node0x26acde0 -> Node0x26acfa0;
-	Node0x26ada40 [shape=record,label="{%11:\l\l  %12 = load %struct._IO_FILE** @stdout, align 8\l  %13 = call i32 (%struct._IO_FILE*, i8*, ...)* @fprintf(%struct._IO_FILE* %12, i8* getelementptr inbounds ([2 x i8]* @.str1, i32 0, i32 0))\l  br label %14\l}"];
-	Node0x26ada40 -> Node0x26acfa0;
-	Node0x26acfa0 [shape=record,label="{%14:\l\l  br label %15\l}"];
-	Node0x26acfa0 -> Node0x26ad6c0;
-	Node0x26ad6c0 [shape=record,label="{%15:\l\l  %indvar.next = add i64 %indvar, 1\l  br label %3\l}"];
-	Node0x26ad6c0 -> Node0x26ad940[constraint=false];
-	Node0x26ad9e0 [shape=record,label="{%16:\l\l  %17 = load %struct._IO_FILE** @stdout, align 8\l  %18 = call i32 (%struct._IO_FILE*, i8*, ...)* @fprintf(%struct._IO_FILE* %17, i8* getelementptr inbounds ([2 x i8]* @.str1, i32 0, i32 0))\l  br label %19\l}"];
-	Node0x26ad9e0 -> Node0x26ace00;
-	Node0x26ace00 [shape=record,label="{%19:\l\l  %indvar.next2 = add i64 %indvar1, 1\l  br label %1\l}"];
-	Node0x26ace00 -> Node0x26acd00[constraint=false];
-	Node0x26ac9c0 [shape=record,label="{%20:\l\l  ret void\l}"];
+	Node0x17d2200 [shape=record,label="{entry:\l  br label %for.cond\l}"];
+	Node0x17d2200 -> Node0x17d4f20;
+	Node0x17d4f20 [shape=record,label="{for.cond:                                         \l  %indvar1 = phi i64 [ %indvar.next2, %for.inc10 ], [ 0, %entry ]\l  %exitcond3 = icmp ne i64 %indvar1, 1536\l  br i1 %exitcond3, label %for.body, label %for.end12\l}"];
+	Node0x17d4f20 -> Node0x17d3680;
+	Node0x17d4f20 -> Node0x17d9fc0;
+	Node0x17d3680 [shape=record,label="{for.body:                                         \l  br label %for.cond1\l}"];
+	Node0x17d3680 -> Node0x17da220;
+	Node0x17da220 [shape=record,label="{for.cond1:                                        \l  %indvar = phi i64 [ %indvar.next, %for.inc ], [ 0, %for.body ]\l  %arrayidx5 = getelementptr [1536 x [1536 x float]]* @C, i64 0, i64 %indvar1, i64 %indvar\l  %j.0 = trunc i64 %indvar to i32\l  %exitcond = icmp ne i64 %indvar, 1536\l  br i1 %exitcond, label %for.body3, label %for.end\l}"];
+	Node0x17da220 -> Node0x17d9ea0;
+	Node0x17da220 -> Node0x17da0f0;
+	Node0x17d9ea0 [shape=record,label="{for.body3:                                        \l  %0 = load %struct._IO_FILE** @stdout, align 8\l  %1 = load float* %arrayidx5, align 4\l  %conv = fpext float %1 to double\l  %call = call i32 (%struct._IO_FILE*, i8*, ...)* @fprintf(%struct._IO_FILE* %0, i8* getelementptr inbounds ([5 x i8]* @.str, i32 0, i32 0), double %conv)\l  %rem = srem i32 %j.0, 80\l  %cmp6 = icmp eq i32 %rem, 79\l  br i1 %cmp6, label %if.then, label %if.end\l}"];
+	Node0x17d9ea0 -> Node0x17d9ec0;
+	Node0x17d9ea0 -> Node0x17da060;
+	Node0x17d9ec0 [shape=record,label="{if.then:                                          \l  %2 = load %struct._IO_FILE** @stdout, align 8\l  %call8 = call i32 (%struct._IO_FILE*, i8*, ...)* @fprintf(%struct._IO_FILE* %2, i8* getelementptr inbounds ([2 x i8]* @.str1, i32 0, i32 0))\l  br label %if.end\l}"];
+	Node0x17d9ec0 -> Node0x17da060;
