[RISCV] Enable LoopDataPrefetch pass (#66201)

So that we can benefit from data prefetch when `Zicbop` extension is
supported.

Tune information for data prefetching are added in `RISCVTuneInfo`.

llvm/lib/Target/RISCV/RISCVProcessors.td

@@ -13,12 +13,20 @@
 class RISCVTuneInfo {
   bits<8> PrefFunctionAlignment = 1;
   bits<8> PrefLoopAlignment = 1;
+
+  // Information needed by LoopDataPrefetch.
+  bits<16> CacheLineSize = 0;
+  bits<16> PrefetchDistance = 0;
+  bits<16> MinPrefetchStride = 1;
+  bits<32> MaxPrefetchIterationsAhead = -1;
 }
 
 def RISCVTuneInfoTable : GenericTable {
   let FilterClass = "RISCVTuneInfo";
   let CppTypeName = "RISCVTuneInfo";
-  let Fields = ["Name", "PrefFunctionAlignment", "PrefLoopAlignment"];
+  let Fields = ["Name", "PrefFunctionAlignment", "PrefLoopAlignment",
+                "CacheLineSize", "PrefetchDistance",
+                "MinPrefetchStride", "MaxPrefetchIterationsAhead"];
 }
 
 def getRISCVTuneInfo : SearchIndex {

llvm/lib/Target/RISCV/RISCVSubtarget.h

@@ -38,6 +38,12 @@ struct RISCVTuneInfo {
   const char *Name;
   uint8_t PrefFunctionAlignment;
   uint8_t PrefLoopAlignment;
+
+  // Information needed by LoopDataPrefetch.
+  uint16_t CacheLineSize;
+  uint16_t PrefetchDistance;
+  uint16_t MinPrefetchStride;
+  unsigned MaxPrefetchIterationsAhead;
 };
 
 #define GET_RISCVTuneInfoTable_DECL
@@ -248,6 +254,22 @@ public:
                               &Mutations) const override;
 
   bool useAA() const override;
+
+  unsigned getCacheLineSize() const override {
+    return TuneInfo->CacheLineSize;
+  };
+  unsigned getPrefetchDistance() const override {
+    return TuneInfo->PrefetchDistance;
+  };
+  unsigned getMinPrefetchStride(unsigned NumMemAccesses,
+                                unsigned NumStridedMemAccesses,
+                                unsigned NumPrefetches,
+                                bool HasCall) const override {
+    return TuneInfo->MinPrefetchStride;
+  };
+  unsigned getMaxPrefetchIterationsAhead() const override {
+    return TuneInfo->MaxPrefetchIterationsAhead;
+  };
 };
 } // End llvm namespace
 

llvm/lib/Target/RISCV/RISCVTargetMachine.cpp

@@ -34,6 +34,7 @@
 #include "llvm/Support/FormattedStream.h"
 #include "llvm/Target/TargetOptions.h"
 #include "llvm/Transforms/IPO.h"
+#include "llvm/Transforms/Scalar.h"
 #include <optional>
 using namespace llvm;
 
@@ -83,6 +84,11 @@ static cl::opt<bool>
                    cl::desc("Enable sinking and folding of instruction copies"),
                    cl::init(false), cl::Hidden);
 
+static cl::opt<bool>
+    EnableLoopDataPrefetch("riscv-enable-loop-data-prefetch", cl::Hidden,
+                           cl::desc("Enable the loop data prefetch pass"),
+                           cl::init(true));
+
 extern "C" LLVM_EXTERNAL_VISIBILITY void LLVMInitializeRISCVTarget() {
   RegisterTargetMachine<RISCVTargetMachine> X(getTheRISCV32Target());
   RegisterTargetMachine<RISCVTargetMachine> Y(getTheRISCV64Target());
@@ -310,6 +316,9 @@ void RISCVPassConfig::addIRPasses() {
   addPass(createAtomicExpandPass());
 
   if (getOptLevel() != CodeGenOptLevel::None) {
+    if (EnableLoopDataPrefetch)
+      addPass(createLoopDataPrefetchPass());
+
     addPass(createRISCVGatherScatterLoweringPass());
     addPass(createInterleavedAccessPass());
     addPass(createRISCVCodeGenPreparePass());

