[X86][AVX] lowerShuffleAsLanePermuteAndPermute - fully populate the lane shuffle mask (PR40730)

As detailed on PR40730, we are not correctly filling in the lane shuffle mask (D53148/rL344446) - we fill in for the correct src lane but don't add it to the correct mask element, so any reference to the correct element is likely to see an UNDEF mask index.

This allows constant folding to propagate UNDEFs prior to the lane mask being (correctly) lowered to vperm2f128.

This patch fixes the issue by fully populating the lane shuffle mask - this is more than is necessary (if we only filled in the required mask elements we might be able to match other shuffle instructions - broadcasts etc.), but its the most cautious approach as this needs to be cherrypicked into the 8.0.0 release branch.

Differential Revision: https://reviews.llvm.org/D58237

llvm-svn: 354117

2 files changed, 12 insertions, 3 deletions

diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index 0ecead8b583..2fa50635a6a 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -14081,7 +14081,6 @@ static SDValue lowerShuffleAsLanePermuteAndPermute(
   int NumEltsPerLane = NumElts / NumLanes;
 
   SmallVector<int, 4> SrcLaneMask(NumLanes, SM_SentinelUndef);
-  SmallVector<int, 16> LaneMask(NumElts, SM_SentinelUndef);
   SmallVector<int, 16> PermMask(NumElts, SM_SentinelUndef);
 
   for (int i = 0; i != NumElts; ++i) {
@@ -14096,10 +14095,20 @@ static SDValue lowerShuffleAsLanePermuteAndPermute(
       return SDValue();
     SrcLaneMask[DstLane] = SrcLane;
 
-    LaneMask[i] = (SrcLane * NumEltsPerLane) + (i % NumEltsPerLane);
     PermMask[i] = (DstLane * NumEltsPerLane) + (M % NumEltsPerLane);
   }
 
+  // Make sure we set all elements of the lane mask, to avoid undef propagation.
+  SmallVector<int, 16> LaneMask(NumElts, SM_SentinelUndef);
+  for (int DstLane = 0; DstLane != NumLanes; ++DstLane) {
+    int SrcLane = SrcLaneMask[DstLane];
+    if (0 <= SrcLane)
+      for (int j = 0; j != NumEltsPerLane; ++j) {
+        LaneMask[(DstLane * NumEltsPerLane) + j] =
+            (SrcLane * NumEltsPerLane) + j;
+      }
+  }
+
   // If we're only shuffling a single lowest lane and the rest are identity
   // then don't bother.
   // TODO - isShuffleMaskInputInPlace could be extended to something like this.
diff --git a/llvm/test/CodeGen/X86/pr40730.ll b/llvm/test/CodeGen/X86/pr40730.ll
index 679812c16f8..12b372dea33 100644
--- a/llvm/test/CodeGen/X86/pr40730.ll
+++ b/llvm/test/CodeGen/X86/pr40730.ll
@@ -19,7 +19,7 @@ define <8 x i32> @shuffle_v8i32_0dcd3f14(<8 x i32> %a, <8 x i32> %b) {
 ; CHECK:      .LCPI1_0:
 ; CHECK-NEXT: .quad   60129542157
 ; CHECK-NEXT: .quad   60129542157
-; CHECK-NEXT: .zero   8
+; CHECK-NEXT: .quad   68719476736
 ; CHECK-NEXT: .quad   60129542157
 
 define <8 x i32> @shuffle_v8i32_0dcd3f14_constant(<8 x i32> %a0)  {