+	Node0x17da060 [shape=record,label="{if.end:                                           \l  br label %for.inc\l}"];
+	Node0x17da060 -> Node0x17da200;
+	Node0x17da200 [shape=record,label="{for.inc:                                          \l  %indvar.next = add i64 %indvar, 1\l  br label %for.cond1\l}"];
+	Node0x17da200 -> Node0x17da220[constraint=false];
+	Node0x17da0f0 [shape=record,label="{for.end:                                          \l  %3 = load %struct._IO_FILE** @stdout, align 8\l  %call9 = call i32 (%struct._IO_FILE*, i8*, ...)* @fprintf(%struct._IO_FILE* %3, i8* getelementptr inbounds ([2 x i8]* @.str1, i32 0, i32 0))\l  br label %for.inc10\l}"];
+	Node0x17da0f0 -> Node0x17da080;
+	Node0x17da080 [shape=record,label="{for.inc10:                                        \l  %indvar.next2 = add i64 %indvar1, 1\l  br label %for.cond\l}"];
+	Node0x17da080 -> Node0x17d4f20[constraint=false];
+	Node0x17d9fc0 [shape=record,label="{for.end12:                                        \l  ret void\l}"];
 	colorscheme = "paired12"
-        subgraph cluster_0x26adae0 {
+        subgraph cluster_0x17d38f0 {
           label = "";
           style = solid;
           color = 1
-          subgraph cluster_0x26aa030 {
-            label = "";
+          subgraph cluster_0x17d4030 {
+            label = "Non affine branch in BB 'for.body3' with LHS: %rem and RHS: 79";
             style = solid;
             color = 6
-            subgraph cluster_0x26a9fb0 {
-              label = "";
+            subgraph cluster_0x17d3fb0 {
+              label = "Non affine branch in BB 'for.body3' with LHS: %rem and RHS: 79";
               style = solid;
               color = 5
-              subgraph cluster_0x26adb60 {
-                label = "";
+              subgraph cluster_0x17d3f30 {
+                label = "Non affine branch in BB 'for.body3' with LHS: %rem and RHS: 79";
                 style = solid;
                 color = 7
-                Node0x26acde0;
-                Node0x26ada40;
+                Node0x17d9ea0;
+                Node0x17d9ec0;
               }
-              Node0x26ad940;
-              Node0x26acfa0;
-              Node0x26ad6c0;
+              Node0x17da220;
+              Node0x17da060;
+              Node0x17da200;
             }
-            Node0x26acd00;
-            Node0x26a8ac0;
-            Node0x26ad9e0;
-            Node0x26ace00;
+            Node0x17d4f20;
+            Node0x17d3680;
+            Node0x17da0f0;
+            Node0x17da080;
           }
-          Node0x26ac9a0;
-          Node0x26ac9c0;
+          Node0x17d2200;
+          Node0x17d9fc0;
         }
 }
diff --git a/polly/www/experiments/matmul/scops.print_array.dot.png b/polly/www/experiments/matmul/scops.print_array.dot.png
index 5b1658a291f8..e3b973b131ab 100644
Binary files a/polly/www/experiments/matmul/scops.print_array.dot.png and b/polly/www/experiments/matmul/scops.print_array.dot.png differ
diff --git a/polly/www/experiments/matmul/scopsonly.init_array.dot b/polly/www/experiments/matmul/scopsonly.init_array.dot
