forked from OSchip/llvm-project
[X86][SSE] Add support for lowering shuffles to PACKSS/PACKUS
If the upper bits of a truncation shuffle patterns have at least the minimum number of sign/zero bits on their inputs then we can safely use PACKSS/PACKUS as shuffles. Partial fix for https://bugs.llvm.org/show_bug.cgi?id=34773 Differential Revision: https://reviews.llvm.org/D38472 llvm-svn: 314788
This commit is contained in:
Simon Pilgrim
parent
d3558b5d5e
commit
f5f291d129
|
|
@ -8664,6 +8664,39 @@ static SDValue lowerVectorShuffleWithUNPCK(const SDLoc &DL, MVT VT,
|
|||
return SDValue();
|
||||
}
|
||||
|
||||
// X86 has dedicated pack instructions that can handle specific truncation
|
||||
// operations: PACKSS and PACKUS.
|
||||
static SDValue lowerVectorShuffleWithPACK(const SDLoc &DL, MVT VT,
|
||||
ArrayRef<int> Mask, SDValue V1,
|
||||
SDValue V2, SelectionDAG &DAG,
|
||||
const X86Subtarget &Subtarget) {
|
||||
unsigned NumElts = VT.getVectorNumElements();
|
||||
unsigned BitSize = VT.getScalarSizeInBits();
|
||||
MVT PackSVT = MVT::getIntegerVT(BitSize * 2);
|
||||
MVT PackVT = MVT::getVectorVT(PackSVT, NumElts / 2);
|
||||
|
||||
// TODO - Add support for unary packs.
|
||||
SmallVector<int, 32> BinaryMask;
|
||||
createPackShuffleMask(VT, BinaryMask, false);
|
||||
|
||||
if (isShuffleEquivalent(V1, V2, Mask, BinaryMask)) {
|
||||
SDValue VV1 = DAG.getBitcast(PackVT, V1);
|
||||
SDValue VV2 = DAG.getBitcast(PackVT, V2);
|
||||
if ((V1.isUndef() || DAG.ComputeNumSignBits(VV1) > BitSize) &&
|
||||
(V2.isUndef() || DAG.ComputeNumSignBits(VV2) > BitSize))
|
||||
return DAG.getNode(X86ISD::PACKSS, DL, VT, VV1, VV2);
|
||||
|
||||
if (Subtarget.hasSSE41() || PackSVT == MVT::i16) {
|
||||
APInt ZeroMask = APInt::getHighBitsSet(BitSize * 2, BitSize);
|
||||
if ((V1.isUndef() || DAG.MaskedValueIsZero(VV1, ZeroMask)) &&
|
||||
(V2.isUndef() || DAG.MaskedValueIsZero(VV2, ZeroMask)))
|
||||
return DAG.getNode(X86ISD::PACKUS, DL, VT, VV1, VV2);
|
||||
}
|
||||
}
|
||||
|
||||
return SDValue();
|
||||
}
|
||||
|
||||
/// \brief Try to emit a bitmask instruction for a shuffle.
|
||||
///
|
||||
/// This handles cases where we can model a blend exactly as a bitmask due to
|
||||
|
|
@ -11403,6 +11436,11 @@ static SDValue lowerV8I16VectorShuffle(const SDLoc &DL, ArrayRef<int> Mask,
|
|||
lowerVectorShuffleWithUNPCK(DL, MVT::v8i16, Mask, V1, V2, DAG))
|
||||
return V;
|
||||
|
||||
// Use dedicated pack instructions for masks that match their pattern.
|
||||
if (SDValue V = lowerVectorShuffleWithPACK(DL, MVT::v8i16, Mask, V1, V2,
|
||||
DAG, Subtarget))
|
||||
return V;
|
||||
|
||||
// Try to use byte rotation instructions.
|
||||
if (SDValue Rotate = lowerVectorShuffleAsByteRotate(DL, MVT::v8i16, V1, V1,
|
||||
Mask, Subtarget, DAG))
|
||||
|
|
@ -11573,6 +11611,11 @@ static SDValue lowerV16I8VectorShuffle(const SDLoc &DL, ArrayRef<int> Mask,
|
|||
DL, MVT::v16i8, V1, V2, Mask, Subtarget, DAG))
|
||||
return Rotate;
|
||||
|
||||
// Use dedicated pack instructions for masks that match their pattern.
|
||||
if (SDValue V = lowerVectorShuffleWithPACK(DL, MVT::v16i8, Mask, V1, V2, DAG,
|
||||
Subtarget))
|
||||
return V;
|
||||
|
||||
// Try to use a zext lowering.
|
||||
if (SDValue ZExt = lowerVectorShuffleAsZeroOrAnyExtend(
|
||||
DL, MVT::v16i8, V1, V2, Mask, Zeroable, Subtarget, DAG))
|
||||
|
|
@ -13067,6 +13110,11 @@ static SDValue lowerV16I16VectorShuffle(const SDLoc &DL, ArrayRef<int> Mask,
|
|||
lowerVectorShuffleWithUNPCK(DL, MVT::v16i16, Mask, V1, V2, DAG))
|
||||
return V;
|
||||
|
||||
// Use dedicated pack instructions for masks that match their pattern.
|
||||
if (SDValue V = lowerVectorShuffleWithPACK(DL, MVT::v16i16, Mask, V1, V2, DAG,
|
||||
Subtarget))
|
||||
return V;
|
||||
|
||||
// Try to use shift instructions.
|
||||
if (SDValue Shift = lowerVectorShuffleAsShift(DL, MVT::v16i16, V1, V2, Mask,
|
||||
Zeroable, Subtarget, DAG))
|
||||
|
|
@ -13153,6 +13201,11 @@ static SDValue lowerV32I8VectorShuffle(const SDLoc &DL, ArrayRef<int> Mask,
|
|||
lowerVectorShuffleWithUNPCK(DL, MVT::v32i8, Mask, V1, V2, DAG))
|
||||
return V;
|
||||
|
||||
// Use dedicated pack instructions for masks that match their pattern.
|
||||
if (SDValue V = lowerVectorShuffleWithPACK(DL, MVT::v32i8, Mask, V1, V2, DAG,
|
||||
Subtarget))
|
||||
return V;
|
||||
|
||||
// Try to use shift instructions.
|
||||
if (SDValue Shift = lowerVectorShuffleAsShift(DL, MVT::v32i8, V1, V2, Mask,
|
||||
Zeroable, Subtarget, DAG))
|
||||
|
|
|
|||
|
|
@ -50,7 +50,7 @@ define void @fptoui8(%f32vec_t %a, %i8vec_t *%p) {
|
|||
; CHECK-NEXT: vpshufb %xmm2, %xmm1, %xmm1
|
||||
; CHECK-NEXT: vpshufb %xmm2, %xmm0, %xmm0
|
||||
; CHECK-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; CHECK-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
|
||||
; CHECK-NEXT: vpackuswb %xmm0, %xmm0, %xmm0
|
||||
; CHECK-NEXT: vmovq %xmm0, (%rdi)
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
|
|
@ -68,7 +68,7 @@ define void @fptosi8(%f32vec_t %a, %i8vec_t *%p) {
|
|||
; CHECK-NEXT: vpshufb %xmm2, %xmm1, %xmm1
|
||||
; CHECK-NEXT: vpshufb %xmm2, %xmm0, %xmm0
|
||||
; CHECK-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; CHECK-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
|
||||
; CHECK-NEXT: vpacksswb %xmm0, %xmm0, %xmm0
|
||||
; CHECK-NEXT: vmovq %xmm0, (%rdi)
|
||||
; CHECK-NEXT: vzeroupper
|
||||
; CHECK-NEXT: retq
|
||||
|
|
|
|||
|
|
@ -556,7 +556,7 @@ define <8 x i16> @variable_ashr16(<8 x i16> %lhs, <8 x i16> %rhs) {
|
|||
; X32-NEXT: vpmovzxwd {{.*#+}} ymm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero
|
||||
; X32-NEXT: vpmovsxwd %xmm0, %ymm0
|
||||
; X32-NEXT: vpsravd %ymm1, %ymm0, %ymm0
|
||||
; X32-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
|
||||
; X32-NEXT: vpackssdw %ymm0, %ymm0, %ymm0
|
||||
; X32-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
|
||||
; X32-NEXT: # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
|
||||
; X32-NEXT: vzeroupper
|
||||
|
|
@ -567,7 +567,7 @@ define <8 x i16> @variable_ashr16(<8 x i16> %lhs, <8 x i16> %rhs) {
|
|||
; X64-NEXT: vpmovzxwd {{.*#+}} ymm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero
|
||||
; X64-NEXT: vpmovsxwd %xmm0, %ymm0
|
||||
; X64-NEXT: vpsravd %ymm1, %ymm0, %ymm0
|
||||
; X64-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
|
||||
; X64-NEXT: vpackssdw %ymm0, %ymm0, %ymm0
|
||||
; X64-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
|
||||
; X64-NEXT: # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
|
||||
; X64-NEXT: vzeroupper
|
||||
|
|
|
|||
|
|
@ -267,15 +267,15 @@ define <16 x i16> @broadcast_mem_v4i16_v16i16(<4 x i16>* %ptr) {
|
|||
; X32-AVX2-LABEL: broadcast_mem_v4i16_v16i16:
|
||||
; X32-AVX2: ## BB#0:
|
||||
; X32-AVX2-NEXT: movl {{[0-9]+}}(%esp), %eax
|
||||
; X32-AVX2-NEXT: vmovq {{.*#+}} xmm0 = mem[0],zero
|
||||
; X32-AVX2-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,2,3,4,5,6,7,4,5,6,7,6,7],zero,zero
|
||||
; X32-AVX2-NEXT: vpmovzxwd {{.*#+}} xmm0 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
|
||||
; X32-AVX2-NEXT: vpackusdw %xmm0, %xmm0, %xmm0
|
||||
; X32-AVX2-NEXT: vpbroadcastq %xmm0, %ymm0
|
||||
; X32-AVX2-NEXT: retl
|
||||
;
|
||||
; X64-AVX2-LABEL: broadcast_mem_v4i16_v16i16:
|
||||
; X64-AVX2: ## BB#0:
|
||||
; X64-AVX2-NEXT: vmovq {{.*#+}} xmm0 = mem[0],zero
|
||||
; X64-AVX2-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,2,3,4,5,6,7,4,5,6,7,6,7],zero,zero
|
||||
; X64-AVX2-NEXT: vpmovzxwd {{.*#+}} xmm0 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero
|
||||
; X64-AVX2-NEXT: vpackusdw %xmm0, %xmm0, %xmm0
|
||||
; X64-AVX2-NEXT: vpbroadcastq %xmm0, %ymm0
|
||||
; X64-AVX2-NEXT: retq
|
||||
;
|
||||
|
|
|
|||
|
|
@ -499,7 +499,7 @@ define <8 x i16> @ashr_8i16(<8 x i16> %r, <8 x i16> %a) nounwind {
|
|||
; X32-NEXT: vpmovzxwd {{.*#+}} ymm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero
|
||||
; X32-NEXT: vpmovsxwd %xmm0, %ymm0
|
||||
; X32-NEXT: vpsravd %ymm1, %ymm0, %ymm0
|
||||
; X32-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
|
||||
; X32-NEXT: vpackssdw %ymm0, %ymm0, %ymm0
|
||||
; X32-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
|
||||
; X32-NEXT: # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
|
||||
; X32-NEXT: vzeroupper
|
||||
|
|
@ -510,7 +510,7 @@ define <8 x i16> @ashr_8i16(<8 x i16> %r, <8 x i16> %a) nounwind {
|
|||
; X64-NEXT: vpmovzxwd {{.*#+}} ymm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero
|
||||
; X64-NEXT: vpmovsxwd %xmm0, %ymm0
|
||||
; X64-NEXT: vpsravd %ymm1, %ymm0, %ymm0
|
||||
; X64-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
|
||||
; X64-NEXT: vpackssdw %ymm0, %ymm0, %ymm0
|
||||
; X64-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
|
||||
; X64-NEXT: # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
|
||||
; X64-NEXT: vzeroupper
|
||||
|
|
|
|||
|
|
@ -57,7 +57,7 @@ define void @any_extend_load_v8i16(<8 x i8> * %ptr) {
|
|||
; KNL: # BB#0:
|
||||
; KNL-NEXT: vpmovzxbw {{.*#+}} xmm0 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero
|
||||
; KNL-NEXT: vpaddb {{.*}}(%rip), %xmm0, %xmm0
|
||||
; KNL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
|
||||
; KNL-NEXT: vpackuswb %xmm0, %xmm0, %xmm0
|
||||
; KNL-NEXT: vmovq %xmm0, (%rdi)
|
||||
; KNL-NEXT: retq
|
||||
;
|
||||
|
|
|
|||
|
|
@ -584,7 +584,7 @@ define void @usat_trunc_wb_128_mem(<8 x i16> %i, <8 x i8>* %res) {
