forked from OSchip/llvm-project
[X86][SSE] Use MOVMSK for all_of/any_of reduction patterns
This is a first attempt at using the MOVMSK instructions to replace all_of/any_of reduction patterns (i.e. an and/or + shuffle chain). So far this only matches patterns where we are reducing an all/none bits source vector (i.e. a comparison result) but we should be able to expand on this in conjunction with improvements to 'bool vector' handling both in the x86 backend as well as the vectorizers etc. Differential Revision: https://reviews.llvm.org/D28810 llvm-svn: 293880
This commit is contained in:
Simon Pilgrim
parent
28912c09b2
commit
20ab6b875a
|
|
@ -28627,6 +28627,85 @@ static SDValue createPSADBW(SelectionDAG &DAG, const SDValue &Zext0,
|
|||
return DAG.getNode(X86ISD::PSADBW, DL, SadVT, SadOp0, SadOp1);
|
||||
}
|
||||
|
||||
// Attempt to replace an all_of/any_of style horizontal reduction with a MOVMSK.
|
||||
static SDValue combineHorizontalPredicateResult(SDNode *Extract,
|
||||
SelectionDAG &DAG,
|
||||
const X86Subtarget &Subtarget) {
|
||||
// Bail without SSE2 or with AVX512VL (which uses predicate registers).
|
||||
if (!Subtarget.hasSSE2() || Subtarget.hasVLX())
|
||||
return SDValue();
|
||||
|
||||
EVT ExtractVT = Extract->getValueType(0);
|
||||
unsigned BitWidth = ExtractVT.getSizeInBits();
|
||||
if (ExtractVT != MVT::i64 && ExtractVT != MVT::i32 && ExtractVT != MVT::i16 &&
|
||||
ExtractVT != MVT::i8)
|
||||
return SDValue();
|
||||
|
||||
// Check for OR(any_of) and AND(all_of) horizontal reduction patterns.
|
||||
for (ISD::NodeType Op : {ISD::OR, ISD::AND}) {
|
||||
SDValue Match = matchBinOpReduction(Extract, Op);
|
||||
if (!Match)
|
||||
continue;
|
||||
|
||||
// EXTRACT_VECTOR_ELT can require implicit extension of the vector element
|
||||
// which we can't support here for now.
|
||||
if (Match.getScalarValueSizeInBits() != BitWidth)
|
||||
continue;
|
||||
|
||||
// We require AVX2 for PMOVMSKB for v16i16/v32i8;
|
||||
unsigned MatchSizeInBits = Match.getValueSizeInBits();
|
||||
if (!(MatchSizeInBits == 128 ||
|
||||
(MatchSizeInBits == 256 &&
|
||||
((Subtarget.hasAVX() && BitWidth >= 32) || Subtarget.hasAVX2()))))
|
||||
return SDValue();
|
||||
|
||||
// Don't bother performing this for 2-element vectors.
|
||||
if (Match.getValueType().getVectorNumElements() <= 2)
|
||||
return SDValue();
|
||||
|
||||
// Check that we are extracting a reduction of all sign bits.
|
||||
if (DAG.ComputeNumSignBits(Match) != BitWidth)
|
||||
return SDValue();
|
||||
|
||||
// For 32/64 bit comparisons use MOVMSKPS/MOVMSKPD, else PMOVMSKB.
|
||||
MVT MaskVT;
|
||||
if (64 == BitWidth || 32 == BitWidth)
|
||||
MaskVT = MVT::getVectorVT(MVT::getFloatingPointVT(BitWidth),
|
||||
MatchSizeInBits / BitWidth);
|
||||
else
|
||||
MaskVT = MVT::getVectorVT(MVT::i8, MatchSizeInBits / 8);
|
||||
|
||||
APInt CompareBits;
|
||||
ISD::CondCode CondCode;
|
||||
if (Op == ISD::OR) {
|
||||
// any_of -> MOVMSK != 0
|
||||
CompareBits = APInt::getNullValue(32);
|
||||
CondCode = ISD::CondCode::SETNE;
|
||||
} else {
|
||||
// all_of -> MOVMSK == ((1 << NumElts) - 1)
|
||||
CompareBits = APInt::getLowBitsSet(32, MaskVT.getVectorNumElements());
|
||||
CondCode = ISD::CondCode::SETEQ;
|
||||
}
|
||||
|
||||
// Perform the select as i32/i64 and then truncate to avoid partial register
|
||||
// stalls.
|
||||
unsigned ResWidth = std::max(BitWidth, 32u);
|
||||
APInt ResOnes = APInt::getAllOnesValue(ResWidth);
|
||||
APInt ResZero = APInt::getNullValue(ResWidth);
|
||||
EVT ResVT = EVT::getIntegerVT(*DAG.getContext(), ResWidth);
|
||||
|
||||
SDLoc DL(Extract);
|
||||
SDValue Res = DAG.getBitcast(MaskVT, Match);
|
||||
Res = DAG.getNode(X86ISD::MOVMSK, DL, MVT::i32, Res);
|
||||
Res = DAG.getSelectCC(DL, Res, DAG.getConstant(CompareBits, DL, MVT::i32),
|
||||
DAG.getConstant(ResOnes, DL, ResVT),
|
||||
DAG.getConstant(ResZero, DL, ResVT), CondCode);
|
||||
return DAG.getSExtOrTrunc(Res, DL, ExtractVT);
|
||||
}
|
||||
|
||||
return SDValue();
|
||||
}
|
||||
|
||||
static SDValue combineBasicSADPattern(SDNode *Extract, SelectionDAG &DAG,
|
||||
const X86Subtarget &Subtarget) {
|
||||
// PSADBW is only supported on SSE2 and up.
|
||||
|
|
@ -28738,6 +28817,10 @@ static SDValue combineExtractVectorElt(SDNode *N, SelectionDAG &DAG,
|
|||
if (SDValue SAD = combineBasicSADPattern(N, DAG, Subtarget))
|
||||
return SAD;
|
||||
|
||||
// Attempt to replace an all_of/any_of horizontal reduction with a MOVMSK.
|
||||
if (SDValue Cmp = combineHorizontalPredicateResult(N, DAG, Subtarget))
|
||||
return Cmp;
|
||||
|
||||
// Only operate on vectors of 4 elements, where the alternative shuffling
|
||||
// gets to be more expensive.
|
||||
if (InputVector.getValueType() != MVT::v4i32)
|
||||
|
|
|
|||
|
|
@ -49,27 +49,16 @@ define i64 @test_v4f64(<4 x double> %a0, <4 x double> %a1) {
|
|||
; SSE-NEXT: movd %xmm0, %rax
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX1-LABEL: test_v4f64:
|
||||
; AVX1: # BB#0:
|
||||
; AVX1-NEXT: vcmpltpd %ymm0, %ymm1, %ymm0
|
||||
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
|
||||
; AVX1-NEXT: vandpd %ymm1, %ymm0, %ymm0
|
||||
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX1-NEXT: vandpd %ymm1, %ymm0, %ymm0
|
||||
; AVX1-NEXT: vmovq %xmm0, %rax
|
||||
; AVX1-NEXT: vzeroupper
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX2-LABEL: test_v4f64:
|
||||
; AVX2: # BB#0:
|
||||
; AVX2-NEXT: vcmpltpd %ymm0, %ymm1, %ymm0
|
||||
; AVX2-NEXT: vextractf128 $1, %ymm0, %xmm1
|
||||
; AVX2-NEXT: vandpd %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX2-NEXT: vpand %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vmovq %xmm0, %rax
|
||||
; AVX2-NEXT: vzeroupper
|
||||
; AVX2-NEXT: retq
|
||||
; AVX-LABEL: test_v4f64:
|
||||
; AVX: # BB#0:
|
||||
; AVX-NEXT: vcmpltpd %ymm0, %ymm1, %ymm0
|
||||
; AVX-NEXT: vmovmskpd %ymm0, %eax
|
||||
; AVX-NEXT: xorl %ecx, %ecx
|
||||
; AVX-NEXT: cmpl $15, %eax
|
||||
; AVX-NEXT: movq $-1, %rax
|
||||
; AVX-NEXT: cmovneq %rcx, %rax
|
||||
; AVX-NEXT: vzeroupper
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: test_v4f64:
|
||||
; AVX512: # BB#0:
|
||||
|
|
@ -98,11 +87,11 @@ define i64 @test_v4f64_legal(<4 x double> %a0, <4 x double> %a1) {
|
|||
; SSE-NEXT: cmpltpd %xmm1, %xmm3
|
||||
; SSE-NEXT: cmpltpd %xmm0, %xmm2
|
||||
; SSE-NEXT: packsswb %xmm3, %xmm2
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm2[2,3,0,1]
|
||||
; SSE-NEXT: pand %xmm2, %xmm0
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; SSE-NEXT: pand %xmm0, %xmm1
|
||||
; SSE-NEXT: movd %xmm1, %eax
|
||||
; SSE-NEXT: movmskps %xmm2, %eax
|
||||
; SSE-NEXT: xorl %ecx, %ecx
|
||||
; SSE-NEXT: cmpl $15, %eax
|
||||
; SSE-NEXT: movl $-1, %eax
|
||||
; SSE-NEXT: cmovnel %ecx, %eax
|
||||
; SSE-NEXT: cltq
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
|
|
@ -111,11 +100,11 @@ define i64 @test_v4f64_legal(<4 x double> %a0, <4 x double> %a1) {
