forked from OSchip/llvm-project
[SelectionDAG] Support 'bit preserving' floating points bitcasts on computeKnownBits/ComputeNumSignBits
For cases where we know the floating point representations match the bitcasted integer equivalent, allow bitcasting to these types. This is especially useful for the X86 floating point compare results which return all/zero bits but as a floating point type. Differential Revision: https://reviews.llvm.org/D39289 llvm-svn: 316831
This commit is contained in:
Simon Pilgrim
parent
1496d188a0
commit
d09c1ac20f
|
|
@ -2096,6 +2096,12 @@ void SelectionDAG::computeKnownBits(SDValue Op, KnownBits &Known,
|
|||
Known.Zero = ~Known.One;
|
||||
return;
|
||||
}
|
||||
if (auto *C = dyn_cast<ConstantFPSDNode>(Op)) {
|
||||
// We know all of the bits for a constant fp!
|
||||
Known.One = C->getValueAPF().bitcastToAPInt();
|
||||
Known.Zero = ~Known.One;
|
||||
return;
|
||||
}
|
||||
|
||||
if (Depth == 6)
|
||||
return; // Limit search depth.
|
||||
|
|
@ -2219,10 +2225,11 @@ void SelectionDAG::computeKnownBits(SDValue Op, KnownBits &Known,
|
|||
}
|
||||
case ISD::BITCAST: {
|
||||
SDValue N0 = Op.getOperand(0);
|
||||
unsigned SubBitWidth = N0.getScalarValueSizeInBits();
|
||||
EVT SubVT = N0.getValueType();
|
||||
unsigned SubBitWidth = SubVT.getScalarSizeInBits();
|
||||
|
||||
// Ignore bitcasts from floating point.
|
||||
if (!N0.getValueType().isInteger())
|
||||
// Ignore bitcasts from unsupported types.
|
||||
if (!(SubVT.isInteger() || SubVT.isFloatingPoint()))
|
||||
break;
|
||||
|
||||
// Fast handling of 'identity' bitcasts.
|
||||
|
|
@ -2960,7 +2967,7 @@ unsigned SelectionDAG::ComputeNumSignBits(SDValue Op, unsigned Depth) const {
|
|||
unsigned SelectionDAG::ComputeNumSignBits(SDValue Op, const APInt &DemandedElts,
|
||||
unsigned Depth) const {
|
||||
EVT VT = Op.getValueType();
|
||||
assert(VT.isInteger() && "Invalid VT!");
|
||||
assert((VT.isInteger() || VT.isFloatingPoint()) && "Invalid VT!");
|
||||
unsigned VTBits = VT.getScalarSizeInBits();
|
||||
unsigned NumElts = DemandedElts.getBitWidth();
|
||||
unsigned Tmp, Tmp2;
|
||||
|
|
@ -3041,10 +3048,11 @@ unsigned SelectionDAG::ComputeNumSignBits(SDValue Op, const APInt &DemandedElts,
|
|||
|
||||
case ISD::BITCAST: {
|
||||
SDValue N0 = Op.getOperand(0);
|
||||
unsigned SrcBits = N0.getScalarValueSizeInBits();
|
||||
EVT SrcVT = N0.getValueType();
|
||||
unsigned SrcBits = SrcVT.getScalarSizeInBits();
|
||||
|
||||
// Ignore bitcasts from floating point.
|
||||
if (!N0.getValueType().isInteger())
|
||||
// Ignore bitcasts from unsupported types..
|
||||
if (!(SrcVT.isInteger() || SrcVT.isFloatingPoint()))
|
||||
break;
|
||||
|
||||
// Fast handling of 'identity' bitcasts.
|
||||
|
|
|
|||
|
|
@ -1245,7 +1245,7 @@ define <2 x i64> @test46(<2 x float> %x, <2 x float> %y) #0 {
|
|||
; KNL: ## BB#0:
|
||||
; KNL-NEXT: vcmpeqps %xmm1, %xmm0, %xmm0
|
||||
; KNL-NEXT: vpmovsxdq %xmm0, %xmm0
|
||||
; KNL-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
|
||||
; KNL-NEXT: vpsrlq $63, %xmm0, %xmm0
|
||||
; KNL-NEXT: retq
|
||||
;
|
||||
; SKX-LABEL: test46:
|
||||
|
|
|
|||
|
|
@ -274,50 +274,19 @@ define i8 @v8i32(<8 x i32> %a, <8 x i32> %b, <8 x i32> %c, <8 x i32> %d) {
|
|||
}
|
||||
|
||||
define i8 @v8f32(<8 x float> %a, <8 x float> %b, <8 x float> %c, <8 x float> %d) {
|
||||
; SSE2-LABEL: v8f32:
|
||||
; SSE2: # BB#0:
|
||||
; SSE2-NEXT: cmpltps %xmm1, %xmm3
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm1 = xmm3[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: cmpltps %xmm0, %xmm2
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm2[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: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; SSE2-NEXT: cmpltps %xmm5, %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: cmpltps %xmm4, %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 %xmm0, %xmm2
|
||||
; SSE2-NEXT: packsswb %xmm0, %xmm2
|
||||
; SSE2-NEXT: pmovmskb %xmm2, %eax
|
||||
; SSE2-NEXT: # kill: %AL<def> %AL<kill> %EAX<kill>
|
||||
; SSE2-NEXT: ret{{[l|q]}}
|
||||
;
|
||||
; SSSE3-LABEL: v8f32:
|
||||
; SSSE3: # BB#0:
|
||||
; SSSE3-NEXT: cmpltps %xmm1, %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, %xmm3
|
||||
; SSSE3-NEXT: cmpltps %xmm0, %xmm2
|
||||
; SSSE3-NEXT: pshufb %xmm1, %xmm2
|
||||
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm3[0]
|
||||
; SSSE3-NEXT: cmpltps %xmm5, %xmm7
|
||||
; SSSE3-NEXT: pshufb %xmm1, %xmm7
|
||||
; SSSE3-NEXT: cmpltps %xmm4, %xmm6
|
||||
; SSSE3-NEXT: pshufb %xmm1, %xmm6
|
||||
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm6 = xmm6[0],xmm7[0]
|
||||
; SSSE3-NEXT: pand %xmm2, %xmm6
|
||||
; SSSE3-NEXT: packsswb %xmm0, %xmm6
|
||||
; SSSE3-NEXT: pmovmskb %xmm6, %eax
|
||||
; SSSE3-NEXT: # kill: %AL<def> %AL<kill> %EAX<kill>
|
||||
; SSSE3-NEXT: ret{{[l|q]}}
|
||||
; SSE2-SSSE3-LABEL: v8f32:
|
||||
; SSE2-SSSE3: # BB#0:
|
||||
; SSE2-SSSE3-NEXT: cmpltps %xmm1, %xmm3
|
||||
; SSE2-SSSE3-NEXT: cmpltps %xmm0, %xmm2
|
||||
; SSE2-SSSE3-NEXT: packssdw %xmm3, %xmm2
|
||||
; SSE2-SSSE3-NEXT: cmpltps %xmm5, %xmm7
|
||||
; SSE2-SSSE3-NEXT: cmpltps %xmm4, %xmm6
|
||||
; SSE2-SSSE3-NEXT: packssdw %xmm7, %xmm6
|
||||
; SSE2-SSSE3-NEXT: pand %xmm2, %xmm6
|
||||
; SSE2-SSSE3-NEXT: packsswb %xmm0, %xmm6
|
||||
; SSE2-SSSE3-NEXT: pmovmskb %xmm6, %eax
|
||||
; SSE2-SSSE3-NEXT: # kill: %AL<def> %AL<kill> %EAX<kill>
|
||||
; SSE2-SSSE3-NEXT: ret{{[l|q]}}
|
||||
;
|
||||
; AVX12-LABEL: v8f32:
|
||||
; AVX12: # BB#0:
|
||||
|
|
|
|||
|
|
@ -135,15 +135,10 @@ define i8 @v8i64(<8 x i64> %a, <8 x i64> %b, <8 x i64> %c, <8 x i64> %d) {
|
|||
define i8 @v8f64(<8 x double> %a, <8 x double> %b, <8 x double> %c, <8 x double> %d) {
|
||||
; SSE-LABEL: v8f64:
|
||||
; SSE: # BB#0:
|
||||
; SSE-NEXT: movapd {{[0-9]+}}(%rsp), %xmm8
|
||||
; SSE-NEXT: movapd {{[0-9]+}}(%rsp), %xmm9
|
||||
; SSE-NEXT: movapd {{[0-9]+}}(%rsp), %xmm10
|
||||
; SSE-NEXT: movapd {{[0-9]+}}(%rsp), %xmm8
|
||||
; SSE-NEXT: movapd {{[0-9]+}}(%rsp), %xmm11
|
||||
; SSE-NEXT: cmpltpd %xmm3, %xmm7
|
||||
; SSE-NEXT: cmpltpd %xmm2, %xmm6
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm6 = xmm6[0,2],xmm7[0,2]
|
||||
; SSE-NEXT: movdqa {{.*#+}} xmm2 = [0,1,4,5,4,5,6,7,0,1,4,5,8,9,12,13]
|
||||
; SSE-NEXT: pshufb %xmm2, %xmm6
|
||||
; SSE-NEXT: cmpltpd %xmm1, %xmm5
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm5 = xmm5[0,2,2,3]
|
||||
; SSE-NEXT: pshuflw {{.*#+}} xmm1 = xmm5[0,2,2,3,4,5,6,7]
|
||||
|
|
@ -151,24 +146,28 @@ define i8 @v8f64(<8 x double> %a, <8 x double> %b, <8 x double> %c, <8 x double>
|
|||
; SSE-NEXT: shufps {{.*#+}} xmm4 = xmm4[0,2,2,3]
|
||||
; SSE-NEXT: pshuflw {{.*#+}} xmm0 = xmm4[0,2,2,3,4,5,6,7]
|
||||
; SSE-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
|
||||
; SSE-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm6[4,5,6,7]
|
||||
; SSE-NEXT: cmpltpd %xmm3, %xmm7
|
||||
; SSE-NEXT: cmpltpd %xmm2, %xmm6