|
|||
; KNL-LABEL: usat_trunc_wb_128_mem:
|
||||
; KNL: ## BB#0:
|
||||
; KNL-NEXT: vpminuw {{.*}}(%rip), %xmm0, %xmm0
|
||||
; KNL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
|
||||
; KNL-NEXT: vpackuswb %xmm0, %xmm0, %xmm0
|
||||
; KNL-NEXT: vmovq %xmm0, (%rdi)
|
||||
; KNL-NEXT: retq
|
||||
;
|
||||
|
|
|
|||
|
|
@ -149,41 +149,18 @@ define i4 @v4f64(<4 x double> %a, <4 x double> %b, <4 x double> %c, <4 x double>
|
|||
}
|
||||
|
||||
define i16 @v16i16(<16 x i16> %a, <16 x i16> %b, <16 x i16> %c, <16 x i16> %d) {
|
||||
; SSE2-LABEL: v16i16:
|
||||
; SSE2: # BB#0:
|
||||
; SSE2-NEXT: pcmpgtw %xmm3, %xmm1
|
||||
; SSE2-NEXT: movdqa {{.*#+}} xmm3 = [255,255,255,255,255,255,255,255]
|
||||
; SSE2-NEXT: pand %xmm3, %xmm1
|
||||
; SSE2-NEXT: pcmpgtw %xmm2, %xmm0
|
||||
; SSE2-NEXT: pand %xmm3, %xmm0
|
||||
; SSE2-NEXT: packuswb %xmm1, %xmm0
|
||||
; SSE2-NEXT: pcmpgtw %xmm7, %xmm5
|
||||
; SSE2-NEXT: pand %xmm3, %xmm5
|
||||
; SSE2-NEXT: pcmpgtw %xmm6, %xmm4
|
||||
; SSE2-NEXT: pand %xmm3, %xmm4
|
||||
; SSE2-NEXT: packuswb %xmm5, %xmm4
|
||||
; SSE2-NEXT: pand %xmm0, %xmm4
|
||||
; SSE2-NEXT: pmovmskb %xmm4, %eax
|
||||
; SSE2-NEXT: # kill: %AX<def> %AX<kill> %EAX<kill>
|
||||
; SSE2-NEXT: retq
|
||||
;
|
||||
; SSSE3-LABEL: v16i16:
|
||||
; SSSE3: # BB#0:
|
||||
; SSSE3-NEXT: pcmpgtw %xmm3, %xmm1
|
||||
; SSSE3-NEXT: movdqa {{.*#+}} xmm3 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
|
||||
; SSSE3-NEXT: pshufb %xmm3, %xmm1
|
||||
; SSSE3-NEXT: pcmpgtw %xmm2, %xmm0
|
||||
; SSSE3-NEXT: pshufb %xmm3, %xmm0
|
||||
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; SSSE3-NEXT: pcmpgtw %xmm7, %xmm5
|
||||
; SSSE3-NEXT: pshufb %xmm3, %xmm5
|
||||
; SSSE3-NEXT: pcmpgtw %xmm6, %xmm4
|
||||
; SSSE3-NEXT: pshufb %xmm3, %xmm4
|
||||
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm4 = xmm4[0],xmm5[0]
|
||||
; SSSE3-NEXT: pand %xmm0, %xmm4
|
||||
; SSSE3-NEXT: pmovmskb %xmm4, %eax
|
||||
; SSSE3-NEXT: # kill: %AX<def> %AX<kill> %EAX<kill>
|
||||
; SSSE3-NEXT: retq
|
||||
; SSE2-SSSE3-LABEL: v16i16:
|
||||
; SSE2-SSSE3: # BB#0:
|
||||
; SSE2-SSSE3-NEXT: pcmpgtw %xmm3, %xmm1
|
||||
; SSE2-SSSE3-NEXT: pcmpgtw %xmm2, %xmm0
|
||||
; SSE2-SSSE3-NEXT: packsswb %xmm1, %xmm0
|
||||
; SSE2-SSSE3-NEXT: pcmpgtw %xmm7, %xmm5
|
||||
; SSE2-SSSE3-NEXT: pcmpgtw %xmm6, %xmm4
|
||||
; SSE2-SSSE3-NEXT: packsswb %xmm5, %xmm4
|
||||
; SSE2-SSSE3-NEXT: pand %xmm0, %xmm4
|
||||
; SSE2-SSSE3-NEXT: pmovmskb %xmm4, %eax
|
||||
; SSE2-SSSE3-NEXT: # kill: %AX<def> %AX<kill> %EAX<kill>
|
||||
; SSE2-SSSE3-NEXT: retq
|
||||
;
|
||||
; AVX1-LABEL: v16i16:
|
||||
; AVX1: # BB#0:
|
||||
|
|
@ -236,42 +213,33 @@ define i8 @v8i32(<8 x i32> %a, <8 x i32> %b, <8 x i32> %c, <8 x i32> %d) {
|
|||
; SSE2-LABEL: v8i32:
|
||||
; SSE2: # BB#0:
|
||||
; SSE2-NEXT: pcmpgtd %xmm3, %xmm1
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
|
||||
; SSE2-NEXT: pshufhw {{.*#+}} xmm1 = xmm1[0,1,2,3,4,6,6,7]
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
|
||||
; SSE2-NEXT: packssdw %xmm0, %xmm1
|
||||
; SSE2-NEXT: pcmpgtd %xmm2, %xmm0
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7]
|
||||
; SSE2-NEXT: pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,4,6,6,7]
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
|
||||
; SSE2-NEXT: packssdw %xmm0, %xmm0
|
||||
; SSE2-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; SSE2-NEXT: pcmpgtd %xmm7, %xmm5
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm1 = xmm5[0,2,2,3,4,5,6,7]
|
||||
; SSE2-NEXT: pshufhw {{.*#+}} xmm1 = xmm1[0,1,2,3,4,6,6,7]
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
|
||||
; SSE2-NEXT: packssdw %xmm0, %xmm5
|
||||
; SSE2-NEXT: pcmpgtd %xmm6, %xmm4
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm2 = xmm4[0,2,2,3,4,5,6,7]
|
||||
; SSE2-NEXT: pshufhw {{.*#+}} xmm2 = xmm2[0,1,2,3,4,6,6,7]
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
|
||||
; SSE2-NEXT: punpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm1[0]
|
||||
; SSE2-NEXT: pand %xmm0, %xmm2
|
||||
; SSE2-NEXT: pand {{.*}}(%rip), %xmm2
|
||||
; SSE2-NEXT: packuswb %xmm2, %xmm2
|
||||
; SSE2-NEXT: pmovmskb %xmm2, %eax
|
||||
; SSE2-NEXT: packssdw %xmm0, %xmm4
|
||||
; SSE2-NEXT: punpcklqdq {{.*#+}} xmm4 = xmm4[0],xmm5[0]
|
||||
; SSE2-NEXT: pand %xmm0, %xmm4
|
||||
; SSE2-NEXT: pand {{.*}}(%rip), %xmm4
|
||||
; SSE2-NEXT: packuswb %xmm4, %xmm4
|
||||
; SSE2-NEXT: pmovmskb %xmm4, %eax
|
||||
; SSE2-NEXT: # kill: %AL<def> %AL<kill> %EAX<kill>
|
||||
; SSE2-NEXT: retq
|
||||
;
|
||||
; SSSE3-LABEL: v8i32:
|
||||
; SSSE3: # BB#0:
|
||||
; SSSE3-NEXT: pcmpgtd %xmm3, %xmm1
|
||||
; SSSE3-NEXT: movdqa {{.*#+}} xmm3 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
|
||||
; SSSE3-NEXT: pshufb %xmm3, %xmm1
|
||||
; SSSE3-NEXT: packssdw %xmm0, %xmm1
|
||||
; SSSE3-NEXT: pcmpgtd %xmm2, %xmm0
|
||||
; SSSE3-NEXT: pshufb %xmm3, %xmm0
|
||||
; SSSE3-NEXT: packssdw %xmm0, %xmm0
|
||||
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; SSSE3-NEXT: pcmpgtd %xmm7, %xmm5
|
||||
; SSSE3-NEXT: pshufb %xmm3, %xmm5
|
||||
; SSSE3-NEXT: packssdw %xmm0, %xmm5
|
||||
; SSSE3-NEXT: pcmpgtd %xmm6, %xmm4
|
||||
; SSSE3-NEXT: pshufb %xmm3, %xmm4
|
||||
; SSSE3-NEXT: packssdw %xmm0, %xmm4
|
||||
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm4 = xmm4[0],xmm5[0]
|
||||
; SSSE3-NEXT: pand %xmm0, %xmm4
|
||||
; SSSE3-NEXT: pshufb {{.*#+}} xmm4 = xmm4[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
|
||||
|
|
|
|||
|
|
@ -40,7 +40,7 @@ define i8 @v8i64(<8 x i64> %a, <8 x i64> %b, <8 x i64> %c, <8 x i64> %d) {
|
|||
; SSE-NEXT: pand %xmm0, %xmm2
|
||||
; SSE-NEXT: psllw $15, %xmm2
|
||||
; SSE-NEXT: psraw $15, %xmm2
|
||||
; SSE-NEXT: pshufb {{.*#+}} xmm2 = xmm2[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
|
||||
; SSE-NEXT: packsswb %xmm0, %xmm2
|
||||
; SSE-NEXT: pmovmskb %xmm2, %eax
|
||||
; SSE-NEXT: # kill: %AL<def> %AL<kill> %EAX<kill>
|
||||
; SSE-NEXT: retq
|
||||
|
|
@ -77,7 +77,7 @@ define i8 @v8i64(<8 x i64> %a, <8 x i64> %b, <8 x i64> %c, <8 x i64> %d) {
|
|||
; AVX1-NEXT: vpand %xmm1, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpsllw $15, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpsraw $15, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
|
||||
; AVX1-NEXT: vpacksswb %xmm0, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpmovmskb %xmm0, %eax
|
||||
; AVX1-NEXT: # kill: %AL<def> %AL<kill> %EAX<kill>
|
||||
; AVX1-NEXT: vzeroupper
|
||||
|
|
@ -107,7 +107,7 @@ define i8 @v8i64(<8 x i64> %a, <8 x i64> %b, <8 x i64> %c, <8 x i64> %d) {
|
|||
; AVX2-NEXT: vpand %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpsllw $15, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpsraw $15, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
|
||||
; AVX2-NEXT: vpacksswb %xmm0, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpmovmskb %xmm0, %eax
|
||||
; AVX2-NEXT: # kill: %AL<def> %AL<kill> %EAX<kill>
|
||||
; AVX2-NEXT: vzeroupper
|
||||
|
|
@ -172,7 +172,7 @@ define i8 @v8f64(<8 x double> %a, <8 x double> %b, <8 x double> %c, <8 x double>
|
|||
; SSE-NEXT: pand %xmm0, %xmm2
|
||||
; SSE-NEXT: psllw $15, %xmm2
|
||||
; SSE-NEXT: psraw $15, %xmm2
|
||||
; SSE-NEXT: pshufb {{.*#+}} xmm2 = xmm2[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
|
||||
; SSE-NEXT: packsswb %xmm0, %xmm2
|
||||
; SSE-NEXT: pmovmskb %xmm2, %eax
|
||||
; SSE-NEXT: # kill: %AL<def> %AL<kill> %EAX<kill>
|
||||
; SSE-NEXT: retq
|
||||
|
|
@ -201,7 +201,7 @@ define i8 @v8f64(<8 x double> %a, <8 x double> %b, <8 x double> %c, <8 x double>
|
|||
; AVX12-NEXT: vpand %xmm1, %xmm0, %xmm0
|
||||
; AVX12-NEXT: vpsllw $15, %xmm0, %xmm0
|
||||
; AVX12-NEXT: vpsraw $15, %xmm0, %xmm0
|
||||
; AVX12-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
|
||||
; AVX12-NEXT: vpacksswb %xmm0, %xmm0, %xmm0
|
||||
; AVX12-NEXT: vpmovmskb %xmm0, %eax
|
||||
; AVX12-NEXT: # kill: %AL<def> %AL<kill> %EAX<kill>
|
||||
; AVX12-NEXT: vzeroupper
|
||||
|
|
@ -235,33 +235,24 @@ define i32 @v32i16(<32 x i16> %a, <32 x i16> %b, <32 x i16> %c, <32 x i16> %d) {
|
|||
; SSE-LABEL: v32i16:
|
||||
; SSE: # BB#0:
|
||||
; SSE-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm8
|
||||
; SSE-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm10
|
||||
; SSE-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm9
|
||||
; SSE-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm10
|
||||
; SSE-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm11
|
||||
; SSE-NEXT: pcmpgtw %xmm5, %xmm1
|
||||
; SSE-NEXT: movdqa {{.*#+}} xmm5 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
|
||||
; SSE-NEXT: pshufb %xmm5, %xmm1
|
||||
; SSE-NEXT: pcmpgtw %xmm4, %xmm0
|
||||
; SSE-NEXT: pshufb %xmm5, %xmm0
|
||||
; SSE-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; SSE-NEXT: packsswb %xmm1, %xmm0
|
||||
; SSE-NEXT: pcmpgtw %xmm7, %xmm3
|
||||
; SSE-NEXT: pshufb %xmm5, %xmm3
|
||||
; SSE-NEXT: pcmpgtw %xmm6, %xmm2
|
||||
; SSE-NEXT: pshufb %xmm5, %xmm2
|
||||
; SSE-NEXT: punpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm3[0]
|
||||
; SSE-NEXT: packsswb %xmm3, %xmm2
|
||||
; SSE-NEXT: pcmpgtw {{[0-9]+}}(%rsp), %xmm11
|
||||
; SSE-NEXT: pshufb %xmm5, %xmm11
|
||||
; SSE-NEXT: pcmpgtw {{[0-9]+}}(%rsp), %xmm9
|
||||
; SSE-NEXT: pshufb %xmm5, %xmm9
|
||||
; SSE-NEXT: punpcklqdq {{.*#+}} xmm9 = xmm9[0],xmm11[0]
|
||||
