Adel Ejjeh
f86d707db6
Reland of #190258, reverted in #194901 due to a null-pointer dereference when the scalar preheader is absent. Fixed by guarding the metadata emission with a null check on `ScalarPH`. Also adds a dedicated test (`vectorize-loop-kind-metadata.ll`) verifying the metadata is emitted only when remarks are enabled. --- Add two new loop metadata attributes — `llvm.loop.vectorize.body` and `llvm.loop.vectorize.epilogue` — that the loop vectorizer sets on the generated vector loop and epilogue loop respectively. The metadata is only emitted when optimization remarks are enabled (`ORE->enabled()`), so it has zero cost in normal compilation. These enable downstream passes (LoopUnroll, WarnMissedTransforms) to produce more precise optimization remarks. Instead of the generic "loop not unrolled" warning on a source line that was vectorized, the unroller can now report: - **"vectorized loop"** for the main vector body - **"epilogue loop"** for the scalar epilogue/remainder - **"epilogue vectorized loop"** for an epilogue that was itself vectorized during epilogue vectorization (carries both attributes) A shared `getLoopVectorizeKindPrefix()` helper in `LoopUtils.h`/`LoopUtils.cpp` reads the metadata and returns the appropriate prefix string, used by both `LoopUnroll.cpp` and `WarnMissedTransforms.cpp`. The metadata emission in `VPlan.cpp` uses `Loop::addIntLoopAttribute` from the NFC PR #194676. Two end-to-end tests exercise the full `loop-vectorize → loop-unroll` pipeline with forced epilogue vectorization (`-enable-epilogue-vectorization -epilogue-vectorization-force-VF=4`) to produce all four loop categories from a single vectorizable function. Each test also includes a plain (non-vectorized) function to cover the baseline "loop" case. Both tests verify stderr diagnostic output and YAML structured remarks. **`LoopUnroll/vectorizer-loop-kind-remarks.ll`** checks for successful-unroll remarks. **`LoopTransformWarning/vectorizer-loop-kind-unroll-warning.ll`** checks for failed-unroll warnings. AI Disclaimer: this patch was generated with assistance of GitHub Copilot/Claude Opus and reviewed by a human.
35 lines
1.3 KiB
LLVM
35 lines
1.3 KiB
LLVM
; RUN: opt < %s -passes=loop-vectorize -force-vector-interleave=1 -force-vector-width=4 \
|
|
; RUN: -pass-remarks-analysis=loop-vectorize -S | FileCheck %s --check-prefix=REMARKS
|
|
; RUN: opt < %s -passes=loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -S \
|
|
; RUN: | FileCheck %s --check-prefix=NO-REMARKS
|
|
|
|
; Verify that llvm.loop.vectorize.body is attached to the vector loop and
|
|
; llvm.loop.vectorize.epilogue is attached to the scalar remainder when
|
|
; optimization remarks are enabled, and absent otherwise.
|
|
|
|
define void @test_metadata(ptr noalias %A, i64 %n) {
|
|
entry:
|
|
br label %loop
|
|
|
|
loop:
|
|
%iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
|
|
%gep = getelementptr inbounds i32, ptr %A, i64 %iv
|
|
%val = load i32, ptr %gep, align 4
|
|
%add = add i32 %val, 1
|
|
store i32 %add, ptr %gep, align 4
|
|
%iv.next = add i64 %iv, 1
|
|
%cmp = icmp slt i64 %iv.next, %n
|
|
br i1 %cmp, label %loop, label %exit
|
|
|
|
exit:
|
|
ret void
|
|
}
|
|
|
|
; With remarks enabled: vector loop has vectorize.body, scalar remainder has vectorize.epilogue.
|
|
; REMARKS-DAG: !{!"llvm.loop.vectorize.body", i32 1}
|
|
; REMARKS-DAG: !{!"llvm.loop.vectorize.epilogue", i32 1}
|
|
|
|
; Without remarks: neither metadata is present.
|
|
; NO-REMARKS-NOT: llvm.loop.vectorize.body
|
|
; NO-REMARKS-NOT: llvm.loop.vectorize.epilogue
|