[X86] combineConcatVectorOps - only concat AVX1 v4i64 shift-by-32 to a shuffle if the concat is free

[RKSimon]

No description provided.

[llvmbot]

@llvm/pr-subscribers-backend-x86

Author: Simon Pilgrim (RKSimon)

Changes

---

Full diff: https://github.com/llvm/llvm-project/pull/145043.diff

3 Files Affected:

• (modified) llvm/lib/Target/X86/X86ISelLowering.cpp (+11-9)
• (modified) llvm/test/CodeGen/X86/vector-shift-lshr-256.ll (+6-12)
• (modified) llvm/test/CodeGen/X86/vector-shift-shl-256.ll (+6-12)

diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index defb7730b4c7d..ebc616b31434a 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -58839,16 +58839,18 @@ static SDValue combineConcatVectorOps(const SDLoc &DL, MVT VT,
           llvm::all_of(Ops, [](SDValue Op) {
             return Op.getConstantOperandAPInt(1) == 32;
           })) {
-        SDValue Res = DAG.getBitcast(MVT::v8i32, ConcatSubOperand(VT, Ops, 0));
-        SDValue Zero = getZeroVector(MVT::v8i32, Subtarget, DAG, DL);
-        if (Opcode == X86ISD::VSHLI) {
-          Res = DAG.getVectorShuffle(MVT::v8i32, DL, Res, Zero,
-                                     {8, 0, 8, 2, 8, 4, 8, 6});
-        } else {
-          Res = DAG.getVectorShuffle(MVT::v8i32, DL, Res, Zero,
-                                     {1, 8, 3, 8, 5, 8, 7, 8});
+        if (SDValue Res = CombineSubOperand(VT, Ops, 0)) {
+          SDValue Zero = getZeroVector(MVT::v8i32, Subtarget, DAG, DL);
+          Res = DAG.getBitcast(MVT::v8i32, Res);
+          if (Opcode == X86ISD::VSHLI) {
+            Res = DAG.getVectorShuffle(MVT::v8i32, DL, Res, Zero,
+                                       {8, 0, 8, 2, 8, 4, 8, 6});
+          } else {
+            Res = DAG.getVectorShuffle(MVT::v8i32, DL, Res, Zero,
+                                       {1, 8, 3, 8, 5, 8, 7, 8});
+          }
+          return DAG.getBitcast(VT, Res);
         }
-        return DAG.getBitcast(VT, Res);
       }
       [[fallthrough]];
     case X86ISD::VSRAI:
diff --git a/llvm/test/CodeGen/X86/vector-shift-lshr-256.ll b/llvm/test/CodeGen/X86/vector-shift-lshr-256.ll
index b45525b6e20f9..3a4bb223618dd 100644
--- a/llvm/test/CodeGen/X86/vector-shift-lshr-256.ll
+++ b/llvm/test/CodeGen/X86/vector-shift-lshr-256.ll
@@ -1974,11 +1974,9 @@ define <4 x i64> @shift32_v4i64(<4 x i64> %a) nounwind {
 define <4 x i64> @shift32_v4i64_concat(<2 x i64> %lo, <2 x i64> %hi) nounwind {
 ; AVX1-LABEL: shift32_v4i64_concat:
 ; AVX1:       # %bb.0:
-; AVX1-NEXT:    # kill: def $xmm0 killed $xmm0 def $ymm0
+; AVX1-NEXT:    vpsrlq $32, %xmm0, %xmm0
+; AVX1-NEXT:    vpsrlq $32, %xmm1, %xmm1
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX1-NEXT:    vxorps %xmm1, %xmm1, %xmm1
-; AVX1-NEXT:    vshufps {{.*#+}} ymm0 = ymm0[1,3],ymm1[1,3],ymm0[5,7],ymm1[5,7]
-; AVX1-NEXT:    vshufps {{.*#+}} ymm0 = ymm0[0,2,1,3,4,6,5,7]
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: shift32_v4i64_concat:
@@ -1990,11 +1988,9 @@ define <4 x i64> @shift32_v4i64_concat(<2 x i64> %lo, <2 x i64> %hi) nounwind {
 ;
 ; XOPAVX1-LABEL: shift32_v4i64_concat:
 ; XOPAVX1:       # %bb.0:
-; XOPAVX1-NEXT:    # kill: def $xmm0 killed $xmm0 def $ymm0
+; XOPAVX1-NEXT:    vpsrlq $32, %xmm0, %xmm0
