[llvm] [DAG] isSplatValue - node is a splat if all demanded elts have the same whole constant value (PR #74443)
via llvm-commits
llvm-commits at lists.llvm.org
Tue Dec 5 01:53:29 PST 2023
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-arm
Author: Simon Pilgrim (RKSimon)
<details>
<summary>Changes</summary>
---
Patch is 326.97 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/74443.diff
13 Files Affected:
- (modified) llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp (+6)
- (modified) llvm/test/CodeGen/ARM/vector-store.ll (+7-10)
- (modified) llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-shuffles.ll (+5-5)
- (modified) llvm/test/CodeGen/X86/fold-pcmpeqd-2.ll (+8-2)
- (modified) llvm/test/CodeGen/X86/var-permute-256.ll (+90-76)
- (modified) llvm/test/CodeGen/X86/vector-interleaved-load-i8-stride-4.ll (+705-713)
- (modified) llvm/test/CodeGen/X86/vector-interleaved-load-i8-stride-6.ll (+1500-1529)
- (modified) llvm/test/CodeGen/X86/vector-shift-ashr-128.ll (+1-1)
- (modified) llvm/test/CodeGen/X86/vector-shift-ashr-256.ll (+1-1)
- (modified) llvm/test/CodeGen/X86/vector-shift-lshr-128.ll (+1-1)
- (modified) llvm/test/CodeGen/X86/vector-shift-lshr-256.ll (+1-1)
- (modified) llvm/test/CodeGen/X86/vector-shift-shl-128.ll (+1-1)
- (modified) llvm/test/CodeGen/X86/vector-shift-shl-256.ll (+1-1)
``````````diff
diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
index 51ae8b703e50f..5be1892a44f6d 100644
--- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
@@ -2881,6 +2881,12 @@ bool SelectionDAG::isSplatValue(SDValue V, const APInt &DemandedElts,
}
}
+ // Fallback - this is a splat if all demanded elts are the same constant.
+ if (computeKnownBits(V, DemandedElts, Depth).isConstant()) {
+ UndefElts = ~DemandedElts;
+ return true;
+ }
+
return false;
}
diff --git a/llvm/test/CodeGen/ARM/vector-store.ll b/llvm/test/CodeGen/ARM/vector-store.ll
index a8a1031637afc..9c8ea7a2c440c 100644
--- a/llvm/test/CodeGen/ARM/vector-store.ll
+++ b/llvm/test/CodeGen/ARM/vector-store.ll
@@ -403,17 +403,14 @@ define void @v3i8store(ptr %p) {
; CHECK-LABEL: v3i8store:
; CHECK: @ %bb.0:
; CHECK-NEXT: sub sp, #4
-; CHECK-NEXT: vmov.i32 d16, #0xff
-; CHECK-NEXT: mov r1, sp
-; CHECK-NEXT: vmov.i32 d17, #0x0
-; CHECK-NEXT: movs r2, #0
-; CHECK-NEXT: vand d16, d17, d16
-; CHECK-NEXT: vst1.32 {d16[0]}, [r1:32]
-; CHECK-NEXT: vld1.32 {d16[0]}, [r1:32]
+; CHECK-NEXT: movs r1, #0
+; CHECK-NEXT: mov r2, sp
+; CHECK-NEXT: str r1, [sp]
+; CHECK-NEXT: vld1.32 {d16[0]}, [r2:32]
+; CHECK-NEXT: strb r1, [r0, #2]
; CHECK-NEXT: vmovl.u16 q8, d16
-; CHECK-NEXT: strb r2, [r0, #2]
-; CHECK-NEXT: vmov.32 r1, d16[0]
-; CHECK-NEXT: strh r1, [r0]
+; CHECK-NEXT: vmov.32 r2, d16[0]
+; CHECK-NEXT: strh r2, [r0]