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm6 = xmm6[0,2],xmm7[0,2]
|
||||
; SSE-NEXT: packssdw %xmm6, %xmm6
|
||||
; SSE-NEXT: pblendw {{.*#+}} xmm6 = xmm0[0,1,2,3],xmm6[4,5,6,7]
|
||||
; SSE-NEXT: cmpltpd {{[0-9]+}}(%rsp), %xmm11
|
||||
; SSE-NEXT: cmpltpd {{[0-9]+}}(%rsp), %xmm8
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm8 = xmm8[0,2],xmm11[0,2]
|
||||
; SSE-NEXT: pshufb %xmm2, %xmm8
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm11 = xmm11[0,2,2,3]
|
||||
; SSE-NEXT: pshuflw {{.*#+}} xmm0 = xmm11[0,2,2,3,4,5,6,7]
|
||||
; SSE-NEXT: cmpltpd {{[0-9]+}}(%rsp), %xmm10
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm10 = xmm10[0,2,2,3]
|
||||
; SSE-NEXT: pshuflw {{.*#+}} xmm1 = xmm10[0,2,2,3,4,5,6,7]
|
||||
; SSE-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
|
||||
; SSE-NEXT: cmpltpd {{[0-9]+}}(%rsp), %xmm9
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm9 = xmm9[0,2,2,3]
|
||||
; SSE-NEXT: pshuflw {{.*#+}} xmm2 = xmm9[0,2,2,3,4,5,6,7]
|
||||
; SSE-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
|
||||
; SSE-NEXT: pblendw {{.*#+}} xmm2 = xmm2[0,1,2,3],xmm8[4,5,6,7]
|
||||
; SSE-NEXT: pand %xmm0, %xmm2
|
||||
; SSE-NEXT: psllw $15, %xmm2
|
||||
; SSE-NEXT: psraw $15, %xmm2
|
||||
; SSE-NEXT: packsswb %xmm0, %xmm2
|
||||
; SSE-NEXT: pmovmskb %xmm2, %eax
|
||||
; SSE-NEXT: cmpltpd {{[0-9]+}}(%rsp), %xmm8
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm8 = xmm8[0,2],xmm9[0,2]
|
||||
; SSE-NEXT: packssdw %xmm8, %xmm8
|
||||
; SSE-NEXT: pblendw {{.*#+}} xmm8 = xmm1[0,1,2,3],xmm8[4,5,6,7]
|
||||
; SSE-NEXT: pand %xmm6, %xmm8
|
||||
; SSE-NEXT: psllw $15, %xmm8
|
||||
; SSE-NEXT: psraw $15, %xmm8
|
||||
; SSE-NEXT: packsswb %xmm0, %xmm8
|
||||
; SSE-NEXT: pmovmskb %xmm8, %eax
|
||||
; SSE-NEXT: # kill: %AL<def> %AL<kill> %EAX<kill>
|
||||
; SSE-NEXT: ret{{[l|q]}}
|
||||
;
|
||||
|
|
@ -718,37 +717,23 @@ define i16 @v16f32(<16 x float> %a, <16 x float> %b, <16 x float> %c, <16 x floa
|
|||
; SSE-LABEL: v16f32:
|
||||
; SSE: # BB#0:
|
||||
; SSE-NEXT: movaps {{[0-9]+}}(%rsp), %xmm8
|
||||
; SSE-NEXT: movaps {{[0-9]+}}(%rsp), %xmm10
|
||||
; SSE-NEXT: movaps {{[0-9]+}}(%rsp), %xmm9
|
||||
; SSE-NEXT: movaps {{[0-9]+}}(%rsp), %xmm10
|
||||
; SSE-NEXT: movaps {{[0-9]+}}(%rsp), %xmm11
|
||||
; SSE-NEXT: cmpltps %xmm3, %xmm7
|
||||
; SSE-NEXT: movdqa {{.*#+}} xmm3 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
|
||||
; SSE-NEXT: pshufb %xmm3, %xmm7
|
||||
; SSE-NEXT: cmpltps %xmm2, %xmm6
|
||||
; SSE-NEXT: pshufb %xmm3, %xmm6
|
||||
; SSE-NEXT: punpcklqdq {{.*#+}} xmm6 = xmm6[0],xmm7[0]
|
||||
; SSE-NEXT: movdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
|
||||
; SSE-NEXT: pshufb %xmm2, %xmm6
|
||||
; SSE-NEXT: packssdw %xmm7, %xmm6
|
||||
; SSE-NEXT: cmpltps %xmm1, %xmm5
|
||||
; SSE-NEXT: pshufb %xmm3, %xmm5
|
||||
; SSE-NEXT: cmpltps %xmm0, %xmm4
|
||||
; SSE-NEXT: pshufb %xmm3, %xmm4
|
||||
; SSE-NEXT: punpcklqdq {{.*#+}} xmm4 = xmm4[0],xmm5[0]
|
||||
; SSE-NEXT: pshufb %xmm2, %xmm4
|
||||
; SSE-NEXT: punpcklqdq {{.*#+}} xmm4 = xmm4[0],xmm6[0]
|
||||
; SSE-NEXT: packssdw %xmm5, %xmm4
|
||||
; SSE-NEXT: packsswb %xmm6, %xmm4
|
||||
; SSE-NEXT: cmpltps {{[0-9]+}}(%rsp), %xmm11
|
||||
; SSE-NEXT: pshufb %xmm3, %xmm11
|
||||
; SSE-NEXT: cmpltps {{[0-9]+}}(%rsp), %xmm9
|
||||
; SSE-NEXT: pshufb %xmm3, %xmm9
|
||||
; SSE-NEXT: punpcklqdq {{.*#+}} xmm9 = xmm9[0],xmm11[0]
|
||||
; SSE-NEXT: pshufb %xmm2, %xmm9
|
||||
; SSE-NEXT: cmpltps {{[0-9]+}}(%rsp), %xmm10
|
||||
; SSE-NEXT: pshufb %xmm3, %xmm10
|
||||
; SSE-NEXT: packssdw %xmm11, %xmm10
|
||||
; SSE-NEXT: cmpltps {{[0-9]+}}(%rsp), %xmm9
|
||||
; SSE-NEXT: cmpltps {{[0-9]+}}(%rsp), %xmm8
|
||||
; SSE-NEXT: pshufb %xmm3, %xmm8
|
||||
; SSE-NEXT: punpcklqdq {{.*#+}} xmm8 = xmm8[0],xmm10[0]
|
||||
; SSE-NEXT: pshufb %xmm2, %xmm8
|
||||
; SSE-NEXT: punpcklqdq {{.*#+}} xmm8 = xmm8[0],xmm9[0]
|
||||
; SSE-NEXT: packssdw %xmm9, %xmm8
|
||||
; SSE-NEXT: packsswb %xmm10, %xmm8
|
||||
; SSE-NEXT: pand %xmm4, %xmm8
|
||||
; SSE-NEXT: pmovmskb %xmm8, %eax
|
||||
; SSE-NEXT: # kill: %AX<def> %AX<kill> %EAX<kill>
|
||||
|
|
@ -759,22 +744,17 @@ define i16 @v16f32(<16 x float> %a, <16 x float> %b, <16 x float> %c, <16 x floa
|
|||
; AVX12-NEXT: vcmpltps %ymm1, %ymm3, %ymm1
|
||||
; AVX12-NEXT: vextractf128 $1, %ymm1, %xmm3
|
||||
; AVX12-NEXT: vpackssdw %xmm3, %xmm1, %xmm1
|
||||
; AVX12-NEXT: vmovdqa {{.*#+}} xmm3 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
|
||||
; AVX12-NEXT: vpshufb %xmm3, %xmm1, %xmm1
|
||||
; AVX12-NEXT: vcmpltps %ymm0, %ymm2, %ymm0
|
||||
; AVX12-NEXT: vextractf128 $1, %ymm0, %xmm2
|
||||
; AVX12-NEXT: vpackssdw %xmm2, %xmm0, %xmm0
|
||||
; AVX12-NEXT: vpshufb %xmm3, %xmm0, %xmm0
|
||||
; AVX12-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; AVX12-NEXT: vpacksswb %xmm1, %xmm0, %xmm0
|
||||
; AVX12-NEXT: vcmpltps %ymm5, %ymm7, %ymm1
|
||||
; AVX12-NEXT: vextractf128 $1, %ymm1, %xmm2
|
||||
; AVX12-NEXT: vpackssdw %xmm2, %xmm1, %xmm1
|
||||
; AVX12-NEXT: vpshufb %xmm3, %xmm1, %xmm1
|
||||
; AVX12-NEXT: vcmpltps %ymm4, %ymm6, %ymm2
|
||||
; AVX12-NEXT: vextractf128 $1, %ymm2, %xmm4
|
||||
; AVX12-NEXT: vpackssdw %xmm4, %xmm2, %xmm2
|
||||
; AVX12-NEXT: vpshufb %xmm3, %xmm2, %xmm2
|
||||
; AVX12-NEXT: vpunpcklqdq {{.*#+}} xmm1 = xmm2[0],xmm1[0]
|
||||
; AVX12-NEXT: vextractf128 $1, %ymm2, %xmm3
|
||||
; AVX12-NEXT: vpackssdw %xmm3, %xmm2, %xmm2
|
||||
; AVX12-NEXT: vpacksswb %xmm1, %xmm2, %xmm1
|
||||
; AVX12-NEXT: vpand %xmm1, %xmm0, %xmm0
|
||||
; AVX12-NEXT: vpmovmskb %xmm0, %eax
|
||||
; AVX12-NEXT: # kill: %AX<def> %AX<kill> %EAX<kill>
|
||||
|
|
|
|||
|
|
@ -12,38 +12,27 @@ define <8 x i32> @sext(<8 x float> %a, <8 x float> %b, <8 x i16> %c, <8 x i16> %
|
|||
; SSE2-LABEL: sext:
|
||||
; SSE2: # BB#0:
|
||||
; SSE2-NEXT: cmpltps %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: cmpltps %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 {{.*#+}} xmm2 = xmm0[0,2,2,3]
|
||||
; SSE2-NEXT: punpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm1[0]
|
||||
; SSE2-NEXT: pand %xmm2, %xmm4
|
||||
; SSE2-NEXT: pandn %xmm5, %xmm2
|
||||
; SSE2-NEXT: por %xmm4, %xmm2
|
||||
; SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
|
||||
; SSE2-NEXT: psrad $16, %xmm0
|
||||
; SSE2-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
|
||||
; SSE2-NEXT: packssdw %xmm1, %xmm0
|
||||
; SSE2-NEXT: pand %xmm0, %xmm4
|
||||
; SSE2-NEXT: pandn %xmm5, %xmm0
|
||||
; SSE2-NEXT: por %xmm4, %xmm0
|
||||
; SSE2-NEXT: punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3]
|
||||
; SSE2-NEXT: psrad $16, %xmm2
|
||||
; SSE2-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
|
||||
; SSE2-NEXT: psrad $16, %xmm1
|
||||
; SSE2-NEXT: movdqa %xmm2, %xmm0
|
||||
; SSE2-NEXT: retq
|
||||
;
|
||||
; SSE41-LABEL: sext:
|
||||
; SSE41: # BB#0:
|
||||
; SSE41-NEXT: cmpltps %xmm3, %xmm1
|
||||
; SSE41-NEXT: movdqa {{.*#+}} xmm3 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
|
||||