|
|||
; AVX-NEXT: vcmpltpd %ymm0, %ymm1, %ymm0
|
||||
; AVX-NEXT: vextractf128 $1, %ymm0, %xmm1
|
||||
; AVX-NEXT: vpacksswb %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX-NEXT: vpand %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; AVX-NEXT: vpand %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vmovd %xmm0, %eax
|
||||
; AVX-NEXT: vmovmskps %xmm0, %eax
|
||||
; AVX-NEXT: xorl %ecx, %ecx
|
||||
; AVX-NEXT: cmpl $15, %eax
|
||||
; AVX-NEXT: movl $-1, %eax
|
||||
; AVX-NEXT: cmovnel %ecx, %eax
|
||||
; AVX-NEXT: cltq
|
||||
; AVX-NEXT: vzeroupper
|
||||
; AVX-NEXT: retq
|
||||
|
|
@ -147,21 +136,21 @@ define i32 @test_v4f32(<4 x float> %a0, <4 x float> %a1) {
|
|||
; SSE-LABEL: test_v4f32:
|
||||
; SSE: # BB#0:
|
||||
; SSE-NEXT: cmpltps %xmm0, %xmm1
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm1[2,3,0,1]
|
||||
; SSE-NEXT: pand %xmm1, %xmm0
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; SSE-NEXT: pand %xmm0, %xmm1
|
||||
; SSE-NEXT: movd %xmm1, %eax
|
||||
; SSE-NEXT: movmskps %xmm1, %eax
|
||||
; SSE-NEXT: xorl %ecx, %ecx
|
||||
; SSE-NEXT: cmpl $15, %eax
|
||||
; SSE-NEXT: movl $-1, %eax
|
||||
; SSE-NEXT: cmovnel %ecx, %eax
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX-LABEL: test_v4f32:
|
||||
; AVX: # BB#0:
|
||||
; AVX-NEXT: vcmpltps %xmm0, %xmm1, %xmm0
|
||||
; AVX-NEXT: vpermilpd {{.*#+}} xmm1 = xmm0[1,0]
|
||||
; AVX-NEXT: vandpd %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; AVX-NEXT: vpand %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vmovd %xmm0, %eax
|
||||
; AVX-NEXT: vmovmskps %xmm0, %eax
|
||||
; AVX-NEXT: xorl %ecx, %ecx
|
||||
; AVX-NEXT: cmpl $15, %eax
|
||||
; AVX-NEXT: movl $-1, %eax
|
||||
; AVX-NEXT: cmovnel %ecx, %eax
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: test_v4f32:
|
||||
|
|
@ -191,38 +180,23 @@ define i32 @test_v8f32(<8 x float> %a0, <8 x float> %a1) {
|
|||
; SSE-NEXT: cmpltps %xmm1, %xmm3
|
||||
; SSE-NEXT: cmpltps %xmm0, %xmm2
|
||||
; SSE-NEXT: andps %xmm3, %xmm2
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm2[2,3,0,1]
|
||||
; SSE-NEXT: pand %xmm2, %xmm0
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; SSE-NEXT: pand %xmm0, %xmm1
|
||||
; SSE-NEXT: movd %xmm1, %eax
|
||||
; SSE-NEXT: movmskps %xmm2, %eax
|
||||
; SSE-NEXT: xorl %ecx, %ecx
|
||||
; SSE-NEXT: cmpl $15, %eax
|
||||
; SSE-NEXT: movl $-1, %eax
|
||||
; SSE-NEXT: cmovnel %ecx, %eax
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX1-LABEL: test_v8f32:
|
||||
; AVX1: # BB#0:
|
||||
; AVX1-NEXT: vcmpltps %ymm0, %ymm1, %ymm0
|
||||
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
|
||||
; AVX1-NEXT: vandps %ymm1, %ymm0, %ymm0
|
||||
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX1-NEXT: vandps %ymm1, %ymm0, %ymm0
|
||||
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; AVX1-NEXT: vandps %ymm1, %ymm0, %ymm0
|
||||
; AVX1-NEXT: vmovd %xmm0, %eax
|
||||
; AVX1-NEXT: vzeroupper
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX2-LABEL: test_v8f32:
|
||||
; AVX2: # BB#0:
|
||||
; AVX2-NEXT: vcmpltps %ymm0, %ymm1, %ymm0
|
||||
; AVX2-NEXT: vextractf128 $1, %ymm0, %xmm1
|
||||
; AVX2-NEXT: vandps %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX2-NEXT: vpand %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; AVX2-NEXT: vpand %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vmovd %xmm0, %eax
|
||||
; AVX2-NEXT: vzeroupper
|
||||
; AVX2-NEXT: retq
|
||||
; AVX-LABEL: test_v8f32:
|
||||
; AVX: # BB#0:
|
||||
; AVX-NEXT: vcmpltps %ymm0, %ymm1, %ymm0
|
||||
; AVX-NEXT: vmovmskps %ymm0, %eax
|
||||
; AVX-NEXT: xorl %ecx, %ecx
|
||||
; AVX-NEXT: cmpl $255, %eax
|
||||
; AVX-NEXT: movl $-1, %eax
|
||||
; AVX-NEXT: cmovnel %ecx, %eax
|
||||
; AVX-NEXT: vzeroupper
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: test_v8f32:
|
||||
; AVX512: # BB#0:
|
||||
|
|
@ -255,15 +229,11 @@ define i32 @test_v8f32_legal(<8 x float> %a0, <8 x float> %a1) {
|
|||
; SSE-NEXT: cmpltps %xmm1, %xmm3
|
||||
; SSE-NEXT: cmpltps %xmm0, %xmm2
|
||||
; SSE-NEXT: packsswb %xmm3, %xmm2
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm2[2,3,0,1]
|
||||
; SSE-NEXT: pand %xmm2, %xmm0
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; SSE-NEXT: pand %xmm0, %xmm1
|
||||
; SSE-NEXT: movdqa %xmm1, %xmm0
|
||||
; SSE-NEXT: psrld $16, %xmm0
|
||||
; SSE-NEXT: pand %xmm1, %xmm0
|
||||
; SSE-NEXT: movd %xmm0, %eax
|
||||
; SSE-NEXT: cwtl
|
||||
; SSE-NEXT: pmovmskb %xmm2, %eax
|
||||
; SSE-NEXT: xorl %ecx, %ecx
|
||||
; SSE-NEXT: cmpl $65535, %eax # imm = 0xFFFF
|
||||
; SSE-NEXT: movl $-1, %eax
|
||||
; SSE-NEXT: cmovnel %ecx, %eax
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX-LABEL: test_v8f32_legal:
|
||||
|
|
@ -271,14 +241,11 @@ define i32 @test_v8f32_legal(<8 x float> %a0, <8 x float> %a1) {
|
|||
; AVX-NEXT: vcmpltps %ymm0, %ymm1, %ymm0
|
||||
; AVX-NEXT: vextractf128 $1, %ymm0, %xmm1
|
||||
; AVX-NEXT: vpacksswb %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX-NEXT: vpand %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; AVX-NEXT: vpand %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpsrld $16, %xmm0, %xmm1
|
||||
; AVX-NEXT: vpand %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vmovd %xmm0, %eax
|
||||
; AVX-NEXT: cwtl
|
||||
; AVX-NEXT: vpmovmskb %xmm0, %eax
|
||||
; AVX-NEXT: xorl %ecx, %ecx
|
||||
; AVX-NEXT: cmpl $65535, %eax # imm = 0xFFFF
|
||||
; AVX-NEXT: movl $-1, %eax
|
||||
; AVX-NEXT: cmovnel %ecx, %eax
|
||||
; AVX-NEXT: vzeroupper
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
|
|
@ -360,21 +327,22 @@ define i64 @test_v4i64(<4 x i64> %a0, <4 x i64> %a1) {
|
|||
; AVX1-NEXT: vpcmpgtq %xmm2, %xmm3, %xmm2
|
||||
; AVX1-NEXT: vpcmpgtq %xmm1, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
|
||||
; AVX1-NEXT: vandps %ymm2, %ymm0, %ymm0
|
||||
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX1-NEXT: vandps %ymm1, %ymm0, %ymm0
|
||||
; AVX1-NEXT: vmovq %xmm0, %rax
|
||||
; AVX1-NEXT: vmovmskpd %ymm0, %eax
|
||||
; AVX1-NEXT: xorl %ecx, %ecx
|
||||
; AVX1-NEXT: cmpl $15, %eax
|
||||
; AVX1-NEXT: movq $-1, %rax
|
||||
; AVX1-NEXT: cmovneq %rcx, %rax
|
||||
; AVX1-NEXT: vzeroupper
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX2-LABEL: test_v4i64:
|
||||
; AVX2: # BB#0:
|
||||
; AVX2-NEXT: vpcmpgtq %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
||||
; AVX2-NEXT: vpand %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX2-NEXT: vpand %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vmovq %xmm0, %rax
|
||||
; AVX2-NEXT: vmovmskpd %ymm0, %eax
|
||||
; AVX2-NEXT: xorl %ecx, %ecx
|
||||
; AVX2-NEXT: cmpl $15, %eax
|
||||
; AVX2-NEXT: movq $-1, %rax
|
||||
; AVX2-NEXT: cmovneq %rcx, %rax
|
||||
; AVX2-NEXT: vzeroupper
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
|
|
@ -405,11 +373,11 @@ define i64 @test_v4i64_legal(<4 x i64> %a0, <4 x i64> %a1) {
|
|||
; SSE-NEXT: pcmpgtq %xmm3, %xmm1
|
||||
