[PATCH] D58237: [X86][AVX] lowerShuffleAsLanePermuteAndPermute - fully populate the lane shuffle mask (PR40730)

[Simon Pilgrim via Phabricator via llvm-commits]

This revision was automatically updated to reflect the committed changes.
Closed by commit rL354117: [X86][AVX] lowerShuffleAsLanePermuteAndPermute - fully populate the lane… (authored by RKSimon, committed by ).

Changed prior to commit:
  https://reviews.llvm.org/D58237?vs=186847&id=186987#toc

Repository:
  rL LLVM

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D58237/new/

https://reviews.llvm.org/D58237

Files:
  llvm/trunk/lib/Target/X86/X86ISelLowering.cpp
  llvm/trunk/test/CodeGen/X86/pr40730.ll


Index: llvm/trunk/test/CodeGen/X86/pr40730.ll
===================================================================
--- llvm/trunk/test/CodeGen/X86/pr40730.ll
+++ llvm/trunk/test/CodeGen/X86/pr40730.ll
@@ -19,7 +19,7 @@
 ; 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)  {
Index: llvm/trunk/lib/Target/X86/X86ISelLowering.cpp
===================================================================
--- llvm/trunk/lib/Target/X86/X86ISelLowering.cpp
+++ llvm/trunk/lib/Target/X86/X86ISelLowering.cpp
@@ -14081,7 +14081,6 @@
   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 @@
       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.


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D58237.186987.patch
Type: text/x-patch
Size: 1848 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20190215/bde22661/attachment.bin>