; SSE41-NEXT: pshufb %xmm3, %xmm1
|
||||
; SSE41-NEXT: cmpltps %xmm2, %xmm0
|
||||
; SSE41-NEXT: pshufb %xmm3, %xmm0
|
||||
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; SSE41-NEXT: pand %xmm0, %xmm4
|
||||
; SSE41-NEXT: pandn %xmm5, %xmm0
|
||||
; SSE41-NEXT: por %xmm4, %xmm0
|
||||
; SSE41-NEXT: pmovsxwd %xmm0, %xmm2
|
||||
; SSE41-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
|
||||
; SSE41-NEXT: pmovsxwd %xmm0, %xmm1
|
||||
; SSE41-NEXT: movdqa %xmm2, %xmm0
|
||||
; SSE41-NEXT: packssdw %xmm1, %xmm0
|
||||
; SSE41-NEXT: pblendvb %xmm0, %xmm4, %xmm5
|
||||
; SSE41-NEXT: pmovsxwd %xmm5, %xmm0
|
||||
; SSE41-NEXT: pshufd {{.*#+}} xmm1 = xmm5[2,3,0,1]
|
||||
; SSE41-NEXT: pmovsxwd %xmm1, %xmm1
|
||||
; SSE41-NEXT: retq
|
||||
;
|
||||
; AVX1-LABEL: sext:
|
||||
|
|
@ -76,39 +65,29 @@ define <8 x i32> @sext(<8 x float> %a, <8 x float> %b, <8 x i16> %c, <8 x i16> %
|
|||
define <8 x i32> @zext(<8 x float> %a, <8 x float> %b, <8 x i16> %c, <8 x i16> %d) {
|
||||
; SSE2-LABEL: zext:
|
||||
; SSE2: # BB#0:
|
||||
; SSE2-NEXT: movaps %xmm0, %xmm6
|
||||
; SSE2-NEXT: cmpltps %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 {{.*#+}} xmm3 = xmm1[0,2,2,3]
|
||||
; SSE2-NEXT: cmpltps %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 {{.*#+}} xmm1 = xmm0[0,2,2,3]
|
||||
; SSE2-NEXT: punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm3[0]
|
||||
; SSE2-NEXT: pand %xmm1, %xmm4
|
||||
; SSE2-NEXT: pandn %xmm5, %xmm1
|
||||
; SSE2-NEXT: por %xmm4, %xmm1
|
||||
; SSE2-NEXT: xorps %xmm2, %xmm2
|
||||
; SSE2-NEXT: movdqa %xmm1, %xmm0
|
||||
; SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
|
||||
; SSE2-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
|
||||
; SSE2-NEXT: cmpltps %xmm2, %xmm6
|
||||
; SSE2-NEXT: packssdw %xmm1, %xmm6
|
||||
; SSE2-NEXT: pand %xmm6, %xmm4
|
||||
; SSE2-NEXT: pandn %xmm5, %xmm6
|
||||
; SSE2-NEXT: por %xmm4, %xmm6
|
||||
; SSE2-NEXT: pxor %xmm1, %xmm1
|
||||
; SSE2-NEXT: movdqa %xmm6, %xmm0
|
||||
; SSE2-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
|
||||
; SSE2-NEXT: punpckhwd {{.*#+}} xmm6 = xmm6[4],xmm1[4],xmm6[5],xmm1[5],xmm6[6],xmm1[6],xmm6[7],xmm1[7]
|
||||
; SSE2-NEXT: movdqa %xmm6, %xmm1
|
||||
; SSE2-NEXT: retq
|
||||
;
|
||||
; SSE41-LABEL: zext:
|
||||
; SSE41: # BB#0:
|
||||
; SSE41-NEXT: cmpltps %xmm3, %xmm1
|
||||
; SSE41-NEXT: movdqa {{.*#+}} xmm3 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
|
||||
; SSE41-NEXT: pshufb %xmm3, %xmm1
|
||||
; SSE41-NEXT: cmpltps %xmm2, %xmm0
|
||||
; SSE41-NEXT: pshufb %xmm3, %xmm0
|
||||
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; SSE41-NEXT: pand %xmm0, %xmm4
|
||||
; SSE41-NEXT: pandn %xmm5, %xmm0
|
||||
; SSE41-NEXT: por %xmm4, %xmm0
|
||||
; SSE41-NEXT: pmovzxwd {{.*#+}} xmm2 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
|
||||
; SSE41-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
|
||||
; SSE41-NEXT: pmovzxwd {{.*#+}} xmm1 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
|
||||
; SSE41-NEXT: movdqa %xmm2, %xmm0
|
||||
; SSE41-NEXT: packssdw %xmm1, %xmm0
|
||||
; SSE41-NEXT: pblendvb %xmm0, %xmm4, %xmm5
|
||||
; SSE41-NEXT: pmovzxwd {{.*#+}} xmm0 = xmm5[0],zero,xmm5[1],zero,xmm5[2],zero,xmm5[3],zero
|
||||
; SSE41-NEXT: pshufd {{.*#+}} xmm1 = xmm5[2,3,0,1]
|
||||
; SSE41-NEXT: pmovzxwd {{.*#+}} xmm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero
|
||||
; SSE41-NEXT: retq
|
||||
;
|
||||
; AVX1-LABEL: zext:
|
||||
|
|
@ -306,25 +285,13 @@ define void @example25() nounwind {
|
|||
; SSE2-NEXT: movaps da+4096(%rax), %xmm1
|
||||
; SSE2-NEXT: movaps da+4112(%rax), %xmm2
|
||||
; SSE2-NEXT: cmpltps db+4112(%rax), %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: cmpltps db+4096(%rax), %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: punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm2[0]
|
||||
; SSE2-NEXT: packssdw %xmm2, %xmm1
|
||||
; SSE2-NEXT: movaps dc+4096(%rax), %xmm2
|
||||
; SSE2-NEXT: movaps dc+4112(%rax), %xmm3
|
||||
; SSE2-NEXT: cmpltps dd+4112(%rax), %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: cmpltps dd+4096(%rax), %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],xmm3[0]
|
||||
; SSE2-NEXT: packssdw %xmm3, %xmm2
|
||||
; SSE2-NEXT: pand %xmm1, %xmm2
|
||||
; SSE2-NEXT: movdqa %xmm2, %xmm1
|
||||
; SSE2-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
|
||||
|
|
@ -341,32 +308,27 @@ define void @example25() nounwind {
|
|||
; SSE41-LABEL: example25:
|
||||
; SSE41: # BB#0: # %vector.ph
|
||||
; SSE41-NEXT: movq $-4096, %rax # imm = 0xF000
|
||||
; SSE41-NEXT: movdqa {{.*#+}} xmm0 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
|
||||
; SSE41-NEXT: movdqa {{.*#+}} xmm1 = [1,1,1,1]
|
||||
; SSE41-NEXT: movdqa {{.*#+}} xmm0 = [1,1,1,1]
|
||||
; SSE41-NEXT: .p2align 4, 0x90
|
||||
; SSE41-NEXT: .LBB5_1: # %vector.body
|
||||
; SSE41-NEXT: # =>This Inner Loop Header: Depth=1
|
||||
; SSE41-NEXT: movaps da+4096(%rax), %xmm2
|
||||
; SSE41-NEXT: movaps da+4112(%rax), %xmm3
|
||||
; SSE41-NEXT: cmpltps db+4112(%rax), %xmm3
|
||||
; SSE41-NEXT: pshufb %xmm0, %xmm3
|
||||
; SSE41-NEXT: cmpltps db+4096(%rax), %xmm2
|
||||
; SSE41-NEXT: pshufb %xmm0, %xmm2
|
||||
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm3[0]
|
||||
; SSE41-NEXT: movaps dc+4096(%rax), %xmm3
|
||||
; SSE41-NEXT: movaps dc+4112(%rax), %xmm4
|
||||
; SSE41-NEXT: cmpltps dd+4112(%rax), %xmm4
|
||||
; SSE41-NEXT: pshufb %xmm0, %xmm4
|
||||
; SSE41-NEXT: cmpltps dd+4096(%rax), %xmm3
|
||||
; SSE41-NEXT: pshufb %xmm0, %xmm3
|
||||
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm3 = xmm3[0],xmm4[0]
|
||||
; SSE41-NEXT: pand %xmm2, %xmm3
|
||||
; SSE41-NEXT: pmovzxwd {{.*#+}} xmm2 = xmm3[0],zero,xmm3[1],zero,xmm3[2],zero,xmm3[3],zero
|
||||
; SSE41-NEXT: movaps da+4096(%rax), %xmm1
|
||||
; SSE41-NEXT: movaps da+4112(%rax), %xmm2
|
||||
; SSE41-NEXT: cmpltps db+4112(%rax), %xmm2
|
||||
; SSE41-NEXT: cmpltps db+4096(%rax), %xmm1
|
||||
; SSE41-NEXT: packssdw %xmm2, %xmm1
|
||||
; SSE41-NEXT: movaps dc+4096(%rax), %xmm2
|
||||
; SSE41-NEXT: movaps dc+4112(%rax), %xmm3
|
||||
; SSE41-NEXT: cmpltps dd+4112(%rax), %xmm3
|
||||
; SSE41-NEXT: cmpltps dd+4096(%rax), %xmm2
|
||||
; SSE41-NEXT: packssdw %xmm3, %xmm2
|
||||
; SSE41-NEXT: pand %xmm1, %xmm2
|
||||
; SSE41-NEXT: punpckhwd {{.*#+}} xmm3 = xmm3[4],xmm0[4],xmm3[5],xmm0[5],xmm3[6],xmm0[6],xmm3[7],xmm0[7]
|
||||
; SSE41-NEXT: pand %xmm1, %xmm3
|
||||
; SSE41-NEXT: movdqa %xmm3, dj+4112(%rax)
|
||||
; SSE41-NEXT: movdqa %xmm2, dj+4096(%rax)
|
||||
; SSE41-NEXT: pmovzxwd {{.*#+}} xmm1 = xmm2[0],zero,xmm2[1],zero,xmm2[2],zero,xmm2[3],zero
|
||||
; SSE41-NEXT: pand %xmm0, %xmm1
|
||||
; SSE41-NEXT: punpckhwd {{.*#+}} xmm2 = xmm2[4],xmm0[4],xmm2[5],xmm0[5],xmm2[6],xmm0[6],xmm2[7],xmm0[7]
|
||||
; SSE41-NEXT: pand %xmm0, %xmm2
|
||||
; SSE41-NEXT: movdqa %xmm2, dj+4112(%rax)
|
||||
; SSE41-NEXT: movdqa %xmm1, dj+4096(%rax)
|
||||
; SSE41-NEXT: addq $32, %rax
|
||||