; SSE-NEXT: pand %xmm0, %xmm9
|
||||
; SSE-NEXT: pcmpgtw {{[0-9]+}}(%rsp), %xmm10
|
||||
; SSE-NEXT: pshufb %xmm5, %xmm10
|
||||
; SSE-NEXT: packsswb %xmm11, %xmm10
|
||||
; SSE-NEXT: pand %xmm0, %xmm10
|
||||
; SSE-NEXT: pcmpgtw {{[0-9]+}}(%rsp), %xmm9
|
||||
; SSE-NEXT: pcmpgtw {{[0-9]+}}(%rsp), %xmm8
|
||||
; SSE-NEXT: pshufb %xmm5, %xmm8
|
||||
; SSE-NEXT: punpcklqdq {{.*#+}} xmm8 = xmm8[0],xmm10[0]
|
||||
; SSE-NEXT: packsswb %xmm9, %xmm8
|
||||
; SSE-NEXT: pand %xmm2, %xmm8
|
||||
; SSE-NEXT: pmovmskb %xmm9, %ecx
|
||||
; SSE-NEXT: pmovmskb %xmm10, %ecx
|
||||
; SSE-NEXT: pmovmskb %xmm8, %eax
|
||||
; SSE-NEXT: shll $16, %eax
|
||||
; SSE-NEXT: orl %ecx, %eax
|
||||
|
|
@ -639,33 +630,27 @@ define i16 @v16i32(<16 x i32> %a, <16 x i32> %b, <16 x i32> %c, <16 x i32> %d) {
|
|||
; SSE-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm9
|
||||
; SSE-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm11
|
||||
; SSE-NEXT: pcmpgtd %xmm7, %xmm3
|
||||
; SSE-NEXT: movdqa {{.*#+}} xmm7 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
|
||||
; SSE-NEXT: pshufb %xmm7, %xmm3
|
||||
; SSE-NEXT: packssdw %xmm0, %xmm3
|
||||
; SSE-NEXT: pcmpgtd %xmm6, %xmm2
|
||||
; SSE-NEXT: pshufb %xmm7, %xmm2
|
||||
; SSE-NEXT: packssdw %xmm0, %xmm2
|
||||
; SSE-NEXT: punpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm3[0]
|
||||
; SSE-NEXT: movdqa {{.*#+}} xmm3 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
|
||||
; SSE-NEXT: pshufb %xmm3, %xmm2
|
||||
; SSE-NEXT: pcmpgtd %xmm5, %xmm1
|
||||
; SSE-NEXT: pshufb %xmm7, %xmm1
|
||||
; SSE-NEXT: packssdw %xmm0, %xmm1
|
||||
; SSE-NEXT: pcmpgtd %xmm4, %xmm0
|
||||
; SSE-NEXT: pshufb %xmm7, %xmm0
|
||||
; SSE-NEXT: packssdw %xmm0, %xmm0
|
||||
; SSE-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; SSE-NEXT: pshufb %xmm3, %xmm0
|
||||
; SSE-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
|
||||
; SSE-NEXT: packsswb %xmm2, %xmm0
|
||||
; SSE-NEXT: pcmpgtd {{[0-9]+}}(%rsp), %xmm11
|
||||
; SSE-NEXT: pshufb %xmm7, %xmm11
|
||||
; SSE-NEXT: packssdw %xmm0, %xmm11
|
||||
; SSE-NEXT: pcmpgtd {{[0-9]+}}(%rsp), %xmm9
|
||||
; SSE-NEXT: pshufb %xmm7, %xmm9
|
||||
; SSE-NEXT: packssdw %xmm0, %xmm9
|
||||
; SSE-NEXT: punpcklqdq {{.*#+}} xmm9 = xmm9[0],xmm11[0]
|
||||
; SSE-NEXT: pshufb %xmm3, %xmm9
|
||||
; SSE-NEXT: pcmpgtd {{[0-9]+}}(%rsp), %xmm10
|
||||
; SSE-NEXT: pshufb %xmm7, %xmm10
|
||||
; SSE-NEXT: packssdw %xmm0, %xmm10
|
||||
; SSE-NEXT: pcmpgtd {{[0-9]+}}(%rsp), %xmm8
|
||||
; SSE-NEXT: pshufb %xmm7, %xmm8
|
||||
; SSE-NEXT: packssdw %xmm0, %xmm8
|
||||
; SSE-NEXT: punpcklqdq {{.*#+}} xmm8 = xmm8[0],xmm10[0]
|
||||
; SSE-NEXT: pshufb %xmm3, %xmm8
|
||||
; SSE-NEXT: punpcklqdq {{.*#+}} xmm8 = xmm8[0],xmm9[0]
|
||||
; SSE-NEXT: packsswb %xmm9, %xmm8
|
||||
; SSE-NEXT: pand %xmm0, %xmm8
|
||||
; SSE-NEXT: pmovmskb %xmm8, %eax
|
||||
; SSE-NEXT: # kill: %AX<def> %AX<kill> %EAX<kill>
|
||||
|
|
|
|||
|
|
@ -6,27 +6,18 @@
|
|||
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512vl,+avx512bw | FileCheck %s --check-prefixes=AVX512
|
||||
|
||||
define i8 @v8i16(<8 x i16> %a, <8 x i16> %b) {
|
||||
; SSE2-LABEL: v8i16:
|
||||
; SSE2: # BB#0:
|
||||
; SSE2-NEXT: pcmpgtw %xmm1, %xmm0
|
||||
; SSE2-NEXT: pand {{.*}}(%rip), %xmm0
|
||||
; SSE2-NEXT: packuswb %xmm0, %xmm0
|
||||
; SSE2-NEXT: pmovmskb %xmm0, %eax
|
||||
; SSE2-NEXT: # kill: %AL<def> %AL<kill> %EAX<kill>
|
||||
; SSE2-NEXT: retq
|
||||
;
|
||||
; SSSE3-LABEL: v8i16:
|
||||
; SSSE3: # BB#0:
|
||||
; SSSE3-NEXT: pcmpgtw %xmm1, %xmm0
|
||||
; SSSE3-NEXT: pshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
|
||||
; SSSE3-NEXT: pmovmskb %xmm0, %eax
|
||||
; SSSE3-NEXT: # kill: %AL<def> %AL<kill> %EAX<kill>
|
||||
; SSSE3-NEXT: retq
|
||||
; SSE2-SSSE3-LABEL: v8i16:
|
||||
; SSE2-SSSE3: # BB#0:
|
||||
; SSE2-SSSE3-NEXT: pcmpgtw %xmm1, %xmm0
|
||||
; SSE2-SSSE3-NEXT: packsswb %xmm0, %xmm0
|
||||
; SSE2-SSSE3-NEXT: pmovmskb %xmm0, %eax
|
||||
; SSE2-SSSE3-NEXT: # kill: %AL<def> %AL<kill> %EAX<kill>
|
||||
; SSE2-SSSE3-NEXT: retq
|
||||
;
|
||||
; AVX12-LABEL: v8i16:
|
||||
; AVX12: # BB#0:
|
||||
; AVX12-NEXT: vpcmpgtw %xmm1, %xmm0, %xmm0
|
||||
; AVX12-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
|
||||
; AVX12-NEXT: vpacksswb %xmm0, %xmm0, %xmm0
|
||||
; AVX12-NEXT: vpmovmskb %xmm0, %eax
|
||||
; AVX12-NEXT: # kill: %AL<def> %AL<kill> %EAX<kill>
|
||||
; AVX12-NEXT: retq
|
||||
|
|
@ -503,30 +494,17 @@ define i4 @v4i16(<4 x i16> %a, <4 x i16> %b) {
|
|||
}
|
||||
|
||||
define i8 @v8i8(<8 x i8> %a, <8 x i8> %b) {
|
||||
; SSE2-LABEL: v8i8:
|
||||
; SSE2: # BB#0:
|
||||
; SSE2-NEXT: psllw $8, %xmm1
|
||||
; SSE2-NEXT: psraw $8, %xmm1
|
||||
; SSE2-NEXT: psllw $8, %xmm0
|
||||
; SSE2-NEXT: psraw $8, %xmm0
|
||||
; SSE2-NEXT: pcmpgtw %xmm1, %xmm0
|
||||
; SSE2-NEXT: pand {{.*}}(%rip), %xmm0
|
||||
; SSE2-NEXT: packuswb %xmm0, %xmm0
|
||||
; SSE2-NEXT: pmovmskb %xmm0, %eax
|
||||
; SSE2-NEXT: # kill: %AL<def> %AL<kill> %EAX<kill>
|
||||
; SSE2-NEXT: retq
|
||||
;
|
||||
; SSSE3-LABEL: v8i8:
|
||||
; SSSE3: # BB#0:
|
||||
; SSSE3-NEXT: psllw $8, %xmm1
|
||||
; SSSE3-NEXT: psraw $8, %xmm1
|
||||
; SSSE3-NEXT: psllw $8, %xmm0
|
||||
; SSSE3-NEXT: psraw $8, %xmm0
|
||||
; SSSE3-NEXT: pcmpgtw %xmm1, %xmm0
|
||||
; SSSE3-NEXT: pshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
|
||||
; SSSE3-NEXT: pmovmskb %xmm0, %eax
|
||||
; SSSE3-NEXT: # kill: %AL<def> %AL<kill> %EAX<kill>
|
||||
; SSSE3-NEXT: retq
|
||||
; SSE2-SSSE3-LABEL: v8i8:
|
||||
; SSE2-SSSE3: # BB#0:
|
||||
; SSE2-SSSE3-NEXT: psllw $8, %xmm1
|
||||
; SSE2-SSSE3-NEXT: psraw $8, %xmm1
|
||||
; SSE2-SSSE3-NEXT: psllw $8, %xmm0
|
||||
; SSE2-SSSE3-NEXT: psraw $8, %xmm0
|
||||
; SSE2-SSSE3-NEXT: pcmpgtw %xmm1, %xmm0
|
||||
; SSE2-SSSE3-NEXT: packsswb %xmm0, %xmm0
|
||||
; SSE2-SSSE3-NEXT: pmovmskb %xmm0, %eax
|
||||
; SSE2-SSSE3-NEXT: # kill: %AL<def> %AL<kill> %EAX<kill>
|
||||
; SSE2-SSSE3-NEXT: retq
|
||||
;
|
||||
; AVX12-LABEL: v8i8:
|
||||
; AVX12: # BB#0:
|
||||
|
|
@ -535,7 +513,7 @@ define i8 @v8i8(<8 x i8> %a, <8 x i8> %b) {
|
|||
; AVX12-NEXT: vpsllw $8, %xmm0, %xmm0
|
||||
; AVX12-NEXT: vpsraw $8, %xmm0, %xmm0
|
||||
; AVX12-NEXT: vpcmpgtw %xmm1, %xmm0, %xmm0
|
||||
; AVX12-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
|
||||
; AVX12-NEXT: vpacksswb %xmm0, %xmm0, %xmm0
|
||||
; AVX12-NEXT: vpmovmskb %xmm0, %eax
|
||||
; AVX12-NEXT: # kill: %AL<def> %AL<kill> %EAX<kill>
|
||||
; AVX12-NEXT: retq
|
||||
|
|
|
|||
|
|
@ -464,20 +464,17 @@ define <8 x i16> @test13(<8 x i16> %x, <8 x i32> %y) nounwind {
|
|||
; SSE2-NEXT: movdqa {{.*#+}} xmm4 = [2147483648,2147483648,2147483648,2147483648]
|
||||
; SSE2-NEXT: movdqa %xmm0, %xmm5
|
||||
; SSE2-NEXT: psubd %xmm2, %xmm0
|
||||
; SSE2-NEXT: pxor %xmm4, %xmm2
|
||||
; SSE2-NEXT: movdqa %xmm2, %xmm6
|
||||
; SSE2-NEXT: pxor %xmm4, %xmm6
|
||||
; SSE2-NEXT: pxor %xmm4, %xmm5
|
||||
; SSE2-NEXT: pcmpgtd %xmm5, %xmm2
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm2 = xmm2[0,2,2,3,4,5,6,7]
|
||||
; SSE2-NEXT: pshufhw {{.*#+}} xmm2 = xmm2[0,1,2,3,4,6,6,7]
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm5 = xmm2[0,2,2,3]
|
||||
; SSE2-NEXT: pcmpgtd %xmm5, %xmm6
|
||||
; SSE2-NEXT: packssdw %xmm0, %xmm6
|
||||
; SSE2-NEXT: movdqa %xmm1, %xmm2
|
||||
; SSE2-NEXT: pxor %xmm4, %xmm2
|
||||
; SSE2-NEXT: pxor %xmm3, %xmm4
|
||||
; SSE2-NEXT: pcmpgtd %xmm4, %xmm2
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm2 = xmm2[0,2,2,3,4,5,6,7]
|
||||
; SSE2-NEXT: pshufhw {{.*#+}} xmm2 = xmm2[0,1,2,3,4,6,6,7]
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
|
||||
; SSE2-NEXT: punpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm5[0]
|
||||
; SSE2-NEXT: packssdw %xmm0, %xmm2
|
||||
; SSE2-NEXT: punpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm6[0]
|
||||
; SSE2-NEXT: psubd %xmm1, %xmm3
|
||||
; SSE2-NEXT: pslld $16, %xmm0
|
||||
; SSE2-NEXT: psrad $16, %xmm0
|
||||
|
|
@ -501,17 +498,17 @@ define <8 x i16> @test13(<8 x i16> %x, <8 x i32> %y) nounwind {
|
|||
; SSSE3-NEXT: pxor %xmm4, %xmm6
|
||||
; SSSE3-NEXT: pxor %xmm4, %xmm5
|
||||
; SSSE3-NEXT: pcmpgtd %xmm5, %xmm6
|
||||
; SSSE3-NEXT: movdqa {{.*#+}} xmm5 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
|
||||
; SSSE3-NEXT: pshufb %xmm5, %xmm6
|
||||
; SSSE3-NEXT: packssdw %xmm0, %xmm6
|
||||
; SSSE3-NEXT: movdqa %xmm1, %xmm2
|
||||
; SSSE3-NEXT: pxor %xmm4, %xmm2
|
||||
; SSSE3-NEXT: pxor %xmm3, %xmm4
|
||||
; SSSE3-NEXT: pcmpgtd %xmm4, %xmm2
|
||||
; SSSE3-NEXT: pshufb %xmm5, %xmm2
|
||||
; SSSE3-NEXT: packssdw %xmm0, %xmm2
|
||||
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm6[0]
|
||||
; SSSE3-NEXT: psubd %xmm1, %xmm3
|
||||
; SSSE3-NEXT: pshufb %xmm5, %xmm0
|
||||
; SSSE3-NEXT: pshufb %xmm5, %xmm3
|
||||
; SSSE3-NEXT: movdqa {{.*#+}} xmm1 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
|
||||
; SSSE3-NEXT: pshufb %xmm1, %xmm0
|
||||
; SSSE3-NEXT: pshufb %xmm1, %xmm3
|
||||
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm3 = xmm3[0],xmm0[0]
|
||||
; SSSE3-NEXT: pandn %xmm3, %xmm2
|
||||
; SSSE3-NEXT: movdqa %xmm2, %xmm0
|
||||
|
|
@ -529,15 +526,15 @@ define <8 x i16> @test13(<8 x i16> %x, <8 x i32> %y) nounwind {
|
|||
; SSE41-NEXT: pxor %xmm5, %xmm0
|
||||
; SSE41-NEXT: pxor %xmm5, %xmm6
|
||||
; SSE41-NEXT: pcmpgtd %xmm6, %xmm0
|
||||
; SSE41-NEXT: movdqa {{.*#+}} xmm1 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
|
||||