; CHECK-NEXT: add sp, #4
; CHECK-NEXT: bx lr
store <3 x i8> zeroinitializer, ptr %p, align 4
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-shuffles.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-shuffles.ll
index a56a81f5f793b..769bfe8cd5ba9 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-shuffles.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-int-shuffles.ll
@@ -244,14 +244,14 @@ define <8 x i64> @vrgather_shuffle_vx_v8i64(<8 x i64> %x) {
; RV32-NEXT: addi a0, a0, %lo(.LCPI13_0)
; RV32-NEXT: vsetivli zero, 8, e64, m4, ta, mu
; RV32-NEXT: vle16.v v16, (a0)
-; RV32-NEXT: vrgatherei16.vv v12, v8, v16
+; RV32-NEXT: vmv.v.i v20, 5
; RV32-NEXT: lui a0, %hi(.LCPI13_1)
; RV32-NEXT: addi a0, a0, %lo(.LCPI13_1)
-; RV32-NEXT: vle16.v v8, (a0)
-; RV32-NEXT: li a0, 140
+; RV32-NEXT: vle16.v v17, (a0)
+; RV32-NEXT: li a0, 115
; RV32-NEXT: vmv.s.x v0, a0
-; RV32-NEXT: vmv.v.i v16, 5
-; RV32-NEXT: vrgatherei16.vv v12, v16, v8, v0.t
+; RV32-NEXT: vrgatherei16.vv v12, v20, v16
+; RV32-NEXT: vrgatherei16.vv v12, v8, v17, v0.t
; RV32-NEXT: vmv.v.v v8, v12
; RV32-NEXT: ret
;
diff --git a/llvm/test/CodeGen/X86/fold-pcmpeqd-2.ll b/llvm/test/CodeGen/X86/fold-pcmpeqd-2.ll
index 88425ea87845d..5d563b141ed66 100644
--- a/llvm/test/CodeGen/X86/fold-pcmpeqd-2.ll
+++ b/llvm/test/CodeGen/X86/fold-pcmpeqd-2.ll
@@ -54,7 +54,10 @@ define void @program_1(ptr %dest, ptr %t0, <4 x float> %p0, <4 x float> %p1, <4
; X32-NEXT: xorps %xmm0, %xmm0
; X32-NEXT: movaps %xmm0, {{[-0-9]+}}(%e{{[sb]}}p) ## 16-byte Spill
; X32-NEXT: movaps {{[-0-9]+}}(%e{{[sb]}}p), %xmm0 ## 16-byte Reload
-; X32-NEXT: mulps %xmm0, %xmm0
+; X32-NEXT: mulss {{\.?LCPI[0-9]+_[0-9]+}}, %xmm0
+; X32-NEXT: movaps %xmm0, {{[-0-9]+}}(%e{{[sb]}}p) ## 16-byte Spill
+; X32-NEXT: movaps {{[-0-9]+}}(%e{{[sb]}}p), %xmm0 ## 16-byte Reload
+; X32-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,0,0,0]
; X32-NEXT: movaps %xmm0, {{[-0-9]+}}(%e{{[sb]}}p) ## 16-byte Spill
; X32-NEXT: movaps {{[-0-9]+}}(%e{{[sb]}}p), %xmm0 ## 16-byte Reload
; X32-NEXT: mulps {{\.?LCPI[0-9]+_[0-9]+}}, %xmm0
@@ -138,7 +141,10 @@ define void @program_1(ptr %dest, ptr %t0, <4 x float> %p0, <4 x float> %p1, <4
; X64-NEXT: xorps %xmm0, %xmm0
; X64-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) ## 16-byte Spill
; X64-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 ## 16-byte Reload
-; X64-NEXT: mulps %xmm0, %xmm0
+; X64-NEXT: mulss {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
+; X64-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) ## 16-byte Spill
+; X64-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 ## 16-byte Reload
+; X64-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,0,0,0]
