From 79ff6e4b2d5189129d7c4e7ab74d0f0e2cce4e79 Mon Sep 17 00:00:00 2001 From: Dawid Jurczak Date: Wed, 25 Aug 2021 13:13:18 +0200 Subject: [PATCH] [LoopIdiom] Don't transform loop into memmove when load from body has more than one use This change fixes issue found by Markus: https://reviews.llvm.org/rG11338e998df1 Before this patch following code was transformed to memmove: for (int i = 15; i >= 1; i--) { p[i] = p[i-1]; sum += p[i-1]; } However load from p[i-1] is used not only by store to p[i] but also by sum computation. Therefore we cannot emit memmove in loop header. Differential Revision: https://reviews.llvm.org/D107964 (cherry picked from commit bdcf04246c401aec9bdddf32fabc99fa4834a477) --- lib/Transforms/Scalar/LoopIdiomRecognize.cpp | 5 +++++ test/Transforms/LoopIdiom/basic.ll | 7 ++----- 2 files changed, 7 insertions(+), 5 deletions(-) diff --git a/lib/Transforms/Scalar/LoopIdiomRecognize.cpp b/lib/Transforms/Scalar/LoopIdiomRecognize.cpp index 3d60e205b00..a153f393448 100644 --- a/lib/Transforms/Scalar/LoopIdiomRecognize.cpp +++ b/lib/Transforms/Scalar/LoopIdiomRecognize.cpp @@ -1247,6 +1247,11 @@ bool LoopIdiomRecognize::processLoopStoreOfLoopLoad( mayLoopAccessLocation(StoreBasePtr, ModRefInfo::ModRef, CurLoop, BECount, StoreSize, *AA, Stores); if (UseMemMove) { + // For memmove case it's not enough to guarantee that loop doesn't access + // TheStore and TheLoad. Additionally we need to make sure that TheStore is + // the only user of TheLoad. + if (!TheLoad->hasOneUse()) + return Changed; Stores.insert(TheLoad); if (mayLoopAccessLocation(StoreBasePtr, ModRefInfo::ModRef, CurLoop, BECount, StoreSize, *AA, Stores)) { diff --git a/test/Transforms/LoopIdiom/basic.ll b/test/Transforms/LoopIdiom/basic.ll index ea6d607c8ef..c8c6d187a0c 100644 --- a/test/Transforms/LoopIdiom/basic.ll +++ b/test/Transforms/LoopIdiom/basic.ll @@ -1300,14 +1300,10 @@ for.end: ; preds = %for.body, %entry ret void } -;; FIXME: Do not form memmove when load has more than one use. +;; Do not form memmove when load has more than one use. define i32 @do_not_form_memmove5(i32* %p) { ; CHECK-LABEL: @do_not_form_memmove5( ; CHECK-NEXT: entry: -; CHECK-NEXT: [[P2:%.*]] = bitcast i32* [[P:%.*]] to i8* -; CHECK-NEXT: [[SCEVGEP:%.*]] = getelementptr i32, i32* [[P:%.*]], i64 1 -; CHECK-NEXT: [[SCEVGEP1:%.*]] = bitcast i32* [[SCEVGEP]] to i8* -; CHECK-NEXT: call void @llvm.memmove.p0i8.p0i8.i64(i8* align 4 [[SCEVGEP1]], i8* align 4 [[P2]], i64 60, i1 false) ; CHECK-NEXT: br label [[FOR_BODY:%.*]] ; CHECK: for.cond.cleanup: ; CHECK-NEXT: [[ADD_LCSSA:%.*]] = phi i32 [ [[ADD:%.*]], [[FOR_BODY]] ] @@ -1321,6 +1317,7 @@ define i32 @do_not_form_memmove5(i32* %p) { ; CHECK-NEXT: [[TMP1:%.*]] = load i32, i32* [[ARRAYIDX]], align 4 ; CHECK-NEXT: [[IDXPROM:%.*]] = zext i32 [[INDEX]] to i64 ; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds i32, i32* [[P:%.*]], i64 [[IDXPROM]] +; CHECK-NEXT: store i32 [[TMP1]], i32* [[ARRAYIDX2]], align 4 ; CHECK-NEXT: [[ADD]] = add nsw i32 [[TMP1]], [[SUM:%.*]] ; CHECK-NEXT: [[CMP:%.*]] = icmp sgt i32 [[INDEX]], 1 ; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY]], label [[FOR_COND_CLEANUP]]