index 7ef7b1397a5e..4685c5b0af53 100644
--- a/polly/www/experiments/matmul/scopsonly.init_array.dot
+++ b/polly/www/experiments/matmul/scopsonly.init_array.dot
@@ -1,47 +1,47 @@
 digraph "Scop Graph for 'init_array' function" {
 	label="Scop Graph for 'init_array' function";
 
-	Node0x24dfca0 [shape=record,label="{%0}"];
-	Node0x24dfca0 -> Node0x24dfdf0;
-	Node0x24dfdf0 [shape=record,label="{%1}"];
-	Node0x24dfdf0 -> Node0x24dee50;
-	Node0x24dfdf0 -> Node0x24def50;
-	Node0x24dee50 [shape=record,label="{%3}"];
-	Node0x24dee50 -> Node0x24deec0;
-	Node0x24deec0 [shape=record,label="{%4}"];
-	Node0x24deec0 -> Node0x24dfdc0;
-	Node0x24deec0 -> Node0x24df0c0;
-	Node0x24dfdc0 [shape=record,label="{%5}"];
-	Node0x24dfdc0 -> Node0x24defb0;
-	Node0x24defb0 [shape=record,label="{%16}"];
-	Node0x24defb0 -> Node0x24deec0[constraint=false];
-	Node0x24df0c0 [shape=record,label="{%17}"];
-	Node0x24df0c0 -> Node0x24deee0;
-	Node0x24deee0 [shape=record,label="{%18}"];
-	Node0x24deee0 -> Node0x24dfdf0[constraint=false];
-	Node0x24def50 [shape=record,label="{%19}"];
+	Node0x17d4370 [shape=record,label="{entry}"];
+	Node0x17d4370 -> Node0x17d9de0;
+	Node0x17d9de0 [shape=record,label="{for.cond}"];
+	Node0x17d9de0 -> Node0x17d9e40;
+	Node0x17d9de0 -> Node0x17d9ea0;
+	Node0x17d9e40 [shape=record,label="{for.body}"];
+	Node0x17d9e40 -> Node0x17d9f90;
+	Node0x17d9f90 [shape=record,label="{for.cond1}"];
+	Node0x17d9f90 -> Node0x17d9ff0;
+	Node0x17d9f90 -> Node0x17da050;
+	Node0x17d9ff0 [shape=record,label="{for.body3}"];
+	Node0x17d9ff0 -> Node0x17d9f00;
+	Node0x17d9f00 [shape=record,label="{for.inc}"];
+	Node0x17d9f00 -> Node0x17d9f90[constraint=false];
+	Node0x17da050 [shape=record,label="{for.end}"];
+	Node0x17da050 -> Node0x17da200;
+	Node0x17da200 [shape=record,label="{for.inc17}"];
+	Node0x17da200 -> Node0x17d9de0[constraint=false];
+	Node0x17d9ea0 [shape=record,label="{for.end19}"];
 	colorscheme = "paired12"
-        subgraph cluster_0x24db4c0 {
+        subgraph cluster_0x17d3a30 {
           label = "";
           style = solid;
           color = 1
-          subgraph cluster_0x24dc4e0 {
+          subgraph cluster_0x17d4ec0 {
             label = "";
             style = filled;
-            color = 3            subgraph cluster_0x24db780 {
+            color = 3            subgraph cluster_0x17d4180 {
               label = "";
               style = solid;
               color = 5
-              Node0x24deec0;
-              Node0x24dfdc0;
-              Node0x24defb0;
+              Node0x17d9f90;
+              Node0x17d9ff0;
+              Node0x17d9f00;
             }
-            Node0x24dfdf0;
-            Node0x24dee50;
-            Node0x24df0c0;
-            Node0x24deee0;
+            Node0x17d9de0;
+            Node0x17d9e40;
+            Node0x17da050;
+            Node0x17da200;
           }
-          Node0x24dfca0;
-          Node0x24def50;
+          Node0x17d4370;
+          Node0x17d9ea0;
         }
 }
diff --git a/polly/www/experiments/matmul/scopsonly.init_array.dot.png b/polly/www/experiments/matmul/scopsonly.init_array.dot.png
