[PATCH] D81212: [X86] Teach combineVectorShiftImm to constant fold undef elements to 0 not undef.

[Craig Topper via Phabricator via llvm-commits]

This revision was automatically updated to reflect the committed changes.
Closed by commit rG7c9a89fed8f5: [X86] Teach combineVectorShiftImm to constant fold undef elements to 0 not… (authored by craig.topper).

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D81212/new/

https://reviews.llvm.org/D81212

Files:
  llvm/lib/Target/X86/X86ISelLowering.cpp
  llvm/test/CodeGen/X86/vec_shift5.ll


Index: llvm/test/CodeGen/X86/vec_shift5.ll
===================================================================
--- llvm/test/CodeGen/X86/vec_shift5.ll
+++ llvm/test/CodeGen/X86/vec_shift5.ll
@@ -149,7 +149,7 @@
 define <2 x i64> @test11() {
 ; X32-LABEL: test11:
 ; X32:       # %bb.0:
-; X32-NEXT:    movaps {{.*#+}} xmm0 = <u,u,3,0>
+; X32-NEXT:    movaps {{.*#+}} xmm0 = [0,0,3,0]
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test11:
@@ -219,7 +219,7 @@
 define <2 x i64> @test16() {
 ; X32-LABEL: test16:
 ; X32:       # %bb.0:
-; X32-NEXT:    movaps {{.*#+}} xmm0 = <u,u,248,0>
+; X32-NEXT:    movaps {{.*#+}} xmm0 = [0,0,248,0]
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: test16:
Index: llvm/lib/Target/X86/X86ISelLowering.cpp
===================================================================
--- llvm/lib/Target/X86/X86ISelLowering.cpp
+++ llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -41439,14 +41439,22 @@
       getTargetConstantBitsFromNode(N0, NumBitsPerElt, UndefElts, EltBits)) {
     assert(EltBits.size() == VT.getVectorNumElements() &&
            "Unexpected shift value type");
-    for (APInt &Elt : EltBits) {
-      if (X86ISD::VSHLI == Opcode)
+    // Undef elements need to fold to 0. It's possible SimplifyDemandedBits
+    // created an undef input due to no input bits being demanded, but user
+    // still expects 0 in other bits.
+    for (unsigned i = 0, e = EltBits.size(); i != e; ++i) {
+      APInt &Elt = EltBits[i];
+      if (UndefElts[i])
+        Elt = 0;
+      else if (X86ISD::VSHLI == Opcode)
         Elt <<= ShiftVal;
       else if (X86ISD::VSRAI == Opcode)
         Elt.ashrInPlace(ShiftVal);
       else
         Elt.lshrInPlace(ShiftVal);
     }
+    // Reset undef elements since they were zeroed above.
+    UndefElts = 0;
     return getConstVector(EltBits, UndefElts, VT.getSimpleVT(), DAG, SDLoc(N));
   }
 


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D81212.268901.patch
Type: text/x-patch
Size: 1850 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20200605/6ad475ca/attachment.bin>