; SSE41-NEXT: jne .LBB5_1
|
||||
; SSE41-NEXT: # BB#2: # %for.end
|
||||
|
|
@ -459,14 +421,8 @@ define void @example24(i16 signext %x, i16 signext %y) nounwind {
|
|||
; SSE2-NEXT: movaps da+4096(%rax), %xmm2
|
||||
; SSE2-NEXT: movaps da+4112(%rax), %xmm3
|
||||
; SSE2-NEXT: cmpltps db+4112(%rax), %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: cmpltps db+4096(%rax), %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],xmm3[0]
|
||||
; SSE2-NEXT: packssdw %xmm3, %xmm2
|
||||
; SSE2-NEXT: movdqa %xmm0, %xmm3
|
||||
; SSE2-NEXT: pand %xmm2, %xmm3
|
||||
; SSE2-NEXT: pandn %xmm1, %xmm2
|
||||
|
|
@ -486,31 +442,26 @@ define void @example24(i16 signext %x, i16 signext %y) nounwind {
|
|||
; SSE41: # BB#0: # %vector.ph
|
||||
; SSE41-NEXT: movd %edi, %xmm0
|
||||
; SSE41-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,0,0,0,4,5,6,7]
|
||||
; SSE41-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,0,1,1]
|
||||
; SSE41-NEXT: movd %esi, %xmm1
|
||||
; SSE41-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[0,0,0,0,4,5,6,7]
|
||||
; SSE41-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,0,1,1]
|
||||
; SSE41-NEXT: pshufd {{.*#+}} xmm1 = xmm0[0,0,1,1]
|
||||
; SSE41-NEXT: movd %esi, %xmm0
|
||||
; SSE41-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,0,0,0,4,5,6,7]
|
||||
; SSE41-NEXT: pshufd {{.*#+}} xmm2 = xmm0[0,0,1,1]
|
||||
; SSE41-NEXT: movq $-4096, %rax # imm = 0xF000
|
||||
; SSE41-NEXT: movdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
|
||||
; SSE41-NEXT: .p2align 4, 0x90
|
||||
; SSE41-NEXT: .LBB6_1: # %vector.body
|
||||
; SSE41-NEXT: # =>This Inner Loop Header: Depth=1
|
||||
; SSE41-NEXT: movaps da+4096(%rax), %xmm3
|
||||
; SSE41-NEXT: movaps da+4112(%rax), %xmm4
|
||||
; SSE41-NEXT: cmpltps db+4112(%rax), %xmm4
|
||||
; SSE41-NEXT: pshufb %xmm2, %xmm4
|
||||
; SSE41-NEXT: cmpltps db+4096(%rax), %xmm3
|
||||
; SSE41-NEXT: pshufb %xmm2, %xmm3
|
||||
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm3 = xmm3[0],xmm4[0]
|
||||
; SSE41-NEXT: movdqa %xmm0, %xmm4
|
||||
; SSE41-NEXT: pand %xmm3, %xmm4
|
||||
; SSE41-NEXT: pandn %xmm1, %xmm3
|
||||
; SSE41-NEXT: por %xmm4, %xmm3
|
||||
; SSE41-NEXT: pshufd {{.*#+}} xmm4 = xmm3[2,3,0,1]
|
||||
; SSE41-NEXT: pmovsxwd %xmm4, %xmm4
|
||||
; SSE41-NEXT: movaps da+4096(%rax), %xmm0
|
||||
; SSE41-NEXT: movaps da+4112(%rax), %xmm3
|
||||
; SSE41-NEXT: cmpltps db+4112(%rax), %xmm3
|
||||
; SSE41-NEXT: cmpltps db+4096(%rax), %xmm0
|
||||
; SSE41-NEXT: packssdw %xmm3, %xmm0
|
||||
; SSE41-NEXT: movdqa %xmm2, %xmm3
|
||||
; SSE41-NEXT: pblendvb %xmm0, %xmm1, %xmm3
|
||||
; SSE41-NEXT: pshufd {{.*#+}} xmm0 = xmm3[2,3,0,1]
|
||||
; SSE41-NEXT: pmovsxwd %xmm0, %xmm0
|
||||
; SSE41-NEXT: pmovsxwd %xmm3, %xmm3
|
||||
; SSE41-NEXT: movdqa %xmm3, dj+4096(%rax)
|
||||
; SSE41-NEXT: movdqa %xmm4, dj+4112(%rax)
|
||||
; SSE41-NEXT: movdqa %xmm0, dj+4112(%rax)
|
||||
; SSE41-NEXT: addq $32, %rax
|
||||
; SSE41-NEXT: jne .LBB6_1
|
||||
; SSE41-NEXT: # BB#2: # %for.end
|
||||
|
|
|
|||
|
|
@ -113,20 +113,15 @@ define <4 x float> @combine_vec_fcopysign_neg_constant1(<4 x float> %x) {
|
|||
define <4 x float> @combine_vec_fcopysign_fneg_fabs_sgn(<4 x float> %x, <4 x float> %y) {
|
||||
; SSE-LABEL: combine_vec_fcopysign_fneg_fabs_sgn:
|
||||
; SSE: # BB#0:
|
||||
; SSE-NEXT: movaps {{.*#+}} xmm2 = [-0.000000e+00,-0.000000e+00,-0.000000e+00,-0.000000e+00]
|
||||
; SSE-NEXT: orps %xmm2, %xmm1
|
||||
; SSE-NEXT: andps %xmm2, %xmm1
|
||||
; SSE-NEXT: andps {{.*}}(%rip), %xmm0
|
||||
; SSE-NEXT: orps %xmm1, %xmm0
|
||||
; SSE-NEXT: orps {{.*}}(%rip), %xmm0
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX-LABEL: combine_vec_fcopysign_fneg_fabs_sgn:
|
||||
; AVX: # BB#0:
|
||||
; AVX-NEXT: vbroadcastss {{.*}}(%rip), %xmm1
|
||||
; AVX-NEXT: vbroadcastss {{.*}}(%rip), %xmm2
|
||||
; AVX-NEXT: vorps %xmm2, %xmm1, %xmm1
|
||||
; AVX-NEXT: vbroadcastss {{.*}}(%rip), %xmm3
|
||||
; AVX-NEXT: vandps %xmm3, %xmm0, %xmm0
|
||||
; AVX-NEXT: vandps %xmm2, %xmm1, %xmm1
|
||||
; AVX-NEXT: vandps %xmm2, %xmm0, %xmm0
|
||||
; AVX-NEXT: vorps %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
%1 = call <4 x float> @llvm.fabs.v4f32(<4 x float> %y)
|
||||
|
|
|
|||
|
|
@ -99,100 +99,85 @@ while.end: ; preds = %while.body, %entry
|
|||
define <16 x float> @foo(<16 x float> %x) {
|
||||
; CHECK-LABEL: foo:
|
||||
; CHECK: ## BB#0: ## %bb
|
||||
; CHECK-NEXT: xorps %xmm4, %xmm4
|
||||
; CHECK-NEXT: movaps %xmm3, %xmm8
|
||||
; CHECK-NEXT: xorps %xmm3, %xmm3
|
||||
; CHECK-NEXT: pxor %xmm6, %xmm6
|
||||
; CHECK-NEXT: pcmpgtd %xmm0, %xmm6
|
||||
; CHECK-NEXT: movdqa {{.*#+}} xmm5 = [255,255,255,255]
|
||||
; CHECK-NEXT: pand %xmm6, %xmm5
|
||||
; CHECK-NEXT: packuswb %xmm5, %xmm5
|
||||
; CHECK-NEXT: packuswb %xmm5, %xmm5
|
||||
; CHECK-NEXT: cvttps2dq %xmm0, %xmm13
|
||||
; CHECK-NEXT: movdqa %xmm0, %xmm10
|
||||
; CHECK-NEXT: cmpltps %xmm4, %xmm10
|
||||
; CHECK-NEXT: movdqa %xmm6, %xmm8
|
||||
; CHECK-NEXT: pxor %xmm10, %xmm8
|
||||
; CHECK-NEXT: cmpltps %xmm3, %xmm10
|
||||
; CHECK-NEXT: movdqa %xmm6, %xmm9
|
||||
; CHECK-NEXT: pxor %xmm10, %xmm9
|
||||
; CHECK-NEXT: cvttps2dq %xmm1, %xmm14
|
||||
; CHECK-NEXT: movaps %xmm1, %xmm11
|
||||
; CHECK-NEXT: cmpltps %xmm4, %xmm11
|
||||
; CHECK-NEXT: movdqa %xmm6, %xmm9
|
||||
; CHECK-NEXT: pxor %xmm11, %xmm9
|
||||
; CHECK-NEXT: cvttps2dq %xmm2, %xmm1
|
||||
; CHECK-NEXT: cmpltps %xmm4, %xmm2
|
||||
; CHECK-NEXT: cmpltps %xmm3, %xmm11
|
||||
; CHECK-NEXT: movdqa %xmm6, %xmm7
|
||||
; CHECK-NEXT: pxor %xmm2, %xmm7
|
||||
; CHECK-NEXT: cvttps2dq %xmm3, %xmm12
|
||||
; CHECK-NEXT: cmpltps %xmm4, %xmm3
|
||||
; CHECK-NEXT: pxor %xmm3, %xmm6
|
||||
; CHECK-NEXT: pxor %xmm11, %xmm7
|
||||
; CHECK-NEXT: cvttps2dq %xmm2, %xmm1
|
||||
; CHECK-NEXT: cmpltps %xmm3, %xmm2
|
||||
; CHECK-NEXT: movdqa %xmm6, %xmm4
|
||||
; CHECK-NEXT: pxor %xmm2, %xmm4
|
||||
; CHECK-NEXT: cvttps2dq %xmm8, %xmm12
|
||||
; CHECK-NEXT: cmpltps %xmm3, %xmm8
|
||||
; CHECK-NEXT: pxor %xmm8, %xmm6
|
||||
; CHECK-NEXT: movdqa {{.*#+}} xmm0 = [1,1,1,1]
|
||||
; CHECK-NEXT: pand %xmm0, %xmm6
|
||||
; CHECK-NEXT: pand %xmm0, %xmm4
|
||||
; CHECK-NEXT: pand %xmm0, %xmm7
|
||||
; CHECK-NEXT: pand %xmm0, %xmm9
|
||||
; CHECK-NEXT: pand %xmm0, %xmm8
|
||||
; CHECK-NEXT: cvtdq2ps %xmm13, %xmm15
|
||||
; CHECK-NEXT: cvtdq2ps %xmm14, %xmm14
|
||||
; CHECK-NEXT: cvtdq2ps %xmm1, %xmm13
|
||||
; CHECK-NEXT: cvtdq2ps %xmm12, %xmm12
|
||||
; CHECK-NEXT: pxor %xmm0, %xmm0
|
||||
; CHECK-NEXT: cmpltps %xmm12, %xmm0
|
||||
; CHECK-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7]
|
||||
; CHECK-NEXT: pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,4,6,6,7]
|
||||
; CHECK-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
|
||||
; CHECK-NEXT: xorps %xmm1, %xmm1
|
||||
; CHECK-NEXT: cmpltps %xmm13, %xmm1
|
||||
; CHECK-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
|
||||
; CHECK-NEXT: pshufhw {{.*#+}} xmm1 = xmm1[0,1,2,3,4,6,6,7]