; SSE-NEXT: pcmpgtq %xmm2, %xmm0
|
||||
; SSE-NEXT: packsswb %xmm1, %xmm0
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; SSE-NEXT: pand %xmm0, %xmm1
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,2,3]
|
||||
; SSE-NEXT: pand %xmm1, %xmm0
|
||||
; SSE-NEXT: movd %xmm0, %eax
|
||||
; SSE-NEXT: movmskps %xmm0, %eax
|
||||
; SSE-NEXT: xorl %ecx, %ecx
|
||||
; SSE-NEXT: cmpl $15, %eax
|
||||
; SSE-NEXT: movl $-1, %eax
|
||||
; SSE-NEXT: cmovnel %ecx, %eax
|
||||
; SSE-NEXT: cltq
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
|
|
@ -420,11 +388,11 @@ define i64 @test_v4i64_legal(<4 x i64> %a0, <4 x i64> %a1) {
|
|||
; AVX1-NEXT: vpcmpgtq %xmm2, %xmm3, %xmm2
|
||||
; AVX1-NEXT: vpcmpgtq %xmm1, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpacksswb %xmm2, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX1-NEXT: vpand %xmm1, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; AVX1-NEXT: vpand %xmm1, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vmovd %xmm0, %eax
|
||||
; AVX1-NEXT: vmovmskps %xmm0, %eax
|
||||
; AVX1-NEXT: xorl %ecx, %ecx
|
||||
; AVX1-NEXT: cmpl $15, %eax
|
||||
; AVX1-NEXT: movl $-1, %eax
|
||||
; AVX1-NEXT: cmovnel %ecx, %eax
|
||||
; AVX1-NEXT: cltq
|
||||
; AVX1-NEXT: vzeroupper
|
||||
; AVX1-NEXT: retq
|
||||
|
|
@ -434,11 +402,11 @@ define i64 @test_v4i64_legal(<4 x i64> %a0, <4 x i64> %a1) {
|
|||
; AVX2-NEXT: vpcmpgtq %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
||||
; AVX2-NEXT: vpacksswb %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX2-NEXT: vpand %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; AVX2-NEXT: vpand %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vmovd %xmm0, %eax
|
||||
; AVX2-NEXT: vmovmskps %xmm0, %eax
|
||||
; AVX2-NEXT: xorl %ecx, %ecx
|
||||
; AVX2-NEXT: cmpl $15, %eax
|
||||
; AVX2-NEXT: movl $-1, %eax
|
||||
; AVX2-NEXT: cmovnel %ecx, %eax
|
||||
; AVX2-NEXT: cltq
|
||||
; AVX2-NEXT: vzeroupper
|
||||
; AVX2-NEXT: retq
|
||||
|
|
@ -470,21 +438,21 @@ define i32 @test_v4i32(<4 x i32> %a0, <4 x i32> %a1) {
|
|||
; SSE-LABEL: test_v4i32:
|
||||
; SSE: # BB#0:
|
||||
; SSE-NEXT: pcmpgtd %xmm1, %xmm0
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; SSE-NEXT: pand %xmm0, %xmm1
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,2,3]
|
||||
; SSE-NEXT: pand %xmm1, %xmm0
|
||||
; SSE-NEXT: movd %xmm0, %eax
|
||||
; SSE-NEXT: movmskps %xmm0, %eax
|
||||
; SSE-NEXT: xorl %ecx, %ecx
|
||||
; SSE-NEXT: cmpl $15, %eax
|
||||
; SSE-NEXT: movl $-1, %eax
|
||||
; SSE-NEXT: cmovnel %ecx, %eax
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX-LABEL: test_v4i32:
|
||||
; AVX: # BB#0:
|
||||
; AVX-NEXT: vpcmpgtd %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX-NEXT: vpand %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; AVX-NEXT: vpand %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vmovd %xmm0, %eax
|
||||
; AVX-NEXT: vmovmskps %xmm0, %eax
|
||||
; AVX-NEXT: xorl %ecx, %ecx
|
||||
; AVX-NEXT: cmpl $15, %eax
|
||||
; AVX-NEXT: movl $-1, %eax
|
||||
; AVX-NEXT: cmovnel %ecx, %eax
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: test_v4i32:
|
||||
|
|
@ -514,11 +482,11 @@ define i32 @test_v8i32(<8 x i32> %a0, <8 x i32> %a1) {
|
|||
; SSE-NEXT: pcmpgtd %xmm3, %xmm1
|
||||
; SSE-NEXT: pcmpgtd %xmm2, %xmm0
|
||||
; SSE-NEXT: pand %xmm1, %xmm0
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; SSE-NEXT: pand %xmm0, %xmm1
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,2,3]
|
||||
; SSE-NEXT: pand %xmm1, %xmm0
|
||||
; SSE-NEXT: movd %xmm0, %eax
|
||||
; SSE-NEXT: movmskps %xmm0, %eax
|
||||
; SSE-NEXT: xorl %ecx, %ecx
|
||||
; SSE-NEXT: cmpl $15, %eax
|
||||
; SSE-NEXT: movl $-1, %eax
|
||||
; SSE-NEXT: cmovnel %ecx, %eax
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX1-LABEL: test_v8i32:
|
||||
|
|
@ -528,25 +496,22 @@ define i32 @test_v8i32(<8 x i32> %a0, <8 x i32> %a1) {
|
|||
; AVX1-NEXT: vpcmpgtd %xmm2, %xmm3, %xmm2
|
||||
; AVX1-NEXT: vpcmpgtd %xmm1, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
|
||||
; AVX1-NEXT: vandps %ymm2, %ymm0, %ymm0
|
||||
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX1-NEXT: vandps %ymm1, %ymm0, %ymm0
|
||||
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; AVX1-NEXT: vandps %ymm1, %ymm0, %ymm0
|
||||
; AVX1-NEXT: vmovd %xmm0, %eax
|
||||
; AVX1-NEXT: vmovmskps %ymm0, %eax
|
||||
; AVX1-NEXT: xorl %ecx, %ecx
|
||||
; AVX1-NEXT: cmpl $255, %eax
|
||||
; AVX1-NEXT: movl $-1, %eax
|
||||
; AVX1-NEXT: cmovnel %ecx, %eax
|
||||
; AVX1-NEXT: vzeroupper
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX2-LABEL: test_v8i32:
|
||||
; AVX2: # BB#0:
|
||||
; AVX2-NEXT: vpcmpgtd %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
||||
; AVX2-NEXT: vpand %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX2-NEXT: vpand %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; AVX2-NEXT: vpand %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vmovd %xmm0, %eax
|
||||
; AVX2-NEXT: vmovmskps %ymm0, %eax
|
||||
; AVX2-NEXT: xorl %ecx, %ecx
|
||||
; AVX2-NEXT: cmpl $255, %eax
|
||||
; AVX2-NEXT: movl $-1, %eax
|
||||
; AVX2-NEXT: cmovnel %ecx, %eax
|
||||
; AVX2-NEXT: vzeroupper
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
|
|
@ -581,15 +546,11 @@ define i32 @test_v8i32_legal(<8 x i32> %a0, <8 x i32> %a1) {
|
|||
; SSE-NEXT: pcmpgtd %xmm3, %xmm1
|
||||
; SSE-NEXT: pcmpgtd %xmm2, %xmm0
|
||||
; SSE-NEXT: packsswb %xmm1, %xmm0
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; SSE-NEXT: pand %xmm0, %xmm1
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,2,3]
|
||||
; SSE-NEXT: pand %xmm1, %xmm0
|
||||
; SSE-NEXT: movdqa %xmm0, %xmm1
|
||||
; SSE-NEXT: psrld $16, %xmm1
|
||||
; SSE-NEXT: pand %xmm0, %xmm1
|
||||
; SSE-NEXT: movd %xmm1, %eax
|
||||
; SSE-NEXT: cwtl
|
||||
; SSE-NEXT: pmovmskb %xmm0, %eax
|
||||
; SSE-NEXT: xorl %ecx, %ecx
|
||||
; SSE-NEXT: cmpl $65535, %eax # imm = 0xFFFF
|
||||
; SSE-NEXT: movl $-1, %eax
|
||||
; SSE-NEXT: cmovnel %ecx, %eax
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX1-LABEL: test_v8i32_legal:
|
||||
|
|
@ -599,14 +560,11 @@ define i32 @test_v8i32_legal(<8 x i32> %a0, <8 x i32> %a1) {
|
|||
; AVX1-NEXT: vpcmpgtd %xmm2, %xmm3, %xmm2
|
||||
; AVX1-NEXT: vpcmpgtd %xmm1, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpacksswb %xmm2, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX1-NEXT: vpand %xmm1, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; AVX1-NEXT: vpand %xmm1, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpsrld $16, %xmm0, %xmm1
|
||||
; AVX1-NEXT: vpand %xmm1, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vmovd %xmm0, %eax
|
||||
; AVX1-NEXT: cwtl
|
||||
; AVX1-NEXT: vpmovmskb %xmm0, %eax
|
||||
; AVX1-NEXT: xorl %ecx, %ecx
|
||||
; AVX1-NEXT: cmpl $65535, %eax # imm = 0xFFFF
|
||||
; AVX1-NEXT: movl $-1, %eax
|
||||
; AVX1-NEXT: cmovnel %ecx, %eax
|
||||
; AVX1-NEXT: vzeroupper
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
|
|
@ -615,14 +573,11 @@ define i32 @test_v8i32_legal(<8 x i32> %a0, <8 x i32> %a1) {
|
|||
; AVX2-NEXT: vpcmpgtd %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
||||
; AVX2-NEXT: vpacksswb %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX2-NEXT: vpand %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; AVX2-NEXT: vpand %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpsrld $16, %xmm0, %xmm1
|
||||
; AVX2-NEXT: vpand %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vmovd %xmm0, %eax
|
||||
; AVX2-NEXT: cwtl
|
||||
; AVX2-NEXT: vpmovmskb %xmm0, %eax
|
||||
; AVX2-NEXT: xorl %ecx, %ecx
|
||||
; AVX2-NEXT: cmpl $65535, %eax # imm = 0xFFFF
|
||||
; AVX2-NEXT: movl $-1, %eax
|
||||
; AVX2-NEXT: cmovnel %ecx, %eax
|
||||
; AVX2-NEXT: vzeroupper
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
|
|
@ -656,27 +611,22 @@ define i16 @test_v8i16(<8 x i16> %a0, <8 x i16> %a1) {
|
|||
; SSE-LABEL: test_v8i16:
|
||||
; SSE: # BB#0:
|
||||
; SSE-NEXT: pcmpgtw %xmm1, %xmm0
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; SSE-NEXT: pand %xmm0, %xmm1
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,2,3]
|
||||
; SSE-NEXT: pand %xmm1, %xmm0
|
||||
; SSE-NEXT: movdqa %xmm0, %xmm1
|
||||
; SSE-NEXT: psrld $16, %xmm1
|
||||
; SSE-NEXT: pand %xmm0, %xmm1
|
||||
; SSE-NEXT: movd %xmm1, %eax
|
||||
; SSE-NEXT: pmovmskb %xmm0, %eax
|
||||
; SSE-NEXT: xorl %ecx, %ecx
|
||||
; SSE-NEXT: cmpl $65535, %eax # imm = 0xFFFF
|
||||
; SSE-NEXT: movl $-1, %eax
|
||||
; SSE-NEXT: cmovnel %ecx, %eax
|
||||
; SSE-NEXT: # kill: %AX<def> %AX<kill> %EAX<kill>
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX-LABEL: test_v8i16:
|
||||
; AVX: # BB#0:
|
||||
; AVX-NEXT: vpcmpgtw %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX-NEXT: vpand %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; AVX-NEXT: vpand %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpsrld $16, %xmm0, %xmm1
|
||||
; AVX-NEXT: vpand %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vmovd %xmm0, %eax
|
||||
; AVX-NEXT: vpmovmskb %xmm0, %eax
|
||||
; AVX-NEXT: xorl %ecx, %ecx
|
||||
; AVX-NEXT: cmpl $65535, %eax # imm = 0xFFFF
|
||||
; AVX-NEXT: movl $-1, %eax
|
||||
; AVX-NEXT: cmovnel %ecx, %eax
|
||||
; AVX-NEXT: # kill: %AX<def> %AX<kill> %EAX<kill>
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
|
|
@ -711,14 +661,11 @@ define i16 @test_v16i16(<16 x i16> %a0, <16 x i16> %a1) {
|
|||
; SSE-NEXT: pcmpgtw %xmm3, %xmm1
|
||||
; SSE-NEXT: pcmpgtw %xmm2, %xmm0
|
||||
; SSE-NEXT: pand %xmm1, %xmm0
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; SSE-NEXT: pand %xmm0, %xmm1
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,2,3]
|
||||
; SSE-NEXT: pand %xmm1, %xmm0
|
||||
; SSE-NEXT: movdqa %xmm0, %xmm1
|
||||
; SSE-NEXT: psrld $16, %xmm1
|
||||
; SSE-NEXT: pand %xmm0, %xmm1
|
||||
; SSE-NEXT: movd %xmm1, %eax
|
||||
; SSE-NEXT: pmovmskb %xmm0, %eax
|
||||
; SSE-NEXT: xorl %ecx, %ecx
|
||||
; SSE-NEXT: cmpl $65535, %eax # imm = 0xFFFF
|
||||
; SSE-NEXT: movl $-1, %eax
|
||||
; SSE-NEXT: cmovnel %ecx, %eax
|
||||
; SSE-NEXT: # kill: %AX<def> %AX<kill> %EAX<kill>
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
|
|
@ -744,15 +691,10 @@ define i16 @test_v16i16(<16 x i16> %a0, <16 x i16> %a1) {
|
|||
; AVX2-LABEL: test_v16i16:
|
||||
; AVX2: # BB#0:
|
||||
; AVX2-NEXT: vpcmpgtw %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
||||
; AVX2-NEXT: vpand %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX2-NEXT: vpand %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; AVX2-NEXT: vpand %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpsrld $16, %xmm0, %xmm1
|
||||
; AVX2-NEXT: vpand %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vmovd %xmm0, %eax
|
||||
; AVX2-NEXT: vpmovmskb %ymm0, %ecx
|
||||
; AVX2-NEXT: xorl %eax, %eax
|
||||
; AVX2-NEXT: cmpl $-1, %ecx
|
||||
; AVX2-NEXT: cmovel %ecx, %eax
|
||||
; AVX2-NEXT: # kill: %AX<def> %AX<kill> %EAX<kill>
|
||||
; AVX2-NEXT: vzeroupper
|
||||
; AVX2-NEXT: retq
|
||||
|
|
@ -792,18 +734,11 @@ define i16 @test_v16i16_legal(<16 x i16> %a0, <16 x i16> %a1) {
|
|||
; SSE-NEXT: pcmpgtw %xmm3, %xmm1
|
||||
; SSE-NEXT: pcmpgtw %xmm2, %xmm0
|
||||
; SSE-NEXT: packsswb %xmm1, %xmm0
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; SSE-NEXT: pand %xmm0, %xmm1
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,2,3]
|
||||
; SSE-NEXT: pand %xmm1, %xmm0
|
||||
; SSE-NEXT: movdqa %xmm0, %xmm1
|
||||
; SSE-NEXT: psrld $16, %xmm1
|
||||
; SSE-NEXT: pand %xmm0, %xmm1
|
||||
; SSE-NEXT: movdqa %xmm1, %xmm0
|
||||
; SSE-NEXT: psrlw $8, %xmm0
|
||||
; SSE-NEXT: pand %xmm1, %xmm0
|
||||
; SSE-NEXT: pextrb $0, %xmm0, %eax
|
||||
; SSE-NEXT: movsbl %al, %eax
|
||||
; SSE-NEXT: pmovmskb %xmm0, %eax
|
||||
; SSE-NEXT: xorl %ecx, %ecx
|
||||
; SSE-NEXT: cmpl $65535, %eax # imm = 0xFFFF
|
||||
; SSE-NEXT: movl $-1, %eax
|
||||
; SSE-NEXT: cmovnel %ecx, %eax
|
||||
; SSE-NEXT: # kill: %AX<def> %AX<kill> %EAX<kill>
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
|
|
@ -814,16 +749,11 @@ define i16 @test_v16i16_legal(<16 x i16> %a0, <16 x i16> %a1) {
|
|||
; AVX1-NEXT: vpcmpgtw %xmm2, %xmm3, %xmm2
|
||||
; AVX1-NEXT: vpcmpgtw %xmm1, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpacksswb %xmm2, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX1-NEXT: vpand %xmm1, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; AVX1-NEXT: vpand %xmm1, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpsrld $16, %xmm0, %xmm1
|
||||
; AVX1-NEXT: vpand %xmm1, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpsrlw $8, %xmm0, %xmm1
|
||||
; AVX1-NEXT: vpand %xmm1, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpextrb $0, %xmm0, %eax
|
||||
; AVX1-NEXT: movsbl %al, %eax
|
||||
; AVX1-NEXT: vpmovmskb %xmm0, %eax
|
||||
; AVX1-NEXT: xorl %ecx, %ecx
|
||||
; AVX1-NEXT: cmpl $65535, %eax # imm = 0xFFFF
|
||||
; AVX1-NEXT: movl $-1, %eax
|
||||
; AVX1-NEXT: cmovnel %ecx, %eax
|
||||
; AVX1-NEXT: # kill: %AX<def> %AX<kill> %EAX<kill>
|
||||
; AVX1-NEXT: vzeroupper
|
||||
; AVX1-NEXT: retq
|
||||
|
|
@ -833,16 +763,11 @@ define i16 @test_v16i16_legal(<16 x i16> %a0, <16 x i16> %a1) {
|
|||
; AVX2-NEXT: vpcmpgtw %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
||||
; AVX2-NEXT: vpacksswb %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX2-NEXT: vpand %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; AVX2-NEXT: vpand %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpsrld $16, %xmm0, %xmm1
|
||||
; AVX2-NEXT: vpand %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpsrlw $8, %xmm0, %xmm1
|
||||
; AVX2-NEXT: vpand %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpextrb $0, %xmm0, %eax
|
||||
; AVX2-NEXT: movsbl %al, %eax
|
||||
; AVX2-NEXT: vpmovmskb %xmm0, %eax
|
||||
; AVX2-NEXT: xorl %ecx, %ecx
|
||||
; AVX2-NEXT: cmpl $65535, %eax # imm = 0xFFFF
|
||||
; AVX2-NEXT: movl $-1, %eax
|
||||
; AVX2-NEXT: cmovnel %ecx, %eax
|
||||
; AVX2-NEXT: # kill: %AX<def> %AX<kill> %EAX<kill>
|
||||
; AVX2-NEXT: vzeroupper
|
||||
; AVX2-NEXT: retq
|
||||
|
|
@ -882,32 +807,22 @@ define i8 @test_v16i8(<16 x i8> %a0, <16 x i8> %a1) {
|
|||
; SSE-LABEL: test_v16i8:
|
||||
; SSE: # BB#0:
|
||||
; SSE-NEXT: pcmpgtb %xmm1, %xmm0
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; SSE-NEXT: pand %xmm0, %xmm1
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,2,3]
|
||||
; SSE-NEXT: pand %xmm1, %xmm0
|
||||
; SSE-NEXT: movdqa %xmm0, %xmm1
|
||||
; SSE-NEXT: psrld $16, %xmm1
|
||||
; SSE-NEXT: pand %xmm0, %xmm1
|
||||
; SSE-NEXT: movdqa %xmm1, %xmm0
|
||||
; SSE-NEXT: psrlw $8, %xmm0
|
||||
; SSE-NEXT: pand %xmm1, %xmm0
|
||||
; SSE-NEXT: pextrb $0, %xmm0, %eax
|
||||
; SSE-NEXT: pmovmskb %xmm0, %eax
|
||||
; SSE-NEXT: xorl %ecx, %ecx
|
||||
; SSE-NEXT: cmpl $65535, %eax # imm = 0xFFFF
|
||||
; SSE-NEXT: movl $-1, %eax
|
||||
; SSE-NEXT: cmovnel %ecx, %eax
|
||||
; SSE-NEXT: # kill: %AL<def> %AL<kill> %EAX<kill>
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX-LABEL: test_v16i8:
|
||||
; AVX: # BB#0:
|
||||
; AVX-NEXT: vpcmpgtb %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX-NEXT: vpand %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; AVX-NEXT: vpand %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpsrld $16, %xmm0, %xmm1
|
||||
; AVX-NEXT: vpand %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpsrlw $8, %xmm0, %xmm1
|
||||
; AVX-NEXT: vpand %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpextrb $0, %xmm0, %eax
|
||||
; AVX-NEXT: vpmovmskb %xmm0, %eax
|
||||
; AVX-NEXT: xorl %ecx, %ecx
|
||||
; AVX-NEXT: cmpl $65535, %eax # imm = 0xFFFF
|
||||
; AVX-NEXT: movl $-1, %eax
|
||||
; AVX-NEXT: cmovnel %ecx, %eax
|
||||
; AVX-NEXT: # kill: %AL<def> %AL<kill> %EAX<kill>
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
|
|
@ -946,17 +861,11 @@ define i8 @test_v32i8(<32 x i8> %a0, <32 x i8> %a1) {
|
|||
; SSE-NEXT: pcmpgtb %xmm3, %xmm1
|
||||
; SSE-NEXT: pcmpgtb %xmm2, %xmm0
|
||||
; SSE-NEXT: pand %xmm1, %xmm0
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; SSE-NEXT: pand %xmm0, %xmm1
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,2,3]
|
||||
; SSE-NEXT: pand %xmm1, %xmm0
|
||||
; SSE-NEXT: movdqa %xmm0, %xmm1
|
||||
; SSE-NEXT: psrld $16, %xmm1
|
||||
; SSE-NEXT: pand %xmm0, %xmm1
|
||||
; SSE-NEXT: movdqa %xmm1, %xmm0
|
||||
; SSE-NEXT: psrlw $8, %xmm0
|
||||
; SSE-NEXT: pand %xmm1, %xmm0
|
||||
; SSE-NEXT: pextrb $0, %xmm0, %eax
|
||||
; SSE-NEXT: pmovmskb %xmm0, %eax
|
||||
; SSE-NEXT: xorl %ecx, %ecx
|
||||
; SSE-NEXT: cmpl $65535, %eax # imm = 0xFFFF
|
||||
; SSE-NEXT: movl $-1, %eax
|
||||
; SSE-NEXT: cmovnel %ecx, %eax
|
||||
; SSE-NEXT: # kill: %AL<def> %AL<kill> %EAX<kill>
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
|
|
@ -984,17 +893,10 @@ define i8 @test_v32i8(<32 x i8> %a0, <32 x i8> %a1) {
|
|||
; AVX2-LABEL: test_v32i8:
|
||||
; AVX2: # BB#0:
|
||||
; AVX2-NEXT: vpcmpgtb %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
||||
; AVX2-NEXT: vpand %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX2-NEXT: vpand %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; AVX2-NEXT: vpand %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpsrld $16, %xmm0, %xmm1
|
||||
; AVX2-NEXT: vpand %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpsrlw $8, %xmm0, %xmm1
|
||||
; AVX2-NEXT: vpand %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpextrb $0, %xmm0, %eax
|
||||
; AVX2-NEXT: vpmovmskb %ymm0, %ecx
|
||||
; AVX2-NEXT: xorl %eax, %eax
|
||||
; AVX2-NEXT: cmpl $-1, %ecx
|
||||
; AVX2-NEXT: cmovel %ecx, %eax
|
||||
; AVX2-NEXT: # kill: %AL<def> %AL<kill> %EAX<kill>
|
||||
; AVX2-NEXT: vzeroupper
|
||||
; AVX2-NEXT: retq
|
||||
|
|
|
|||
|
|
@ -49,27 +49,14 @@ define i64 @test_v4f64(<4 x double> %a0, <4 x double> %a1) {
|
|||
; SSE-NEXT: movd %xmm0, %rax
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX1-LABEL: test_v4f64:
|
||||
; AVX1: # BB#0:
|
||||
; AVX1-NEXT: vcmpltpd %ymm0, %ymm1, %ymm0
|
||||
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
|
||||
; AVX1-NEXT: vorpd %ymm1, %ymm0, %ymm0
|
||||
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX1-NEXT: vorpd %ymm1, %ymm0, %ymm0
|
||||
; AVX1-NEXT: vmovq %xmm0, %rax
|
||||
; AVX1-NEXT: vzeroupper
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX2-LABEL: test_v4f64:
|
||||
; AVX2: # BB#0:
|
||||
; AVX2-NEXT: vcmpltpd %ymm0, %ymm1, %ymm0
|
||||
; AVX2-NEXT: vextractf128 $1, %ymm0, %xmm1
|
||||
; AVX2-NEXT: vorpd %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX2-NEXT: vpor %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vmovq %xmm0, %rax
|
||||
; AVX2-NEXT: vzeroupper
|
||||
; AVX2-NEXT: retq
|
||||
; AVX-LABEL: test_v4f64:
|
||||
; AVX: # BB#0:
|
||||
; AVX-NEXT: vcmpltpd %ymm0, %ymm1, %ymm0
|
||||
; AVX-NEXT: vmovmskpd %ymm0, %eax
|
||||
; AVX-NEXT: negl %eax
|
||||
; AVX-NEXT: sbbq %rax, %rax
|
||||
; AVX-NEXT: vzeroupper
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: test_v4f64:
|
||||
; AVX512: # BB#0:
|
||||
|
|
@ -98,11 +85,9 @@ define i64 @test_v4f64_legal(<4 x double> %a0, <4 x double> %a1) {
|
|||
; SSE-NEXT: cmpltpd %xmm1, %xmm3
|
||||
; SSE-NEXT: cmpltpd %xmm0, %xmm2
|
||||
; SSE-NEXT: packsswb %xmm3, %xmm2
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm2[2,3,0,1]
|
||||
; SSE-NEXT: por %xmm2, %xmm0
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; SSE-NEXT: por %xmm0, %xmm1
|
||||
; SSE-NEXT: movd %xmm1, %eax
|
||||
; SSE-NEXT: movmskps %xmm2, %eax
|
||||
; SSE-NEXT: negl %eax
|
||||
; SSE-NEXT: sbbl %eax, %eax
|
||||
; SSE-NEXT: cltq
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
|
|
@ -111,11 +96,9 @@ define i64 @test_v4f64_legal(<4 x double> %a0, <4 x double> %a1) {
|
|||
; AVX-NEXT: vcmpltpd %ymm0, %ymm1, %ymm0
|
||||
; AVX-NEXT: vextractf128 $1, %ymm0, %xmm1
|
||||
; AVX-NEXT: vpacksswb %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX-NEXT: vpor %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; AVX-NEXT: vpor %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vmovd %xmm0, %eax
|
||||
; AVX-NEXT: vmovmskps %xmm0, %eax
|
||||
; AVX-NEXT: negl %eax
|
||||
; AVX-NEXT: sbbl %eax, %eax
|
||||
; AVX-NEXT: cltq
|
||||
; AVX-NEXT: vzeroupper
|
||||
; AVX-NEXT: retq
|
||||
|
|
@ -147,21 +130,17 @@ define i32 @test_v4f32(<4 x float> %a0, <4 x float> %a1) {
|
|||
; SSE-LABEL: test_v4f32:
|
||||
; SSE: # BB#0:
|
||||
; SSE-NEXT: cmpltps %xmm0, %xmm1
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm1[2,3,0,1]
|
||||
; SSE-NEXT: por %xmm1, %xmm0
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; SSE-NEXT: por %xmm0, %xmm1
|
||||
; SSE-NEXT: movd %xmm1, %eax
|
||||
; SSE-NEXT: movmskps %xmm1, %eax
|
||||
; SSE-NEXT: negl %eax
|
||||
; SSE-NEXT: sbbl %eax, %eax
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX-LABEL: test_v4f32:
|
||||
; AVX: # BB#0:
|
||||
; AVX-NEXT: vcmpltps %xmm0, %xmm1, %xmm0
|
||||
; AVX-NEXT: vpermilpd {{.*#+}} xmm1 = xmm0[1,0]
|
||||
; AVX-NEXT: vorpd %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; AVX-NEXT: vpor %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vmovd %xmm0, %eax
|
||||
; AVX-NEXT: vmovmskps %xmm0, %eax
|
||||
; AVX-NEXT: negl %eax
|
||||
; AVX-NEXT: sbbl %eax, %eax
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: test_v4f32:
|
||||
|
|
@ -191,38 +170,19 @@ define i32 @test_v8f32(<8 x float> %a0, <8 x float> %a1) {
|
|||
; SSE-NEXT: cmpltps %xmm1, %xmm3
|
||||
; SSE-NEXT: cmpltps %xmm0, %xmm2
|
||||
; SSE-NEXT: orps %xmm3, %xmm2
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm2[2,3,0,1]
|
||||
; SSE-NEXT: por %xmm2, %xmm0
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; SSE-NEXT: por %xmm0, %xmm1
|
||||
; SSE-NEXT: movd %xmm1, %eax
|
||||
; SSE-NEXT: movmskps %xmm2, %eax
|
||||
; SSE-NEXT: negl %eax
|
||||
; SSE-NEXT: sbbl %eax, %eax
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX1-LABEL: test_v8f32:
|
||||
; AVX1: # BB#0:
|
||||
; AVX1-NEXT: vcmpltps %ymm0, %ymm1, %ymm0
|
||||
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
|
||||
; AVX1-NEXT: vorps %ymm1, %ymm0, %ymm0
|
||||
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX1-NEXT: vorps %ymm1, %ymm0, %ymm0
|
||||
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; AVX1-NEXT: vorps %ymm1, %ymm0, %ymm0
|
||||
; AVX1-NEXT: vmovd %xmm0, %eax
|
||||
; AVX1-NEXT: vzeroupper
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX2-LABEL: test_v8f32:
|
||||
; AVX2: # BB#0:
|
||||
; AVX2-NEXT: vcmpltps %ymm0, %ymm1, %ymm0
|
||||
; AVX2-NEXT: vextractf128 $1, %ymm0, %xmm1
|
||||
; AVX2-NEXT: vorps %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX2-NEXT: vpor %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; AVX2-NEXT: vpor %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vmovd %xmm0, %eax
|
||||
; AVX2-NEXT: vzeroupper
|
||||
; AVX2-NEXT: retq
|
||||
; AVX-LABEL: test_v8f32:
|
||||
; AVX: # BB#0:
|
||||
; AVX-NEXT: vcmpltps %ymm0, %ymm1, %ymm0
|
||||
; AVX-NEXT: vmovmskps %ymm0, %eax
|
||||
; AVX-NEXT: negl %eax
|
||||
; AVX-NEXT: sbbl %eax, %eax
|
||||
; AVX-NEXT: vzeroupper
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: test_v8f32:
|
||||
; AVX512: # BB#0:
|
||||
|
|
@ -255,15 +215,9 @@ define i32 @test_v8f32_legal(<8 x float> %a0, <8 x float> %a1) {
|
|||
; SSE-NEXT: cmpltps %xmm1, %xmm3
|
||||
; SSE-NEXT: cmpltps %xmm0, %xmm2
|
||||
; SSE-NEXT: packsswb %xmm3, %xmm2
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm2[2,3,0,1]
|
||||
; SSE-NEXT: por %xmm2, %xmm0
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; SSE-NEXT: por %xmm0, %xmm1
|
||||
; SSE-NEXT: movdqa %xmm1, %xmm0
|
||||
; SSE-NEXT: psrld $16, %xmm0
|
||||
; SSE-NEXT: por %xmm1, %xmm0
|
||||
; SSE-NEXT: movd %xmm0, %eax
|
||||
; SSE-NEXT: cwtl
|
||||
; SSE-NEXT: pmovmskb %xmm2, %eax
|
||||
; SSE-NEXT: negl %eax
|
||||
; SSE-NEXT: sbbl %eax, %eax
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX-LABEL: test_v8f32_legal:
|
||||
|
|
@ -271,14 +225,9 @@ define i32 @test_v8f32_legal(<8 x float> %a0, <8 x float> %a1) {
|
|||
; AVX-NEXT: vcmpltps %ymm0, %ymm1, %ymm0
|
||||
; AVX-NEXT: vextractf128 $1, %ymm0, %xmm1
|
||||
; AVX-NEXT: vpacksswb %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX-NEXT: vpor %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; AVX-NEXT: vpor %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpsrld $16, %xmm0, %xmm1
|
||||
; AVX-NEXT: vpor %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vmovd %xmm0, %eax
|
||||
; AVX-NEXT: cwtl
|
||||
; AVX-NEXT: vpmovmskb %xmm0, %eax
|
||||
; AVX-NEXT: negl %eax
|
||||
; AVX-NEXT: sbbl %eax, %eax
|
||||
; AVX-NEXT: vzeroupper
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
|
|
@ -360,21 +309,18 @@ define i64 @test_v4i64(<4 x i64> %a0, <4 x i64> %a1) {
|
|||
; AVX1-NEXT: vpcmpgtq %xmm2, %xmm3, %xmm2
|
||||
; AVX1-NEXT: vpcmpgtq %xmm1, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
|
||||
; AVX1-NEXT: vorps %ymm2, %ymm0, %ymm0
|
||||
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX1-NEXT: vorps %ymm1, %ymm0, %ymm0
|
||||
; AVX1-NEXT: vmovq %xmm0, %rax
|
||||
; AVX1-NEXT: vmovmskpd %ymm0, %eax
|
||||
; AVX1-NEXT: negl %eax
|
||||
; AVX1-NEXT: sbbq %rax, %rax
|
||||
; AVX1-NEXT: vzeroupper
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX2-LABEL: test_v4i64:
|
||||
; AVX2: # BB#0:
|
||||
; AVX2-NEXT: vpcmpgtq %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
||||
; AVX2-NEXT: vpor %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX2-NEXT: vpor %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vmovq %xmm0, %rax
|
||||
; AVX2-NEXT: vmovmskpd %ymm0, %eax
|
||||
; AVX2-NEXT: negl %eax
|
||||
; AVX2-NEXT: sbbq %rax, %rax
|
||||
; AVX2-NEXT: vzeroupper
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
|
|
@ -405,11 +351,9 @@ define i64 @test_v4i64_legal(<4 x i64> %a0, <4 x i64> %a1) {
|
|||
; SSE-NEXT: pcmpgtq %xmm3, %xmm1
|
||||
; SSE-NEXT: pcmpgtq %xmm2, %xmm0
|
||||
; SSE-NEXT: packsswb %xmm1, %xmm0
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; SSE-NEXT: por %xmm0, %xmm1
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,2,3]
|
||||
; SSE-NEXT: por %xmm1, %xmm0
|
||||
; SSE-NEXT: movd %xmm0, %eax
|
||||
; SSE-NEXT: movmskps %xmm0, %eax
|
||||
; SSE-NEXT: negl %eax
|
||||
; SSE-NEXT: sbbl %eax, %eax
|
||||
; SSE-NEXT: cltq
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
|
|
@ -420,11 +364,9 @@ define i64 @test_v4i64_legal(<4 x i64> %a0, <4 x i64> %a1) {
|
|||
; AVX1-NEXT: vpcmpgtq %xmm2, %xmm3, %xmm2
|
||||
; AVX1-NEXT: vpcmpgtq %xmm1, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpacksswb %xmm2, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX1-NEXT: vpor %xmm1, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; AVX1-NEXT: vpor %xmm1, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vmovd %xmm0, %eax
|
||||
; AVX1-NEXT: vmovmskps %xmm0, %eax
|
||||
; AVX1-NEXT: negl %eax
|
||||
; AVX1-NEXT: sbbl %eax, %eax
|
||||
; AVX1-NEXT: cltq
|
||||
; AVX1-NEXT: vzeroupper
|
||||
; AVX1-NEXT: retq
|
||||
|
|
@ -434,11 +376,9 @@ define i64 @test_v4i64_legal(<4 x i64> %a0, <4 x i64> %a1) {
|
|||
; AVX2-NEXT: vpcmpgtq %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
||||
; AVX2-NEXT: vpacksswb %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX2-NEXT: vpor %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; AVX2-NEXT: vpor %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vmovd %xmm0, %eax
|
||||
; AVX2-NEXT: vmovmskps %xmm0, %eax
|
||||
; AVX2-NEXT: negl %eax
|
||||
; AVX2-NEXT: sbbl %eax, %eax
|
||||
; AVX2-NEXT: cltq
|
||||
; AVX2-NEXT: vzeroupper
|
||||
; AVX2-NEXT: retq
|
||||
|
|
@ -470,21 +410,17 @@ define i32 @test_v4i32(<4 x i32> %a0, <4 x i32> %a1) {
|
|||
; SSE-LABEL: test_v4i32:
|
||||
; SSE: # BB#0:
|
||||
; SSE-NEXT: pcmpgtd %xmm1, %xmm0