index 92c4f9882bd6..f101d4d30815 100644
Binary files a/polly/www/experiments/matmul/scopsonly.init_array.dot.png and b/polly/www/experiments/matmul/scopsonly.init_array.dot.png differ
diff --git a/polly/www/experiments/matmul/scopsonly.main.dot b/polly/www/experiments/matmul/scopsonly.main.dot
index d375349730ae..3b3f32880197 100644
--- a/polly/www/experiments/matmul/scopsonly.main.dot
+++ b/polly/www/experiments/matmul/scopsonly.main.dot
@@ -1,65 +1,65 @@
 digraph "Scop Graph for 'main' function" {
 	label="Scop Graph for 'main' function";
 
-	Node0x24deb60 [shape=record,label="{%0}"];
-	Node0x24deb60 -> Node0x24deaa0;
-	Node0x24deaa0 [shape=record,label="{%1}"];
-	Node0x24deaa0 -> Node0x24e12a0;
-	Node0x24deaa0 -> Node0x24e0e30;
-	Node0x24e12a0 [shape=record,label="{%2}"];
-	Node0x24e12a0 -> Node0x24e0e00;
-	Node0x24e0e00 [shape=record,label="{%3}"];
-	Node0x24e0e00 -> Node0x24e1410;
-	Node0x24e0e00 -> Node0x24e1470;
-	Node0x24e1410 [shape=record,label="{%4}"];
-	Node0x24e1410 -> Node0x24e1380;
-	Node0x24e1380 [shape=record,label="{%5}"];
-	Node0x24e1380 -> Node0x24deaf0;
-	Node0x24e1380 -> Node0x24e1620;
-	Node0x24deaf0 [shape=record,label="{%6}"];
-	Node0x24deaf0 -> Node0x24e1680;
-	Node0x24e1680 [shape=record,label="{%12}"];
-	Node0x24e1680 -> Node0x24e1380[constraint=false];
-	Node0x24e1620 [shape=record,label="{%13}"];
-	Node0x24e1620 -> Node0x24e16e0;
-	Node0x24e16e0 [shape=record,label="{%14}"];
-	Node0x24e16e0 -> Node0x24e0e00[constraint=false];
-	Node0x24e1470 [shape=record,label="{%15}"];
-	Node0x24e1470 -> Node0x24e01a0;
-	Node0x24e01a0 [shape=record,label="{%16}"];
-	Node0x24e01a0 -> Node0x24deaa0[constraint=false];
-	Node0x24e0e30 [shape=record,label="{%17}"];
+	Node0x17d3950 [shape=record,label="{entry}"];
+	Node0x17d3950 -> Node0x17d21a0;
+	Node0x17d21a0 [shape=record,label="{for.cond}"];
+	Node0x17d21a0 -> Node0x17db9a0;
+	Node0x17d21a0 -> Node0x17da4f0;
+	Node0x17db9a0 [shape=record,label="{for.body}"];
+	Node0x17db9a0 -> Node0x17da5e0;
+	Node0x17da5e0 [shape=record,label="{for.cond1}"];
+	Node0x17da5e0 -> Node0x17da640;
+	Node0x17da5e0 -> Node0x17da6a0;
+	Node0x17da640 [shape=record,label="{for.body3}"];
+	Node0x17da640 -> Node0x17da550;
+	Node0x17da550 [shape=record,label="{for.cond6}"];
+	Node0x17da550 -> Node0x17da5b0;
+	Node0x17da550 -> Node0x17da850;
+	Node0x17da5b0 [shape=record,label="{for.body8}"];
+	Node0x17da5b0 -> Node0x17da8b0;
+	Node0x17da8b0 [shape=record,label="{for.inc}"];
+	Node0x17da8b0 -> Node0x17da550[constraint=false];
+	Node0x17da850 [shape=record,label="{for.end}"];
+	Node0x17da850 -> Node0x17db930;
+	Node0x17db930 [shape=record,label="{for.inc25}"];
+	Node0x17db930 -> Node0x17da5e0[constraint=false];
+	Node0x17da6a0 [shape=record,label="{for.end27}"];
+	Node0x17da6a0 -> Node0x17dada0;
+	Node0x17dada0 [shape=record,label="{for.inc28}"];
+	Node0x17dada0 -> Node0x17d21a0[constraint=false];
+	Node0x17da4f0 [shape=record,label="{for.end30}"];
 	colorscheme = "paired12"
-        subgraph cluster_0x24dfc10 {