; X64-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) ## 16-byte Spill
; X64-NEXT: movaps (%rsp), %xmm0 ## 16-byte Reload
; X64-NEXT: mulps {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
diff --git a/llvm/test/CodeGen/X86/var-permute-256.ll b/llvm/test/CodeGen/X86/var-permute-256.ll
index 6c07c4ca523f8..853d8a278960d 100644
--- a/llvm/test/CodeGen/X86/var-permute-256.ll
+++ b/llvm/test/CodeGen/X86/var-permute-256.ll
@@ -25,18 +25,20 @@ define <4 x i64> @var_shuffle_v4i64(<4 x i64> %v, <4 x i64> %indices) nounwind {
;
; AVX1-LABEL: var_shuffle_v4i64:
; AVX1: # %bb.0:
-; AVX1-NEXT: vperm2f128 {{.*#+}} ymm2 = ymm0[2,3,2,3]
-; AVX1-NEXT: vpaddq %xmm1, %xmm1, %xmm3
-; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm1
+; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
+; AVX1-NEXT: vpaddq %xmm2, %xmm2, %xmm2
+; AVX1-NEXT: vmovddup {{.*#+}} xmm3 = [2,2]
+; AVX1-NEXT: # xmm3 = mem[0,0]
+; AVX1-NEXT: vpcmpgtq %xmm3, %xmm2, %xmm4
; AVX1-NEXT: vpaddq %xmm1, %xmm1, %xmm1
-; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm3, %ymm4
-; AVX1-NEXT: vpermilpd %ymm4, %ymm2, %ymm2
+; AVX1-NEXT: vpcmpgtq %xmm3, %xmm1, %xmm3
+; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm3, %ymm3
+; AVX1-NEXT: vperm2f128 {{.*#+}} ymm4 = ymm0[2,3,2,3]
+; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm1, %ymm1
+; AVX1-NEXT: vpermilpd %ymm1, %ymm4, %ymm2
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
-; AVX1-NEXT: vpermilpd %ymm4, %ymm0, %ymm0
-; AVX1-NEXT: vpcmpgtq {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm3, %xmm3
-; AVX1-NEXT: vpcmpgtq {{\.?LCPI[0-9]+_[0-9]+}}+16(%rip), %xmm1, %xmm1
-; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm3, %ymm1
-; AVX1-NEXT: vblendvpd %ymm1, %ymm2, %ymm0, %ymm0
+; AVX1-NEXT: vpermilpd %ymm1, %ymm0, %ymm0
+; AVX1-NEXT: vblendvpd %ymm3, %ymm2, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: var_shuffle_v4i64:
@@ -88,15 +90,16 @@ define <8 x i32> @var_shuffle_v8i32(<8 x i32> %v, <8 x i32> %indices) nounwind {
;
; AVX1-LABEL: var_shuffle_v8i32:
; AVX1: # %bb.0:
-; AVX1-NEXT: vperm2f128 {{.*#+}} ymm2 = ymm0[2,3,2,3]
-; AVX1-NEXT: vpermilps %ymm1, %ymm2, %ymm2
+; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
+; AVX1-NEXT: vbroadcastss {{.*#+}} xmm3 = [3,3,3,3]
+; AVX1-NEXT: vpcmpgtd %xmm3, %xmm2, %xmm2
+; AVX1-NEXT: vpcmpgtd %xmm3, %xmm1, %xmm3
+; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm3, %ymm2
+; AVX1-NEXT: vperm2f128 {{.*#+}} ymm3 = ymm0[2,3,2,3]
+; AVX1-NEXT: vpermilps %ymm1, %ymm3, %ymm3
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
; AVX1-NEXT: vpermilps %ymm1, %ymm0, %ymm0
-; AVX1-NEXT: vpcmpgtd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1, %xmm3
-; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm1