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; SSE-NEXT: por %xmm0, %xmm1
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,2,3]
|
||||
; SSE-NEXT: por %xmm1, %xmm0
|
||||
; SSE-NEXT: movd %xmm0, %eax
|
||||
; SSE-NEXT: movmskps %xmm0, %eax
|
||||
; SSE-NEXT: negl %eax
|
||||
; SSE-NEXT: sbbl %eax, %eax
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX-LABEL: test_v4i32:
|
||||
; AVX: # BB#0:
|
||||
; AVX-NEXT: vpcmpgtd %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX-NEXT: vpor %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; AVX-NEXT: vpor %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vmovd %xmm0, %eax
|
||||
; AVX-NEXT: vmovmskps %xmm0, %eax
|
||||
; AVX-NEXT: negl %eax
|
||||
; AVX-NEXT: sbbl %eax, %eax
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: test_v4i32:
|
||||
|
|
@ -514,11 +450,9 @@ define i32 @test_v8i32(<8 x i32> %a0, <8 x i32> %a1) {
|
|||
; SSE-NEXT: pcmpgtd %xmm3, %xmm1
|
||||
; SSE-NEXT: pcmpgtd %xmm2, %xmm0
|
||||
; SSE-NEXT: por %xmm1, %xmm0
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; SSE-NEXT: por %xmm0, %xmm1
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,2,3]
|
||||
; SSE-NEXT: por %xmm1, %xmm0
|
||||
; SSE-NEXT: movd %xmm0, %eax
|
||||
; SSE-NEXT: movmskps %xmm0, %eax
|
||||
; SSE-NEXT: negl %eax
|
||||
; SSE-NEXT: sbbl %eax, %eax
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX1-LABEL: test_v8i32:
|
||||
|
|
@ -528,25 +462,18 @@ define i32 @test_v8i32(<8 x i32> %a0, <8 x i32> %a1) {
|
|||
; AVX1-NEXT: vpcmpgtd %xmm2, %xmm3, %xmm2
|
||||
; AVX1-NEXT: vpcmpgtd %xmm1, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
|
||||
; AVX1-NEXT: vorps %ymm2, %ymm0, %ymm0
|
||||
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX1-NEXT: vorps %ymm1, %ymm0, %ymm0
|
||||
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; AVX1-NEXT: vorps %ymm1, %ymm0, %ymm0
|
||||
; AVX1-NEXT: vmovd %xmm0, %eax
|
||||
; AVX1-NEXT: vmovmskps %ymm0, %eax
|
||||
; AVX1-NEXT: negl %eax
|
||||
; AVX1-NEXT: sbbl %eax, %eax
|
||||
; AVX1-NEXT: vzeroupper
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX2-LABEL: test_v8i32:
|
||||
; AVX2: # BB#0:
|
||||
; AVX2-NEXT: vpcmpgtd %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
||||
; AVX2-NEXT: vpor %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX2-NEXT: vpor %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; AVX2-NEXT: vpor %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vmovd %xmm0, %eax
|
||||
; AVX2-NEXT: vmovmskps %ymm0, %eax
|
||||
; AVX2-NEXT: negl %eax
|
||||
; AVX2-NEXT: sbbl %eax, %eax
|
||||
; AVX2-NEXT: vzeroupper
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
|
|
@ -581,15 +508,9 @@ define i32 @test_v8i32_legal(<8 x i32> %a0, <8 x i32> %a1) {
|
|||
; SSE-NEXT: pcmpgtd %xmm3, %xmm1
|
||||
; SSE-NEXT: pcmpgtd %xmm2, %xmm0
|
||||
; SSE-NEXT: packsswb %xmm1, %xmm0
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; SSE-NEXT: por %xmm0, %xmm1
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,2,3]
|
||||
; SSE-NEXT: por %xmm1, %xmm0
|
||||
; SSE-NEXT: movdqa %xmm0, %xmm1
|
||||
; SSE-NEXT: psrld $16, %xmm1
|
||||
; SSE-NEXT: por %xmm0, %xmm1
|
||||
; SSE-NEXT: movd %xmm1, %eax
|
||||
; SSE-NEXT: cwtl
|
||||
; SSE-NEXT: pmovmskb %xmm0, %eax
|
||||
; SSE-NEXT: negl %eax
|
||||
; SSE-NEXT: sbbl %eax, %eax
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX1-LABEL: test_v8i32_legal:
|
||||
|
|
@ -599,14 +520,9 @@ define i32 @test_v8i32_legal(<8 x i32> %a0, <8 x i32> %a1) {
|
|||
; AVX1-NEXT: vpcmpgtd %xmm2, %xmm3, %xmm2
|
||||
; AVX1-NEXT: vpcmpgtd %xmm1, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpacksswb %xmm2, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX1-NEXT: vpor %xmm1, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; AVX1-NEXT: vpor %xmm1, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpsrld $16, %xmm0, %xmm1
|
||||
; AVX1-NEXT: vpor %xmm1, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vmovd %xmm0, %eax
|
||||
; AVX1-NEXT: cwtl
|
||||
; AVX1-NEXT: vpmovmskb %xmm0, %eax
|
||||
; AVX1-NEXT: negl %eax
|
||||
; AVX1-NEXT: sbbl %eax, %eax
|
||||
; AVX1-NEXT: vzeroupper
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
|
|
@ -615,14 +531,9 @@ define i32 @test_v8i32_legal(<8 x i32> %a0, <8 x i32> %a1) {
|
|||
; AVX2-NEXT: vpcmpgtd %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
||||
; AVX2-NEXT: vpacksswb %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX2-NEXT: vpor %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; AVX2-NEXT: vpor %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpsrld $16, %xmm0, %xmm1
|
||||
; AVX2-NEXT: vpor %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vmovd %xmm0, %eax
|
||||
; AVX2-NEXT: cwtl
|
||||
; AVX2-NEXT: vpmovmskb %xmm0, %eax
|
||||
; AVX2-NEXT: negl %eax
|
||||
; AVX2-NEXT: sbbl %eax, %eax
|
||||
; AVX2-NEXT: vzeroupper
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
|
|
@ -656,27 +567,18 @@ define i16 @test_v8i16(<8 x i16> %a0, <8 x i16> %a1) {
|
|||
; SSE-LABEL: test_v8i16:
|
||||
; SSE: # BB#0:
|
||||
; SSE-NEXT: pcmpgtw %xmm1, %xmm0
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; SSE-NEXT: por %xmm0, %xmm1
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,2,3]
|
||||
; SSE-NEXT: por %xmm1, %xmm0
|
||||
; SSE-NEXT: movdqa %xmm0, %xmm1
|
||||
; SSE-NEXT: psrld $16, %xmm1
|
||||
; SSE-NEXT: por %xmm0, %xmm1
|
||||
; SSE-NEXT: movd %xmm1, %eax
|
||||
; SSE-NEXT: pmovmskb %xmm0, %eax
|
||||
; SSE-NEXT: negl %eax
|
||||
; SSE-NEXT: sbbl %eax, %eax
|
||||
; SSE-NEXT: # kill: %AX<def> %AX<kill> %EAX<kill>
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX-LABEL: test_v8i16:
|
||||
; AVX: # BB#0:
|
||||
; AVX-NEXT: vpcmpgtw %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX-NEXT: vpor %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; AVX-NEXT: vpor %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpsrld $16, %xmm0, %xmm1
|
||||
; AVX-NEXT: vpor %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vmovd %xmm0, %eax
|
||||
; AVX-NEXT: vpmovmskb %xmm0, %eax
|
||||
; AVX-NEXT: negl %eax
|
||||
; AVX-NEXT: sbbl %eax, %eax
|
||||
; AVX-NEXT: # kill: %AX<def> %AX<kill> %EAX<kill>
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
|
|
@ -711,14 +613,9 @@ define i16 @test_v16i16(<16 x i16> %a0, <16 x i16> %a1) {
|
|||
; SSE-NEXT: pcmpgtw %xmm3, %xmm1
|
||||
; SSE-NEXT: pcmpgtw %xmm2, %xmm0
|
||||
; SSE-NEXT: por %xmm1, %xmm0
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; SSE-NEXT: por %xmm0, %xmm1
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,2,3]
|
||||
; SSE-NEXT: por %xmm1, %xmm0
|
||||
; SSE-NEXT: movdqa %xmm0, %xmm1
|
||||
; SSE-NEXT: psrld $16, %xmm1
|
||||
; SSE-NEXT: por %xmm0, %xmm1
|
||||
; SSE-NEXT: movd %xmm1, %eax
|
||||
; SSE-NEXT: pmovmskb %xmm0, %eax
|
||||
; SSE-NEXT: negl %eax
|
||||
; SSE-NEXT: sbbl %eax, %eax
|
||||
; SSE-NEXT: # kill: %AX<def> %AX<kill> %EAX<kill>
