forked from OSchip/llvm-project
[X86][AVX512] Add support for AVX512 VMOVSD/VMOVSS shuffle decoding
llvm-svn: 259427
This commit is contained in:
Simon Pilgrim
parent
55634d8e8d
commit
f5c23ad3d7
|
|
@ -652,22 +652,26 @@ bool llvm::EmitAnyX86InstComments(const MCInst *MI, raw_ostream &OS,
|
|||
|
||||
case X86::MOVSDrr:
|
||||
case X86::VMOVSDrr:
|
||||
case X86::VMOVSDZrr:
|
||||
Src2Name = getRegName(MI->getOperand(2).getReg());
|
||||
Src1Name = getRegName(MI->getOperand(1).getReg());
|
||||
// FALL THROUGH.
|
||||
case X86::MOVSDrm:
|
||||
case X86::VMOVSDrm:
|
||||
case X86::VMOVSDZrm:
|
||||
DecodeScalarMoveMask(MVT::v2f64, nullptr == Src2Name, ShuffleMask);
|
||||
DestName = getRegName(MI->getOperand(0).getReg());
|
||||
break;
|
||||
|
||||
case X86::MOVSSrr:
|
||||
case X86::VMOVSSrr:
|
||||
case X86::VMOVSSZrr:
|
||||
Src2Name = getRegName(MI->getOperand(2).getReg());
|
||||
Src1Name = getRegName(MI->getOperand(1).getReg());
|
||||
// FALL THROUGH.
|
||||
case X86::MOVSSrm:
|
||||
case X86::VMOVSSrm:
|
||||
case X86::VMOVSSZrm:
|
||||
DecodeScalarMoveMask(MVT::v4f32, nullptr == Src2Name, ShuffleMask);
|
||||
DestName = getRegName(MI->getOperand(0).getReg());
|
||||
break;
|
||||
|
|
|
|||
|
|
@ -74,20 +74,10 @@ define <4 x float> @merge_4f32_f32_3zuu(float* %ptr) nounwind uwtable noinline s
|
|||
; SSE-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX1-LABEL: merge_4f32_f32_3zuu:
|
||||
; AVX1: # BB#0:
|
||||
; AVX1-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX2-LABEL: merge_4f32_f32_3zuu:
|
||||
; AVX2: # BB#0:
|
||||
; AVX2-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512F-LABEL: merge_4f32_f32_3zuu:
|
||||
; AVX512F: # BB#0:
|
||||
; AVX512F-NEXT: vmovss 12(%rdi), %xmm0
|
||||
; AVX512F-NEXT: retq
|
||||
; AVX-LABEL: merge_4f32_f32_3zuu:
|
||||
; AVX: # BB#0:
|
||||
; AVX-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
||||
; AVX-NEXT: retq
|
||||
%ptr0 = getelementptr inbounds float, float* %ptr, i64 3
|
||||
%val0 = load float, float* %ptr0
|
||||
%res0 = insertelement <4 x float> undef, float %val0, i32 0
|
||||
|
|
@ -122,26 +112,12 @@ define <4 x float> @merge_4f32_f32_34z6(float* %ptr) nounwind uwtable noinline s
|
|||
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,1],xmm1[1,0]
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX1-LABEL: merge_4f32_f32_34z6:
|
||||
; AVX1: # BB#0:
|
||||
; AVX1-NEXT: vmovq {{.*#+}} xmm0 = mem[0],zero
|
||||
; AVX1-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,1],xmm1[1,0]
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX2-LABEL: merge_4f32_f32_34z6:
|
||||
; AVX2: # BB#0:
|
||||
; AVX2-NEXT: vmovq {{.*#+}} xmm0 = mem[0],zero
|
||||
; AVX2-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
||||
; AVX2-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,1],xmm1[1,0]
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512F-LABEL: merge_4f32_f32_34z6:
|
||||
; AVX512F: # BB#0:
|
||||
; AVX512F-NEXT: vmovq {{.*#+}} xmm0 = mem[0],zero
|
||||
; AVX512F-NEXT: vmovss 24(%rdi), %xmm1
|
||||
; AVX512F-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,1],xmm1[1,0]
|
||||
; AVX512F-NEXT: retq
|
||||
; AVX-LABEL: merge_4f32_f32_34z6:
|
||||
; AVX: # BB#0:
|
||||
; AVX-NEXT: vmovq {{.*#+}} xmm0 = mem[0],zero
|
||||
; AVX-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
||||
; AVX-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,1],xmm1[1,0]
|
||||
; AVX-NEXT: retq
|
||||
%ptr0 = getelementptr inbounds float, float* %ptr, i64 3
|
||||
%ptr1 = getelementptr inbounds float, float* %ptr, i64 4
|
||||
%ptr3 = getelementptr inbounds float, float* %ptr, i64 6
|
||||
|
|
|
|||
|
|