|
||||
; CHECK-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
|
||||
; CHECK-NEXT: punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm0[0]
|
||||
; CHECK-NEXT: pxor %xmm0, %xmm0
|
||||
; CHECK-NEXT: packssdw %xmm0, %xmm1
|
||||
; CHECK-NEXT: xorps %xmm0, %xmm0
|
||||
; CHECK-NEXT: cmpltps %xmm14, %xmm0
|
||||
; CHECK-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7]
|
||||
; CHECK-NEXT: pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,4,6,6,7]
|
||||
; CHECK-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
|
||||
; CHECK-NEXT: cmpltps %xmm15, %xmm4
|
||||
; CHECK-NEXT: pshuflw {{.*#+}} xmm4 = xmm4[0,2,2,3,4,5,6,7]
|
||||
; CHECK-NEXT: pshufhw {{.*#+}} xmm4 = xmm4[0,1,2,3,4,6,6,7]
|
||||
; CHECK-NEXT: pshufd {{.*#+}} xmm4 = xmm4[0,2,2,3]
|
||||
; CHECK-NEXT: punpcklqdq {{.*#+}} xmm4 = xmm4[0],xmm0[0]
|
||||
; CHECK-NEXT: movdqa {{.*#+}} xmm0 = [255,255,255,255,255,255,255,255]
|
||||
; CHECK-NEXT: pand %xmm0, %xmm1
|
||||
; CHECK-NEXT: pand %xmm0, %xmm4
|
||||
; CHECK-NEXT: packuswb %xmm5, %xmm5
|
||||
; CHECK-NEXT: packuswb %xmm5, %xmm5
|
||||
; CHECK-NEXT: packuswb %xmm1, %xmm4
|
||||
; CHECK-NEXT: pand %xmm5, %xmm4
|
||||
; CHECK-NEXT: movdqa %xmm4, %xmm1
|
||||
; CHECK-NEXT: cmpltps %xmm15, %xmm3
|
||||
; CHECK-NEXT: packssdw %xmm0, %xmm3
|
||||
; CHECK-NEXT: packsswb %xmm1, %xmm3
|
||||
; CHECK-NEXT: pand %xmm5, %xmm3
|
||||
; CHECK-NEXT: movdqa %xmm3, %xmm1
|
||||
; CHECK-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
|
||||
; CHECK-NEXT: movdqa %xmm1, %xmm0
|
||||
; CHECK-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
|
||||
; CHECK-NEXT: pslld $31, %xmm0
|
||||
; CHECK-NEXT: psrad $31, %xmm0
|
||||
; CHECK-NEXT: pxor %xmm8, %xmm0
|
||||
; CHECK-NEXT: pxor %xmm15, %xmm0
|
||||
; CHECK-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
|
||||
; CHECK-NEXT: pslld $31, %xmm1
|
||||
; CHECK-NEXT: psrad $31, %xmm1
|
||||
; CHECK-NEXT: punpckhbw {{.*#+}} xmm4 = xmm4[8],xmm0[8],xmm4[9],xmm0[9],xmm4[10],xmm0[10],xmm4[11],xmm0[11],xmm4[12],xmm0[12],xmm4[13],xmm0[13],xmm4[14],xmm0[14],xmm4[15],xmm0[15]
|
||||
; CHECK-NEXT: pxor %xmm9, %xmm1
|
||||
; CHECK-NEXT: pxor %xmm14, %xmm1
|
||||
; CHECK-NEXT: movdqa %xmm4, %xmm5
|
||||
; CHECK-NEXT: punpckhbw {{.*#+}} xmm3 = xmm3[8],xmm0[8],xmm3[9],xmm0[9],xmm3[10],xmm0[10],xmm3[11],xmm0[11],xmm3[12],xmm0[12],xmm3[13],xmm0[13],xmm3[14],xmm0[14],xmm3[15],xmm0[15]
|
||||
; CHECK-NEXT: movdqa %xmm3, %xmm5
|
||||
; CHECK-NEXT: punpcklwd {{.*#+}} xmm5 = xmm5[0],xmm0[0],xmm5[1],xmm0[1],xmm5[2],xmm0[2],xmm5[3],xmm0[3]
|
||||
; CHECK-NEXT: pslld $31, %xmm5
|
||||
; CHECK-NEXT: psrad $31, %xmm5
|
||||
; CHECK-NEXT: pxor %xmm7, %xmm5
|
||||
; CHECK-NEXT: punpckhwd {{.*#+}} xmm3 = xmm3[4],xmm0[4],xmm3[5],xmm0[5],xmm3[6],xmm0[6],xmm3[7],xmm0[7]
|
||||
; CHECK-NEXT: pslld $31, %xmm3
|
||||
; CHECK-NEXT: psrad $31, %xmm3
|
||||
; CHECK-NEXT: pxor %xmm9, %xmm0
|
||||
; CHECK-NEXT: pxor %xmm15, %xmm0
|
||||
; CHECK-NEXT: pxor %xmm7, %xmm1
|
||||
; CHECK-NEXT: pxor %xmm14, %xmm1
|
||||
; CHECK-NEXT: pxor %xmm4, %xmm5
|
||||
; CHECK-NEXT: pxor %xmm13, %xmm5
|
||||
; CHECK-NEXT: punpckhwd {{.*#+}} xmm4 = xmm4[4],xmm0[4],xmm4[5],xmm0[5],xmm4[6],xmm0[6],xmm4[7],xmm0[7]
|
||||
; CHECK-NEXT: pslld $31, %xmm4
|
||||
; CHECK-NEXT: psrad $31, %xmm4
|
||||
; CHECK-NEXT: pxor %xmm6, %xmm4
|
||||
; CHECK-NEXT: pxor %xmm12, %xmm4
|
||||
; CHECK-NEXT: pand %xmm3, %xmm4
|
||||
; CHECK-NEXT: pxor %xmm6, %xmm3
|
||||
; CHECK-NEXT: pxor %xmm12, %xmm3
|
||||
; CHECK-NEXT: pand %xmm8, %xmm3
|
||||
; CHECK-NEXT: pand %xmm2, %xmm5
|
||||
; CHECK-NEXT: pand %xmm11, %xmm1
|
||||
; CHECK-NEXT: pand %xmm10, %xmm0
|
||||
; CHECK-NEXT: pxor %xmm8, %xmm0
|
||||
; CHECK-NEXT: pxor %xmm9, %xmm1
|
||||
; CHECK-NEXT: pxor %xmm7, %xmm5
|
||||
; CHECK-NEXT: pxor %xmm6, %xmm4
|
||||
; CHECK-NEXT: pxor %xmm9, %xmm0
|
||||
; CHECK-NEXT: pxor %xmm7, %xmm1
|
||||
; CHECK-NEXT: pxor %xmm4, %xmm5
|
||||
; CHECK-NEXT: pxor %xmm6, %xmm3
|
||||
; CHECK-NEXT: movdqa %xmm5, %xmm2
|
||||
; CHECK-NEXT: movdqa %xmm4, %xmm3
|
||||
; CHECK-NEXT: retq
|
||||
bb:
|
||||
%v3 = icmp slt <16 x i32> undef, zeroinitializer
|
||||
|
|
|
|||
|
|
@ -2190,58 +2190,29 @@ define <16 x i1> @test_cmp_v16f64(<16 x double> %a0, <16 x double> %a1) nounwind
|
|||
define <32 x i1> @test_cmp_v32f32(<32 x float> %a0, <32 x float> %a1) nounwind {
|
||||
; SSE2-LABEL: test_cmp_v32f32:
|
||||
; SSE2: # BB#0:
|
||||
; SSE2-NEXT: movaps {{[0-9]+}}(%rsp), %xmm8
|
||||
; SSE2-NEXT: movaps {{[0-9]+}}(%rsp), %xmm9
|
||||
; SSE2-NEXT: movaps {{[0-9]+}}(%rsp), %xmm10
|
||||
; SSE2-NEXT: movaps {{[0-9]+}}(%rsp), %xmm11
|
||||
; SSE2-NEXT: movaps {{[0-9]+}}(%rsp), %xmm10
|
||||
; SSE2-NEXT: movaps {{[0-9]+}}(%rsp), %xmm12
|
||||
; SSE2-NEXT: movaps {{[0-9]+}}(%rsp), %xmm8
|
||||
; SSE2-NEXT: movaps {{[0-9]+}}(%rsp), %xmm13
|
||||
; SSE2-NEXT: movaps {{[0-9]+}}(%rsp), %xmm14
|
||||
; SSE2-NEXT: movaps {{[0-9]+}}(%rsp), %xmm15
|
||||
; SSE2-NEXT: cmpltps %xmm3, %xmm15
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm3 = xmm15[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: cmpltps %xmm2, %xmm14
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm2 = xmm14[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],xmm3[0]
|
||||
; SSE2-NEXT: movdqa {{.*#+}} xmm3 = [255,255,255,255,255,255,255,255]
|
||||
; SSE2-NEXT: pand %xmm3, %xmm2
|
||||
; SSE2-NEXT: packssdw %xmm15, %xmm14
|
||||
; SSE2-NEXT: cmpltps %xmm1, %xmm13
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm1 = xmm13[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: cmpltps %xmm0, %xmm12
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm12[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: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; SSE2-NEXT: pand %xmm3, %xmm0
|
||||
; SSE2-NEXT: packuswb %xmm2, %xmm0
|
||||
; SSE2-NEXT: cmpltps %xmm7, %xmm11
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm1 = xmm11[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: cmpltps %xmm0, %xmm8
|
||||
; SSE2-NEXT: packssdw %xmm13, %xmm8
|
||||
; SSE2-NEXT: packsswb %xmm14, %xmm8
|
||||
; SSE2-NEXT: cmpltps %xmm7, %xmm12
|
||||
; SSE2-NEXT: cmpltps %xmm6, %xmm10
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm2 = xmm10[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: cmpltps %xmm5, %xmm9
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm1 = xmm9[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: cmpltps %xmm4, %xmm8
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm4 = xmm8[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: movdqa %xmm4, -{{[0-9]+}}(%rsp)
|
||||
; SSE2-NEXT: packssdw %xmm12, %xmm10
|
||||
; SSE2-NEXT: cmpltps %xmm5, %xmm11
|
||||
; SSE2-NEXT: cmpltps %xmm4, %xmm9
|
||||
; SSE2-NEXT: packssdw %xmm11, %xmm9
|
||||
; SSE2-NEXT: packsswb %xmm10, %xmm9
|
||||
; SSE2-NEXT: movdqa %xmm9, -{{[0-9]+}}(%rsp)
|
||||
; SSE2-NEXT: movb -{{[0-9]+}}(%rsp), %al
|
||||
; SSE2-NEXT: andb $1, %al