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
|
|
@ -744,15 +641,9 @@ define i16 @test_v16i16(<16 x i16> %a0, <16 x i16> %a1) {
|
|||
; AVX2-LABEL: test_v16i16:
|
||||
; AVX2: # BB#0:
|
||||
; AVX2-NEXT: vpcmpgtw %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
||||
; AVX2-NEXT: vpor %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX2-NEXT: vpor %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; AVX2-NEXT: vpor %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpsrld $16, %xmm0, %xmm1
|
||||
; AVX2-NEXT: vpor %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vmovd %xmm0, %eax
|
||||
; AVX2-NEXT: vpmovmskb %ymm0, %eax
|
||||
; AVX2-NEXT: negl %eax
|
||||
; AVX2-NEXT: sbbl %eax, %eax
|
||||
; AVX2-NEXT: # kill: %AX<def> %AX<kill> %EAX<kill>
|
||||
; AVX2-NEXT: vzeroupper
|
||||
; AVX2-NEXT: retq
|
||||
|
|
@ -792,18 +683,9 @@ define i16 @test_v16i16_legal(<16 x i16> %a0, <16 x i16> %a1) {
|
|||
; SSE-NEXT: pcmpgtw %xmm3, %xmm1
|
||||
; SSE-NEXT: pcmpgtw %xmm2, %xmm0
|
||||
; SSE-NEXT: packsswb %xmm1, %xmm0
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; SSE-NEXT: por %xmm0, %xmm1
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,2,3]
|
||||
; SSE-NEXT: por %xmm1, %xmm0
|
||||
; SSE-NEXT: movdqa %xmm0, %xmm1
|
||||
; SSE-NEXT: psrld $16, %xmm1
|
||||
; SSE-NEXT: por %xmm0, %xmm1
|
||||
; SSE-NEXT: movdqa %xmm1, %xmm0
|
||||
; SSE-NEXT: psrlw $8, %xmm0
|
||||
; SSE-NEXT: por %xmm1, %xmm0
|
||||
; SSE-NEXT: pextrb $0, %xmm0, %eax
|
||||
; SSE-NEXT: movsbl %al, %eax
|
||||
; SSE-NEXT: pmovmskb %xmm0, %eax
|
||||
; SSE-NEXT: negl %eax
|
||||
; SSE-NEXT: sbbl %eax, %eax
|
||||
; SSE-NEXT: # kill: %AX<def> %AX<kill> %EAX<kill>
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
|
|
@ -814,16 +696,9 @@ define i16 @test_v16i16_legal(<16 x i16> %a0, <16 x i16> %a1) {
|
|||
; AVX1-NEXT: vpcmpgtw %xmm2, %xmm3, %xmm2
|
||||
; AVX1-NEXT: vpcmpgtw %xmm1, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpacksswb %xmm2, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX1-NEXT: vpor %xmm1, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; AVX1-NEXT: vpor %xmm1, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpsrld $16, %xmm0, %xmm1
|
||||
; AVX1-NEXT: vpor %xmm1, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpsrlw $8, %xmm0, %xmm1
|
||||
; AVX1-NEXT: vpor %xmm1, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpextrb $0, %xmm0, %eax
|
||||
; AVX1-NEXT: movsbl %al, %eax
|
||||
; AVX1-NEXT: vpmovmskb %xmm0, %eax
|
||||
; AVX1-NEXT: negl %eax
|
||||
; AVX1-NEXT: sbbl %eax, %eax
|
||||
; AVX1-NEXT: # kill: %AX<def> %AX<kill> %EAX<kill>
|
||||
; AVX1-NEXT: vzeroupper
|
||||
; AVX1-NEXT: retq
|
||||
|
|
@ -833,16 +708,9 @@ define i16 @test_v16i16_legal(<16 x i16> %a0, <16 x i16> %a1) {
|
|||
; AVX2-NEXT: vpcmpgtw %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
||||
; AVX2-NEXT: vpacksswb %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX2-NEXT: vpor %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; AVX2-NEXT: vpor %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpsrld $16, %xmm0, %xmm1
|
||||
; AVX2-NEXT: vpor %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpsrlw $8, %xmm0, %xmm1
|
||||
; AVX2-NEXT: vpor %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpextrb $0, %xmm0, %eax
|
||||
; AVX2-NEXT: movsbl %al, %eax
|
||||
; AVX2-NEXT: vpmovmskb %xmm0, %eax
|
||||
; AVX2-NEXT: negl %eax
|
||||
; AVX2-NEXT: sbbl %eax, %eax
|
||||
; AVX2-NEXT: # kill: %AX<def> %AX<kill> %EAX<kill>
|
||||
; AVX2-NEXT: vzeroupper
|
||||
; AVX2-NEXT: retq
|
||||
|
|
@ -882,32 +750,18 @@ define i8 @test_v16i8(<16 x i8> %a0, <16 x i8> %a1) {
|
|||
; SSE-LABEL: test_v16i8:
|
||||
; SSE: # BB#0:
|
||||
; SSE-NEXT: pcmpgtb %xmm1, %xmm0
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; SSE-NEXT: por %xmm0, %xmm1
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,2,3]
|
||||
; SSE-NEXT: por %xmm1, %xmm0
|
||||
; SSE-NEXT: movdqa %xmm0, %xmm1
|
||||
; SSE-NEXT: psrld $16, %xmm1
|
||||
; SSE-NEXT: por %xmm0, %xmm1
|
||||
; SSE-NEXT: movdqa %xmm1, %xmm0
|
||||
; SSE-NEXT: psrlw $8, %xmm0
|
||||
; SSE-NEXT: por %xmm1, %xmm0
|
||||
; SSE-NEXT: pextrb $0, %xmm0, %eax
|
||||
; SSE-NEXT: pmovmskb %xmm0, %eax
|
||||
; SSE-NEXT: negl %eax
|
||||
; SSE-NEXT: sbbl %eax, %eax
|
||||
; SSE-NEXT: # kill: %AL<def> %AL<kill> %EAX<kill>
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX-LABEL: test_v16i8:
|
||||
; AVX: # BB#0:
|
||||
; AVX-NEXT: vpcmpgtb %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX-NEXT: vpor %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; AVX-NEXT: vpor %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpsrld $16, %xmm0, %xmm1
|
||||
; AVX-NEXT: vpor %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpsrlw $8, %xmm0, %xmm1
|
||||
; AVX-NEXT: vpor %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpextrb $0, %xmm0, %eax
|
||||
; AVX-NEXT: vpmovmskb %xmm0, %eax
|
||||
; AVX-NEXT: negl %eax
|
||||
; AVX-NEXT: sbbl %eax, %eax
|
||||
; AVX-NEXT: # kill: %AL<def> %AL<kill> %EAX<kill>
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
|
|
@ -946,17 +800,9 @@ define i8 @test_v32i8(<32 x i8> %a0, <32 x i8> %a1) {
|
|||
; SSE-NEXT: pcmpgtb %xmm3, %xmm1
|
||||
; SSE-NEXT: pcmpgtb %xmm2, %xmm0
|
||||
; SSE-NEXT: por %xmm1, %xmm0
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; SSE-NEXT: por %xmm0, %xmm1
|
||||
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,2,3]
|
||||
; SSE-NEXT: por %xmm1, %xmm0
|
||||
; SSE-NEXT: movdqa %xmm0, %xmm1
|
||||
; SSE-NEXT: psrld $16, %xmm1
|
||||
; SSE-NEXT: por %xmm0, %xmm1
|
||||
; SSE-NEXT: movdqa %xmm1, %xmm0
|
||||
; SSE-NEXT: psrlw $8, %xmm0
|
||||
; SSE-NEXT: por %xmm1, %xmm0
|
||||
; SSE-NEXT: pextrb $0, %xmm0, %eax
|
||||
; SSE-NEXT: pmovmskb %xmm0, %eax
|
||||
; SSE-NEXT: negl %eax
|
||||
; SSE-NEXT: sbbl %eax, %eax
|
||||
; SSE-NEXT: # kill: %AL<def> %AL<kill> %EAX<kill>
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
|
|
@ -984,17 +830,9 @@ define i8 @test_v32i8(<32 x i8> %a0, <32 x i8> %a1) {
|
|||
; AVX2-LABEL: test_v32i8:
|
||||
; AVX2: # BB#0:
|
||||
; AVX2-NEXT: vpcmpgtb %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
|
||||
; AVX2-NEXT: vpor %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
|
||||
; AVX2-NEXT: vpor %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[1,1,2,3]
|
||||
; AVX2-NEXT: vpor %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpsrld $16, %xmm0, %xmm1
|
||||
; AVX2-NEXT: vpor %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpsrlw $8, %xmm0, %xmm1
|
||||
; AVX2-NEXT: vpor %ymm1, %ymm0, %ymm0
|
||||
; AVX2-NEXT: vpextrb $0, %xmm0, %eax
|
||||
; AVX2-NEXT: vpmovmskb %ymm0, %eax
|
||||
; AVX2-NEXT: negl %eax
|
||||
; AVX2-NEXT: sbbl %eax, %eax
|
||||
; AVX2-NEXT: # kill: %AL<def> %AL<kill> %EAX<kill>
|
||||
; AVX2-NEXT: vzeroupper
|
||||
; AVX2-NEXT: retq
|
||||
|
|
|
|||
Loading…
Reference in New Issue