+        subgraph cluster_0x17d3f30 {
           label = "";
           style = solid;
           color = 1
-          subgraph cluster_0x24de570 {
+          subgraph cluster_0x17d38d0 {
             label = "";
             style = filled;
-            color = 3            subgraph cluster_0x24de7a0 {
+            color = 3            subgraph cluster_0x17d3850 {
               label = "";
               style = solid;
               color = 5
-              subgraph cluster_0x24de720 {
+              subgraph cluster_0x17d37d0 {
                 label = "";
                 style = solid;
                 color = 7
-                Node0x24e1380;
-                Node0x24deaf0;
-                Node0x24e1680;
+                Node0x17da550;
+                Node0x17da5b0;
+                Node0x17da8b0;
               }
-              Node0x24e0e00;
-              Node0x24e1410;
-              Node0x24e1620;
-              Node0x24e16e0;
+              Node0x17da5e0;
+              Node0x17da640;
+              Node0x17da850;
+              Node0x17db930;
             }
-            Node0x24deaa0;
-            Node0x24e12a0;
-            Node0x24e1470;
-            Node0x24e01a0;
+            Node0x17d21a0;
+            Node0x17db9a0;
+            Node0x17da6a0;
+            Node0x17dada0;
           }
-          Node0x24deb60;
-          Node0x24e0e30;
+          Node0x17d3950;
+          Node0x17da4f0;
         }
 }
diff --git a/polly/www/experiments/matmul/scopsonly.main.dot.png b/polly/www/experiments/matmul/scopsonly.main.dot.png
index f0cf154bc79a..32634243888d 100644
Binary files a/polly/www/experiments/matmul/scopsonly.main.dot.png and b/polly/www/experiments/matmul/scopsonly.main.dot.png differ
diff --git a/polly/www/experiments/matmul/scopsonly.print_array.dot b/polly/www/experiments/matmul/scopsonly.print_array.dot
index 7c46729e31d8..c900d0f1be11 100644
--- a/polly/www/experiments/matmul/scopsonly.print_array.dot
+++ b/polly/www/experiments/matmul/scopsonly.print_array.dot
@@ -1,60 +1,60 @@
 digraph "Scop Graph for 'print_array' function" {
 	label="Scop Graph for 'print_array' function";
 
-	Node0x24df2c0 [shape=record,label="{%0}"];
-	Node0x24df2c0 -> Node0x24df2a0;
-	Node0x24df2a0 [shape=record,label="{%1}"];
-	Node0x24df2a0 -> Node0x24dee90;
-	Node0x24df2a0 -> Node0x24dee20;
-	Node0x24dee90 [shape=record,label="{%2}"];
-	Node0x24dee90 -> Node0x24debd0;
-	Node0x24debd0 [shape=record,label="{%3}"];
-	Node0x24debd0 -> Node0x24df150;
-	Node0x24debd0 -> Node0x24de990;
-	Node0x24df150 [shape=record,label="{%4}"];
-	Node0x24df150 -> Node0x24df3a0;
-	Node0x24df150 -> Node0x24defb0;
-	Node0x24df3a0 [shape=record,label="{%11}"];
-	Node0x24df3a0 -> Node0x24defb0;
-	Node0x24defb0 [shape=record,label="{%14}"];
-	Node0x24defb0 -> Node0x24df530;
-	Node0x24df530 [shape=record,label="{%15}"];
-	Node0x24df530 -> Node0x24debd0[constraint=false];
-	Node0x24de990 [shape=record,label="{%16}"];
-	Node0x24de990 -> Node0x24df9a0;
-	Node0x24df9a0 [shape=record,label="{%19}"];
-	Node0x24df9a0 -> Node0x24df2a0[constraint=false];
