mirror of
https://github.com/intel/llvm.git
synced 2026-01-31 07:26:01 +08:00
0b9f1cc024
See the following case:
```
@GlobIntONE = global i32 0, align 4
define ptr @src() {
entry:
br label %for.body.peel.begin
for.body.peel.begin: ; preds = %entry
br label %for.body.peel
for.body.peel: ; preds = %for.body.peel.begin
br i1 true, label %cleanup.peel, label %cleanup.loopexit.peel
cleanup.loopexit.peel: ; preds = %for.body.peel
br label %cleanup.peel
cleanup.peel: ; preds = %cleanup.loopexit.peel, %for.body.peel
%retval.2.peel = phi ptr [ undef, %for.body.peel ], [ @GlobIntONE, %cleanup.loopexit.peel ]
br i1 true, label %for.body.peel.next, label %cleanup7
for.body.peel.next: ; preds = %cleanup.peel
br label %for.body.peel.next1
for.body.peel.next1: ; preds = %for.body.peel.next
br label %entry.peel.newph
entry.peel.newph: ; preds = %for.body.peel.next1
br label %for.body
for.body: ; preds = %cleanup, %entry.peel.newph
%retval.0 = phi ptr [ %retval.2.peel, %entry.peel.newph ], [ %retval.2, %cleanup ]
br i1 false, label %cleanup, label %cleanup.loopexit
cleanup.loopexit: ; preds = %for.body
br label %cleanup
cleanup: ; preds = %cleanup.loopexit, %for.body
%retval.2 = phi ptr [ %retval.0, %for.body ], [ @GlobIntONE, %cleanup.loopexit ]
br i1 false, label %for.body, label %cleanup7.loopexit
cleanup7.loopexit: ; preds = %cleanup
%retval.2.lcssa.ph = phi ptr [ %retval.2, %cleanup ]
br label %cleanup7
cleanup7: ; preds = %cleanup7.loopexit, %cleanup.peel
%retval.2.lcssa = phi ptr [ %retval.2.peel, %cleanup.peel ], [ %retval.2.lcssa.ph, %cleanup7.loopexit ]
ret ptr %retval.2.lcssa
}
define ptr @tgt() {
entry:
br label %for.body.peel.begin
for.body.peel.begin: ; preds = %entry
br label %for.body.peel
for.body.peel: ; preds = %for.body.peel.begin
br i1 true, label %cleanup.peel, label %cleanup.loopexit.peel
cleanup.loopexit.peel: ; preds = %for.body.peel
br label %cleanup.peel
cleanup.peel: ; preds = %cleanup.loopexit.peel, %for.body.peel
%retval.2.peel = phi ptr [ undef, %for.body.peel ], [ @GlobIntONE, %cleanup.loopexit.peel ]
br i1 true, label %for.body.peel.next, label %cleanup7
for.body.peel.next: ; preds = %cleanup.peel
br label %for.body.peel.next1
for.body.peel.next1: ; preds = %for.body.peel.next
br label %entry.peel.newph
entry.peel.newph: ; preds = %for.body.peel.next1
br label %for.body
for.body: ; preds = %cleanup, %entry.peel.newph
br i1 false, label %cleanup, label %cleanup.loopexit
cleanup.loopexit: ; preds = %for.body
br label %cleanup
cleanup: ; preds = %cleanup.loopexit, %for.body
br i1 false, label %for.body, label %cleanup7.loopexit
cleanup7.loopexit: ; preds = %cleanup
%retval.2.lcssa.ph = phi ptr [ %retval.2.peel, %cleanup ]
br label %cleanup7
cleanup7: ; preds = %cleanup7.loopexit, %cleanup.peel
%retval.2.lcssa = phi ptr [ %retval.2.peel, %cleanup.peel ], [ %retval.2.lcssa.ph, %cleanup7.loopexit ]
ret ptr %retval.2.lcssa
}
```
1. `simplifyInstruction(%retval.2.peel)` returns `@GlobIntONE`. Thus,
`ScalarEvolution::createNodeForPHI` returns SCEV expr `@GlobIntONE` for
`%retval.2.peel`.
2. `SimplifyIndvar::replaceIVUserWithLoopInvariant` tries to replace the
use of `%retval.2.peel` in `%retval.2.lcssa.ph` with `@GlobIntONE`.
3. `simplifyLoopAfterUnroll -> simplifyLoopIVs -> SCEVExpander::expand`
reuses `%retval.2.peel = phi ptr [ undef, %for.body.peel ], [
@GlobIntONE, %cleanup.loopexit.peel ]` to generate code for
`@GlobIntONE`. It is incorrect.
This patch disallows simplifying `phi(undef, X)` to `X` by setting
`CanUseUndef` to false.
Closes https://github.com/llvm/llvm-project/issues/114879.
Polly - Polyhedral optimizations for LLVM ----------------------------------------- http://polly.llvm.org/ Polly uses a mathematical representation, the polyhedral model, to represent and transform loops and other control flow structures. Using an abstract representation it is possible to reason about transformations in a more general way and to use highly optimized linear programming libraries to figure out the optimal loop structure. These transformations can be used to do constant propagation through arrays, remove dead loop iterations, optimize loops for cache locality, optimize arrays, apply advanced automatic parallelization, drive vectorization, or they can be used to do software pipelining.