-; AVX1-NEXT: vpcmpgtd {{\.?LCPI[0-9]+_[0-9]+}}+16(%rip), %xmm1, %xmm1
-; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm3, %ymm1
-; AVX1-NEXT: vblendvps %ymm1, %ymm2, %ymm0, %ymm0
+; AVX1-NEXT: vblendvps %ymm2, %ymm3, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; INT256-LABEL: var_shuffle_v8i32:
@@ -445,18 +448,20 @@ define <4 x double> @var_shuffle_v4f64(<4 x double> %v, <4 x i64> %indices) noun
;
; AVX1-LABEL: var_shuffle_v4f64:
; AVX1: # %bb.0:
-; AVX1-NEXT: vperm2f128 {{.*#+}} ymm2 = ymm0[2,3,2,3]
-; AVX1-NEXT: vpaddq %xmm1, %xmm1, %xmm3
-; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm1
+; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
+; AVX1-NEXT: vpaddq %xmm2, %xmm2, %xmm2
+; AVX1-NEXT: vmovddup {{.*#+}} xmm3 = [2,2]
+; AVX1-NEXT: # xmm3 = mem[0,0]
+; AVX1-NEXT: vpcmpgtq %xmm3, %xmm2, %xmm4
; AVX1-NEXT: vpaddq %xmm1, %xmm1, %xmm1
-; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm3, %ymm4
-; AVX1-NEXT: vpermilpd %ymm4, %ymm2, %ymm2
+; AVX1-NEXT: vpcmpgtq %xmm3, %xmm1, %xmm3
+; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm3, %ymm3
+; AVX1-NEXT: vperm2f128 {{.*#+}} ymm4 = ymm0[2,3,2,3]
+; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm1, %ymm1
+; AVX1-NEXT: vpermilpd %ymm1, %ymm4, %ymm2
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
-; AVX1-NEXT: vpermilpd %ymm4, %ymm0, %ymm0
-; AVX1-NEXT: vpcmpgtq {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm3, %xmm3
-; AVX1-NEXT: vpcmpgtq {{\.?LCPI[0-9]+_[0-9]+}}+16(%rip), %xmm1, %xmm1
-; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm3, %ymm1
-; AVX1-NEXT: vblendvpd %ymm1, %ymm2, %ymm0, %ymm0
+; AVX1-NEXT: vpermilpd %ymm1, %ymm0, %ymm0
+; AVX1-NEXT: vblendvpd %ymm3, %ymm2, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: var_shuffle_v4f64:
@@ -508,15 +513,16 @@ define <8 x float> @var_shuffle_v8f32(<8 x float> %v, <8 x i32> %indices) nounwi
;
; AVX1-LABEL: var_shuffle_v8f32:
; AVX1: # %bb.0:
-; AVX1-NEXT: vperm2f128 {{.*#+}} ymm2 = ymm0[2,3,2,3]
-; AVX1-NEXT: vpermilps %ymm1, %ymm2, %ymm2
+; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
+; AVX1-NEXT: vbroadcastss {{.*#+}} xmm3 = [3,3,3,3]
+; AVX1-NEXT: vpcmpgtd %xmm3, %xmm2, %xmm2
+; AVX1-NEXT: vpcmpgtd %xmm3, %xmm1, %xmm3
+; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm3, %ymm2
+; AVX1-NEXT: vperm2f128 {{.*#+}} ymm3 = ymm0[2,3,2,3]
+; AVX1-NEXT: vpermilps %ymm1, %ymm3, %ymm3
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
; AVX1-NEXT: vpermilps %ymm1, %ymm0, %ymm0
-; AVX1-NEXT: vpcmpgtd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1, %xmm3
-; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm1
-; AVX1-NEXT: vpcmpgtd {{\.?LCPI[0-9]+_[0-9]+}}+16(%rip), %xmm1, %xmm1
-; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm3, %ymm1