|
||||
; SSE2-NEXT: movb %al, 2(%rdi)
|
||||
|
|
@ -2290,7 +2261,7 @@ define <32 x i1> @test_cmp_v32f32(<32 x float> %a0, <32 x float> %a1) nounwind {
|
|||
; SSE2-NEXT: movb %cl, 2(%rdi)
|
||||
; SSE2-NEXT: andb $1, %al
|
||||
; SSE2-NEXT: movb %al, 2(%rdi)
|
||||
; SSE2-NEXT: movdqa %xmm0, -{{[0-9]+}}(%rsp)
|
||||
; SSE2-NEXT: movdqa %xmm8, -{{[0-9]+}}(%rsp)
|
||||
; SSE2-NEXT: movb -{{[0-9]+}}(%rsp), %al
|
||||
; SSE2-NEXT: andb $1, %al
|
||||
; SSE2-NEXT: movb %al, (%rdi)
|
||||
|
|
@ -7886,75 +7857,70 @@ define <32 x i1> @test_cmp_v32f64(<32 x double> %a0, <32 x double> %a1) nounwind
|
|||
; SSE2-NEXT: movapd {{[0-9]+}}(%rsp), %xmm7
|
||||
; SSE2-NEXT: cmpltpd %xmm6, %xmm7
|
||||
; SSE2-NEXT: shufps {{.*#+}} xmm4 = xmm4[0,2,2,3]
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm6 = xmm4[0,1,0,2,4,5,6,7]
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm4 = xmm4[0,1,0,2,4,5,6,7]
|
||||
; SSE2-NEXT: shufps {{.*#+}} xmm7 = xmm7[0,2,2,3]
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm4 = xmm7[0,1,0,2,4,5,6,7]
|
||||
; SSE2-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm6[0],xmm4[1],xmm6[1]
|
||||
; SSE2-NEXT: movsd {{.*#+}} xmm4 = xmm5[0],xmm4[1]
|
||||
; SSE2-NEXT: movapd {{[0-9]+}}(%rsp), %xmm5
|
||||
; SSE2-NEXT: cmpltpd %xmm1, %xmm5
|
||||
; SSE2-NEXT: movapd {{[0-9]+}}(%rsp), %xmm6
|
||||
; SSE2-NEXT: cmpltpd %xmm0, %xmm6
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm6 = xmm7[0,1,0,2,4,5,6,7]
|
||||
; SSE2-NEXT: punpckldq {{.*#+}} xmm6 = xmm6[0],xmm4[0],xmm6[1],xmm4[1]
|
||||
; SSE2-NEXT: movsd {{.*#+}} xmm6 = xmm5[0],xmm6[1]
|
||||
; SSE2-NEXT: movapd {{[0-9]+}}(%rsp), %xmm4
|
||||
; SSE2-NEXT: cmpltpd %xmm1, %xmm4
|
||||
; SSE2-NEXT: movapd {{[0-9]+}}(%rsp), %xmm1
|
||||
; SSE2-NEXT: shufps {{.*#+}} xmm5 = xmm5[0,2,2,3]
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm5[0,2,2,3,4,5,6,7]
|
||||
; SSE2-NEXT: shufps {{.*#+}} xmm6 = xmm6[0,2,2,3]
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm5 = xmm6[0,2,2,3,4,5,6,7]
|
||||
; SSE2-NEXT: punpckldq {{.*#+}} xmm5 = xmm5[0],xmm0[0],xmm5[1],xmm0[1]
|
||||
; SSE2-NEXT: cmpltpd %xmm0, %xmm1
|
||||
; SSE2-NEXT: shufps {{.*#+}} xmm4 = xmm4[0,2,2,3]
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm4[0,2,2,3,4,5,6,7]
|
||||
; SSE2-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,2,2,3]
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm4 = xmm1[0,2,2,3,4,5,6,7]
|
||||
; SSE2-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm0[0],xmm4[1],xmm0[1]
|
||||
; SSE2-NEXT: movapd {{[0-9]+}}(%rsp), %xmm0
|
||||
; SSE2-NEXT: cmpltpd %xmm3, %xmm0
|
||||
; SSE2-NEXT: movapd {{[0-9]+}}(%rsp), %xmm3
|
||||
; SSE2-NEXT: cmpltpd %xmm2, %xmm3
|
||||
; SSE2-NEXT: movapd {{[0-9]+}}(%rsp), %xmm6
|
||||
; SSE2-NEXT: movapd {{[0-9]+}}(%rsp), %xmm1
|
||||
; SSE2-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,2,2,3]
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm2 = xmm0[0,1,0,2,4,5,6,7]
|
||||
; SSE2-NEXT: shufps {{.*#+}} xmm3 = xmm3[0,2,2,3]
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm3[0,1,0,2,4,5,6,7]
|
||||
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
|
||||
; SSE2-NEXT: movapd {{[0-9]+}}(%rsp), %xmm2
|
||||
; SSE2-NEXT: movsd {{.*#+}} xmm0 = xmm4[0],xmm0[1]
|
||||
; SSE2-NEXT: movapd {{[0-9]+}}(%rsp), %xmm3
|
||||
; SSE2-NEXT: movsd {{.*#+}} xmm0 = xmm5[0],xmm0[1]
|
||||
; SSE2-NEXT: movapd {{.*#+}} xmm2 = [255,255,255,255,255,255,255,255]
|
||||
; SSE2-NEXT: andpd %xmm2, %xmm4
|
||||
; SSE2-NEXT: andpd %xmm2, %xmm0
|
||||
; SSE2-NEXT: packuswb %xmm4, %xmm0
|
||||
; SSE2-NEXT: packsswb %xmm6, %xmm0
|
||||
; SSE2-NEXT: movapd {{[0-9]+}}(%rsp), %xmm4
|
||||
; SSE2-NEXT: cmpltpd {{[0-9]+}}(%rsp), %xmm4
|
||||
; SSE2-NEXT: shufps {{.*#+}} xmm4 = xmm4[0,2,2,3]
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm4 = xmm4[0,2,2,3,4,5,6,7]
|
||||
; SSE2-NEXT: cmpltpd {{[0-9]+}}(%rsp), %xmm3
|
||||
; SSE2-NEXT: shufps {{.*#+}} xmm3 = xmm3[0,2,2,3]
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm5 = xmm3[0,2,2,3,4,5,6,7]
|
||||
; SSE2-NEXT: punpckldq {{.*#+}} xmm5 = xmm5[0],xmm4[0],xmm5[1],xmm4[1]
|
||||
; SSE2-NEXT: movapd {{[0-9]+}}(%rsp), %xmm3
|
||||
; SSE2-NEXT: cmpltpd {{[0-9]+}}(%rsp), %xmm3
|
||||
; SSE2-NEXT: shufps {{.*#+}} xmm3 = xmm3[0,2,2,3]
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm4 = xmm3[0,1,0,2,4,5,6,7]
|
||||
; SSE2-NEXT: cmpltpd {{[0-9]+}}(%rsp), %xmm6
|
||||
; SSE2-NEXT: shufps {{.*#+}} xmm6 = xmm6[0,2,2,3]
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm3 = xmm6[0,1,0,2,4,5,6,7]
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm3 = xmm3[0,2,2,3,4,5,6,7]
|
||||
; SSE2-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm4[0],xmm3[1],xmm4[1]
|
||||
; SSE2-NEXT: movapd {{[0-9]+}}(%rsp), %xmm4
|
||||
; SSE2-NEXT: movsd {{.*#+}} xmm3 = xmm5[0],xmm3[1]
|
||||
; SSE2-NEXT: movapd {{[0-9]+}}(%rsp), %xmm5
|
||||
; SSE2-NEXT: cmpltpd {{[0-9]+}}(%rsp), %xmm5
|
||||
; SSE2-NEXT: shufps {{.*#+}} xmm5 = xmm5[0,2,2,3]
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm5 = xmm5[0,2,2,3,4,5,6,7]
|
||||
; SSE2-NEXT: cmpltpd {{[0-9]+}}(%rsp), %xmm4
|
||||
; SSE2-NEXT: shufps {{.*#+}} xmm4 = xmm4[0,2,2,3]
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm4 = xmm4[0,1,0,2,4,5,6,7]
|
||||
; SSE2-NEXT: cmpltpd {{[0-9]+}}(%rsp), %xmm2
|
||||
; SSE2-NEXT: shufps {{.*#+}} xmm2 = xmm2[0,2,2,3]
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm2 = xmm2[0,1,0,2,4,5,6,7]
|
||||
; SSE2-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm4[0],xmm2[1],xmm4[1]
|
||||
; SSE2-NEXT: movapd {{[0-9]+}}(%rsp), %xmm4
|
||||
; SSE2-NEXT: movsd {{.*#+}} xmm2 = xmm3[0],xmm2[1]
|
||||
; SSE2-NEXT: movapd {{[0-9]+}}(%rsp), %xmm3
|
||||
; SSE2-NEXT: cmpltpd {{[0-9]+}}(%rsp), %xmm3
|
||||
; SSE2-NEXT: shufps {{.*#+}} xmm3 = xmm3[0,2,2,3]
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm3 = xmm3[0,2,2,3,4,5,6,7]
|
||||
; SSE2-NEXT: cmpltpd {{[0-9]+}}(%rsp), %xmm4
|
||||
; SSE2-NEXT: shufps {{.*#+}} xmm4 = xmm4[0,2,2,3]
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm4 = xmm4[0,2,2,3,4,5,6,7]
|
||||
; SSE2-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm5[0],xmm4[1],xmm5[1]
|
||||
; SSE2-NEXT: movapd {{[0-9]+}}(%rsp), %xmm5
|
||||
; SSE2-NEXT: cmpltpd {{[0-9]+}}(%rsp), %xmm5
|
||||
; SSE2-NEXT: shufps {{.*#+}} xmm5 = xmm5[0,2,2,3]
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm5 = xmm5[0,1,0,2,4,5,6,7]
|
||||
; SSE2-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm3[0],xmm4[1],xmm3[1]
|
||||
; SSE2-NEXT: movapd {{[0-9]+}}(%rsp), %xmm3
|
||||
; SSE2-NEXT: cmpltpd {{[0-9]+}}(%rsp), %xmm3
|
||||
; SSE2-NEXT: shufps {{.*#+}} xmm3 = xmm3[0,2,2,3]
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm3 = xmm3[0,1,0,2,4,5,6,7]
|
||||
; SSE2-NEXT: cmpltpd {{[0-9]+}}(%rsp), %xmm1
|
||||
; SSE2-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,2,2,3]
|
||||
; SSE2-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[0,1,0,2,4,5,6,7]
|
||||