; SSE41-NEXT: pshufb %xmm1, %xmm0
|
||||
; SSE41-NEXT: movdqa %xmm2, %xmm6
|
||||
; SSE41-NEXT: pxor %xmm5, %xmm6
|
||||
; SSE41-NEXT: packssdw %xmm0, %xmm0
|
||||
; SSE41-NEXT: movdqa %xmm2, %xmm1
|
||||
; SSE41-NEXT: pxor %xmm5, %xmm1
|
||||
; SSE41-NEXT: pxor %xmm4, %xmm5
|
||||
; SSE41-NEXT: pcmpgtd %xmm5, %xmm6
|
||||
; SSE41-NEXT: pshufb %xmm1, %xmm6
|
||||
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm6[0]
|
||||
; SSE41-NEXT: pcmpgtd %xmm5, %xmm1
|
||||
; SSE41-NEXT: packssdw %xmm0, %xmm1
|
||||
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; SSE41-NEXT: psubd %xmm2, %xmm4
|
||||
; SSE41-NEXT: movdqa {{.*#+}} xmm1 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
|
||||
; SSE41-NEXT: pshufb %xmm1, %xmm3
|
||||
; SSE41-NEXT: pshufb %xmm1, %xmm4
|
||||
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm3 = xmm3[0],xmm4[0]
|
||||
|
|
@ -855,35 +852,30 @@ vector.ph:
|
|||
define <8 x i16> @test15(<8 x i16> %x, <8 x i32> %y) nounwind {
|
||||
; SSE2-LABEL: test15:
|
||||
; SSE2: # BB#0: # %vector.ph
|
||||
; SSE2-NEXT: pxor %xmm4, %xmm4
|
||||
; SSE2-NEXT: movdqa %xmm0, %xmm3
|
||||
; SSE2-NEXT: punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm4[0],xmm3[1],xmm4[1],xmm3[2],xmm4[2],xmm3[3],xmm4[3]
|
||||
; SSE2-NEXT: punpckhwd {{.*#+}} xmm0 = xmm0[4],xmm4[4],xmm0[5],xmm4[5],xmm0[6],xmm4[6],xmm0[7],xmm4[7]
|
||||
; SSE2-NEXT: pxor %xmm4, %xmm4
|
||||
; SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1],xmm0[2],xmm4[2],xmm0[3],xmm4[3]
|
||||
; SSE2-NEXT: punpckhwd {{.*#+}} xmm3 = xmm3[4],xmm4[4],xmm3[5],xmm4[5],xmm3[6],xmm4[6],xmm3[7],xmm4[7]
|
||||
; SSE2-NEXT: movdqa {{.*#+}} xmm4 = [2147483648,2147483648,2147483648,2147483648]
|
||||
; SSE2-NEXT: movdqa %xmm0, %xmm5
|
||||
; SSE2-NEXT: psubd %xmm2, %xmm0
|
||||
; SSE2-NEXT: movdqa %xmm3, %xmm5
|
||||
; SSE2-NEXT: psubd %xmm2, %xmm3
|
||||
; SSE2-NEXT: pxor %xmm4, %xmm2
|
||||
; SSE2-NEXT: pxor %xmm4, %xmm5
|
||||
; SSE2-NEXT: pcmpgtd %xmm2, %xmm5
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm2 = xmm5[0,2,2,3,4,5,6,7]
|
||||
; SSE2-NEXT: pshufhw {{.*#+}} xmm2 = xmm2[0,1,2,3,4,6,6,7]
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
|
||||
; SSE2-NEXT: movdqa %xmm1, %xmm5
|
||||
; SSE2-NEXT: pxor %xmm4, %xmm5
|
||||
; SSE2-NEXT: pxor %xmm3, %xmm4
|
||||
; SSE2-NEXT: pcmpgtd %xmm5, %xmm4
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm4 = xmm4[0,2,2,3,4,5,6,7]
|
||||
; SSE2-NEXT: pshufhw {{.*#+}} xmm4 = xmm4[0,1,2,3,4,6,6,7]
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm4[0,2,2,3]
|
||||
; SSE2-NEXT: punpcklqdq {{.*#+}} xmm4 = xmm4[0],xmm2[0]
|
||||
; SSE2-NEXT: psubd %xmm1, %xmm3
|
||||
; SSE2-NEXT: pslld $16, %xmm0
|
||||
; SSE2-NEXT: psrad $16, %xmm0
|
||||
; SSE2-NEXT: packssdw %xmm0, %xmm5
|
||||
; SSE2-NEXT: movdqa %xmm1, %xmm2
|
||||
; SSE2-NEXT: pxor %xmm4, %xmm2
|
||||
; SSE2-NEXT: pxor %xmm0, %xmm4
|
||||
; SSE2-NEXT: pcmpgtd %xmm2, %xmm4
|
||||
; SSE2-NEXT: packssdw %xmm0, %xmm4
|
||||
; SSE2-NEXT: punpcklqdq {{.*#+}} xmm4 = xmm4[0],xmm5[0]
|
||||
; SSE2-NEXT: psubd %xmm1, %xmm0
|
||||
; SSE2-NEXT: pslld $16, %xmm3
|
||||
; SSE2-NEXT: psrad $16, %xmm3
|
||||
; SSE2-NEXT: packssdw %xmm0, %xmm3
|
||||
; SSE2-NEXT: pand %xmm4, %xmm3
|
||||
; SSE2-NEXT: movdqa %xmm3, %xmm0
|
||||
; SSE2-NEXT: pslld $16, %xmm0
|
||||
; SSE2-NEXT: psrad $16, %xmm0
|
||||
; SSE2-NEXT: packssdw %xmm3, %xmm0
|
||||
; SSE2-NEXT: pand %xmm4, %xmm0
|
||||
; SSE2-NEXT: retq
|
||||
;
|
||||
; SSSE3-LABEL: test15:
|
||||
|
|
@ -898,17 +890,17 @@ define <8 x i16> @test15(<8 x i16> %x, <8 x i32> %y) nounwind {
|
|||
; SSSE3-NEXT: pxor %xmm4, %xmm2
|
||||
; SSSE3-NEXT: pxor %xmm4, %xmm5
|
||||
; SSSE3-NEXT: pcmpgtd %xmm2, %xmm5
|
||||
; SSSE3-NEXT: movdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
|
||||
; SSSE3-NEXT: pshufb %xmm2, %xmm5
|
||||
; SSSE3-NEXT: movdqa %xmm1, %xmm6
|
||||
; SSSE3-NEXT: pxor %xmm4, %xmm6
|
||||
; SSSE3-NEXT: packssdw %xmm0, %xmm5
|
||||
; SSSE3-NEXT: movdqa %xmm1, %xmm2
|
||||
; SSSE3-NEXT: pxor %xmm4, %xmm2
|
||||
; SSSE3-NEXT: pxor %xmm3, %xmm4
|
||||
; SSSE3-NEXT: pcmpgtd %xmm6, %xmm4
|
||||
; SSSE3-NEXT: pshufb %xmm2, %xmm4
|
||||
; SSSE3-NEXT: pcmpgtd %xmm2, %xmm4
|
||||
; SSSE3-NEXT: packssdw %xmm0, %xmm4
|
||||
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm4 = xmm4[0],xmm5[0]
|
||||
; SSSE3-NEXT: psubd %xmm1, %xmm3
|
||||
; SSSE3-NEXT: pshufb %xmm2, %xmm0
|
||||
; SSSE3-NEXT: pshufb %xmm2, %xmm3
|
||||
; SSSE3-NEXT: movdqa {{.*#+}} xmm1 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
|
||||
; SSSE3-NEXT: pshufb %xmm1, %xmm0
|
||||
; SSSE3-NEXT: pshufb %xmm1, %xmm3
|
||||
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm3 = xmm3[0],xmm0[0]
|
||||
; SSSE3-NEXT: pand %xmm4, %xmm3
|
||||
; SSSE3-NEXT: movdqa %xmm3, %xmm0
|
||||
|
|
@ -925,15 +917,15 @@ define <8 x i16> @test15(<8 x i16> %x, <8 x i32> %y) nounwind {
|
|||
; SSE41-NEXT: pxor %xmm4, %xmm1
|
||||
; SSE41-NEXT: pxor %xmm4, %xmm5
|
||||
; SSE41-NEXT: pcmpgtd %xmm1, %xmm5
|
||||
; SSE41-NEXT: movdqa {{.*#+}} xmm1 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
|
||||
; SSE41-NEXT: pshufb %xmm1, %xmm5
|
||||
; SSE41-NEXT: movdqa %xmm2, %xmm6
|
||||
; SSE41-NEXT: pxor %xmm4, %xmm6
|
||||
; SSE41-NEXT: packssdw %xmm0, %xmm5
|
||||
; SSE41-NEXT: movdqa %xmm2, %xmm1
|
||||
; SSE41-NEXT: pxor %xmm4, %xmm1
|
||||
; SSE41-NEXT: pxor %xmm3, %xmm4
|
||||
; SSE41-NEXT: pcmpgtd %xmm6, %xmm4
|
||||
; SSE41-NEXT: pshufb %xmm1, %xmm4
|
||||
; SSE41-NEXT: pcmpgtd %xmm1, %xmm4
|
||||
; SSE41-NEXT: packssdw %xmm0, %xmm4
|
||||
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm5 = xmm5[0],xmm4[0]
|
||||
; SSE41-NEXT: psubd %xmm2, %xmm3
|
||||
; SSE41-NEXT: movdqa {{.*#+}} xmm1 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
|
||||
; SSE41-NEXT: pshufb %xmm1, %xmm0
|
||||
; SSE41-NEXT: pshufb %xmm1, %xmm3
|
||||
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm3[0]
|
||||
|
|
@ -1000,35 +992,30 @@ vector.ph:
|
|||
define <8 x i16> @test16(<8 x i16> %x, <8 x i32> %y) nounwind {
|
||||
; SSE2-LABEL: test16:
|
||||
; SSE2: # BB#0: # %vector.ph
|
||||
; SSE2-NEXT: pxor %xmm4, %xmm4
|
||||
; SSE2-NEXT: movdqa %xmm0, %xmm3
|
||||
; SSE2-NEXT: punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm4[0],xmm3[1],xmm4[1],xmm3[2],xmm4[2],xmm3[3],xmm4[3]
|
||||
; SSE2-NEXT: punpckhwd {{.*#+}} xmm0 = xmm0[4],xmm4[4],xmm0[5],xmm4[5],xmm0[6],xmm4[6],xmm0[7],xmm4[7]
|
||||
; SSE2-NEXT: pxor %xmm4, %xmm4
|
||||
; SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1],xmm0[2],xmm4[2],xmm0[3],xmm4[3]
|
||||
; SSE2-NEXT: punpckhwd {{.*#+}} xmm3 = xmm3[4],xmm4[4],xmm3[5],xmm4[5],xmm3[6],xmm4[6],xmm3[7],xmm4[7]
|
||||
; SSE2-NEXT: movdqa {{.*#+}} xmm4 = [2147483648,2147483648,2147483648,2147483648]
|
||||
; SSE2-NEXT: movdqa %xmm0, %xmm5
|
||||
; SSE2-NEXT: psubd %xmm2, %xmm0
|
||||
; SSE2-NEXT: movdqa %xmm3, %xmm5
|
||||
; SSE2-NEXT: psubd %xmm2, %xmm3
|
||||
; SSE2-NEXT: pxor %xmm4, %xmm2
|
||||
; SSE2-NEXT: pxor %xmm4, %xmm5
|
||||
; SSE2-NEXT: pcmpgtd %xmm2, %xmm5
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm2 = xmm5[0,2,2,3,4,5,6,7]
|
||||
; SSE2-NEXT: pshufhw {{.*#+}} xmm2 = xmm2[0,1,2,3,4,6,6,7]
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
|
||||
; SSE2-NEXT: movdqa %xmm1, %xmm5
|
||||
; SSE2-NEXT: pxor %xmm4, %xmm5
|
||||
; SSE2-NEXT: pxor %xmm3, %xmm4
|
||||
; SSE2-NEXT: pcmpgtd %xmm5, %xmm4
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm4 = xmm4[0,2,2,3,4,5,6,7]
|
||||
; SSE2-NEXT: pshufhw {{.*#+}} xmm4 = xmm4[0,1,2,3,4,6,6,7]
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm4[0,2,2,3]
|
||||
; SSE2-NEXT: punpcklqdq {{.*#+}} xmm4 = xmm4[0],xmm2[0]
|
||||
; SSE2-NEXT: psubd %xmm1, %xmm3
|
||||
; SSE2-NEXT: pslld $16, %xmm0
|
||||
; SSE2-NEXT: psrad $16, %xmm0
|
||||
; SSE2-NEXT: packssdw %xmm0, %xmm5
|
||||
; SSE2-NEXT: movdqa %xmm1, %xmm2
|
||||
; SSE2-NEXT: pxor %xmm4, %xmm2
|
||||
; SSE2-NEXT: pxor %xmm0, %xmm4
|
||||
; SSE2-NEXT: pcmpgtd %xmm2, %xmm4
|
||||
; SSE2-NEXT: packssdw %xmm0, %xmm4
|
||||
; SSE2-NEXT: punpcklqdq {{.*#+}} xmm4 = xmm4[0],xmm5[0]
|
||||
; SSE2-NEXT: psubd %xmm1, %xmm0
|
||||
; SSE2-NEXT: pslld $16, %xmm3
|
||||
; SSE2-NEXT: psrad $16, %xmm3
|
||||
; SSE2-NEXT: packssdw %xmm0, %xmm3
|
||||
; SSE2-NEXT: pand %xmm4, %xmm3
|
||||
; SSE2-NEXT: movdqa %xmm3, %xmm0
|
||||
; SSE2-NEXT: pslld $16, %xmm0
|
||||
; SSE2-NEXT: psrad $16, %xmm0
|
||||
; SSE2-NEXT: packssdw %xmm3, %xmm0
|
||||
; SSE2-NEXT: pand %xmm4, %xmm0
|
||||
; SSE2-NEXT: retq
|
||||
;
|
||||
; SSSE3-LABEL: test16:
|
||||
|
|
@ -1043,17 +1030,17 @@ define <8 x i16> @test16(<8 x i16> %x, <8 x i32> %y) nounwind {
|
|||
; SSSE3-NEXT: pxor %xmm4, %xmm2
|
||||
; SSSE3-NEXT: pxor %xmm4, %xmm5
|
||||
; SSSE3-NEXT: pcmpgtd %xmm2, %xmm5
|
||||
; SSSE3-NEXT: movdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
|
||||
; SSSE3-NEXT: pshufb %xmm2, %xmm5
|
||||
; SSSE3-NEXT: movdqa %xmm1, %xmm6
|
||||
; SSSE3-NEXT: pxor %xmm4, %xmm6
|
||||
; SSSE3-NEXT: packssdw %xmm0, %xmm5
|
||||
; SSSE3-NEXT: movdqa %xmm1, %xmm2
|
||||
; SSSE3-NEXT: pxor %xmm4, %xmm2
|
||||
; SSSE3-NEXT: pxor %xmm3, %xmm4
|
||||
; SSSE3-NEXT: pcmpgtd %xmm6, %xmm4
|
||||
; SSSE3-NEXT: pshufb %xmm2, %xmm4
|
||||
; SSSE3-NEXT: pcmpgtd %xmm2, %xmm4
|
||||
; SSSE3-NEXT: packssdw %xmm0, %xmm4
|
||||
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm4 = xmm4[0],xmm5[0]
|
||||
; SSSE3-NEXT: psubd %xmm1, %xmm3
|
||||
