[llvm] 60ae9c9 - [SLP]Do not consider non-profitable loads slices
via llvm-commits
llvm-commits at lists.llvm.org
Thu Jul 17 05:00:05 PDT 2025
Author: Alexey Bataev
Date: 2025-07-17T08:00:02-04:00
New Revision: 60ae9c9c632dec978e71d1d3ab3c3d18eca16c77
URL: https://github.com/llvm/llvm-project/commit/60ae9c9c632dec978e71d1d3ab3c3d18eca16c77
DIFF: https://github.com/llvm/llvm-project/commit/60ae9c9c632dec978e71d1d3ab3c3d18eca16c77.diff
LOG: [SLP]Do not consider non-profitable loads slices
If all slices are small and end up with strided or even vectorization
states, better to not consider these candidates for the vectorization
and try to vectorize the whole bunch as gathered loads.
Reviewers: hiraditya, RKSimon, HanKuanChen
Reviewed By: RKSimon, HanKuanChen
Pull Request: https://github.com/llvm/llvm-project/pull/149209
Added:
Modified:
llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
llvm/test/Transforms/SLPVectorizer/X86/matched-nodes-updated.ll
Removed:
################################################################################
diff --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
index da6af353c709f..6ad5c60105a28 100644
--- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -11693,6 +11693,7 @@ void BoUpSLP::transformNodes() {
if (StartIdx + VF > End)
continue;
SmallVector<std::pair<unsigned, unsigned>> Slices;
+ bool AllStrided = true;
for (unsigned Cnt = StartIdx; Cnt + VF <= End; Cnt += VF) {
ArrayRef<Value *> Slice = VL.slice(Cnt, VF);
// If any instruction is vectorized already - do not try again.
@@ -11743,6 +11744,9 @@ void BoUpSLP::transformNodes() {
SmallVector<Value *> PointerOps;
LoadsState Res =
canVectorizeLoads(Slice, Slice.front(), Order, PointerOps);
+ AllStrided &= Res == LoadsState::StridedVectorize ||
+ Res == LoadsState::ScatterVectorize ||
+ Res == LoadsState::Gather;
// Do not vectorize gathers.
if (Res == LoadsState::ScatterVectorize ||
Res == LoadsState::Gather) {
@@ -11772,6 +11776,11 @@ void BoUpSLP::transformNodes() {
}
Slices.emplace_back(Cnt, Slice.size());
}
+ // Do not try to vectorize if all slides are strided or gathered with
+ // vector factor 2 and there are more than 2 slices. Better to handle
+ // them in gathered loads analysis, may result in better vectorization.
+ if (VF == 2 && AllStrided && Slices.size() > 2)
+ continue;
auto AddCombinedNode = [&](unsigned Idx, unsigned Cnt, unsigned Sz) {
E.CombinedEntriesWithIndices.emplace_back(Idx, Cnt);
if (StartIdx == Cnt)
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/matched-nodes-updated.ll b/llvm/test/Transforms/SLPVectorizer/X86/matched-nodes-updated.ll
index f56af934f19f5..b1864b43512d8 100644
--- a/llvm/test/Transforms/SLPVectorizer/X86/matched-nodes-updated.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/matched-nodes-updated.ll
@@ -14,50 +14,44 @@ define i32 @test(i32 %s.0) {
; CHECK: [[IF_END3:.*]]:
; CHECK-NEXT: br label %[[IF_END6:.*]]
; CHECK: [[IF_END6]]:
-; CHECK-NEXT: [[J_4:%.*]] = phi i32 [ 0, %[[IF_END3]] ], [ [[TMP28:%.*]], %[[O]] ]
-; CHECK-NEXT: [[TMP2:%.*]] = phi <2 x i32> [ poison, %[[IF_END3]] ], [ zeroinitializer, %[[O]] ]
-; CHECK-NEXT: [[TMP3:%.*]] = phi <2 x i32> [ poison, %[[IF_END3]] ], [ zeroinitializer, %[[O]] ]
-; CHECK-NEXT: [[TMP4:%.*]] = phi <2 x i32> [ poison, %[[IF_END3]] ], [ [[TMP22:%.*]], %[[O]] ]
+; CHECK-NEXT: [[TMP2:%.*]] = phi <2 x i32> [ poison, %[[IF_END3]] ], [ [[TMP24:%.*]], %[[O]] ]