-	Node0x24dee20 [shape=record,label="{%20}"];
+	Node0x17d2200 [shape=record,label="{entry}"];
+	Node0x17d2200 -> Node0x17d4f20;
+	Node0x17d4f20 [shape=record,label="{for.cond}"];
+	Node0x17d4f20 -> Node0x17d9fd0;
+	Node0x17d4f20 -> Node0x17da030;
+	Node0x17d9fd0 [shape=record,label="{for.body}"];
+	Node0x17d9fd0 -> Node0x17da120;
+	Node0x17da120 [shape=record,label="{for.cond1}"];
+	Node0x17da120 -> Node0x17da180;
+	Node0x17da120 -> Node0x17da1e0;
+	Node0x17da180 [shape=record,label="{for.body3}"];
+	Node0x17da180 -> Node0x17da090;
+	Node0x17da180 -> Node0x17da0f0;
+	Node0x17da090 [shape=record,label="{if.then}"];
+	Node0x17da090 -> Node0x17da0f0;
+	Node0x17da0f0 [shape=record,label="{if.end}"];
+	Node0x17da0f0 -> Node0x17da390;
+	Node0x17da390 [shape=record,label="{for.inc}"];
+	Node0x17da390 -> Node0x17da120[constraint=false];
+	Node0x17da1e0 [shape=record,label="{for.end}"];
+	Node0x17da1e0 -> Node0x17d9e40;
+	Node0x17d9e40 [shape=record,label="{for.inc10}"];
+	Node0x17d9e40 -> Node0x17d4f20[constraint=false];
+	Node0x17da030 [shape=record,label="{for.end12}"];
 	colorscheme = "paired12"
-        subgraph cluster_0x24dbe40 {
+        subgraph cluster_0x17d38f0 {
           label = "";
           style = solid;
           color = 1
-          subgraph cluster_0x24db6e0 {
-            label = "";
+          subgraph cluster_0x17d4030 {
+            label = "Non affine branch in BB 'for.body3' with LHS: %rem and RHS: 79";
             style = solid;
             color = 6
-            subgraph cluster_0x24db660 {
-              label = "";
+            subgraph cluster_0x17d3fb0 {
+              label = "Non affine branch in BB 'for.body3' with LHS: %rem and RHS: 79";
               style = solid;
               color = 5
-              subgraph cluster_0x24db5e0 {
-                label = "";
+              subgraph cluster_0x17d3f30 {
+                label = "Non affine branch in BB 'for.body3' with LHS: %rem and RHS: 79";
                 style = solid;
                 color = 7
-                Node0x24df150;
-                Node0x24df3a0;
+                Node0x17da180;
+                Node0x17da090;
               }
-              Node0x24debd0;
-              Node0x24defb0;
-              Node0x24df530;
+              Node0x17da120;
+              Node0x17da0f0;
+              Node0x17da390;
             }
-            Node0x24df2a0;
-            Node0x24dee90;
-            Node0x24de990;
-            Node0x24df9a0;
+            Node0x17d4f20;
+            Node0x17d9fd0;
+            Node0x17da1e0;
+            Node0x17d9e40;
           }
-          Node0x24df2c0;
-          Node0x24dee20;
+          Node0x17d2200;
+          Node0x17da030;
         }
 }
diff --git a/polly/www/experiments/matmul/scopsonly.print_array.dot.png b/polly/www/experiments/matmul/scopsonly.print_array.dot.png
index 3426e7b06fbc..b0d4b45aace4 100644
Binary files a/polly/www/experiments/matmul/scopsonly.print_array.dot.png and b/polly/www/experiments/matmul/scopsonly.print_array.dot.png differ