; SSSE3-NEXT: pshufb %xmm2, %xmm0
|
||||
; SSSE3-NEXT: pshufb %xmm2, %xmm3
|
||||
; SSSE3-NEXT: movdqa {{.*#+}} xmm1 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
|
||||
; SSSE3-NEXT: pshufb %xmm1, %xmm0
|
||||
; SSSE3-NEXT: pshufb %xmm1, %xmm3
|
||||
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm3 = xmm3[0],xmm0[0]
|
||||
; SSSE3-NEXT: pand %xmm4, %xmm3
|
||||
; SSSE3-NEXT: movdqa %xmm3, %xmm0
|
||||
|
|
@ -1070,15 +1057,15 @@ define <8 x i16> @test16(<8 x i16> %x, <8 x i32> %y) nounwind {
|
|||
; SSE41-NEXT: pxor %xmm4, %xmm1
|
||||
; SSE41-NEXT: pxor %xmm4, %xmm5
|
||||
; SSE41-NEXT: pcmpgtd %xmm1, %xmm5
|
||||
; SSE41-NEXT: movdqa {{.*#+}} xmm1 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
|
||||
; SSE41-NEXT: pshufb %xmm1, %xmm5
|
||||
; SSE41-NEXT: movdqa %xmm2, %xmm6
|
||||
; SSE41-NEXT: pxor %xmm4, %xmm6
|
||||
; SSE41-NEXT: packssdw %xmm0, %xmm5
|
||||
; SSE41-NEXT: movdqa %xmm2, %xmm1
|
||||
; SSE41-NEXT: pxor %xmm4, %xmm1
|
||||
; SSE41-NEXT: pxor %xmm3, %xmm4
|
||||
; SSE41-NEXT: pcmpgtd %xmm6, %xmm4
|
||||
; SSE41-NEXT: pshufb %xmm1, %xmm4
|
||||
; SSE41-NEXT: pcmpgtd %xmm1, %xmm4
|
||||
; SSE41-NEXT: packssdw %xmm0, %xmm4
|
||||
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm5 = xmm5[0],xmm4[0]
|
||||
; SSE41-NEXT: psubd %xmm2, %xmm3
|
||||
; SSE41-NEXT: movdqa {{.*#+}} xmm1 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
|
||||
; SSE41-NEXT: pshufb %xmm1, %xmm0
|
||||
; SSE41-NEXT: pshufb %xmm1, %xmm3
|
||||
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm3[0]
|
||||
|
|
|
|||
|
|
@ -88,7 +88,8 @@ define void @shuffle_v16i16_to_v8i16_1(<16 x i16>* %L, <8 x i16>* %S) nounwind {
|
|||
; AVX2-LABEL: shuffle_v16i16_to_v8i16_1:
|
||||
; AVX2: # BB#0:
|
||||
; AVX2-NEXT: vmovdqa (%rdi), %ymm0
|
||||
; AVX2-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[2,3,6,7,10,11,14,15,10,11,14,15,14,15],zero,zero,ymm0[18,19,22,23,26,27,30,31,26,27,30,31,30,31],zero,zero
|
||||
; AVX2-NEXT: vpsrld $16, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpackusdw %ymm0, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
|
||||
; AVX2-NEXT: vmovdqa %xmm0, (%rsi)
|
||||
; AVX2-NEXT: vzeroupper
|
||||
|
|
|
|||
|
|
@ -886,16 +886,11 @@ define <32 x i1> @test_cmp_v32i16(<32 x i16> %a0, <32 x i16> %a1) nounwind {
|
|||
; SSE2-LABEL: test_cmp_v32i16:
|
||||
; SSE2: # BB#0:
|
||||
; SSE2-NEXT: pcmpgtw %xmm5, %xmm1
|
||||
; SSE2-NEXT: movdqa {{.*#+}} xmm5 = [255,255,255,255,255,255,255,255]
|
||||
; SSE2-NEXT: pand %xmm5, %xmm1
|
||||
; SSE2-NEXT: pcmpgtw %xmm4, %xmm0
|
||||
; SSE2-NEXT: pand %xmm5, %xmm0
|
||||
; SSE2-NEXT: packuswb %xmm1, %xmm0
|
||||
; SSE2-NEXT: packsswb %xmm1, %xmm0
|
||||
; SSE2-NEXT: pcmpgtw %xmm7, %xmm3
|
||||
; SSE2-NEXT: pand %xmm5, %xmm3
|
||||
; SSE2-NEXT: pcmpgtw %xmm6, %xmm2
|
||||
; SSE2-NEXT: pand %xmm5, %xmm2
|
||||
; SSE2-NEXT: packuswb %xmm3, %xmm2
|
||||
; SSE2-NEXT: packsswb %xmm3, %xmm2
|
||||
; SSE2-NEXT: movdqa %xmm2, -{{[0-9]+}}(%rsp)
|
||||
; SSE2-NEXT: movb -{{[0-9]+}}(%rsp), %al
|
||||
; SSE2-NEXT: andb $1, %al
|
||||
|
|
@ -3410,48 +3405,27 @@ define <32 x i1> @test_cmp_v32i32(<32 x i32> %a0, <32 x i32> %a1) nounwind {
|
|||
; SSE2-LABEL: test_cmp_v32i32:
|
||||
; SSE2: # BB#0:
|
||||
; SSE2-NEXT: pcmpgtd {{[0-9]+}}(%rsp), %xmm3
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm3 = xmm3[0,2,2,3,4,5,6,7]
|
||||
; SSE2-NEXT: pshufhw {{.*#+}} xmm3 = xmm3[0,1,2,3,4,6,6,7]
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm3[0,2,2,3]
|
||||
; SSE2-NEXT: packssdw %xmm0, %xmm3
|
||||
; SSE2-NEXT: pcmpgtd {{[0-9]+}}(%rsp), %xmm2
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm2 = xmm2[0,2,2,3,4,5,6,7]
|
||||
; SSE2-NEXT: pshufhw {{.*#+}} xmm2 = xmm2[0,1,2,3,4,6,6,7]
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
|
||||
; SSE2-NEXT: packssdw %xmm0, %xmm2
|
||||
; SSE2-NEXT: punpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm3[0]
|
||||
; SSE2-NEXT: movdqa {{.*#+}} xmm3 = [255,255,255,255,255,255,255,255]
|
||||
; SSE2-NEXT: pand %xmm3, %xmm2
|
||||
; SSE2-NEXT: pcmpgtd {{[0-9]+}}(%rsp), %xmm1
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
|
||||
; SSE2-NEXT: pshufhw {{.*#+}} xmm1 = xmm1[0,1,2,3,4,6,6,7]
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
|
||||
; SSE2-NEXT: packssdw %xmm0, %xmm1
|
||||
; SSE2-NEXT: pcmpgtd {{[0-9]+}}(%rsp), %xmm0
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7]
|
||||
; SSE2-NEXT: pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,4,6,6,7]
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
|
||||
; SSE2-NEXT: packssdw %xmm0, %xmm0
|
||||
; SSE2-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; SSE2-NEXT: pand %xmm3, %xmm0
|
||||
; SSE2-NEXT: packuswb %xmm2, %xmm0
|
||||
; SSE2-NEXT: packsswb %xmm2, %xmm0
|
||||
; SSE2-NEXT: pcmpgtd {{[0-9]+}}(%rsp), %xmm7
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm1 = xmm7[0,2,2,3,4,5,6,7]
|
||||
; SSE2-NEXT: pshufhw {{.*#+}} xmm1 = xmm1[0,1,2,3,4,6,6,7]
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
|
||||
; SSE2-NEXT: packssdw %xmm0, %xmm7
|
||||
; SSE2-NEXT: pcmpgtd {{[0-9]+}}(%rsp), %xmm6
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm2 = xmm6[0,2,2,3,4,5,6,7]
|
||||
; SSE2-NEXT: pshufhw {{.*#+}} xmm2 = xmm2[0,1,2,3,4,6,6,7]
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
|
||||
; SSE2-NEXT: punpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm1[0]
|
||||
; SSE2-NEXT: pand %xmm3, %xmm2
|
||||
; SSE2-NEXT: packssdw %xmm0, %xmm6
|
||||
; SSE2-NEXT: punpcklqdq {{.*#+}} xmm6 = xmm6[0],xmm7[0]
|
||||
; SSE2-NEXT: pcmpgtd {{[0-9]+}}(%rsp), %xmm5
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm1 = xmm5[0,2,2,3,4,5,6,7]
|
||||
; SSE2-NEXT: pshufhw {{.*#+}} xmm1 = xmm1[0,1,2,3,4,6,6,7]
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
|
||||
; SSE2-NEXT: packssdw %xmm0, %xmm5
|
||||
; SSE2-NEXT: pcmpgtd {{[0-9]+}}(%rsp), %xmm4
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm4 = xmm4[0,2,2,3,4,5,6,7]
|
||||
; SSE2-NEXT: pshufhw {{.*#+}} xmm4 = xmm4[0,1,2,3,4,6,6,7]
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm4[0,2,2,3]
|
||||
; SSE2-NEXT: punpcklqdq {{.*#+}} xmm4 = xmm4[0],xmm1[0]
|
||||
; SSE2-NEXT: pand %xmm3, %xmm4
|
||||
; SSE2-NEXT: packuswb %xmm2, %xmm4
|
||||
; SSE2-NEXT: packssdw %xmm0, %xmm4
|
||||
; SSE2-NEXT: punpcklqdq {{.*#+}} xmm4 = xmm4[0],xmm5[0]
|
||||
; SSE2-NEXT: packsswb %xmm6, %xmm4
|
||||
; SSE2-NEXT: movdqa %xmm4, -{{[0-9]+}}(%rsp)
|
||||
; SSE2-NEXT: movb -{{[0-9]+}}(%rsp), %al
|
||||
; SSE2-NEXT: andb $1, %al
|
||||
|
|
@ -3555,107 +3529,121 @@ define <32 x i1> @test_cmp_v32i32(<32 x i32> %a0, <32 x i32> %a1) nounwind {
|
|||
;
|
||||
; SSE42-LABEL: test_cmp_v32i32:
|
||||
; SSE42: # BB#0:
|
||||
; SSE42-NEXT: pcmpgtd {{[0-9]+}}(%rsp), %xmm0
|
||||
; SSE42-NEXT: pcmpgtd {{[0-9]+}}(%rsp), %xmm1
|
||||
; SSE42-NEXT: pcmpgtd {{[0-9]+}}(%rsp), %xmm2
|
||||
; SSE42-NEXT: pcmpgtd {{[0-9]+}}(%rsp), %xmm3
|
||||
; SSE42-NEXT: pcmpgtd {{[0-9]+}}(%rsp), %xmm4
|
||||
; SSE42-NEXT: pcmpgtd {{[0-9]+}}(%rsp), %xmm5
|
||||
; SSE42-NEXT: pcmpgtd {{[0-9]+}}(%rsp), %xmm6
|
||||
; SSE42-NEXT: packssdw %xmm0, %xmm3
|
||||
; SSE42-NEXT: pcmpgtd {{[0-9]+}}(%rsp), %xmm2
|
||||
; SSE42-NEXT: packssdw %xmm0, %xmm2
|
||||
; SSE42-NEXT: punpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm3[0]
|
||||
; SSE42-NEXT: pcmpgtd {{[0-9]+}}(%rsp), %xmm1
|
||||
; SSE42-NEXT: packssdw %xmm0, %xmm1
|
||||
; SSE42-NEXT: pcmpgtd {{[0-9]+}}(%rsp), %xmm0
|
||||
; SSE42-NEXT: packssdw %xmm0, %xmm0
|
||||
; SSE42-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; SSE42-NEXT: packsswb %xmm2, %xmm0
|
||||
; SSE42-NEXT: pcmpgtd {{[0-9]+}}(%rsp), %xmm7
|
||||
; SSE42-NEXT: pextrb $12, %xmm7, %eax
|
||||
; SSE42-NEXT: packssdw %xmm0, %xmm7
|
||||
; SSE42-NEXT: pcmpgtd {{[0-9]+}}(%rsp), %xmm6
|
||||
; SSE42-NEXT: packssdw %xmm0, %xmm6
|
||||
; SSE42-NEXT: punpcklqdq {{.*#+}} xmm6 = xmm6[0],xmm7[0]
|
||||
; SSE42-NEXT: pcmpgtd {{[0-9]+}}(%rsp), %xmm5
|
||||
; SSE42-NEXT: packssdw %xmm0, %xmm5
|
||||
; SSE42-NEXT: pcmpgtd {{[0-9]+}}(%rsp), %xmm4
|
||||
; SSE42-NEXT: packssdw %xmm0, %xmm4
|
||||
; SSE42-NEXT: punpcklqdq {{.*#+}} xmm4 = xmm4[0],xmm5[0]
|
||||
; SSE42-NEXT: packsswb %xmm6, %xmm4
|
||||
; SSE42-NEXT: pextrb $15, %xmm4, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $8, %xmm7, %eax
|
||||
; SSE42-NEXT: pextrb $14, %xmm4, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $4, %xmm7, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $0, %xmm7, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $12, %xmm6, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $8, %xmm6, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $4, %xmm6, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $0, %xmm6, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $12, %xmm5, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $8, %xmm5, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $4, %xmm5, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $0, %xmm5, %eax
|
||||