+; CHECK-NEXT: [[TMP3:%.*]] = phi <4 x i32> [ poison, %[[IF_END3]] ], [ zeroinitializer, %[[O]] ]
+; CHECK-NEXT: [[TMP4:%.*]] = phi <2 x i32> [ poison, %[[IF_END3]] ], [ [[TMP29:%.*]], %[[O]] ]
; CHECK-NEXT: [[TMP5:%.*]] = xor <2 x i32> [[TMP4]], zeroinitializer
-; CHECK-NEXT: [[TMP6:%.*]] = shufflevector <2 x i32> [[TMP22]], <2 x i32> poison, <8 x i32> <i32 poison, i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
-; CHECK-NEXT: [[TMP7:%.*]] = shufflevector <2 x i32> [[TMP22]], <2 x i32> poison, <8 x i32> <i32 0, i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
-; CHECK-NEXT: [[TMP8:%.*]] = shufflevector <8 x i32> <i32 0, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>, <8 x i32> [[TMP7]], <8 x i32> <i32 0, i32 9, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
-; CHECK-NEXT: [[TMP9:%.*]] = shufflevector <2 x i32> [[TMP2]], <2 x i32> poison, <8 x i32> <i32 0, i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
-; CHECK-NEXT: [[TMP10:%.*]] = shufflevector <8 x i32> [[TMP8]], <8 x i32> [[TMP9]], <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 6, i32 7>
-; CHECK-NEXT: [[TMP11:%.*]] = shufflevector <2 x i32> [[TMP3]], <2 x i32> poison, <8 x i32> <i32 0, i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
-; CHECK-NEXT: [[TMP27:%.*]] = shufflevector <8 x i32> [[TMP10]], <8 x i32> [[TMP11]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 6, i32 7>
-; CHECK-NEXT: [[TMP30:%.*]] = shufflevector <2 x i32> [[TMP5]], <2 x i32> poison, <8 x i32> <i32 0, i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
+; CHECK-NEXT: [[TMP6:%.*]] = insertelement <8 x i32> <i32 0, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>, i32 [[TMP22:%.*]], i32 1
+; CHECK-NEXT: [[TMP7:%.*]] = shufflevector <4 x i32> [[TMP3]], <4 x i32> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison>
+; CHECK-NEXT: [[TMP27:%.*]] = shufflevector <8 x i32> [[TMP6]], <8 x i32> [[TMP7]], <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 10, i32 11, i32 poison, i32 poison>
+; CHECK-NEXT: [[TMP30:%.*]] = shufflevector <2 x i32> [[TMP5]], <2 x i32> poison, <8 x i32> <i32 1, i32 0, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP31:%.*]] = shufflevector <8 x i32> [[TMP27]], <8 x i32> [[TMP30]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 8, i32 9>
; CHECK-NEXT: br i1 false, label %[[IF_END24:.*]], label %[[IF_THEN11:.*]]
; CHECK: [[IF_THEN11]]:
-; CHECK-NEXT: [[TMP12:%.*]] = shufflevector <2 x i32> [[TMP4]], <2 x i32> poison, <8 x i32> <i32 poison, i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
-; CHECK-NEXT: [[TMP13:%.*]] = shufflevector <2 x i32> [[TMP4]], <2 x i32> poison, <8 x i32> <i32 0, i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
-; CHECK-NEXT: [[TMP14:%.*]] = shufflevector <8 x i32> [[TMP13]], <8 x i32> <i32 0, i32 poison, i32 0, i32 0, i32 0, i32 0, i32 0, i32 poison>, <8 x i32> <i32 8, i32 1, i32 10, i32 11, i32 12, i32 13, i32 14, i32 poison>
-; CHECK-NEXT: [[TMP15:%.*]] = insertelement <8 x i32> poison, i32 [[J_4]], i32 0
-; CHECK-NEXT: [[TMP16:%.*]] = shufflevector <8 x i32> [[TMP15]], <8 x i32> poison, <8 x i32> <i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 0>
-; CHECK-NEXT: [[TMP29:%.*]] = shufflevector <8 x i32> [[TMP14]], <8 x i32> [[TMP16]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 15>
