[llvm] 14ae02f - [X86][AVX] Only share broadcasts of different widths from the same SDValue of the same SDNode (PR48215)

[Simon Pilgrim via llvm-commits]

Author: Simon Pilgrim
Date: 2020-11-19T12:15:18Z
New Revision: 14ae02fb3397961bb5f99a0df60622375fc1976d

URL: https://github.com/llvm/llvm-project/commit/14ae02fb3397961bb5f99a0df60622375fc1976d
DIFF: https://github.com/llvm/llvm-project/commit/14ae02fb3397961bb5f99a0df60622375fc1976d.diff

LOG: [X86][AVX] Only share broadcasts of different widths from the same SDValue of the same SDNode (PR48215)

D57663 allowed us to reuse broadcasts of the same scalar value by extracting low subvectors from the widest type.

Unfortunately we weren't ensuring the broadcasts were from the same SDValue, just the same SDNode - which failed on multiple-value nodes like ISD::SDIVREM

FYI: I intend to request this be merged into the 11.x release branch.

Differential Revision: https://reviews.llvm.org/D91709

Added: 
    

Modified: 
    llvm/lib/Target/X86/X86ISelLowering.cpp
    llvm/test/CodeGen/X86/pr48215.ll

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index 41b58af023b3..ae4cc6424ae6 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -36715,8 +36715,10 @@ static SDValue combineTargetShuffle(SDValue N, SelectionDAG &DAG,
       return DAG.getNode(X86ISD::VBROADCAST, DL, VT, Src.getOperand(0));
 
     // Share broadcast with the longest vector and extract low subvector (free).
+    // Ensure the same SDValue from the SDNode use is being used.
     for (SDNode *User : Src->uses())
       if (User != N.getNode() && User->getOpcode() == X86ISD::VBROADCAST &&
+          Src == User->getOperand(0) &&
           User->getValueSizeInBits(0).getFixedSize() >
               VT.getFixedSizeInBits()) {
         return extractSubVector(SDValue(User, 0), 0, DAG, DL,

diff  --git a/llvm/test/CodeGen/X86/pr48215.ll b/llvm/test/CodeGen/X86/pr48215.ll
index c825955a2970..125bde728c3f 100644
--- a/llvm/test/CodeGen/X86/pr48215.ll
+++ b/llvm/test/CodeGen/X86/pr48215.ll
@@ -33,12 +33,14 @@ define i32 @PR48215(i32 %a0, i32 %a1)  {
 ; AVX2-NEXT:    idivl %esi
 ; AVX2-NEXT:    vmovd %eax, %xmm0
 ; AVX2-NEXT:    vpbroadcastd %xmm0, %ymm0
-; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [0,1,2,3,4,5,6,7]
+; AVX2-NEXT:    vmovd %edx, %xmm1
+; AVX2-NEXT:    vpbroadcastd %xmm1, %xmm1
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [0,1,2,3,4,5,6,7]
+; AVX2-NEXT:    vpcmpgtd %ymm0, %ymm2, %ymm0
 ; AVX2-NEXT:    vmovdqa {{.*#+}} xmm2 = [4,5,6,7]
-; AVX2-NEXT:    vpcmpgtd %ymm0, %ymm1, %ymm1
-; AVX2-NEXT:    vmovmskps %ymm1, %ecx
-; AVX2-NEXT:    vpcmpgtd %xmm0, %xmm2, %xmm0
-; AVX2-NEXT:    vmovmskps %xmm0, %eax
+; AVX2-NEXT:    vpcmpgtd %xmm1, %xmm2, %xmm1
+; AVX2-NEXT:    vmovmskps %ymm0, %ecx
+; AVX2-NEXT:    vmovmskps %xmm1, %eax
 ; AVX2-NEXT:    addl %ecx, %eax
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
@@ -49,8 +51,9 @@ define i32 @PR48215(i32 %a0, i32 %a1)  {
 ; AVX512-NEXT:    cltd
 ; AVX512-NEXT:    idivl %esi
 ; AVX512-NEXT:    vpbroadcastd %eax, %ymm0
+; AVX512-NEXT:    vpbroadcastd %edx, %xmm1
 ; AVX512-NEXT:    vpcmpltd {{.*}}(%rip), %ymm0, %k0
-; AVX512-NEXT:    vpcmpltd {{.*}}(%rip), %xmm0, %k1
+; AVX512-NEXT:    vpcmpltd {{.*}}(%rip), %xmm1, %k1
 ; AVX512-NEXT:    kmovw %k0, %eax
 ; AVX512-NEXT:    movzbl %al, %ecx
 ; AVX512-NEXT:    kmovw %k1, %eax