@ -50,20 +50,10 @@ define <4 x double> @merge_4f64_f64_2345(double* %ptr) nounwind uwtable noinline
|
|||
}
|
||||
|
||||
define <4 x double> @merge_4f64_f64_3zuu(double* %ptr) nounwind uwtable noinline ssp {
|
||||
; AVX1-LABEL: merge_4f64_f64_3zuu:
|
||||
; AVX1: # BB#0:
|
||||
; AVX1-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX2-LABEL: merge_4f64_f64_3zuu:
|
||||
; AVX2: # BB#0:
|
||||
; AVX2-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512F-LABEL: merge_4f64_f64_3zuu:
|
||||
; AVX512F: # BB#0:
|
||||
; AVX512F-NEXT: vmovsd 24(%rdi), %xmm0
|
||||
; AVX512F-NEXT: retq
|
||||
; AVX-LABEL: merge_4f64_f64_3zuu:
|
||||
; AVX: # BB#0:
|
||||
; AVX-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
|
||||
; AVX-NEXT: retq
|
||||
%ptr0 = getelementptr inbounds double, double* %ptr, i64 3
|
||||
%val0 = load double, double* %ptr0
|
||||
%res0 = insertelement <4 x double> undef, double %val0, i32 0
|
||||
|
|
@ -121,7 +111,7 @@ define <4 x double> @merge_4f64_f64_34z6(double* %ptr) nounwind uwtable noinline
|
|||
; AVX512F-LABEL: merge_4f64_f64_34z6:
|
||||
; AVX512F: # BB#0:
|
||||
; AVX512F-NEXT: vmovdqu 24(%rdi), %xmm0
|
||||
; AVX512F-NEXT: vmovsd 48(%rdi), %xmm1
|
||||
; AVX512F-NEXT: vmovsd {{.*#+}} xmm1 = mem[0],zero
|
||||
; AVX512F-NEXT: vpslldq {{.*#+}} xmm1 = zero,zero,zero,zero,zero,zero,zero,zero,xmm1[0,1,2,3,4,5,6,7]
|
||||
; AVX512F-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
|
||||
; AVX512F-NEXT: retq
|
||||
|
|
@ -315,10 +305,10 @@ define <8 x float> @merge_8f32_f32_1u3u5zu8(float* %ptr) nounwind uwtable noinli
|
|||
;
|
||||
; AVX512F-LABEL: merge_8f32_f32_1u3u5zu8:
|
||||
; AVX512F: # BB#0:
|
||||
; AVX512F-NEXT: vmovss 32(%rdi), %xmm0
|
||||
; AVX512F-NEXT: vmovss 20(%rdi), %xmm1
|
||||
; AVX512F-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
||||
; AVX512F-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
||||
; AVX512F-NEXT: vshufps {{.*#+}} xmm0 = xmm1[0,1],xmm0[1,0]
|
||||
; AVX512F-NEXT: vmovss 4(%rdi), %xmm1
|
||||
; AVX512F-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
||||
; AVX512F-NEXT: vinsertps {{.*#+}} xmm1 = xmm1[0,1],mem[0],xmm1[3]
|
||||
; AVX512F-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
|
||||
; AVX512F-NEXT: retq
|
||||
|
|
|
|||
|
|
@ -95,11 +95,11 @@ define <8 x double> @merge_8f64_f64_12zzuuzz(double* %ptr) nounwind uwtable noin
|
|||
define <8 x double> @merge_8f64_f64_1u3u5zu8(double* %ptr) nounwind uwtable noinline ssp {
|
||||
; ALL-LABEL: merge_8f64_f64_1u3u5zu8:
|
||||
; ALL: # BB#0:
|
||||
; ALL-NEXT: vmovsd 40(%rdi), %xmm0
|
||||
; ALL-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
|
||||
; ALL-NEXT: vmovddup {{.*#+}} xmm1 = mem[0,0]
|
||||
; ALL-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
|
||||
; ALL-NEXT: vmovsd 8(%rdi), %xmm1
|
||||
; ALL-NEXT: vmovsd 24(%rdi), %xmm2
|
||||
; ALL-NEXT: vmovsd {{.*#+}} xmm1 = mem[0],zero
|
||||
; ALL-NEXT: vmovsd {{.*#+}} xmm2 = mem[0],zero
|
||||
; ALL-NEXT: vinsertf128 $1, %xmm2, %ymm1, %ymm1
|
||||
; ALL-NEXT: vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
|
||||
; ALL-NEXT: retq
|
||||
|
|
@ -249,7 +249,7 @@ define <16 x float> @merge_16f32_f32_0uu3zzuuuuuzCuEF(float* %ptr) nounwind uwta
|
|||
; ALL-LABEL: merge_16f32_f32_0uu3zzuuuuuzCuEF:
|
||||
; ALL: # BB#0:
|
||||
; ALL-NEXT: vmovq {{.*#+}} xmm0 = mem[0],zero
|
||||
; ALL-NEXT: vmovss 48(%rdi), %xmm1
|
||||
; ALL-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
|
||||
; ALL-NEXT: vunpcklpd {{.*#+}} xmm0 = xmm1[0],xmm0[0]
|
||||
; ALL-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
|
||||
; ALL-NEXT: vmovupd (%rdi), %xmm1
|
||||
|
|
|
|||
Loading…
Reference in New Issue