; SSE42-NEXT: pextrb $13, %xmm4, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $12, %xmm4, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $11, %xmm4, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $10, %xmm4, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $9, %xmm4, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $8, %xmm4, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $7, %xmm4, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $6, %xmm4, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $5, %xmm4, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $4, %xmm4, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $3, %xmm4, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $2, %xmm4, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $1, %xmm4, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $0, %xmm4, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $12, %xmm3, %eax
|
||||
; SSE42-NEXT: pextrb $15, %xmm0, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $8, %xmm3, %eax
|
||||
; SSE42-NEXT: pextrb $14, %xmm0, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $4, %xmm3, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $0, %xmm3, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $12, %xmm2, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $8, %xmm2, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $4, %xmm2, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $0, %xmm2, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $12, %xmm1, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $8, %xmm1, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $4, %xmm1, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $0, %xmm1, %eax
|
||||
; SSE42-NEXT: pextrb $13, %xmm0, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $12, %xmm0, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $11, %xmm0, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $10, %xmm0, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $9, %xmm0, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $8, %xmm0, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $7, %xmm0, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $6, %xmm0, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $5, %xmm0, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $4, %xmm0, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $3, %xmm0, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $2, %xmm0, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $1, %xmm0, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $0, %xmm0, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
|
|
@ -4365,26 +4353,17 @@ define <64 x i1> @test_cmp_v64i16(<64 x i16> %a0, <64 x i16> %a1) nounwind {
|
|||
; SSE2-LABEL: test_cmp_v64i16:
|
||||
; SSE2: # BB#0:
|
||||
; SSE2-NEXT: pcmpgtw {{[0-9]+}}(%rsp), %xmm1
|
||||
; SSE2-NEXT: movdqa {{.*#+}} xmm8 = [255,255,255,255,255,255,255,255]
|
||||
; SSE2-NEXT: pand %xmm8, %xmm1
|
||||
; SSE2-NEXT: pcmpgtw {{[0-9]+}}(%rsp), %xmm0
|
||||
; SSE2-NEXT: pand %xmm8, %xmm0
|
||||
; SSE2-NEXT: packuswb %xmm1, %xmm0
|
||||
; SSE2-NEXT: packsswb %xmm1, %xmm0
|
||||
; SSE2-NEXT: pcmpgtw {{[0-9]+}}(%rsp), %xmm3
|
||||
; SSE2-NEXT: pand %xmm8, %xmm3
|
||||
; SSE2-NEXT: pcmpgtw {{[0-9]+}}(%rsp), %xmm2
|
||||
; SSE2-NEXT: pand %xmm8, %xmm2
|
||||
; SSE2-NEXT: packuswb %xmm3, %xmm2
|
||||
; SSE2-NEXT: packsswb %xmm3, %xmm2
|
||||
; SSE2-NEXT: pcmpgtw {{[0-9]+}}(%rsp), %xmm5
|
||||
; SSE2-NEXT: pand %xmm8, %xmm5
|
||||
; SSE2-NEXT: pcmpgtw {{[0-9]+}}(%rsp), %xmm4
|
||||
; SSE2-NEXT: pand %xmm8, %xmm4
|
||||
; SSE2-NEXT: packuswb %xmm5, %xmm4
|
||||
; SSE2-NEXT: packsswb %xmm5, %xmm4
|
||||
; SSE2-NEXT: pcmpgtw {{[0-9]+}}(%rsp), %xmm7
|
||||
; SSE2-NEXT: pand %xmm8, %xmm7
|
||||
; SSE2-NEXT: pcmpgtw {{[0-9]+}}(%rsp), %xmm6
|
||||
; SSE2-NEXT: pand %xmm8, %xmm6
|
||||
; SSE2-NEXT: packuswb %xmm7, %xmm6
|
||||
; SSE2-NEXT: packsswb %xmm7, %xmm6
|
||||
; SSE2-NEXT: movdqa %xmm6, -{{[0-9]+}}(%rsp)
|
||||
; SSE2-NEXT: movb -{{[0-9]+}}(%rsp), %al
|
||||
; SSE2-NEXT: andb $1, %al
|
||||
|
|
@ -9358,123 +9337,157 @@ define <32 x i1> @test_cmp_v32i64(<32 x i64> %a0, <32 x i64> %a1) nounwind {
|
|||
;
|
||||
; SSE42-LABEL: test_cmp_v32i64:
|
||||
; SSE42: # BB#0:
|
||||
; SSE42-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm15
|
||||
; SSE42-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm14
|
||||
; SSE42-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm13
|
||||
; SSE42-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm12
|
||||
; SSE42-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm11
|
||||
; SSE42-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm10
|
||||
; SSE42-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm9
|
||||
; SSE42-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm11
|
||||
; SSE42-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm8
|
||||
; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm0
|
||||
; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm1
|
||||
; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm2
|
||||
; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm3
|
||||
; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm4
|
||||
; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm5
|
||||
; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm6
|
||||
; SSE42-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm14
|
||||
; SSE42-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm13
|
||||
; SSE42-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm15
|
||||
; SSE42-NEXT: movdqa {{[0-9]+}}(%rsp), %xmm12
|
||||
; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm7
|
||||
; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm8
|
||||
; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm9
|
||||
; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm10
|
||||
; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm11
|
||||
; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm6
|
||||
; SSE42-NEXT: shufps {{.*#+}} xmm6 = xmm6[0,2],xmm7[0,2]
|
||||
; SSE42-NEXT: movdqa {{.*#+}} xmm7 = [0,1,4,5,4,5,6,7,0,1,4,5,8,9,12,13]
|
||||
; SSE42-NEXT: pshufb %xmm7, %xmm6
|
||||
; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm5
|
||||
; SSE42-NEXT: pshufd {{.*#+}} xmm5 = xmm5[0,2,2,3]
|
||||
; SSE42-NEXT: pshuflw {{.*#+}} xmm5 = xmm5[0,2,2,3,4,5,6,7]
|
||||
; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm4
|
||||
; SSE42-NEXT: pshufd {{.*#+}} xmm4 = xmm4[0,2,2,3]
|
||||
; SSE42-NEXT: pshuflw {{.*#+}} xmm4 = xmm4[0,2,2,3,4,5,6,7]
|
||||
; SSE42-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm5[0],xmm4[1],xmm5[1]
|
||||
; SSE42-NEXT: pblendw {{.*#+}} xmm4 = xmm4[0,1,2,3],xmm6[4,5,6,7]
|
||||
; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm3
|
||||
; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm2
|
||||
; SSE42-NEXT: shufps {{.*#+}} xmm2 = xmm2[0,2],xmm3[0,2]
|
||||
; SSE42-NEXT: pshufb %xmm7, %xmm2
|
||||
; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm1
|
||||
; SSE42-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
|
||||
; SSE42-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
|
||||
; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm0
|
||||
; SSE42-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
|
||||
; SSE42-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7]
|
||||
; SSE42-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
|
||||
; SSE42-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm2[4,5,6,7]
|
||||
; SSE42-NEXT: packsswb %xmm4, %xmm0
|
||||
; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm12
|
||||
; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm13
|
||||
; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm14
|
||||
; SSE42-NEXT: movdqa {{.*#+}} xmm1 = [0,1,8,9,2,3,10,11,8,9,12,13,10,11,14,15]
|
||||
; SSE42-NEXT: pshufb %xmm1, %xmm12
|
||||
; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm15
|
||||
; SSE42-NEXT: pextrb $8, %xmm15, %eax
|
||||
; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm13
|
||||
; SSE42-NEXT: shufps {{.*#+}} xmm13 = xmm13[0,2],xmm15[0,2]
|
||||
; SSE42-NEXT: pshufb %xmm7, %xmm13
|
||||
; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm14
|
||||
; SSE42-NEXT: pshufd {{.*#+}} xmm2 = xmm14[0,2,2,3]
|
||||
; SSE42-NEXT: pshuflw {{.*#+}} xmm2 = xmm2[0,1,0,2,4,5,6,7]
|
||||
; SSE42-NEXT: pblendw {{.*#+}} xmm2 = xmm2[0,1,2,3],xmm13[4,5,6,7]
|
||||
; SSE42-NEXT: pblendw {{.*#+}} xmm2 = xmm12[0,1],xmm2[2,3,4,5,6,7]
|
||||
; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm8
|
||||
; SSE42-NEXT: pshufb %xmm1, %xmm8
|
||||
; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm11
|
||||
; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm9
|
||||
; SSE42-NEXT: shufps {{.*#+}} xmm9 = xmm9[0,2],xmm11[0,2]
|
||||
; SSE42-NEXT: pshufb %xmm7, %xmm9
|
||||
; SSE42-NEXT: pcmpgtq {{[0-9]+}}(%rsp), %xmm10
|
||||
; SSE42-NEXT: pshufd {{.*#+}} xmm1 = xmm10[0,2,2,3]
|
||||
; SSE42-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[0,1,0,2,4,5,6,7]
|
||||
; SSE42-NEXT: pblendw {{.*#+}} xmm1 = xmm1[0,1,2,3],xmm9[4,5,6,7]
|
||||
; SSE42-NEXT: pblendw {{.*#+}} xmm1 = xmm8[0,1],xmm1[2,3,4,5,6,7]
|
||||
; SSE42-NEXT: packsswb %xmm2, %xmm1
|
||||
; SSE42-NEXT: pextrb $15, %xmm1, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $0, %xmm15, %eax
|
||||
; SSE42-NEXT: pextrb $14, %xmm1, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $8, %xmm14, %eax
|
||||
; SSE42-NEXT: pextrb $13, %xmm1, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $0, %xmm14, %eax
|
||||
; SSE42-NEXT: pextrb $12, %xmm1, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $8, %xmm13, %eax
|
||||
; SSE42-NEXT: pextrb $11, %xmm1, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $0, %xmm13, %eax