-; AVX1-NEXT: vblendvps %ymm1, %ymm2, %ymm0, %ymm0
+; AVX1-NEXT: vblendvps %ymm2, %ymm3, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; INT256-LABEL: var_shuffle_v8f32:
@@ -569,17 +575,19 @@ define <4 x i64> @var_shuffle_v4i64_from_v2i64(<2 x i64> %v, <4 x i64> %indices)
; AVX1-LABEL: var_shuffle_v4i64_from_v2i64:
; AVX1: # %bb.0:
; AVX1-NEXT: # kill: def $xmm0 killed $xmm0 def $ymm0
-; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
-; AVX1-NEXT: vpaddq %xmm1, %xmm1, %xmm2
-; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm1
+; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
+; AVX1-NEXT: vpaddq %xmm2, %xmm2, %xmm2
+; AVX1-NEXT: vmovddup {{.*#+}} xmm3 = [2,2]
+; AVX1-NEXT: # xmm3 = mem[0,0]
+; AVX1-NEXT: vpcmpgtq %xmm3, %xmm2, %xmm4
; AVX1-NEXT: vpaddq %xmm1, %xmm1, %xmm1
-; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm2, %ymm3
-; AVX1-NEXT: vpermilpd %ymm3, %ymm0, %ymm0
-; AVX1-NEXT: vpcmpgtq {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm2, %xmm2
-; AVX1-NEXT: vpcmpgtq {{\.?LCPI[0-9]+_[0-9]+}}+16(%rip), %xmm1, %xmm1
-; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm2, %ymm1
-; AVX1-NEXT: vpermilpd %ymm3, %ymm0, %ymm2
-; AVX1-NEXT: vblendvpd %ymm1, %ymm2, %ymm0, %ymm0
+; AVX1-NEXT: vpcmpgtq %xmm3, %xmm1, %xmm3
+; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm3, %ymm3
+; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
+; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm1, %ymm1
+; AVX1-NEXT: vpermilpd %ymm1, %ymm0, %ymm0
+; AVX1-NEXT: vpermilpd %ymm1, %ymm0, %ymm1
+; AVX1-NEXT: vblendvpd %ymm3, %ymm1, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: var_shuffle_v4i64_from_v2i64:
@@ -633,14 +641,15 @@ define <8 x i32> @var_shuffle_v8i32_from_v4i32(<4 x i32> %v, <8 x i32> %indices)
; AVX1-LABEL: var_shuffle_v8i32_from_v4i32:
; AVX1: # %bb.0: # %entry
; AVX1-NEXT: # kill: def $xmm0 killed $xmm0 def $ymm0
-; AVX1-NEXT: vpermilps %ymm1, %ymm0, %ymm2
+; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
+; AVX1-NEXT: vbroadcastss {{.*#+}} xmm3 = [3,3,3,3]
+; AVX1-NEXT: vpcmpgtd %xmm3, %xmm2, %xmm2
+; AVX1-NEXT: vpcmpgtd %xmm3, %xmm1, %xmm3
+; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm3, %ymm2
+; AVX1-NEXT: vpermilps %ymm1, %ymm0, %ymm3
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
; AVX1-NEXT: vpermilps %ymm1, %ymm0, %ymm0
-; AVX1-NEXT: vpcmpgtd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1, %xmm3
-; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm1
-; AVX1-NEXT: vpcmpgtd {{\.?LCPI[0-9]+_[0-9]+}}+16(%rip), %xmm1, %xmm1
-; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm3, %ymm1
-; AVX1-NEXT: vblendvps %ymm1, %ymm2, %ymm0, %ymm0
