[PATCH] D94972: [SLP]Need to shrink the load vector after reordering.

[Alexey Bataev via Phabricator via llvm-commits]

ABataev created this revision.
ABataev added reviewers: RKSimon, spatel, dtemirbulatov, anton-afanasyev.
Herald added a subscriber: hiraditya.
ABataev requested review of this revision.
Herald added a project: LLVM.

After merging the shuffles, we cannot rely on the previous shuffle
anymore and need to shrink the final shuffle, if it is required.

Reported in D92668 <https://reviews.llvm.org/D92668>.

The previous patch in D93967 <https://reviews.llvm.org/D93967> was reverted because the original code had a bug. This patch fixes it.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D94972

Files:
  llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
  llvm/test/Transforms/SLPVectorizer/X86/shrink_after_reorder.ll


Index: llvm/test/Transforms/SLPVectorizer/X86/shrink_after_reorder.ll
===================================================================
--- llvm/test/Transforms/SLPVectorizer/X86/shrink_after_reorder.ll
+++ llvm/test/Transforms/SLPVectorizer/X86/shrink_after_reorder.ll
@@ -10,7 +10,8 @@
 ; CHECK-NEXT:    [[TMP1:%.*]] = load <2 x i32>, <2 x i32>* [[TMP0]], align 8
 ; CHECK-NEXT:    [[SHUFFLE:%.*]] = shufflevector <2 x i32> [[TMP1]], <2 x i32> poison, <4 x i32> <i32 1, i32 0, i32 1, i32 0>
 ; CHECK-NEXT:    [[TMP27:%.*]] = getelementptr inbounds i32, i32* [[PTR1:%.*]], i32 3
-; CHECK-NEXT:    [[TMP2:%.*]] = add nsw <2 x i32> [[TMP1]], <i32 -1, i32 -1>
+; CHECK-NEXT:    [[SHRINK_SHUFFLE:%.*]] = shufflevector <4 x i32> [[SHUFFLE]], <4 x i32> poison, <2 x i32> <i32 0, i32 1>
+; CHECK-NEXT:    [[TMP2:%.*]] = add nsw <2 x i32> [[SHRINK_SHUFFLE]], <i32 -1, i32 -1>
 ; CHECK-NEXT:    [[SHUFFLE1:%.*]] = shufflevector <2 x i32> [[TMP2]], <2 x i32> poison, <4 x i32> <i32 0, i32 1, i32 0, i32 1>
 ; CHECK-NEXT:    [[TMP34:%.*]] = getelementptr inbounds i32, i32* [[PTR1]], i32 4
 ; CHECK-NEXT:    [[TMP40:%.*]] = getelementptr inbounds i32, i32* [[PTR1]], i32 5
@@ -65,7 +66,7 @@
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
 ; CHECK:       for.body:
-; CHECK-NEXT:    [[TMP0:%.*]] = phi <2 x i16> [ undef, [[ENTRY:%.*]] ], [ [[TMP0]], [[IF_END:%.*]] ]
+; CHECK-NEXT:    [[TMP0:%.*]] = phi <2 x i16> [ undef, [[ENTRY:%.*]] ], [ [[SHRINK_SHUFFLE:%.*]], [[IF_END:%.*]] ]
 ; CHECK-NEXT:    [[SHUFFLE:%.*]] = shufflevector <2 x i16> [[TMP0]], <2 x i16> poison, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 1, i32 1, i32 1, i32 1>
 ; CHECK-NEXT:    br label [[IF_END]]
 ; CHECK:       if.end:
@@ -77,6 +78,7 @@
 ; CHECK-NEXT:    [[ARRAYIDX11_6:%.*]] = getelementptr inbounds i16, i16* undef, i32 6
 ; CHECK-NEXT:    [[ARRAYIDX11_7:%.*]] = getelementptr inbounds i16, i16* undef, i32 7
 ; CHECK-NEXT:    store <8 x i16> [[SHUFFLE]], <8 x i16>* undef, align 2
+; CHECK-NEXT:    [[SHRINK_SHUFFLE]] = shufflevector <8 x i16> [[SHUFFLE]], <8 x i16> poison, <2 x i32> <i32 0, i32 4>
 ; CHECK-NEXT:    br label [[FOR_BODY]]
 ;
 entry:
Index: llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
===================================================================
--- llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -4274,18 +4274,16 @@
       if (E->isSame(VL)) {
         Value *V = vectorizeTree(E);
         if (VL.size() == E->Scalars.size() && !E->ReuseShuffleIndices.empty()) {
-          // We need to get the vectorized value but without shuffle.
-          if (auto *SV = dyn_cast<ShuffleVectorInst>(V)) {
-            V = SV->getOperand(0);
-          } else {
-            // Reshuffle to get only unique values.
-            SmallVector<int, 4> UniqueIdxs;
-            SmallSet<int, 4> UsedIdxs;
-            for (int Idx : E->ReuseShuffleIndices)
-              if (UsedIdxs.insert(Idx).second)
-                UniqueIdxs.emplace_back(Idx);
-            V = Builder.CreateShuffleVector(V, UniqueIdxs);
+          // Reshuffle to get only unique values.
+          SmallVector<int, 4> UniqueIdxs;
+          SmallSet<int, 4> UsedIdxs;
+          int Pos = 0;
+          for (int Idx : E->ReuseShuffleIndices) {
+            if (UsedIdxs.insert(Idx).second)
+              UniqueIdxs.emplace_back(Pos);
+            ++Pos;
           }
+          V = Builder.CreateShuffleVector(V, UniqueIdxs, "shrink.shuffle");
         }
         return V;
       }


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D94972.317565.patch
Type: text/x-patch
Size: 3526 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20210119/2aac799f/attachment.bin>