|
||||
; SSE42-NEXT: pextrb $10, %xmm1, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $8, %xmm12, %eax
|
||||
; SSE42-NEXT: pextrb $9, %xmm1, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $0, %xmm12, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $8, %xmm11, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $0, %xmm11, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $8, %xmm10, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $0, %xmm10, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $8, %xmm9, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $0, %xmm9, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $8, %xmm8, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $0, %xmm8, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $8, %xmm7, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $0, %xmm7, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $8, %xmm6, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $0, %xmm6, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $8, %xmm5, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $0, %xmm5, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $8, %xmm4, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $0, %xmm4, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $8, %xmm3, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $0, %xmm3, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $8, %xmm2, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $0, %xmm2, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $8, %xmm1, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $7, %xmm1, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $6, %xmm1, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $5, %xmm1, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $4, %xmm1, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $3, %xmm1, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $2, %xmm1, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $1, %xmm1, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $0, %xmm1, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $15, %xmm0, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $14, %xmm0, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $13, %xmm0, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $12, %xmm0, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $11, %xmm0, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $10, %xmm0, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $9, %xmm0, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $8, %xmm0, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $7, %xmm0, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $6, %xmm0, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $5, %xmm0, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $4, %xmm0, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $3, %xmm0, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $2, %xmm0, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $1, %xmm0, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: pextrb $0, %xmm0, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
|
|
|
|||
|
|
@ -320,7 +320,7 @@ define <8 x i16> @var_shift_v8i16(<8 x i16> %a, <8 x i16> %b) nounwind {
|
|||
; AVX2-NEXT: vpmovzxwd {{.*#+}} ymm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero
|
||||
; AVX2-NEXT: vpmovsxwd %xmm0, %ymm0
|
||||
; AVX2-NEXT: vpsravd %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
|
||||
; AVX2-NEXT: vpackssdw %ymm0, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
|
||||
; AVX2-NEXT: # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
|
||||
; AVX2-NEXT: vzeroupper
|
||||
|
|
@ -1253,7 +1253,7 @@ define <8 x i16> @constant_shift_v8i16(<8 x i16> %a) nounwind {
|
|||
; AVX2: # BB#0:
|
||||
; AVX2-NEXT: vpmovsxwd %xmm0, %ymm0
|
||||
; AVX2-NEXT: vpsravd {{.*}}(%rip), %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
|
||||
; AVX2-NEXT: vpackssdw %ymm0, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
|
||||
; AVX2-NEXT: # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
|
||||
; AVX2-NEXT: vzeroupper
|
||||
|
|
|
|||
|
|
@ -398,9 +398,8 @@ define <8 x i16> @trunc8i32_8i16_ashr(<8 x i32> %a) {
|
|||
; SSSE3: # BB#0: # %entry
|
||||
; SSSE3-NEXT: psrad $16, %xmm0
|
||||
; SSSE3-NEXT: psrad $16, %xmm1
|
||||
; SSSE3-NEXT: movdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
|
||||
; SSSE3-NEXT: pshufb %xmm2, %xmm1
|
||||
; SSSE3-NEXT: pshufb %xmm2, %xmm0
|
||||
; SSSE3-NEXT: packssdw %xmm0, %xmm1
|
||||
; SSSE3-NEXT: packssdw %xmm0, %xmm0
|
||||
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; SSSE3-NEXT: retq
|
||||
;
|
||||
|
|
@ -408,9 +407,8 @@ define <8 x i16> @trunc8i32_8i16_ashr(<8 x i32> %a) {
|
|||
; SSE41: # BB#0: # %entry
|
||||
; SSE41-NEXT: psrad $16, %xmm0
|
||||
; SSE41-NEXT: psrad $16, %xmm1
|
||||
; SSE41-NEXT: movdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
|
||||
; SSE41-NEXT: pshufb %xmm2, %xmm1
|
||||
; SSE41-NEXT: pshufb %xmm2, %xmm0
|
||||
; SSE41-NEXT: packssdw %xmm0, %xmm1
|
||||
; SSE41-NEXT: packssdw %xmm0, %xmm0
|
||||
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; SSE41-NEXT: retq
|
||||
;
|
||||
|
|
@ -419,9 +417,8 @@ define <8 x i16> @trunc8i32_8i16_ashr(<8 x i32> %a) {
|
|||
; AVX1-NEXT: vpsrad $16, %xmm0, %xmm1
|
||||
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
|
||||
; AVX1-NEXT: vpsrad $16, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
|
||||
; AVX1-NEXT: vpshufb %xmm2, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpshufb %xmm2, %xmm1, %xmm1
|
||||
; AVX1-NEXT: vpackssdw %xmm0, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpackssdw %xmm0, %xmm1, %xmm1
|
||||
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
|
||||
; AVX1-NEXT: vzeroupper
|
||||
; AVX1-NEXT: retq
|
||||
|
|
@ -429,7 +426,7 @@ define <8 x i16> @trunc8i32_8i16_ashr(<8 x i32> %a) {
|
|||
; AVX2-LABEL: trunc8i32_8i16_ashr:
|
||||
; AVX2: # BB#0: # %entry
|
||||
; AVX2-NEXT: vpsrad $16, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
|
||||
; AVX2-NEXT: vpackssdw %ymm0, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
|
||||
; AVX2-NEXT: # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
|
||||
; AVX2-NEXT: vzeroupper
|
||||
|
|
@ -492,25 +489,26 @@ define <8 x i16> @trunc8i32_8i16_lshr(<8 x i32> %a) {
|
|||
;
|
||||
; SSE41-LABEL: trunc8i32_8i16_lshr:
|
||||
; SSE41: # BB#0: # %entry
|
||||
; SSE41-NEXT: movdqa {{.*#+}} xmm2 = [2,3,6,7,10,11,14,15,10,11,14,15,14,15,255,255]
|
||||
; SSE41-NEXT: pshufb %xmm2, %xmm1
|
||||
; SSE41-NEXT: pshufb %xmm2, %xmm0
|
||||
; SSE41-NEXT: psrld $16, %xmm0
|
||||
; SSE41-NEXT: psrld $16, %xmm1
|
||||
; SSE41-NEXT: packusdw %xmm0, %xmm1
|
||||
; SSE41-NEXT: packusdw %xmm0, %xmm0
|
||||
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; SSE41-NEXT: retq
|
||||
;
|
||||
; AVX1-LABEL: trunc8i32_8i16_lshr:
|
||||
; AVX1: # BB#0: # %entry
|
||||
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
|
||||
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = [2,3,6,7,10,11,14,15,10,11,14,15,14,15,255,255]
|
||||
; AVX1-NEXT: vpshufb %xmm2, %xmm1, %xmm1
|
||||
; AVX1-NEXT: vpshufb %xmm2, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; AVX1-NEXT: vpsrld $16, %xmm1, %xmm1
|
||||
; AVX1-NEXT: vpsrld $16, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpackusdw %xmm1, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vzeroupper
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX2-LABEL: trunc8i32_8i16_lshr:
|
||||
; AVX2: # BB#0: # %entry
|
||||
; AVX2-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[2,3,6,7,10,11,14,15,10,11,14,15,14,15],zero,zero,ymm0[18,19,22,23,26,27,30,31,26,27,30,31,30,31],zero,zero
|
||||
; AVX2-NEXT: vpsrld $16, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpackusdw %ymm0, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
|
||||
; AVX2-NEXT: # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
|
||||
; AVX2-NEXT: vzeroupper
|
||||
|
|
@ -786,10 +784,9 @@ define void @trunc16i32_16i16_ashr(<16 x i32> %a) {
|
|||
; AVX2: # BB#0: # %entry
|
||||
; AVX2-NEXT: vpsrad $16, %ymm1, %ymm1
|
||||
; AVX2-NEXT: vpsrad $16, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vmovdqa {{.*#+}} ymm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
|
||||
; AVX2-NEXT: vpshufb %ymm2, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpackssdw %ymm0, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
|
||||
; AVX2-NEXT: vpshufb %ymm2, %ymm1, %ymm1
|
||||
; AVX2-NEXT: vpackssdw %ymm0, %ymm1, %ymm1
|
||||
; AVX2-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
|
||||
; AVX2-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vmovdqu %ymm0, (%rax)
|
||||
|
|
@ -879,10 +876,11 @@ define void @trunc16i32_16i16_lshr(<16 x i32> %a) {
|
|||
;
|
||||
; AVX2-LABEL: trunc16i32_16i16_lshr:
|
||||
; AVX2: # BB#0: # %entry
|
||||
; AVX2-NEXT: vmovdqa {{.*#+}} ymm2 = [2,3,6,7,10,11,14,15,10,11,14,15,14,15,255,255,18,19,22,23,26,27,30,31,26,27,30,31,30,31,255,255]
|
||||
; AVX2-NEXT: vpshufb %ymm2, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpsrld $16, %ymm1, %ymm1
|
||||
; AVX2-NEXT: vpsrld $16, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpackusdw %ymm0, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
|
||||
; AVX2-NEXT: vpshufb %ymm2, %ymm1, %ymm1
|
||||