llvm/test/CodeGen/RISCV/O3-pipeline.ll

@@ -12,10 +12,10 @@
 ; CHECK-NEXT: Target Pass Configuration
 ; CHECK-NEXT: Machine Module Information
 ; CHECK-NEXT: Target Transform Information
-; CHECK-NEXT: Type-Based Alias Analysis
-; CHECK-NEXT: Scoped NoAlias Alias Analysis
 ; CHECK-NEXT: Assumption Cache Tracker
 ; CHECK-NEXT: Profile summary info
+; CHECK-NEXT: Type-Based Alias Analysis
+; CHECK-NEXT: Scoped NoAlias Alias Analysis
 ; CHECK-NEXT: Create Garbage Collector Module Metadata
 ; CHECK-NEXT: Machine Branch Probability Analysis
 ; CHECK-NEXT: Default Regalloc Eviction Advisor
@@ -28,6 +28,12 @@
 ; CHECK-NEXT:       Expand Atomic instructions
 ; CHECK-NEXT:       Dominator Tree Construction
 ; CHECK-NEXT:       Natural Loop Information
+; CHECK-NEXT:       Canonicalize natural loops
+; CHECK-NEXT:       Lazy Branch Probability Analysis
+; CHECK-NEXT:       Lazy Block Frequency Analysis
+; CHECK-NEXT:       Optimization Remark Emitter
+; CHECK-NEXT:       Scalar Evolution Analysis
+; CHECK-NEXT:       Loop Data Prefetch
 ; CHECK-NEXT:       RISC-V gather/scatter lowering
 ; CHECK-NEXT:       Interleaved Access Pass
 ; CHECK-NEXT:       RISC-V CodeGenPrepare

llvm/test/Transforms/LoopDataPrefetch/RISCV/basic.ll

@@ -0,0 +1,43 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 3
+; RUN: opt -mtriple=riscv64 -cache-line-size=64 -prefetch-distance=64 \
+; RUN:   -passes=loop-data-prefetch -S < %s | FileCheck %s
+
+define void @foo(ptr nocapture %a, ptr nocapture readonly %b) {
+; CHECK-LABEL: define void @foo(
+; CHECK-SAME: ptr nocapture [[A:%.*]], ptr nocapture readonly [[B:%.*]]) {
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
+; CHECK:       for.body:
+; CHECK-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
+; CHECK-NEXT:    [[TMP0:%.*]] = shl nuw nsw i64 [[INDVARS_IV]], 3
+; CHECK-NEXT:    [[TMP1:%.*]] = add i64 [[TMP0]], 64
+; CHECK-NEXT:    [[SCEVGEP:%.*]] = getelementptr i8, ptr [[B]], i64 [[TMP1]]
+; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds double, ptr [[B]], i64 [[INDVARS_IV]]
+; CHECK-NEXT:    call void @llvm.prefetch.p0(ptr [[SCEVGEP]], i32 0, i32 3, i32 1)
+; CHECK-NEXT:    [[TMP2:%.*]] = load double, ptr [[ARRAYIDX]], align 8
+; CHECK-NEXT:    [[ADD:%.*]] = fadd double [[TMP2]], 1.000000e+00
+; CHECK-NEXT:    [[ARRAYIDX2:%.*]] = getelementptr inbounds double, ptr [[A]], i64 [[INDVARS_IV]]
+; CHECK-NEXT:    store double [[ADD]], ptr [[ARRAYIDX2]], align 8
+; CHECK-NEXT:    [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
+; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 1600
+; CHECK-NEXT:    br i1 [[EXITCOND]], label [[FOR_END:%.*]], label [[FOR_BODY]]
+; CHECK:       for.end:
+; CHECK-NEXT:    ret void
+;
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %arrayidx = getelementptr inbounds double, ptr %b, i64 %indvars.iv
+  %0 = load double, ptr %arrayidx, align 8
+  %add = fadd double %0, 1.000000e+00
+  %arrayidx2 = getelementptr inbounds double, ptr %a, i64 %indvars.iv
+  store double %add, ptr %arrayidx2, align 8
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 1600
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret void
+}

llvm/test/Transforms/LoopDataPrefetch/RISCV/lit.local.cfg

@@ -0,0 +1,2 @@
+if not "RISCV" in config.root.targets:
+    config.unsupported = True