; SSE2-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm5[0],xmm1[1],xmm5[1]
|
||||
; SSE2-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm3[0],xmm1[1],xmm3[1]
|
||||
; SSE2-NEXT: movsd {{.*#+}} xmm1 = xmm4[0],xmm1[1]
|
||||
; SSE2-NEXT: andpd %xmm2, %xmm3
|
||||
; SSE2-NEXT: andpd %xmm2, %xmm1
|
||||
; SSE2-NEXT: packuswb %xmm3, %xmm1
|
||||
; SSE2-NEXT: packsswb %xmm2, %xmm1
|
||||
; SSE2-NEXT: movdqa %xmm1, -{{[0-9]+}}(%rsp)
|
||||
; SSE2-NEXT: movb -{{[0-9]+}}(%rsp), %al
|
||||
; SSE2-NEXT: andb $1, %al
|
||||
|
|
@ -8065,137 +8031,179 @@ define <32 x i1> @test_cmp_v32f64(<32 x double> %a0, <32 x double> %a1) nounwind
|
|||
; SSE42-NEXT: pushq %r12
|
||||
; SSE42-NEXT: pushq %rbx
|
||||
; SSE42-NEXT: movapd {{[0-9]+}}(%rsp), %xmm8
|
||||
; SSE42-NEXT: cmpltpd %xmm0, %xmm8
|
||||
; SSE42-NEXT: movapd {{[0-9]+}}(%rsp), %xmm0
|
||||
; SSE42-NEXT: cmpltpd %xmm1, %xmm0
|
||||
; SSE42-NEXT: movapd {{[0-9]+}}(%rsp), %xmm1
|
||||
; SSE42-NEXT: cmpltpd %xmm2, %xmm1
|
||||
; SSE42-NEXT: movapd {{[0-9]+}}(%rsp), %xmm2
|
||||
; SSE42-NEXT: cmpltpd %xmm3, %xmm2
|
||||
; SSE42-NEXT: movapd {{[0-9]+}}(%rsp), %xmm3
|
||||
; SSE42-NEXT: cmpltpd %xmm4, %xmm3
|
||||
; SSE42-NEXT: movapd {{[0-9]+}}(%rsp), %xmm4
|
||||
; SSE42-NEXT: cmpltpd %xmm5, %xmm4
|
||||
; SSE42-NEXT: movapd {{[0-9]+}}(%rsp), %xmm5
|
||||
; SSE42-NEXT: cmpltpd %xmm6, %xmm5
|
||||
; SSE42-NEXT: cmpltpd %xmm7, %xmm8
|
||||
; SSE42-NEXT: movapd {{[0-9]+}}(%rsp), %xmm7
|
||||
; SSE42-NEXT: cmpltpd %xmm6, %xmm7
|
||||
; SSE42-NEXT: shufps {{.*#+}} xmm8 = xmm8[0,2,2,3]
|
||||
; SSE42-NEXT: pshuflw {{.*#+}} xmm6 = xmm8[0,1,0,2,4,5,6,7]
|
||||
; SSE42-NEXT: shufps {{.*#+}} xmm7 = xmm7[0,2,2,3]
|
||||
; SSE42-NEXT: pshuflw {{.*#+}} xmm7 = xmm7[0,1,0,2,4,5,6,7]
|
||||
; SSE42-NEXT: punpckldq {{.*#+}} xmm7 = xmm7[0],xmm6[0],xmm7[1],xmm6[1]
|
||||
; SSE42-NEXT: movapd {{[0-9]+}}(%rsp), %xmm6
|
||||
; SSE42-NEXT: cmpltpd %xmm7, %xmm6
|
||||
; SSE42-NEXT: movapd {{[0-9]+}}(%rsp), %xmm7
|
||||
; SSE42-NEXT: cmpltpd {{[0-9]+}}(%rsp), %xmm7
|
||||
; SSE42-NEXT: pextrb $8, %xmm7, %r8d
|
||||
; SSE42-NEXT: pextrb $0, %xmm7, %r13d
|
||||
; SSE42-NEXT: movapd {{[0-9]+}}(%rsp), %xmm7
|
||||
; SSE42-NEXT: cmpltpd {{[0-9]+}}(%rsp), %xmm7
|
||||
; SSE42-NEXT: pextrb $8, %xmm7, %r14d
|
||||
; SSE42-NEXT: pextrb $0, %xmm7, %ebx
|
||||
; SSE42-NEXT: movapd {{[0-9]+}}(%rsp), %xmm7
|
||||
; SSE42-NEXT: cmpltpd {{[0-9]+}}(%rsp), %xmm7
|
||||
; SSE42-NEXT: pextrb $8, %xmm7, %r15d
|
||||
; SSE42-NEXT: pextrb $0, %xmm7, %ebp
|
||||
; SSE42-NEXT: movapd {{[0-9]+}}(%rsp), %xmm7
|
||||
; SSE42-NEXT: cmpltpd {{[0-9]+}}(%rsp), %xmm7
|
||||
; SSE42-NEXT: pextrb $8, %xmm7, %r12d
|
||||
; SSE42-NEXT: pextrb $0, %xmm7, %ecx
|
||||
; SSE42-NEXT: movapd {{[0-9]+}}(%rsp), %xmm7
|
||||
; SSE42-NEXT: cmpltpd {{[0-9]+}}(%rsp), %xmm7
|
||||
; SSE42-NEXT: pextrb $8, %xmm7, %r11d
|
||||
; SSE42-NEXT: pextrb $0, %xmm7, %edx
|
||||
; SSE42-NEXT: movapd {{[0-9]+}}(%rsp), %xmm7
|
||||
; SSE42-NEXT: cmpltpd {{[0-9]+}}(%rsp), %xmm7
|
||||
; SSE42-NEXT: pextrb $8, %xmm7, %r9d
|
||||
; SSE42-NEXT: pextrb $0, %xmm7, %esi
|
||||
; SSE42-NEXT: movapd {{[0-9]+}}(%rsp), %xmm7
|
||||
; SSE42-NEXT: cmpltpd {{[0-9]+}}(%rsp), %xmm7
|
||||
; SSE42-NEXT: pextrb $8, %xmm7, %eax
|
||||
; SSE42-NEXT: movl %eax, -{{[0-9]+}}(%rsp) # 4-byte Spill
|
||||
; SSE42-NEXT: pextrb $0, %xmm7, %r10d
|
||||
; SSE42-NEXT: movapd {{[0-9]+}}(%rsp), %xmm7
|
||||
; SSE42-NEXT: cmpltpd {{[0-9]+}}(%rsp), %xmm7
|
||||
; SSE42-NEXT: cmpltpd %xmm5, %xmm6
|
||||
; SSE42-NEXT: movapd {{[0-9]+}}(%rsp), %xmm5
|
||||
; SSE42-NEXT: cmpltpd %xmm4, %xmm5
|
||||
; SSE42-NEXT: shufps {{.*#+}} xmm6 = xmm6[0,2,2,3]
|
||||
; SSE42-NEXT: pshuflw {{.*#+}} xmm4 = xmm6[0,2,2,3,4,5,6,7]
|
||||
; SSE42-NEXT: shufps {{.*#+}} xmm5 = xmm5[0,2,2,3]
|
||||
; SSE42-NEXT: pshuflw {{.*#+}} xmm5 = xmm5[0,2,2,3,4,5,6,7]
|
||||
; SSE42-NEXT: punpckldq {{.*#+}} xmm5 = xmm5[0],xmm4[0],xmm5[1],xmm4[1]
|
||||
; SSE42-NEXT: pblendw {{.*#+}} xmm5 = xmm5[0,1,2,3],xmm7[4,5,6,7]
|
||||
; SSE42-NEXT: movapd {{[0-9]+}}(%rsp), %xmm4
|
||||
; SSE42-NEXT: cmpltpd %xmm3, %xmm4
|
||||
; SSE42-NEXT: movapd {{[0-9]+}}(%rsp), %xmm3
|
||||
; SSE42-NEXT: cmpltpd %xmm2, %xmm3
|
||||
; SSE42-NEXT: shufps {{.*#+}} xmm4 = xmm4[0,2,2,3]
|
||||
; SSE42-NEXT: pshuflw {{.*#+}} xmm2 = xmm4[0,1,0,2,4,5,6,7]
|
||||
; SSE42-NEXT: shufps {{.*#+}} xmm3 = xmm3[0,2,2,3]
|
||||
; SSE42-NEXT: pshuflw {{.*#+}} xmm3 = xmm3[0,1,0,2,4,5,6,7]
|
||||
; SSE42-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm2[0],xmm3[1],xmm2[1]
|
||||
; SSE42-NEXT: movapd {{[0-9]+}}(%rsp), %xmm2
|
||||
; SSE42-NEXT: cmpltpd %xmm1, %xmm2
|
||||
; SSE42-NEXT: movapd {{[0-9]+}}(%rsp), %xmm4
|
||||
; SSE42-NEXT: cmpltpd %xmm0, %xmm4
|
||||
; SSE42-NEXT: movapd {{[0-9]+}}(%rsp), %xmm1
|
||||
; SSE42-NEXT: shufps {{.*#+}} xmm2 = xmm2[0,2,2,3]
|
||||
; SSE42-NEXT: pshuflw {{.*#+}} xmm2 = xmm2[0,2,2,3,4,5,6,7]
|
||||
; SSE42-NEXT: shufps {{.*#+}} xmm4 = xmm4[0,2,2,3]
|
||||
; SSE42-NEXT: pshuflw {{.*#+}} xmm0 = xmm4[0,2,2,3,4,5,6,7]
|
||||
; SSE42-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
|
||||
; SSE42-NEXT: movapd {{[0-9]+}}(%rsp), %xmm2
|
||||
; SSE42-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm3[4,5,6,7]
|
||||
; SSE42-NEXT: movapd {{[0-9]+}}(%rsp), %xmm3
|
||||
; SSE42-NEXT: packsswb %xmm5, %xmm0
|
||||
; SSE42-NEXT: movapd {{[0-9]+}}(%rsp), %xmm4
|
||||
; SSE42-NEXT: cmpltpd {{[0-9]+}}(%rsp), %xmm4
|
||||
; SSE42-NEXT: shufps {{.*#+}} xmm4 = xmm4[0,2,2,3]
|
||||
; SSE42-NEXT: pshuflw {{.*#+}} xmm4 = xmm4[0,1,0,2,4,5,6,7]
|
||||
; SSE42-NEXT: cmpltpd {{[0-9]+}}(%rsp), %xmm3
|
||||
; SSE42-NEXT: shufps {{.*#+}} xmm3 = xmm3[0,2,2,3]
|
||||
; SSE42-NEXT: pshuflw {{.*#+}} xmm3 = xmm3[0,1,0,2,4,5,6,7]
|
||||
; SSE42-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm4[0],xmm3[1],xmm4[1]
|
||||
; SSE42-NEXT: movapd {{[0-9]+}}(%rsp), %xmm4
|
||||
; SSE42-NEXT: cmpltpd {{[0-9]+}}(%rsp), %xmm4
|
||||
; SSE42-NEXT: shufps {{.*#+}} xmm4 = xmm4[0,2,2,3]
|
||||
; SSE42-NEXT: pshuflw {{.*#+}} xmm4 = xmm4[0,2,2,3,4,5,6,7]
|
||||
; SSE42-NEXT: cmpltpd {{[0-9]+}}(%rsp), %xmm2
|
||||
; SSE42-NEXT: shufps {{.*#+}} xmm2 = xmm2[0,2,2,3]
|
||||
; SSE42-NEXT: pshuflw {{.*#+}} xmm2 = xmm2[0,2,2,3,4,5,6,7]
|
||||
; SSE42-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm4[0],xmm2[1],xmm4[1]
|
||||
; SSE42-NEXT: movapd {{[0-9]+}}(%rsp), %xmm4
|
||||
; SSE42-NEXT: pblendw {{.*#+}} xmm2 = xmm2[0,1,2,3],xmm3[4,5,6,7]
|
||||
; SSE42-NEXT: movapd {{[0-9]+}}(%rsp), %xmm3
|
||||
; SSE42-NEXT: cmpltpd {{[0-9]+}}(%rsp), %xmm3
|
||||
; SSE42-NEXT: shufps {{.*#+}} xmm3 = xmm3[0,2,2,3]
|
||||
; SSE42-NEXT: pshuflw {{.*#+}} xmm3 = xmm3[0,1,0,2,4,5,6,7]
|
||||
; SSE42-NEXT: cmpltpd {{[0-9]+}}(%rsp), %xmm4
|
||||
; SSE42-NEXT: shufps {{.*#+}} xmm4 = xmm4[0,2,2,3]
|
||||
; SSE42-NEXT: pshuflw {{.*#+}} xmm4 = xmm4[0,1,0,2,4,5,6,7]
|
||||
; SSE42-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm3[0],xmm4[1],xmm3[1]
|
||||
