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

[RKSimon]

Summary

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.

[wristow]

LGTM

llvm/lib/Target/X86/X86ISelLowering.cpp

if (SrcVT.getSizeInBits() > 128)
       return DAG.getNode(X86ISD::VBROADCAST, DL, VT,
                          extract128BitVector(Src, 0, DAG, DL));
 
     // broadcast(scalar_to_vector(x)) -> broadcast(x).
     if (Src.getOpcode() == ISD::SCALAR_TO_VECTOR)
       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,
                                 VT.getSizeInBits());
       }
 
     // vbroadcast(scalarload X) -> vbroadcast_load X
     // For float loads, extract other uses of the scalar from the broadcast.

llvm/test/CodeGen/X86/pr48215.ll

 ;
 ; AVX2-LABEL: PR48215:
 ; AVX2:       ## %bb.0:
 ; AVX2-NEXT:    movl %edi, %eax
 ; AVX2-NEXT:    cltd
 ; 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
 ;
 ; AVX512-LABEL: PR48215:
 ; AVX512:       ## %bb.0:
 ; AVX512-NEXT:    movl %edi, %eax
 ; 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
 ; AVX512-NEXT:    andl $15, %eax
 ; AVX512-NEXT:    addl %ecx, %eax
 ; AVX512-NEXT:    vzeroupper
 ; AVX512-NEXT:    retq
   %d = sdiv i32 %a0, %a1