[llvm] [X86] Merge insertsubvector(load(p0),load_subv(p0),hi) -> subvbroadcast(p0) if either load is oneuse (PR #128857)

[via llvm-commits]

llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-backend-x86

Author: Simon Pilgrim (RKSimon)

<details>
<summary>Changes</summary>

This fold is currently limited to cases where the load_subv(p0) has oneuse, but its beneficial if either load has oneuse and will be replaced.

Yes another yak shave for #<!-- -->122671

---
Full diff: https://github.com/llvm/llvm-project/pull/128857.diff


2 Files Affected:

- (modified) llvm/lib/Target/X86/X86ISelLowering.cpp (+3-2) 
- (modified) llvm/test/CodeGen/X86/vector-interleaved-store-i8-stride-7.ll (+4-8) 


``````````diff
diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index 84aaf86550842..2791021ee0f10 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -58562,8 +58562,9 @@ static SDValue combineINSERT_SUBVECTOR(SDNode *N, SelectionDAG &DAG,
 
   // If we're splatting the lower half subvector of a full vector load into the
   // upper half, attempt to create a subvector broadcast.
-  if (IdxVal == (OpVT.getVectorNumElements() / 2) && SubVec.hasOneUse() &&
-      Vec.getValueSizeInBits() == (2 * SubVec.getValueSizeInBits())) {
+  if (IdxVal == (OpVT.getVectorNumElements() / 2) &&
+      Vec.getValueSizeInBits() == (2 * SubVec.getValueSizeInBits()) &&
+      (Vec.hasOneUse() || SubVec.hasOneUse())) {
     auto *VecLd = dyn_cast<LoadSDNode>(Vec);
     auto *SubLd = dyn_cast<LoadSDNode>(SubVec);
     if (VecLd && SubLd &&
diff --git a/llvm/test/CodeGen/X86/vector-interleaved-store-i8-stride-7.ll b/llvm/test/CodeGen/X86/vector-interleaved-store-i8-stride-7.ll
index c1dba071b4353..b6cbddd667d8e 100644
--- a/llvm/test/CodeGen/X86/vector-interleaved-store-i8-stride-7.ll
+++ b/llvm/test/CodeGen/X86/vector-interleaved-store-i8-stride-7.ll
@@ -10210,11 +10210,9 @@ define void @store_i8_stride7_vf64(ptr %in.vecptr0, ptr %in.vecptr1, ptr %in.vec
 ; AVX512BW-NEXT:    vpshufb %ymm28, %ymm18, %ymm23
 ; AVX512BW-NEXT:    vporq %ymm2, %ymm23, %ymm2
 ; AVX512BW-NEXT:    vinserti64x4 $1, %ymm2, %zmm1, %zmm1
-; AVX512BW-NEXT:    vmovdqa64 (%rdx), %zmm2
-; AVX512BW-NEXT:    vinserti64x4 $1, %ymm14, %zmm2, %zmm2
+; AVX512BW-NEXT:    vbroadcasti64x4 {{.*#+}} zmm2 = mem[0,1,2,3,0,1,2,3]
 ; AVX512BW-NEXT:    vpshufb %zmm20, %zmm2, %zmm2
-; AVX512BW-NEXT:    vmovdqa64 (%rcx), %zmm20
-; AVX512BW-NEXT:    vinserti64x4 $1, %ymm15, %zmm20, %zmm20
+; AVX512BW-NEXT:    vbroadcasti64x4 {{.*#+}} zmm20 = mem[0,1,2,3,0,1,2,3]
 ; AVX512BW-NEXT:    vpshufb %zmm22, %zmm20, %zmm20
 ; AVX512BW-NEXT:    vporq %zmm2, %zmm20, %zmm2
 ; AVX512BW-NEXT:    vpermq {{.*#+}} zmm1 = zmm1[2,3,2,3,6,7,6,7]
@@ -10816,11 +10814,9 @@ define void @store_i8_stride7_vf64(ptr %in.vecptr0, ptr %in.vecptr1, ptr %in.vec
 ; AVX512DQ-BW-NEXT:    vpshufb %ymm28, %ymm18, %ymm23
 ; AVX512DQ-BW-NEXT:    vporq %ymm2, %ymm23, %ymm2
 ; AVX512DQ-BW-NEXT:    vinserti64x4 $1, %ymm2, %zmm1, %zmm1
-; AVX512DQ-BW-NEXT:    vmovdqa64 (%rdx), %zmm2
-; AVX512DQ-BW-NEXT:    vinserti64x4 $1, %ymm14, %zmm2, %zmm2
+; AVX512DQ-BW-NEXT:    vbroadcasti64x4 {{.*#+}} zmm2 = mem[0,1,2,3,0,1,2,3]
 ; AVX512DQ-BW-NEXT:    vpshufb %zmm20, %zmm2, %zmm2
-; AVX512DQ-BW-NEXT:    vmovdqa64 (%rcx), %zmm20
-; AVX512DQ-BW-NEXT:    vinserti64x4 $1, %ymm15, %zmm20, %zmm20
+; AVX512DQ-BW-NEXT:    vbroadcasti64x4 {{.*#+}} zmm20 = mem[0,1,2,3,0,1,2,3]
 ; AVX512DQ-BW-NEXT:    vpshufb %zmm22, %zmm20, %zmm20
 ; AVX512DQ-BW-NEXT:    vporq %zmm2, %zmm20, %zmm2
 ; AVX512DQ-BW-NEXT:    vpermq {{.*#+}} zmm1 = zmm1[2,3,2,3,6,7,6,7]

``````````

</details>


https://github.com/llvm/llvm-project/pull/128857