; AVX2-NEXT: vpackusdw %ymm0, %ymm1, %ymm1
|
||||
; AVX2-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
|
||||
; AVX2-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vmovdqu %ymm0, (%rax)
|
||||
|
|
@ -1000,14 +998,13 @@ define void @trunc16i32_16i8_ashr(<16 x i32> %a) {
|
|||
; AVX2: # BB#0: # %entry
|
||||
; AVX2-NEXT: vpsrad $24, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpsrad $24, %ymm1, %ymm1
|
||||
; AVX2-NEXT: vmovdqa {{.*#+}} ymm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
|
||||
; AVX2-NEXT: vpshufb %ymm2, %ymm1, %ymm1
|
||||
; AVX2-NEXT: vpackssdw %ymm0, %ymm1, %ymm1
|
||||
; AVX2-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
|
||||
; AVX2-NEXT: vmovdqa {{.*#+}} xmm3 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
|
||||
; AVX2-NEXT: vpshufb %xmm3, %xmm1, %xmm1
|
||||
; AVX2-NEXT: vpshufb %ymm2, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vmovdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
|
||||
; AVX2-NEXT: vpshufb %xmm2, %xmm1, %xmm1
|
||||
; AVX2-NEXT: vpackssdw %ymm0, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
|
||||
; AVX2-NEXT: vpshufb %xmm3, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpshufb %xmm2, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; AVX2-NEXT: vmovdqu %xmm0, (%rax)
|
||||
; AVX2-NEXT: vzeroupper
|
||||
|
|
@ -1056,14 +1053,15 @@ define void @trunc16i32_16i8_lshr(<16 x i32> %a) {
|
|||
;
|
||||
; AVX2-LABEL: trunc16i32_16i8_lshr:
|
||||
; AVX2: # BB#0: # %entry
|
||||
; AVX2-NEXT: vmovdqa {{.*#+}} ymm2 = [3,255,7,255,11,255,15,255,11,255,15,255,15,255,255,255,19,255,23,255,27,255,31,255,27,255,31,255,31,255,255,255]
|
||||
; AVX2-NEXT: vpshufb %ymm2, %ymm1, %ymm1
|
||||
; AVX2-NEXT: vpsrld $24, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpsrld $24, %ymm1, %ymm1
|
||||
; AVX2-NEXT: vpackssdw %ymm0, %ymm1, %ymm1
|
||||
; AVX2-NEXT: vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
|
||||
; AVX2-NEXT: vmovdqa {{.*#+}} xmm3 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
|
||||
; AVX2-NEXT: vpshufb %xmm3, %xmm1, %xmm1
|
||||
; AVX2-NEXT: vpshufb %ymm2, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vmovdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
|
||||
; AVX2-NEXT: vpshufb %xmm2, %xmm1, %xmm1
|
||||
; AVX2-NEXT: vpackssdw %ymm0, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
|
||||
; AVX2-NEXT: vpshufb %xmm3, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpshufb %xmm2, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; AVX2-NEXT: vmovdqu %xmm0, (%rax)
|
||||
; AVX2-NEXT: vzeroupper
|
||||
|
|
@ -1169,38 +1167,13 @@ entry:
|
|||
}
|
||||
|
||||
define void @trunc16i16_16i8_ashr(<16 x i16> %a) {
|
||||
; SSE2-LABEL: trunc16i16_16i8_ashr:
|
||||
; SSE2: # BB#0: # %entry
|
||||
; SSE2-NEXT: psraw $8, %xmm0
|
||||
; SSE2-NEXT: psraw $8, %xmm1
|
||||
; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [255,255,255,255,255,255,255,255]
|
||||
; SSE2-NEXT: pand %xmm2, %xmm1
|
||||
; SSE2-NEXT: pand %xmm2, %xmm0
|
||||
; SSE2-NEXT: packuswb %xmm1, %xmm0
|
||||
; SSE2-NEXT: movdqu %xmm0, (%rax)
|
||||
; SSE2-NEXT: retq
|
||||
;
|
||||
; SSSE3-LABEL: trunc16i16_16i8_ashr:
|
||||
; SSSE3: # BB#0: # %entry
|
||||
; SSSE3-NEXT: psraw $8, %xmm0
|
||||
; SSSE3-NEXT: psraw $8, %xmm1
|
||||
; SSSE3-NEXT: movdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
|
||||
; SSSE3-NEXT: pshufb %xmm2, %xmm1
|
||||
; SSSE3-NEXT: pshufb %xmm2, %xmm0
|
||||
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; SSSE3-NEXT: movdqu %xmm0, (%rax)
|
||||
; SSSE3-NEXT: retq
|
||||
;
|
||||
; SSE41-LABEL: trunc16i16_16i8_ashr:
|
||||
; SSE41: # BB#0: # %entry
|
||||
; SSE41-NEXT: psraw $8, %xmm0
|
||||
; SSE41-NEXT: psraw $8, %xmm1
|
||||
; SSE41-NEXT: movdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
|
||||
; SSE41-NEXT: pshufb %xmm2, %xmm1
|
||||
; SSE41-NEXT: pshufb %xmm2, %xmm0
|
||||
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; SSE41-NEXT: movdqu %xmm0, (%rax)
|
||||
; SSE41-NEXT: retq
|
||||
; SSE-LABEL: trunc16i16_16i8_ashr:
|
||||
; SSE: # BB#0: # %entry
|
||||
; SSE-NEXT: psraw $8, %xmm1
|
||||
; SSE-NEXT: psraw $8, %xmm0
|
||||
; SSE-NEXT: packsswb %xmm1, %xmm0
|
||||
; SSE-NEXT: movdqu %xmm0, (%rax)
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX1-LABEL: trunc16i16_16i8_ashr:
|
||||
; AVX1: # BB#0: # %entry
|
||||
|
|
@ -1267,31 +1240,13 @@ entry:
|
|||
}
|
||||
|
||||
define void @trunc16i16_16i8_lshr(<16 x i16> %a) {
|
||||
; SSE2-LABEL: trunc16i16_16i8_lshr:
|
||||
; SSE2: # BB#0: # %entry
|
||||
; SSE2-NEXT: psrlw $8, %xmm1
|
||||
; SSE2-NEXT: psrlw $8, %xmm0
|
||||
; SSE2-NEXT: packuswb %xmm1, %xmm0
|
||||
; SSE2-NEXT: movdqu %xmm0, (%rax)
|
||||
; SSE2-NEXT: retq
|
||||
;
|
||||
; SSSE3-LABEL: trunc16i16_16i8_lshr:
|
||||
; SSSE3: # BB#0: # %entry
|
||||
; SSSE3-NEXT: movdqa {{.*#+}} xmm2 = <1,3,5,7,9,11,13,15,u,u,u,u,u,u,u,u>
|
||||
; SSSE3-NEXT: pshufb %xmm2, %xmm1
|
||||
; SSSE3-NEXT: pshufb %xmm2, %xmm0
|
||||
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; SSSE3-NEXT: movdqu %xmm0, (%rax)
|
||||
; SSSE3-NEXT: retq
|
||||
;
|
||||
; SSE41-LABEL: trunc16i16_16i8_lshr:
|
||||
; SSE41: # BB#0: # %entry
|
||||
; SSE41-NEXT: movdqa {{.*#+}} xmm2 = <1,3,5,7,9,11,13,15,u,u,u,u,u,u,u,u>
|
||||
; SSE41-NEXT: pshufb %xmm2, %xmm1
|
||||
; SSE41-NEXT: pshufb %xmm2, %xmm0
|
||||
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; SSE41-NEXT: movdqu %xmm0, (%rax)
|
||||
; SSE41-NEXT: retq
|
||||
; SSE-LABEL: trunc16i16_16i8_lshr:
|
||||
; SSE: # BB#0: # %entry
|
||||
; SSE-NEXT: psrlw $8, %xmm1
|
||||
; SSE-NEXT: psrlw $8, %xmm0
|
||||
; SSE-NEXT: packuswb %xmm1, %xmm0
|
||||
; SSE-NEXT: movdqu %xmm0, (%rax)
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX1-LABEL: trunc16i16_16i8_lshr:
|
||||
; AVX1: # BB#0: # %entry
|
||||
|
|
@ -1308,10 +1263,7 @@ define void @trunc16i16_16i8_lshr(<16 x i16> %a) {
|
|||
; AVX2: # BB#0: # %entry
|
||||
; AVX2-NEXT: vpsrlw $8, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
||||
; AVX2-NEXT: vmovdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
|
||||
; AVX2-NEXT: vpshufb %xmm2, %xmm1, %xmm1
|
||||
; AVX2-NEXT: vpshufb %xmm2, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; AVX2-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vmovdqu %xmm0, (%rax)
|
||||
; AVX2-NEXT: vzeroupper
|
||||
; AVX2-NEXT: retq
|
||||
|
|
|
|||
|
|
@ -99,10 +99,9 @@ define void @test3(<4 x i32> %induction30, <4 x i16>* %tmp16, <4 x i16>* %tmp17,
|
|||
; AVX1-NEXT: vpxor %xmm3, %xmm3, %xmm3
|
||||
; AVX1-NEXT: vpcmpeqd %xmm3, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vblendvps %xmm0, %xmm1, %xmm2, %xmm1
|
||||
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
|
||||
; AVX1-NEXT: vpshufb %xmm2, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpackssdw %xmm0, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vmovq %xmm0, (%rdi)
|
||||
; AVX1-NEXT: vpshufb %xmm2, %xmm1, %xmm0
|
||||
; AVX1-NEXT: vpshufb {{.*#+}} xmm0 = xmm1[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
|
||||
; AVX1-NEXT: vmovq %xmm0, (%rsi)
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
|
|
@ -123,10 +122,9 @@ define void @test3(<4 x i32> %induction30, <4 x i16>* %tmp16, <4 x i16>* %tmp17,
|
|||
; AVX2-NEXT: vpxor %xmm3, %xmm3, %xmm3
|
||||
; AVX2-NEXT: vpcmpeqd %xmm3, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vblendvps %xmm0, %xmm1, %xmm2, %xmm1
|
||||
; AVX2-NEXT: vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
|
||||
; AVX2-NEXT: vpshufb %xmm2, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpackssdw %xmm0, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vmovq %xmm0, (%rdi)
|
||||
; AVX2-NEXT: vpshufb %xmm2, %xmm1, %xmm0
|
||||
; AVX2-NEXT: vpshufb {{.*#+}} xmm0 = xmm1[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
|
||||
; AVX2-NEXT: vmovq %xmm0, (%rsi)
|
||||
; AVX2-NEXT: retq
|
||||
%tmp6 = srem <4 x i32> %induction30, <i32 3, i32 3, i32 3, i32 3>
|
||||
|
|
|
|||
|
|
@ -10,7 +10,6 @@ define void @update(i64* %dst_i, i64* %src_i, i32 %n) nounwind {
|
|||
; CHECK-NEXT: movl $0, (%esp)
|
||||
; CHECK-NEXT: pcmpeqd %xmm0, %xmm0
|
||||
; CHECK-NEXT: movdqa {{.*#+}} xmm1 = [4,4,4,4,4,4,4,4]
|
||||
; CHECK-NEXT: movdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
|
||||
; CHECK-NEXT: jmp .LBB0_1
|
||||
; CHECK-NEXT: .p2align 4, 0x90
|
||||
; CHECK-NEXT: .LBB0_2: # %forbody
|
||||
|
|
@ -22,11 +21,11 @@ define void @update(i64* %dst_i, i64* %src_i, i32 %n) nounwind {
|
|||
; CHECK-NEXT: movl %edx, {{[0-9]+}}(%esp)
|
||||
; CHECK-NEXT: addl {{[0-9]+}}(%esp), %ecx
|
||||
; CHECK-NEXT: movl %ecx, {{[0-9]+}}(%esp)
|
||||
; CHECK-NEXT: pmovzxbw {{.*#+}} xmm3 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero
|
||||
; CHECK-NEXT: psubw %xmm0, %xmm3
|
||||
; CHECK-NEXT: pand %xmm1, %xmm3
|
||||
; CHECK-NEXT: pshufb %xmm2, %xmm3
|
||||
; CHECK-NEXT: movq %xmm3, (%edx,%eax,8)
|
||||
; CHECK-NEXT: pmovzxbw {{.*#+}} xmm2 = mem[0],zero,mem[1],zero,mem[2],zero,mem[3],zero,mem[4],zero,mem[5],zero,mem[6],zero,mem[7],zero
|
||||
; CHECK-NEXT: psubw %xmm0, %xmm2
|
||||
; CHECK-NEXT: pand %xmm1, %xmm2
|
||||
; CHECK-NEXT: packsswb %xmm0, %xmm2
|
||||
; CHECK-NEXT: movq %xmm2, (%edx,%eax,8)
|
||||
; CHECK-NEXT: incl (%esp)
|
||||
; CHECK-NEXT: .LBB0_1: # %forcond
|
||||
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
|
||||
|
|
|
|||
Loading…
Reference in New Issue