[PATCH] D101397: [SLP]Try to vectorize tiny trees with shuffled gathers.

[Alexey Bataev via Phabricator via llvm-commits]

This revision was landed with ongoing or failed builds.
This revision was automatically updated to reflect the committed changes.
Closed by commit rG8af4723c5819: [SLP]Try to vectorize tiny trees with shuffled gathers. (authored by ABataev).

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D101397/new/

https://reviews.llvm.org/D101397

Files:
  llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
  llvm/test/Transforms/SLPVectorizer/X86/tiny-tree.ll


Index: llvm/test/Transforms/SLPVectorizer/X86/tiny-tree.ll
===================================================================
--- llvm/test/Transforms/SLPVectorizer/X86/tiny-tree.ll
+++ llvm/test/Transforms/SLPVectorizer/X86/tiny-tree.ll
@@ -272,21 +272,18 @@
 ; CHECK-NEXT:    [[TMP1:%.*]] = load i32, i32* [[V1:%.*]], align 4
 ; CHECK-NEXT:    [[TMP2:%.*]] = load i32, i32* [[V2:%.*]], align 4
 ; CHECK-NEXT:    [[PTR0:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 0
-; CHECK-NEXT:    store i32 [[TMP1]], i32* [[PTR0]], align 16
 ; CHECK-NEXT:    [[PTR1:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 1
-; CHECK-NEXT:    store i32 [[TMP2]], i32* [[PTR1]], align 4
 ; CHECK-NEXT:    [[PTR2:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 2
-; CHECK-NEXT:    store i32 [[TMP1]], i32* [[PTR2]], align 8
 ; CHECK-NEXT:    [[PTR3:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 3
-; CHECK-NEXT:    store i32 [[TMP2]], i32* [[PTR3]], align 4
 ; CHECK-NEXT:    [[PTR4:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 4
-; CHECK-NEXT:    store i32 [[TMP1]], i32* [[PTR4]], align 16
 ; CHECK-NEXT:    [[PTR5:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 5
-; CHECK-NEXT:    store i32 [[TMP2]], i32* [[PTR5]], align 4
 ; CHECK-NEXT:    [[PTR6:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 6
-; CHECK-NEXT:    store i32 [[TMP1]], i32* [[PTR6]], align 8
 ; CHECK-NEXT:    [[PTR7:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 7
-; CHECK-NEXT:    store i32 [[TMP2]], i32* [[PTR7]], align 4
+; CHECK-NEXT:    [[TMP3:%.*]] = insertelement <2 x i32> poison, i32 [[TMP1]], i32 0
+; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <2 x i32> [[TMP3]], i32 [[TMP2]], i32 1
+; CHECK-NEXT:    [[SHUFFLE:%.*]] = shufflevector <2 x i32> [[TMP4]], <2 x i32> poison, <8 x i32> <i32 0, i32 1, i32 0, i32 1, i32 0, i32 1, i32 0, i32 1>
+; CHECK-NEXT:    [[TMP5:%.*]] = bitcast i32* [[PTR0]] to <8 x i32>*
+; CHECK-NEXT:    store <8 x i32> [[SHUFFLE]], <8 x i32>* [[TMP5]], align 16
 ; CHECK-NEXT:    ret void
 ;
   %1 = load i32, i32* %v1, align 4
Index: llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
===================================================================
--- llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -4032,10 +4032,15 @@
   if (VectorizableTree.size() != 2)
     return false;
 
-  // Handle splat and all-constants stores.
+  // Handle splat and all-constants stores. Also try to vectorize tiny trees
+  // with the second gather nodes if they have less scalar operands rather than
+  // the initial tree element (may be profitable to shuffle the second gather).
   if (VectorizableTree[0]->State == TreeEntry::Vectorize &&
       (allConstant(VectorizableTree[1]->Scalars) ||
-       isSplat(VectorizableTree[1]->Scalars)))
+       isSplat(VectorizableTree[1]->Scalars) ||
+       (VectorizableTree[1]->State == TreeEntry::NeedToGather &&
+        VectorizableTree[1]->Scalars.size() <
+            VectorizableTree[0]->Scalars.size())))
     return true;
 
   // Gathering cost would be too much for tiny trees.


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D101397.341177.patch
Type: text/x-patch
Size: 3107 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20210428/84722fdc/attachment.bin>