+; CHECK-NEXT: [[TMP11:%.*]] = shufflevector <2 x i32> [[TMP2]], <2 x i32> poison, <8 x i32> <i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 0, i32 poison>
+; CHECK-NEXT: [[TMP12:%.*]] = shufflevector <8 x i32> <i32 0, i32 poison, i32 0, i32 0, i32 0, i32 0, i32 0, i32 poison>, <8 x i32> [[TMP11]], <8 x i32> <i32 0, i32 8, i32 2, i32 3, i32 4, i32 5, i32 6, i32 14>
; CHECK-NEXT: br label %[[IF_END24]]
; CHECK: [[IF_THEN18:.*]]:
; CHECK-NEXT: br label %[[T]]
; CHECK: [[T]]:
-; CHECK-NEXT: [[TMP34:%.*]] = phi <8 x i32> [ [[TMP33:%.*]], %[[O]] ], [ poison, %[[IF_THEN18]] ]
+; CHECK-NEXT: [[TMP13:%.*]] = phi <8 x i32> [ [[TMP33:%.*]], %[[O]] ], [ poison, %[[IF_THEN18]] ]
; CHECK-NEXT: [[TMP17]] = extractelement <4 x i32> [[TMP23:%.*]], i32 0
; CHECK-NEXT: br i1 false, label %[[IF_END24]], label %[[K]]
; CHECK: [[IF_END24]]:
-; CHECK-NEXT: [[TMP18:%.*]] = phi <8 x i32> [ [[TMP29]], %[[IF_THEN11]] ], [ [[TMP31]], %[[IF_END6]] ], [ [[TMP34]], %[[T]] ]
-; CHECK-NEXT: [[TMP19:%.*]] = shufflevector <8 x i32> [[TMP18]], <8 x i32> poison, <2 x i32> <i32 7, i32 1>
+; CHECK-NEXT: [[TMP18:%.*]] = phi <8 x i32> [ [[TMP12]], %[[IF_THEN11]] ], [ [[TMP31]], %[[IF_END6]] ], [ [[TMP13]], %[[T]] ]
; CHECK-NEXT: [[TMP20:%.*]] = shufflevector <8 x i32> [[TMP18]], <8 x i32> poison, <4 x i32> <i32 0, i32 5, i32 6, i32 7>
-; CHECK-NEXT: [[TMP21:%.*]] = shufflevector <8 x i32> [[TMP18]], <8 x i32> poison, <4 x i32> <i32 2, i32 3, i32 4, i32 6>
+; CHECK-NEXT: [[TMP19:%.*]] = shufflevector <8 x i32> [[TMP18]], <8 x i32> poison, <2 x i32> <i32 6, i32 1>
+; CHECK-NEXT: [[TMP34:%.*]] = shufflevector <8 x i32> [[TMP18]], <8 x i32> poison, <4 x i32> <i32 2, i32 3, i32 4, i32 7>
; CHECK-NEXT: br label %[[O]]
; CHECK: [[O]]:
-; CHECK-NEXT: [[TMP22]] = phi <2 x i32> [ zeroinitializer, %[[K]] ], [ [[TMP19]], %[[IF_END24]] ]
; CHECK-NEXT: [[TMP23]] = phi <4 x i32> [ [[TMP1]], %[[K]] ], [ [[TMP20]], %[[IF_END24]] ]
-; CHECK-NEXT: [[TMP24:%.*]] = phi <4 x i32> [ zeroinitializer, %[[K]] ], [ [[TMP21]], %[[IF_END24]] ]
+; CHECK-NEXT: [[TMP24]] = phi <2 x i32> [ zeroinitializer, %[[K]] ], [ [[TMP19]], %[[IF_END24]] ]
+; CHECK-NEXT: [[TMP21:%.*]] = phi <4 x i32> [ zeroinitializer, %[[K]] ], [ [[TMP34]], %[[IF_END24]] ]
+; CHECK-NEXT: [[TMP22]] = extractelement <2 x i32> [[TMP24]], i32 1
; CHECK-NEXT: [[TMP25:%.*]] = shufflevector <4 x i32> [[TMP23]], <4 x i32> poison, <8 x i32> <i32 0, i32 poison, i32 0, i32 0, i32 poison, i32 poison, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP26:%.*]] = shufflevector <8 x i32> [[TMP25]], <8 x i32> <i32 poison, i32 0, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>, <8 x i32> <i32 0, i32 9, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP32:%.*]] = shufflevector <4 x i32> [[TMP23]], <4 x i32> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP33]] = shufflevector <8 x i32> [[TMP26]], <8 x i32> [[TMP32]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
-; CHECK-NEXT: [[TMP28]] = extractelement <4 x i32> [[TMP24]], i32 3
+; CHECK-NEXT: [[TMP35:%.*]] = shufflevector <2 x i32> [[TMP24]], <2 x i32> poison, <2 x i32> <i32 1, i32 poison>
+; CHECK-NEXT: [[TMP28:%.*]] = shufflevector <4 x i32> [[TMP21]], <4 x i32> poison, <2 x i32> <i32 poison, i32 3>
+; CHECK-NEXT: [[TMP29]] = shufflevector <2 x i32> [[TMP35]], <2 x i32> [[TMP28]], <2 x i32> <i32 0, i32 3>
; CHECK-NEXT: br i1 false, label %[[T]], label %[[IF_END6]]
;
entry:
More information about the llvm-commits
mailing list