+; AVX1-NEXT: vblendvps %ymm2, %ymm3, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; INT256-LABEL: var_shuffle_v8i32_from_v4i32:
@@ -990,17 +999,19 @@ define <4 x double> @var_shuffle_v4f64_from_v2f64(<2 x double> %v, <4 x i64> %in
; AVX1-LABEL: var_shuffle_v4f64_from_v2f64:
; AVX1: # %bb.0:
; AVX1-NEXT: # kill: def $xmm0 killed $xmm0 def $ymm0
-; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
-; AVX1-NEXT: vpaddq %xmm1, %xmm1, %xmm2
-; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm1
+; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
+; AVX1-NEXT: vpaddq %xmm2, %xmm2, %xmm2
+; AVX1-NEXT: vmovddup {{.*#+}} xmm3 = [2,2]
+; AVX1-NEXT: # xmm3 = mem[0,0]
+; AVX1-NEXT: vpcmpgtq %xmm3, %xmm2, %xmm4
; AVX1-NEXT: vpaddq %xmm1, %xmm1, %xmm1
-; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm2, %ymm3
-; AVX1-NEXT: vpermilpd %ymm3, %ymm0, %ymm0
-; AVX1-NEXT: vpcmpgtq {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm2, %xmm2
-; AVX1-NEXT: vpcmpgtq {{\.?LCPI[0-9]+_[0-9]+}}+16(%rip), %xmm1, %xmm1
-; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm2, %ymm1
-; AVX1-NEXT: vpermilpd %ymm3, %ymm0, %ymm2
-; AVX1-NEXT: vblendvpd %ymm1, %ymm2, %ymm0, %ymm0
+; AVX1-NEXT: vpcmpgtq %xmm3, %xmm1, %xmm3
+; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm3, %ymm3
+; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
+; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm1, %ymm1
+; AVX1-NEXT: vpermilpd %ymm1, %ymm0, %ymm0
+; AVX1-NEXT: vpermilpd %ymm1, %ymm0, %ymm1
+; AVX1-NEXT: vblendvpd %ymm3, %ymm1, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: var_shuffle_v4f64_from_v2f64:
@@ -1054,14 +1065,15 @@ define <8 x float> @var_shuffle_v8f32_from_v4f32(<4 x float> %v, <8 x i32> %indi
; AVX1-LABEL: var_shuffle_v8f32_from_v4f32:
; AVX1: # %bb.0: # %entry
; AVX1-NEXT: # kill: def $xmm0 killed $xmm0 def $ymm0
-; AVX1-NEXT: vpermilps %ymm1, %ymm0, %ymm2
+; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm2
+; AVX1-NEXT: vbroadcastss {{.*#+}} xmm3 = [3,3,3,3]
+; AVX1-NEXT: vpcmpgtd %xmm3, %xmm2, %xmm2
+; AVX1-NEXT: vpcmpgtd %xmm3, %xmm1, %xmm3
+; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm3, %ymm2
+; AVX1-NEXT: vpermilps %ymm1, %ymm0, %ymm3
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
; AVX1-NEXT: vpermilps %ymm1, %ymm0, %ymm0
-; AVX1-NEXT: vpcmpgtd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1, %xmm3
-; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm1
-; AVX1-NEXT: vpcmpgtd {{\.?LCPI[0-9]+_[0-9]+}}+16(%rip), %xmm1, %xmm1
-; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm3, %ymm1
-; AVX1-NEXT: vblendvps %ymm1, %ymm2, %ymm0, %ymm0
+; AVX1-NEXT: vblendvps %ymm2, %ymm3, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; INT256-LABEL: var_shuffle_v8f32_from_v4f32:
@@ -1271,20 +1283,22 @@ define <4 x i64> @var_shuffle_v4i64_with_v16i8_indices(<4 x i64> %v, <16 x i8> %
;
; AVX1-LABEL: var_shuffle_v4i64_with_v16i8_indices:
; AVX1: # %bb.0:
-; AVX1-NEXT: vpsrld $16, %xmm1, %xmm2
-; AVX1-NEXT: vpmovzxbq {{.*#+}} xmm2 = xmm2[0],zero,zero,zero,zero,zero,zero,zero,xmm2[1],zero,zero,zero,zero,zero,zero,zero
+; AVX1-NEXT: vpmovzxbq {{.*#+}} xmm2 = xmm1[0],zero,zero,zero,zero,zero,zero,zero,xmm1[1],zero,zero,zero,zero,zero,zero,zero
+; AVX1-NEXT: vpsrld $16, %xmm1, %xmm1
; AVX1-NEXT: vpmovzxbq {{.*#+}} xmm1 = xmm1[0],zero,zero,zero,zero,zero,zero,zero,xmm1[1],zero,zero,zero,zero,zero,zero,zero
-; AVX1-NEXT: vperm2f128 {{.*#+}} ymm3 = ymm0[2,3,2,3]
; AVX1-NEXT: vpaddq %xmm1, %xmm1, %xmm1
+; AVX1-NEXT: vmovddup {{.*#+}} xmm3 = [2,2]
+; AVX1-NEXT: # xmm3 = mem[0,0]
+; AVX1-NEXT: vpcmpgtq %xmm3, %xmm1, %xmm4
; AVX1-NEXT: vpaddq %xmm2, %xmm2, %xmm2
-; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm1, %ymm4
-; AVX1-NEXT: vpermilpd %ymm4, %ymm3, %ymm3
+; AVX1-NEXT: vpcmpgtq %xmm3, %xmm2, %xmm3
+; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm3, %ymm3
+; AVX1-NEXT: vperm2f128 {{.*#+}} ymm4 = ymm0[2,3,2,3]
+; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm2, %ymm1
+; AVX1-NEXT: vpermilpd %ymm1, %ymm4, %ymm2
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
-; AVX1-NEXT: vpermilpd %ymm4, %ymm0, %ymm0
-; AVX1-NEXT: vpcmpgtq {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1, %xmm1
-; AVX1-NEXT: vpcmpgtq {{\.?LCPI[0-9]+_[0-9]+}}+16(%rip), %xmm2, %xmm2
-; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm1, %ymm1
-; AVX1-NEXT: vblendvpd %ymm1, %ymm3, %ymm0, %ymm0
+; AVX1-NEXT: vpermilpd %ymm1, %ymm0, %ymm0
+; AVX1-NEXT: vblendvpd %ymm3, %ymm2, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: var_shuffle_v4i64_with_v16i8_indices:
diff --git a/llvm/test/CodeGen/X86/vector-interleaved-load-i8-stride-4.ll b/llvm/test/CodeGen/X86/vector-interleaved-load-i8-stride-4.ll
index c9cbb0994810f..e2195f1fc25a1 100644
--- a/llvm/test/CodeGen/X86/vector-interleaved-load-i8-stride-4.ll
+++ b/llvm/test/CodeGen/X86/vector-interleaved-load-i8-stride-4.ll
@@ -156,64 +156,62 @@ define void @load_i8_stride4_vf4(ptr %in.vec, ptr %out.vec0, ptr %out.vec1, ptr
define void @load_i8_stride4_vf8(ptr %in.vec, ptr %out.vec0, ptr %out.vec1, ptr %out.vec2, ptr %out.vec3) nounwind {
; SSE-LABEL: load_i8_stride4_vf8:
; SSE: # %bb.0:
-; SSE-NEXT: movdqa (%rdi), %xmm1
+; SSE-NEXT: movdqa (%rdi), %xmm3
; SSE-NEXT: movdqa 16(%rdi), %xmm4
; SSE-NEXT: movdqa {{.*#+}} xmm0 = [255,0,255,0,255,0,255,0]
+; SSE-NEXT: movdqa %xmm4, %xmm1
; SSE-NEXT: movdqa %xmm4, %xmm2
-; SSE-NEXT: pand %xmm0, %xmm2
-; SSE-NEXT: pand %xmm1, %xmm0
-; SSE-NEXT: packuswb %xmm2, %xmm0
