[llvm] b9cfa01 - [SLP]Fix emission of the shrink shuffles.

[Alexey Bataev via llvm-commits]

Author: Alexey Bataev
Date: 2021-10-18T13:13:12-07:00
New Revision: b9cfa016daae725e4ed8173b431afb5e01cb80a6

URL: https://github.com/llvm/llvm-project/commit/b9cfa016daae725e4ed8173b431afb5e01cb80a6
DIFF: https://github.com/llvm/llvm-project/commit/b9cfa016daae725e4ed8173b431afb5e01cb80a6.diff

LOG: [SLP]Fix emission of the shrink shuffles.

Need to follow the order of the reused scalars from the
ReuseShuffleIndices mask rather than rely on the natural order.

Differential Revision: https://reviews.llvm.org/D111898

Added: 
    

Modified: 
    llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
    llvm/test/Transforms/SLPVectorizer/X86/shrink_after_reorder2.ll

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
index 9a69ddbad5d58..674f40571c1a8 100644
--- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -5669,17 +5669,18 @@ Value *BoUpSLP::vectorizeTree(ArrayRef<Value *> VL) {
 
             // block:
             // %phi = phi <2 x > { .., %entry} {%shuffle, %block}
-            // %2 = shuffle <2 x > %phi, %poison, <4 x > <0, 0, 1, 1>
+            // %2 = shuffle <2 x > %phi, poison, <4 x > <1, 1, 0, 0>
             // ... (use %2)
-            // %shuffle = shuffle <2 x> %2, poison, <2 x> {0, 2}
+            // %shuffle = shuffle <2 x> %2, poison, <2 x> {2, 0}
             // br %block
-            SmallVector<int> UniqueIdxs;
+            SmallVector<int> UniqueIdxs(VF, UndefMaskElem);
             SmallSet<int, 4> UsedIdxs;
             int Pos = 0;
             int Sz = VL.size();
             for (int Idx : E->ReuseShuffleIndices) {
-              if (Idx != Sz && UsedIdxs.insert(Idx).second)
-                UniqueIdxs.emplace_back(Pos);
+              if (Idx != Sz && Idx != UndefMaskElem &&
+                  UsedIdxs.insert(Idx).second)
+                UniqueIdxs[Idx] = Pos;
               ++Pos;
             }
             assert(VF >= UsedIdxs.size() && "Expected vectorization factor "

diff  --git a/llvm/test/Transforms/SLPVectorizer/X86/shrink_after_reorder2.ll b/llvm/test/Transforms/SLPVectorizer/X86/shrink_after_reorder2.ll
index 5c92ddef01c4e..a4a388e9d095c 100644
--- a/llvm/test/Transforms/SLPVectorizer/X86/shrink_after_reorder2.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/shrink_after_reorder2.ll
@@ -23,7 +23,7 @@ define void @foo(%class.e* %this, %struct.a* %p, i32 %add7) {
 ; CHECK:       sw.bb:
 ; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i32* [[G]] to <2 x i32>*
 ; CHECK-NEXT:    [[TMP3:%.*]] = load <2 x i32>, <2 x i32>* [[TMP2]], align 4
-; CHECK-NEXT:    [[SHRINK_SHUFFLE:%.*]] = shufflevector <4 x i32> [[SHUFFLE]], <4 x i32> poison, <2 x i32> <i32 0, i32 2>
+; CHECK-NEXT:    [[SHRINK_SHUFFLE:%.*]] = shufflevector <4 x i32> [[SHUFFLE]], <4 x i32> poison, <2 x i32> <i32 2, i32 0>
 ; CHECK-NEXT:    [[TMP4:%.*]] = xor <2 x i32> [[SHRINK_SHUFFLE]], <i32 -1, i32 -1>
 ; CHECK-NEXT:    [[TMP5:%.*]] = add <2 x i32> [[TMP3]], [[TMP4]]
 ; CHECK-NEXT:    br label [[SW_EPILOG]]