; SSE42-NEXT: movapd {{[0-9]+}}(%rsp), %xmm3
|
||||
; SSE42-NEXT: cmpltpd {{[0-9]+}}(%rsp), %xmm3
|
||||
; SSE42-NEXT: shufps {{.*#+}} xmm3 = xmm3[0,2,2,3]
|
||||
; SSE42-NEXT: pshuflw {{.*#+}} xmm3 = xmm3[0,2,2,3,4,5,6,7]
|
||||
; SSE42-NEXT: cmpltpd {{[0-9]+}}(%rsp), %xmm1
|
||||
; SSE42-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,2,2,3]
|
||||
; SSE42-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
|
||||
; SSE42-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm3[0],xmm1[1],xmm3[1]
|
||||
; SSE42-NEXT: pblendw {{.*#+}} xmm1 = xmm1[0,1,2,3],xmm4[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 $14, %xmm1, %eax
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $13, %xmm1, %r8d
|
||||
; SSE42-NEXT: pextrb $12, %xmm1, %r9d
|
||||
; SSE42-NEXT: pextrb $11, %xmm1, %r10d
|
||||
; SSE42-NEXT: pextrb $10, %xmm1, %r11d
|
||||
; SSE42-NEXT: pextrb $9, %xmm1, %r14d
|
||||
; SSE42-NEXT: pextrb $8, %xmm1, %r15d
|
||||
; SSE42-NEXT: pextrb $7, %xmm1, %r12d
|
||||
; SSE42-NEXT: pextrb $6, %xmm1, %r13d
|
||||
; SSE42-NEXT: pextrb $5, %xmm1, %ebx
|
||||
; SSE42-NEXT: pextrb $4, %xmm1, %ebp
|
||||
; SSE42-NEXT: pextrb $3, %xmm1, %eax
|
||||
; SSE42-NEXT: pextrb $2, %xmm1, %ecx
|
||||
; SSE42-NEXT: pextrb $1, %xmm1, %edx
|
||||
; SSE42-NEXT: pextrb $0, %xmm1, %esi
|
||||
; SSE42-NEXT: andb $1, %r8b
|
||||
; SSE42-NEXT: movb %r8b, 2(%rdi)
|
||||
; SSE42-NEXT: andb $1, %r13b
|
||||
; SSE42-NEXT: movb %r13b, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $8, %xmm7, %eax
|
||||
; SSE42-NEXT: movl %eax, -{{[0-9]+}}(%rsp) # 4-byte Spill
|
||||
; SSE42-NEXT: pextrb $0, %xmm7, %r13d
|
||||
; SSE42-NEXT: andb $1, %r14b
|
||||
; SSE42-NEXT: movb %r14b, 2(%rdi)
|
||||
; SSE42-NEXT: andb $1, %bl
|
||||
; SSE42-NEXT: movb %bl, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $8, %xmm6, %r14d
|
||||
; SSE42-NEXT: pextrb $0, %xmm6, %r8d
|
||||
; SSE42-NEXT: andb $1, %r15b
|
||||
; SSE42-NEXT: movb %r15b, 2(%rdi)
|
||||
; SSE42-NEXT: andb $1, %bpl
|
||||
; SSE42-NEXT: movb %bpl, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $8, %xmm5, %r15d
|
||||
; SSE42-NEXT: pextrb $0, %xmm5, %ebp
|
||||
; SSE42-NEXT: andb $1, %r12b
|
||||
; SSE42-NEXT: movb %r12b, 2(%rdi)
|
||||
; SSE42-NEXT: andb $1, %cl
|
||||
; SSE42-NEXT: movb %cl, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $8, %xmm4, %r12d
|
||||
; SSE42-NEXT: pextrb $0, %xmm4, %ebx
|
||||
; SSE42-NEXT: andb $1, %r11b
|
||||
; SSE42-NEXT: movb %r11b, 2(%rdi)
|
||||
; SSE42-NEXT: andb $1, %dl
|
||||
; SSE42-NEXT: movb %dl, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $8, %xmm3, %r11d
|
||||
; SSE42-NEXT: pextrb $0, %xmm3, %ecx
|
||||
; SSE42-NEXT: andb $1, %r9b
|
||||
; SSE42-NEXT: movb %r9b, 2(%rdi)
|
||||
; SSE42-NEXT: andb $1, %sil
|
||||
; SSE42-NEXT: movb %sil, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $8, %xmm2, %r9d
|
||||
; SSE42-NEXT: pextrb $0, %xmm2, %edx
|
||||
; SSE42-NEXT: movl -{{[0-9]+}}(%rsp), %eax # 4-byte Reload
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: andb $1, %r10b
|
||||
; SSE42-NEXT: movb %r10b, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $8, %xmm1, %r10d
|
||||
; SSE42-NEXT: pextrb $0, %xmm1, %esi
|
||||
; SSE42-NEXT: movl -{{[0-9]+}}(%rsp), %eax # 4-byte Reload
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: andb $1, %r11b
|
||||
; SSE42-NEXT: movb %r11b, 2(%rdi)
|
||||
; SSE42-NEXT: andb $1, %r14b
|
||||
; SSE42-NEXT: movb %r14b, 2(%rdi)
|
||||
; SSE42-NEXT: andb $1, %r15b
|
||||
; SSE42-NEXT: movb %r15b, 2(%rdi)
|
||||
; SSE42-NEXT: andb $1, %r12b
|
||||
; SSE42-NEXT: movb %r12b, 2(%rdi)
|
||||
; SSE42-NEXT: andb $1, %r13b
|
||||
; SSE42-NEXT: movb %r13b, 2(%rdi)
|
||||
; SSE42-NEXT: pextrb $8, %xmm0, %r13d
|
||||
; SSE42-NEXT: pextrb $0, %xmm0, %eax
|
||||
; SSE42-NEXT: andb $1, %r14b
|
||||
; SSE42-NEXT: movb %r14b, (%rdi)
|
||||
; SSE42-NEXT: andb $1, %r8b
|
||||
; SSE42-NEXT: movb %r8b, (%rdi)
|
||||
; SSE42-NEXT: pextrb $8, %xmm8, %r8d
|
||||
; SSE42-NEXT: pextrb $0, %xmm8, %r14d
|
||||
; SSE42-NEXT: andb $1, %r15b
|
||||
; SSE42-NEXT: movb %r15b, (%rdi)
|
||||
; SSE42-NEXT: andb $1, %bpl
|
||||
; SSE42-NEXT: movb %bpl, (%rdi)
|
||||
; SSE42-NEXT: andb $1, %r12b
|
||||
; SSE42-NEXT: movb %r12b, (%rdi)
|
||||
; SSE42-NEXT: andb $1, %bl
|
||||
; SSE42-NEXT: movb %bl, (%rdi)
|
||||
; SSE42-NEXT: andb $1, %r11b
|
||||
; SSE42-NEXT: movb %r11b, (%rdi)
|
||||
; SSE42-NEXT: movb %bl, 2(%rdi)
|
||||
; SSE42-NEXT: andb $1, %bpl
|
||||
; SSE42-NEXT: movb %bpl, 2(%rdi)
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, 2(%rdi)
|
||||
; SSE42-NEXT: andb $1, %cl
|
||||
; SSE42-NEXT: movb %cl, (%rdi)
|
||||
; SSE42-NEXT: andb $1, %r9b
|
||||
; SSE42-NEXT: movb %r9b, (%rdi)
|
||||
; SSE42-NEXT: movb %cl, 2(%rdi)
|
||||
; SSE42-NEXT: andb $1, %dl
|
||||
; SSE42-NEXT: movb %dl, (%rdi)
|
||||
; SSE42-NEXT: andb $1, %r10b
|
||||
; SSE42-NEXT: movb %r10b, (%rdi)
|
||||
; SSE42-NEXT: movb %dl, 2(%rdi)
|
||||
; SSE42-NEXT: andb $1, %sil
|
||||
; SSE42-NEXT: movb %sil, (%rdi)
|
||||
; SSE42-NEXT: andb $1, %r13b
|
||||
; SSE42-NEXT: movb %r13b, (%rdi)
|
||||
; SSE42-NEXT: movb %sil, 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, %r8d
|
||||
; SSE42-NEXT: pextrb $12, %xmm0, %r9d
|
||||
; SSE42-NEXT: pextrb $11, %xmm0, %r10d
|
||||
; SSE42-NEXT: pextrb $10, %xmm0, %r11d
|
||||
; SSE42-NEXT: pextrb $9, %xmm0, %r14d
|
||||
; SSE42-NEXT: pextrb $8, %xmm0, %r15d
|
||||
; SSE42-NEXT: pextrb $7, %xmm0, %r12d
|
||||
; SSE42-NEXT: pextrb $6, %xmm0, %r13d
|
||||
; SSE42-NEXT: pextrb $5, %xmm0, %ebx
|
||||
; SSE42-NEXT: pextrb $4, %xmm0, %ebp
|
||||
; SSE42-NEXT: pextrb $3, %xmm0, %eax
|
||||
; SSE42-NEXT: pextrb $2, %xmm0, %ecx
|
||||
; SSE42-NEXT: pextrb $1, %xmm0, %edx
|
||||
; SSE42-NEXT: pextrb $0, %xmm0, %esi
|
||||
; SSE42-NEXT: andb $1, %r8b
|
||||
; SSE42-NEXT: movb %r8b, (%rdi)
|
||||
; SSE42-NEXT: andb $1, %r9b
|
||||
; SSE42-NEXT: movb %r9b, (%rdi)
|
||||
; SSE42-NEXT: andb $1, %r10b
|
||||
; SSE42-NEXT: movb %r10b, (%rdi)
|
||||
; SSE42-NEXT: andb $1, %r11b
|
||||
; SSE42-NEXT: movb %r11b, (%rdi)
|
||||
; SSE42-NEXT: andb $1, %r14b
|
||||
; SSE42-NEXT: movb %r14b, (%rdi)
|
||||
; SSE42-NEXT: andb $1, %r15b
|
||||
; SSE42-NEXT: movb %r15b, (%rdi)
|
||||
; SSE42-NEXT: andb $1, %r12b
|
||||
; SSE42-NEXT: movb %r12b, (%rdi)
|
||||
; SSE42-NEXT: andb $1, %r13b
|
||||
; SSE42-NEXT: movb %r13b, (%rdi)
|
||||
; SSE42-NEXT: andb $1, %bl
|
||||
; SSE42-NEXT: movb %bl, (%rdi)
|
||||
; SSE42-NEXT: andb $1, %bpl
|
||||
; SSE42-NEXT: movb %bpl, (%rdi)
|
||||
; SSE42-NEXT: andb $1, %al
|
||||
; SSE42-NEXT: movb %al, (%rdi)
|
||||
; SSE42-NEXT: andb $1, %cl
|
||||
; SSE42-NEXT: movb %cl, (%rdi)
|
||||
; SSE42-NEXT: andb $1, %dl
|
||||
; SSE42-NEXT: movb %dl, (%rdi)
|
||||
; SSE42-NEXT: andb $1, %sil
|
||||
; SSE42-NEXT: movb %sil, (%rdi)
|
||||
; SSE42-NEXT: movq %rdi, %rax
|
||||
; SSE42-NEXT: popq %rbx
|
||||
; SSE42-NEXT: popq %r12
|
||||
|
|
|
|||
Loading…
Reference in New Issue