+; SSE-NEXT: pshuflw {{.*#+}} xmm5 = xmm4[3,1,2,3,4,5,6,7]
+; SSE-NEXT: pand %xmm0, %xmm4
+; SSE-NEXT: pand %xmm3, %xmm0
+; SSE-NEXT: packuswb %xmm4, %xmm0
; SSE-NEXT: packuswb %xmm0, %xmm0
-; SSE-NEXT: pxor %xmm7, %xmm7
-; SSE-NEXT: movdqa %xmm4, %xmm2
-; SSE-NEXT: punpckhbw {{.*#+}} xmm2 = xmm2[8],xmm7[8],xmm2[9],xmm7[9],xmm2[10],xmm7[10],xmm2[11],xmm7[11],xmm2[12],xmm7[12],xmm2[13],xmm7[13],xmm2[14],xmm7[14],xmm2[15],xmm7[15]
-; SSE-NEXT: pshufd {{.*#+}} xmm3 = xmm2[0,2,2,3]
-; SSE-NEXT: pshuflw {{.*#+}} xmm5 = xmm3[0,1,1,3,4,5,6,7]
-; SSE-NEXT: movdqa %xmm4, %xmm3
-; SSE-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm7[0],xmm3[1],xmm7[1],xmm3[2],xmm7[2],xmm3[3],xmm7[3],xmm3[4],xmm7[4],xmm3[5],xmm7[5],xmm3[6],xmm7[6],xmm3[7],xmm7[7]
-; SSE-NEXT: pshufd {{.*#+}} xmm6 = xmm3[0,2,2,3]
-; SSE-NEXT: pshuflw {{.*#+}} xmm8 = xmm6[0,1,1,3,4,5,6,7]
-; SSE-NEXT: punpckldq {{.*#+}} xmm8 = xmm8[0],xmm5[0],xmm8[1],xmm5[1]
-; SSE-NEXT: movdqa %xmm1, %xmm5
-; SSE-NEXT: punpckhbw {{.*#+}} xmm5 = xmm5[8],xmm7[8],xmm5[9],xmm7[9],xmm5[10],xmm7[10],xmm5[11],xmm7[11],xmm5[12],xmm7[12],xmm5[13],xmm7[13],xmm5[14],xmm7[14],xmm5[15],xmm7[15]
-; SSE-NEXT: pshufd {{.*#+}} xmm6 = xmm5[0,2,2,3]
-; SSE-NEXT: pshuflw {{.*#+}} xmm9 = xmm6[1,3,2,3,4,5,6,7]
-; SSE-NEXT: movdqa %xmm1, %xmm6
-; SSE-NEXT: punpcklbw {{.*#+}} xmm6 = xmm6[0],xmm7[0],xmm6[1],xmm7[1],xmm6[2],xmm7[2],xmm6[3],xmm7[3],xmm6[4],xmm7[4],xmm6[5],xmm7[5],xmm6[6],xmm7[6],xmm6[7],xmm7[7]
-; SSE-NEXT: pshufd {{.*#+}} xmm7 = xmm6[0,2,2,3]
-; SSE-NEXT: pshuflw {{.*#+}} xmm7 = xmm7[1,3,2,3,4,5,6,7]
-; SSE-NEXT: punpckldq {{.*#+}} xmm7 = xmm7[0],xmm9[0],xmm7[1],xmm9[1]
-; SSE-NEXT: packuswb %xmm8, %xmm7
-; SSE-NEXT: pshufd {{.*#+}} xmm7 = xmm7[0,3,2,3]
-; SSE-NEXT: movdqa {{.*#+}} xmm8 = [255,255,255,255,255,255,255,255]
-; SSE-NEXT: pand %xmm8, %xmm4
-; SSE-NEXT: pshuflw {{.*#+}} xmm4 = xmm4[3,1,2,3,4,5,6,7]
-; SSE-NEXT: pshufhw {{.*#+}} xmm4 = xmm4[0,1,2,3,7,5,6,7]
-; SSE-NEXT: pshufd {{.*#+}} xmm4 = xmm4[0,1,2,0]
-; SSE-NEXT: pshufhw {{.*#+}} xmm4 = xmm4[0,1,2,3,7,6,5,4]
-; SSE-NEXT: pand %xmm8, %xmm1
-; SSE-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[3,1,2,3,4,5,6,7]
-; SSE-NEXT: pshufhw {{.*#+}} xmm1 = xmm1[0,1,2,3,7,5,6,7]
-; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
-; SSE-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[1,0,3,2,4,5,6,7]
-; SSE-NEXT: packuswb %xmm4, %xmm1
-; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,3,2,3]
+; SSE-NEXT: pxor %xmm6, %xmm6
+; SSE-NEXT: punpckhbw {{.*#+}} xmm1 = xmm1[8],xmm6[8],xmm1[9],xmm6[9],xmm1[10],xmm6[10],xmm1[11],xmm6[11],xmm1[12],xmm6[12],xmm1[13],xmm6[13]...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/74443
More information about the llvm-commits
mailing list