+; XOPAVX1-NEXT:    vpsrlq $32, %xmm1, %xmm1
 ; XOPAVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; XOPAVX1-NEXT:    vxorps %xmm1, %xmm1, %xmm1
-; XOPAVX1-NEXT:    vshufps {{.*#+}} ymm0 = ymm0[1,3],ymm1[1,3],ymm0[5,7],ymm1[5,7]
-; XOPAVX1-NEXT:    vshufps {{.*#+}} ymm0 = ymm0[0,2,1,3,4,6,5,7]
 ; XOPAVX1-NEXT:    retq
 ;
 ; XOPAVX2-LABEL: shift32_v4i64_concat:
@@ -2020,11 +2016,9 @@ define <4 x i64> @shift32_v4i64_concat(<2 x i64> %lo, <2 x i64> %hi) nounwind {
 ;
 ; X86-AVX1-LABEL: shift32_v4i64_concat:
 ; X86-AVX1:       # %bb.0:
-; X86-AVX1-NEXT:    # kill: def $xmm0 killed $xmm0 def $ymm0
+; X86-AVX1-NEXT:    vpsrlq $32, %xmm0, %xmm0
+; X86-AVX1-NEXT:    vpsrlq $32, %xmm1, %xmm1
 ; X86-AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; X86-AVX1-NEXT:    vxorps %xmm1, %xmm1, %xmm1
-; X86-AVX1-NEXT:    vshufps {{.*#+}} ymm0 = ymm0[1,3],ymm1[1,3],ymm0[5,7],ymm1[5,7]
-; X86-AVX1-NEXT:    vshufps {{.*#+}} ymm0 = ymm0[0,2,1,3,4,6,5,7]
 ; X86-AVX1-NEXT:    retl
 ;
 ; X86-AVX2-LABEL: shift32_v4i64_concat:
diff --git a/llvm/test/CodeGen/X86/vector-shift-shl-256.ll b/llvm/test/CodeGen/X86/vector-shift-shl-256.ll
index 2248ee997d525..b56a8b5b2294c 100644
--- a/llvm/test/CodeGen/X86/vector-shift-shl-256.ll
+++ b/llvm/test/CodeGen/X86/vector-shift-shl-256.ll
@@ -1827,11 +1827,9 @@ define <4 x i64> @shift32_v4i64(<4 x i64> %a) nounwind {
 define <4 x i64> @shift32_v4i64_concat(<2 x i64> %lo, <2 x i64> %hi) nounwind {
 ; AVX1-LABEL: shift32_v4i64_concat:
 ; AVX1:       # %bb.0:
-; AVX1-NEXT:    # kill: def $xmm0 killed $xmm0 def $ymm0
+; AVX1-NEXT:    vpsllq $32, %xmm0, %xmm0
+; AVX1-NEXT:    vpsllq $32, %xmm1, %xmm1
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX1-NEXT:    vxorps %xmm1, %xmm1, %xmm1
-; AVX1-NEXT:    vshufps {{.*#+}} ymm0 = ymm1[0,2],ymm0[0,2],ymm1[4,6],ymm0[4,6]
-; AVX1-NEXT:    vshufps {{.*#+}} ymm0 = ymm0[0,2,1,3,4,6,5,7]
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: shift32_v4i64_concat:
@@ -1843,11 +1841,9 @@ define <4 x i64> @shift32_v4i64_concat(<2 x i64> %lo, <2 x i64> %hi) nounwind {
 ;
 ; XOPAVX1-LABEL: shift32_v4i64_concat:
 ; XOPAVX1:       # %bb.0:
-; XOPAVX1-NEXT:    # kill: def $xmm0 killed $xmm0 def $ymm0
+; XOPAVX1-NEXT:    vpsllq $32, %xmm0, %xmm0
+; XOPAVX1-NEXT:    vpsllq $32, %xmm1, %xmm1
 ; XOPAVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; XOPAVX1-NEXT:    vxorps %xmm1, %xmm1, %xmm1
-; XOPAVX1-NEXT:    vshufps {{.*#+}} ymm0 = ymm1[0,2],ymm0[0,2],ymm1[4,6],ymm0[4,6]
-; XOPAVX1-NEXT:    vshufps {{.*#+}} ymm0 = ymm0[0,2,1,3,4,6,5,7]
 ; XOPAVX1-NEXT:    retq
 ;
 ; XOPAVX2-LABEL: shift32_v4i64_concat:
@@ -1873,11 +1869,9 @@ define <4 x i64> @shift32_v4i64_concat(<2 x i64> %lo, <2 x i64> %hi) nounwind {
 ;
 ; X86-AVX1-LABEL: shift32_v4i64_concat:
 ; X86-AVX1:       # %bb.0:
-; X86-AVX1-NEXT:    # kill: def $xmm0 killed $xmm0 def $ymm0
+; X86-AVX1-NEXT:    vpsllq $32, %xmm0, %xmm0
+; X86-AVX1-NEXT:    vpsllq $32, %xmm1, %xmm1
 ; X86-AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; X86-AVX1-NEXT:    vxorps %xmm1, %xmm1, %xmm1
-; X86-AVX1-NEXT:    vshufps {{.*#+}} ymm0 = ymm1[0,2],ymm0[0,2],ymm1[4,6],ymm0[4,6]
-; X86-AVX1-NEXT:    vshufps {{.*#+}} ymm0 = ymm0[0,2,1,3,4,6,5,7]
 ; X86-AVX1-NEXT:    retl
 ;
 ; X86-AVX2-LABEL: shift32_v4i64_concat: