forked from OSchip/llvm-project
[X86] Mark vector STRICT_FADD/STRICT_FSUB as Legal and add mutation to X86ISelDAGToDAG
The prevents LegalizeVectorOps from scalarizing them. We'll need to remove the X86 mutation code when we add isel patterns.
This commit is contained in:
Craig Topper
parent
0cc12b8a83
commit
95f44cf44a
|
|
@ -5220,6 +5220,8 @@ void X86DAGToDAGISel::Select(SDNode *Node) {
|
|||
SelectCode(Res.getNode());
|
||||
return;
|
||||
}
|
||||
case ISD::STRICT_FADD:
|
||||
case ISD::STRICT_FSUB:
|
||||
case ISD::STRICT_FP_TO_SINT:
|
||||
case ISD::STRICT_FP_TO_UINT:
|
||||
case ISD::STRICT_FP_ROUND:
|
||||
|
|
|
|||
|
|
@ -817,8 +817,12 @@ X86TargetLowering::X86TargetLowering(const X86TargetMachine &TM,
|
|||
setOperationAction(ISD::STORE, MVT::v2f32, Custom);
|
||||
|
||||
// FIXME: Currently mutated to non-strict form in X86ISelDAGToDAG::Select,
|
||||
// but its sufficient to pretend their Legal since they will be someday.
|
||||
// but its sufficient to pretend they're Legal since they will be someday.
|
||||
setOperationAction(ISD::STRICT_FP_ROUND, MVT::v4f32, Legal);
|
||||
setOperationAction(ISD::STRICT_FADD, MVT::v4f32, Legal);
|
||||
setOperationAction(ISD::STRICT_FADD, MVT::v2f64, Legal);
|
||||
setOperationAction(ISD::STRICT_FSUB, MVT::v4f32, Legal);
|
||||
setOperationAction(ISD::STRICT_FSUB, MVT::v2f64, Legal);
|
||||
}
|
||||
|
||||
if (!Subtarget.useSoftFloat() && Subtarget.hasSSE2()) {
|
||||
|
|
@ -1109,8 +1113,12 @@ X86TargetLowering::X86TargetLowering(const X86TargetMachine &TM,
|
|||
setOperationAction(ISD::SINT_TO_FP, MVT::v8i32, Legal);
|
||||
|
||||
// FIXME: Currently mutated to non-strict form in X86ISelDAGToDAG::Select,
|
||||
// but its sufficient to pretend their Legal since they will be someday.
|
||||
// but its sufficient to pretend they're Legal since they will be someday.
|
||||
setOperationAction(ISD::STRICT_FP_ROUND, MVT::v8f32, Legal);
|
||||
setOperationAction(ISD::STRICT_FADD, MVT::v8f32, Legal);
|
||||
setOperationAction(ISD::STRICT_FADD, MVT::v4f64, Legal);
|
||||
setOperationAction(ISD::STRICT_FSUB, MVT::v8f32, Legal);
|
||||
setOperationAction(ISD::STRICT_FSUB, MVT::v4f64, Legal);
|
||||
|
||||
if (!Subtarget.hasAVX512())
|
||||
setOperationAction(ISD::BITCAST, MVT::v32i1, Custom);
|
||||
|
|
@ -1375,7 +1383,11 @@ X86TargetLowering::X86TargetLowering(const X86TargetMachine &TM,
|
|||
|
||||
// FIXME: Currently mutated to non-strict form in X86ISelDAGToDAG::Select,
|
||||
// but its sufficient to pretend their Legal since they will be someday.
|
||||
setOperationAction(ISD::STRICT_FP_ROUND, MVT::v16f32, Legal);
|
||||
setOperationAction(ISD::STRICT_FP_ROUND, MVT::v16f32, Legal);
|
||||
setOperationAction(ISD::STRICT_FADD, MVT::v16f32, Legal);
|
||||
setOperationAction(ISD::STRICT_FADD, MVT::v8f64, Legal);
|
||||
setOperationAction(ISD::STRICT_FSUB, MVT::v16f32, Legal);
|
||||
setOperationAction(ISD::STRICT_FSUB, MVT::v8f64, Legal);
|
||||
|
||||
setTruncStoreAction(MVT::v8i64, MVT::v8i8, Legal);
|
||||
setTruncStoreAction(MVT::v8i64, MVT::v8i16, Legal);
|
||||
|
|
|
|||
|
|
@ -18,22 +18,12 @@ declare <4 x float> @llvm.experimental.constrained.fdiv.v4f32(<4 x float>, <4 x
|
|||
define <2 x double> @f1(<2 x double> %a, <2 x double> %b) #0 {
|
||||
; SSE-LABEL: f1:
|
||||
; SSE: # %bb.0:
|
||||
; SSE-NEXT: movapd %xmm0, %xmm2
|
||||
; SSE-NEXT: addsd %xmm1, %xmm2
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm1 = xmm1[1,1]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm0 = xmm0[1,1]
|
||||
; SSE-NEXT: addsd %xmm1, %xmm0
|
||||
; SSE-NEXT: unpcklpd {{.*#+}} xmm2 = xmm2[0],xmm0[0]
|
||||
; SSE-NEXT: movapd %xmm2, %xmm0
|
||||
; SSE-NEXT: addpd %xmm1, %xmm0
|
||||
; SSE-NEXT: ret{{[l|q]}}
|
||||
;
|
||||
; AVX-LABEL: f1:
|
||||
; AVX: # %bb.0:
|
||||
; AVX-NEXT: vaddsd %xmm1, %xmm0, %xmm2
|
||||
; AVX-NEXT: vpermilpd {{.*#+}} xmm1 = xmm1[1,0]
|
||||
; AVX-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
|
||||
; AVX-NEXT: vaddsd %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vunpcklpd {{.*#+}} xmm0 = xmm2[0],xmm0[0]
|
||||
; AVX-NEXT: vaddpd %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: ret{{[l|q]}}
|
||||
%ret = call <2 x double> @llvm.experimental.constrained.fadd.v2f64(<2 x double> %a, <2 x double> %b,
|
||||
metadata !"round.dynamic",
|
||||
|
|
@ -44,42 +34,12 @@ define <2 x double> @f1(<2 x double> %a, <2 x double> %b) #0 {
|
|||
define <4 x float> @f2(<4 x float> %a, <4 x float> %b) #0 {
|
||||
; SSE-LABEL: f2:
|
||||
; SSE: # %bb.0:
|
||||
; SSE-NEXT: movaps %xmm1, %xmm2
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm2 = xmm2[3,1],xmm1[2,3]
|
||||
; SSE-NEXT: movaps %xmm0, %xmm3
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm3 = xmm3[3,1],xmm0[2,3]
|
||||
; SSE-NEXT: addss %xmm2, %xmm3
|
||||
; SSE-NEXT: movaps %xmm1, %xmm2
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm2 = xmm2[1],xmm1[1]
|
||||
; SSE-NEXT: movaps %xmm0, %xmm4
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm4 = xmm4[1],xmm0[1]
|
||||
; SSE-NEXT: addss %xmm2, %xmm4
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm4 = xmm4[0],xmm3[0],xmm4[1],xmm3[1]
|
||||
; SSE-NEXT: movaps %xmm0, %xmm2
|
||||
; SSE-NEXT: addss %xmm1, %xmm2
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm1 = xmm1[1,1,2,3]
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[1,1,2,3]
|
||||
; SSE-NEXT: addss %xmm1, %xmm0
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1]
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm2 = xmm2[0],xmm4[0]
|
||||
; SSE-NEXT: movaps %xmm2, %xmm0
|
||||
; SSE-NEXT: addps %xmm1, %xmm0
|
||||
; SSE-NEXT: ret{{[l|q]}}
|
||||
;
|
||||
; AVX-LABEL: f2:
|
||||
; AVX: # %bb.0:
|
||||
; AVX-NEXT: vaddss %xmm1, %xmm0, %xmm2
|
||||
; AVX-NEXT: vmovshdup {{.*#+}} xmm3 = xmm1[1,1,3,3]
|
||||
; AVX-NEXT: vmovshdup {{.*#+}} xmm4 = xmm0[1,1,3,3]
|
||||
; AVX-NEXT: vaddss %xmm3, %xmm4, %xmm3
|
||||
; AVX-NEXT: vinsertps {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[2,3]
|
||||
; AVX-NEXT: vpermilpd {{.*#+}} xmm3 = xmm1[1,0]
|
||||
; AVX-NEXT: vpermilpd {{.*#+}} xmm4 = xmm0[1,0]
|
||||
; AVX-NEXT: vaddss %xmm3, %xmm4, %xmm3
|
||||
; AVX-NEXT: vinsertps {{.*#+}} xmm2 = xmm2[0,1],xmm3[0],xmm2[3]
|
||||
; AVX-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[3,1,2,3]
|
||||
; AVX-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,1,2,3]
|
||||
; AVX-NEXT: vaddss %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vinsertps {{.*#+}} xmm0 = xmm2[0,1,2],xmm0[0]
|
||||
; AVX-NEXT: vaddps %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: ret{{[l|q]}}
|
||||
%ret = call <4 x float> @llvm.experimental.constrained.fadd.v4f32(<4 x float> %a, <4 x float> %b,
|
||||
metadata !"round.dynamic",
|
||||
|
|
@ -90,22 +50,12 @@ define <4 x float> @f2(<4 x float> %a, <4 x float> %b) #0 {
|
|||
define <2 x double> @f3(<2 x double> %a, <2 x double> %b) #0 {
|
||||
; SSE-LABEL: f3:
|
||||
; SSE: # %bb.0:
|
||||
; SSE-NEXT: movapd %xmm0, %xmm2
|
||||
; SSE-NEXT: subsd %xmm1, %xmm2
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm1 = xmm1[1,1]
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm0 = xmm0[1,1]
|
||||
; SSE-NEXT: subsd %xmm1, %xmm0
|
||||
; SSE-NEXT: unpcklpd {{.*#+}} xmm2 = xmm2[0],xmm0[0]
|
||||
; SSE-NEXT: movapd %xmm2, %xmm0
|
||||
; SSE-NEXT: subpd %xmm1, %xmm0
|
||||
; SSE-NEXT: ret{{[l|q]}}
|
||||
;
|
||||
; AVX-LABEL: f3:
|
||||
; AVX: # %bb.0:
|
||||
; AVX-NEXT: vsubsd %xmm1, %xmm0, %xmm2
|
||||
; AVX-NEXT: vpermilpd {{.*#+}} xmm1 = xmm1[1,0]
|
||||
; AVX-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
|
||||
; AVX-NEXT: vsubsd %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vunpcklpd {{.*#+}} xmm0 = xmm2[0],xmm0[0]
|
||||
; AVX-NEXT: vsubpd %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: ret{{[l|q]}}
|
||||
%ret = call <2 x double> @llvm.experimental.constrained.fsub.v2f64(<2 x double> %a, <2 x double> %b,
|
||||
metadata !"round.dynamic",
|
||||
|
|
@ -116,42 +66,12 @@ define <2 x double> @f3(<2 x double> %a, <2 x double> %b) #0 {
|
|||
define <4 x float> @f4(<4 x float> %a, <4 x float> %b) #0 {
|
||||
; SSE-LABEL: f4:
|
||||
; SSE: # %bb.0:
|
||||
; SSE-NEXT: movaps %xmm1, %xmm2
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm2 = xmm2[3,1],xmm1[2,3]
|
||||
; SSE-NEXT: movaps %xmm0, %xmm3
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm3 = xmm3[3,1],xmm0[2,3]
|
||||
; SSE-NEXT: subss %xmm2, %xmm3
|
||||
; SSE-NEXT: movaps %xmm1, %xmm2
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm2 = xmm2[1],xmm1[1]
|
||||
; SSE-NEXT: movaps %xmm0, %xmm4
|
||||
; SSE-NEXT: unpckhpd {{.*#+}} xmm4 = xmm4[1],xmm0[1]
|
||||
; SSE-NEXT: subss %xmm2, %xmm4
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm4 = xmm4[0],xmm3[0],xmm4[1],xmm3[1]
|
||||
; SSE-NEXT: movaps %xmm0, %xmm2
|
||||
; SSE-NEXT: subss %xmm1, %xmm2
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm1 = xmm1[1,1,2,3]
|
||||
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[1,1,2,3]
|
||||
; SSE-NEXT: subss %xmm1, %xmm0
|
||||
; SSE-NEXT: unpcklps {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1]
|
||||
; SSE-NEXT: movlhps {{.*#+}} xmm2 = xmm2[0],xmm4[0]
|
||||
; SSE-NEXT: movaps %xmm2, %xmm0
|
||||
; SSE-NEXT: subps %xmm1, %xmm0
|
||||
; SSE-NEXT: ret{{[l|q]}}
|
||||
;
|
||||
; AVX-LABEL: f4:
|
||||
; AVX: # %bb.0:
|
||||
; AVX-NEXT: vsubss %xmm1, %xmm0, %xmm2
|
||||
; AVX-NEXT: vmovshdup {{.*#+}} xmm3 = xmm1[1,1,3,3]
|
||||
; AVX-NEXT: vmovshdup {{.*#+}} xmm4 = xmm0[1,1,3,3]
|
||||
; AVX-NEXT: vsubss %xmm3, %xmm4, %xmm3
|
||||
; AVX-NEXT: vinsertps {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[2,3]
|
||||
; AVX-NEXT: vpermilpd {{.*#+}} xmm3 = xmm1[1,0]
|
||||
; AVX-NEXT: vpermilpd {{.*#+}} xmm4 = xmm0[1,0]
|
||||
; AVX-NEXT: vsubss %xmm3, %xmm4, %xmm3
|
||||
; AVX-NEXT: vinsertps {{.*#+}} xmm2 = xmm2[0,1],xmm3[0],xmm2[3]
|
||||
; AVX-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[3,1,2,3]
|
||||
; AVX-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,1,2,3]
|
||||
; AVX-NEXT: vsubss %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: vinsertps {{.*#+}} xmm0 = xmm2[0,1,2],xmm0[0]
|
||||
; AVX-NEXT: vsubps %xmm1, %xmm0, %xmm0
|
||||
; AVX-NEXT: ret{{[l|q]}}
|
||||
%ret = call <4 x float> @llvm.experimental.constrained.fsub.v4f32(<4 x float> %a, <4 x float> %b,
|
||||
metadata !"round.dynamic",
|
||||
|
|
|
|||
|
|
@ -16,19 +16,7 @@ declare <8 x float> @llvm.experimental.constrained.fdiv.v8f32(<8 x float>, <8 x
|
|||
define <4 x double> @f1(<4 x double> %a, <4 x double> %b) #0 {
|
||||
; CHECK-LABEL: f1:
|
||||
; CHECK: # %bb.0:
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm1, %xmm2
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm0, %xmm3
|
||||
; CHECK-NEXT: vaddsd %xmm2, %xmm3, %xmm4
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm2 = xmm2[1,0]
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm3 = xmm3[1,0]
|
||||
; CHECK-NEXT: vaddsd %xmm2, %xmm3, %xmm2
|
||||
; CHECK-NEXT: vunpcklpd {{.*#+}} xmm2 = xmm4[0],xmm2[0]
|
||||
; CHECK-NEXT: vaddsd %xmm1, %xmm0, %xmm3
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm1 = xmm1[1,0]
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
|
||||
; CHECK-NEXT: vaddsd %xmm1, %xmm0, %xmm0
|
||||
; CHECK-NEXT: vunpcklpd {{.*#+}} xmm0 = xmm3[0],xmm0[0]
|
||||
; CHECK-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
|
||||
; CHECK-NEXT: vaddpd %ymm1, %ymm0, %ymm0
|
||||
; CHECK-NEXT: ret{{[l|q]}}
|
||||
%ret = call <4 x double> @llvm.experimental.constrained.fadd.v4f64(<4 x double> %a, <4 x double> %b,
|
||||
metadata !"round.dynamic",
|
||||
|
|
@ -39,35 +27,7 @@ define <4 x double> @f1(<4 x double> %a, <4 x double> %b) #0 {
|
|||
define <8 x float> @f2(<8 x float> %a, <8 x float> %b) #0 {
|
||||
; CHECK-LABEL: f2:
|
||||
; CHECK: # %bb.0:
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm1, %xmm2
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm0, %xmm3
|
||||
; CHECK-NEXT: vaddss %xmm2, %xmm3, %xmm4
|
||||
; CHECK-NEXT: vmovshdup {{.*#+}} xmm5 = xmm2[1,1,3,3]
|
||||
; CHECK-NEXT: vmovshdup {{.*#+}} xmm6 = xmm3[1,1,3,3]
|
||||
; CHECK-NEXT: vaddss %xmm5, %xmm6, %xmm5
|
||||
; CHECK-NEXT: vinsertps {{.*#+}} xmm4 = xmm4[0],xmm5[0],xmm4[2,3]
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm5 = xmm2[1,0]
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm6 = xmm3[1,0]
|
||||
; CHECK-NEXT: vaddss %xmm5, %xmm6, %xmm5
|
||||
; CHECK-NEXT: vinsertps {{.*#+}} xmm4 = xmm4[0,1],xmm5[0],xmm4[3]
|
||||
; CHECK-NEXT: vpermilps {{.*#+}} xmm2 = xmm2[3,1,2,3]
|
||||
; CHECK-NEXT: vpermilps {{.*#+}} xmm3 = xmm3[3,1,2,3]
|
||||
; CHECK-NEXT: vaddss %xmm2, %xmm3, %xmm2
|
||||
; CHECK-NEXT: vinsertps {{.*#+}} xmm2 = xmm4[0,1,2],xmm2[0]
|
||||
; CHECK-NEXT: vaddss %xmm1, %xmm0, %xmm3
|
||||
; CHECK-NEXT: vmovshdup {{.*#+}} xmm4 = xmm1[1,1,3,3]
|
||||
; CHECK-NEXT: vmovshdup {{.*#+}} xmm5 = xmm0[1,1,3,3]
|
||||
; CHECK-NEXT: vaddss %xmm4, %xmm5, %xmm4
|
||||
; CHECK-NEXT: vinsertps {{.*#+}} xmm3 = xmm3[0],xmm4[0],xmm3[2,3]
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm4 = xmm1[1,0]
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm5 = xmm0[1,0]
|
||||
; CHECK-NEXT: vaddss %xmm4, %xmm5, %xmm4
|
||||
; CHECK-NEXT: vinsertps {{.*#+}} xmm3 = xmm3[0,1],xmm4[0],xmm3[3]
|
||||
; CHECK-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[3,1,2,3]
|
||||
; CHECK-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,1,2,3]
|
||||
; CHECK-NEXT: vaddss %xmm1, %xmm0, %xmm0
|
||||
; CHECK-NEXT: vinsertps {{.*#+}} xmm0 = xmm3[0,1,2],xmm0[0]
|
||||
; CHECK-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
|
||||
; CHECK-NEXT: vaddps %ymm1, %ymm0, %ymm0
|
||||
; CHECK-NEXT: ret{{[l|q]}}
|
||||
%ret = call <8 x float> @llvm.experimental.constrained.fadd.v8f32(<8 x float> %a, <8 x float> %b,
|
||||
metadata !"round.dynamic",
|
||||
|
|
@ -78,19 +38,7 @@ define <8 x float> @f2(<8 x float> %a, <8 x float> %b) #0 {
|
|||
define <4 x double> @f3(<4 x double> %a, <4 x double> %b) #0 {
|
||||
; CHECK-LABEL: f3:
|
||||
; CHECK: # %bb.0:
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm1, %xmm2
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm0, %xmm3
|
||||
; CHECK-NEXT: vsubsd %xmm2, %xmm3, %xmm4
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm2 = xmm2[1,0]
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm3 = xmm3[1,0]
|
||||
; CHECK-NEXT: vsubsd %xmm2, %xmm3, %xmm2
|
||||
; CHECK-NEXT: vunpcklpd {{.*#+}} xmm2 = xmm4[0],xmm2[0]
|
||||
; CHECK-NEXT: vsubsd %xmm1, %xmm0, %xmm3
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm1 = xmm1[1,0]
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
|
||||
; CHECK-NEXT: vsubsd %xmm1, %xmm0, %xmm0
|
||||
; CHECK-NEXT: vunpcklpd {{.*#+}} xmm0 = xmm3[0],xmm0[0]
|
||||
; CHECK-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
|
||||
; CHECK-NEXT: vsubpd %ymm1, %ymm0, %ymm0
|
||||
; CHECK-NEXT: ret{{[l|q]}}
|
||||
%ret = call <4 x double> @llvm.experimental.constrained.fsub.v4f64(<4 x double> %a, <4 x double> %b,
|
||||
metadata !"round.dynamic",
|
||||
|
|
@ -101,35 +49,7 @@ define <4 x double> @f3(<4 x double> %a, <4 x double> %b) #0 {
|
|||
define <8 x float> @f4(<8 x float> %a, <8 x float> %b) #0 {
|
||||
; CHECK-LABEL: f4:
|
||||
; CHECK: # %bb.0:
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm1, %xmm2
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm0, %xmm3
|
||||
; CHECK-NEXT: vsubss %xmm2, %xmm3, %xmm4
|
||||
; CHECK-NEXT: vmovshdup {{.*#+}} xmm5 = xmm2[1,1,3,3]
|
||||
; CHECK-NEXT: vmovshdup {{.*#+}} xmm6 = xmm3[1,1,3,3]
|
||||
; CHECK-NEXT: vsubss %xmm5, %xmm6, %xmm5
|
||||
; CHECK-NEXT: vinsertps {{.*#+}} xmm4 = xmm4[0],xmm5[0],xmm4[2,3]
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm5 = xmm2[1,0]
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm6 = xmm3[1,0]
|
||||
; CHECK-NEXT: vsubss %xmm5, %xmm6, %xmm5
|
||||
; CHECK-NEXT: vinsertps {{.*#+}} xmm4 = xmm4[0,1],xmm5[0],xmm4[3]
|
||||
; CHECK-NEXT: vpermilps {{.*#+}} xmm2 = xmm2[3,1,2,3]
|
||||
; CHECK-NEXT: vpermilps {{.*#+}} xmm3 = xmm3[3,1,2,3]
|
||||
; CHECK-NEXT: vsubss %xmm2, %xmm3, %xmm2
|
||||
; CHECK-NEXT: vinsertps {{.*#+}} xmm2 = xmm4[0,1,2],xmm2[0]
|
||||
; CHECK-NEXT: vsubss %xmm1, %xmm0, %xmm3
|
||||
; CHECK-NEXT: vmovshdup {{.*#+}} xmm4 = xmm1[1,1,3,3]
|
||||
; CHECK-NEXT: vmovshdup {{.*#+}} xmm5 = xmm0[1,1,3,3]
|
||||
; CHECK-NEXT: vsubss %xmm4, %xmm5, %xmm4
|
||||
; CHECK-NEXT: vinsertps {{.*#+}} xmm3 = xmm3[0],xmm4[0],xmm3[2,3]
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm4 = xmm1[1,0]
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm5 = xmm0[1,0]
|
||||
; CHECK-NEXT: vsubss %xmm4, %xmm5, %xmm4
|
||||
; CHECK-NEXT: vinsertps {{.*#+}} xmm3 = xmm3[0,1],xmm4[0],xmm3[3]
|
||||
; CHECK-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[3,1,2,3]
|
||||
; CHECK-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,1,2,3]
|
||||
; CHECK-NEXT: vsubss %xmm1, %xmm0, %xmm0
|
||||
; CHECK-NEXT: vinsertps {{.*#+}} xmm0 = xmm3[0,1,2],xmm0[0]
|
||||
; CHECK-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
|
||||
; CHECK-NEXT: vsubps %ymm1, %ymm0, %ymm0
|
||||
; CHECK-NEXT: ret{{[l|q]}}
|
||||
%ret = call <8 x float> @llvm.experimental.constrained.fsub.v8f32(<8 x float> %a, <8 x float> %b,
|
||||
metadata !"round.dynamic",
|
||||
|
|
|
|||
|
|
@ -14,35 +14,7 @@ declare <16 x float> @llvm.experimental.constrained.fdiv.v16f32(<16 x float>, <1
|
|||
define <8 x double> @f1(<8 x double> %a, <8 x double> %b) #0 {
|
||||
; CHECK-LABEL: f1:
|
||||
; CHECK: # %bb.0:
|
||||
; CHECK-NEXT: vextractf32x4 $3, %zmm1, %xmm2
|
||||
; CHECK-NEXT: vextractf32x4 $3, %zmm0, %xmm3
|
||||
; CHECK-NEXT: vaddsd %xmm2, %xmm3, %xmm4
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm2 = xmm2[1,0]
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm3 = xmm3[1,0]
|
||||
; CHECK-NEXT: vaddsd %xmm2, %xmm3, %xmm2
|
||||
; CHECK-NEXT: vunpcklpd {{.*#+}} xmm2 = xmm4[0],xmm2[0]
|
||||
; CHECK-NEXT: vextractf32x4 $2, %zmm1, %xmm3
|
||||
; CHECK-NEXT: vextractf32x4 $2, %zmm0, %xmm4
|
||||
; CHECK-NEXT: vaddsd %xmm3, %xmm4, %xmm5
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm3 = xmm3[1,0]
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm4 = xmm4[1,0]
|
||||
; CHECK-NEXT: vaddsd %xmm3, %xmm4, %xmm3
|
||||
; CHECK-NEXT: vunpcklpd {{.*#+}} xmm3 = xmm5[0],xmm3[0]
|
||||
; CHECK-NEXT: vinsertf128 $1, %xmm2, %ymm3, %ymm2
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm1, %xmm3
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm0, %xmm4
|
||||
; CHECK-NEXT: vaddsd %xmm3, %xmm4, %xmm5
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm3 = xmm3[1,0]
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm4 = xmm4[1,0]
|
||||
; CHECK-NEXT: vaddsd %xmm3, %xmm4, %xmm3
|
||||
; CHECK-NEXT: vunpcklpd {{.*#+}} xmm3 = xmm5[0],xmm3[0]
|
||||
; CHECK-NEXT: vaddsd %xmm1, %xmm0, %xmm4
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm1 = xmm1[1,0]
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
|
||||
; CHECK-NEXT: vaddsd %xmm1, %xmm0, %xmm0
|
||||
; CHECK-NEXT: vunpcklpd {{.*#+}} xmm0 = xmm4[0],xmm0[0]
|
||||
; CHECK-NEXT: vinsertf128 $1, %xmm3, %ymm0, %ymm0
|
||||
; CHECK-NEXT: vinsertf64x4 $1, %ymm2, %zmm0, %zmm0
|
||||
; CHECK-NEXT: vaddpd %zmm1, %zmm0, %zmm0
|
||||
; CHECK-NEXT: ret{{[l|q]}}
|
||||
%ret = call <8 x double> @llvm.experimental.constrained.fadd.v8f64(<8 x double> %a, <8 x double> %b,
|
||||
metadata !"round.dynamic",
|
||||
|
|
@ -53,67 +25,7 @@ define <8 x double> @f1(<8 x double> %a, <8 x double> %b) #0 {
|
|||
define <16 x float> @f2(<16 x float> %a, <16 x float> %b) #0 {
|
||||
; CHECK-LABEL: f2:
|
||||
; CHECK: # %bb.0:
|
||||
; CHECK-NEXT: vextractf32x4 $3, %zmm1, %xmm2
|
||||
; CHECK-NEXT: vextractf32x4 $3, %zmm0, %xmm3
|
||||
; CHECK-NEXT: vaddss %xmm2, %xmm3, %xmm4
|
||||
; CHECK-NEXT: vmovshdup {{.*#+}} xmm5 = xmm2[1,1,3,3]
|
||||
; CHECK-NEXT: vmovshdup {{.*#+}} xmm6 = xmm3[1,1,3,3]
|
||||
; CHECK-NEXT: vaddss %xmm5, %xmm6, %xmm5
|
||||
; CHECK-NEXT: vinsertps {{.*#+}} xmm4 = xmm4[0],xmm5[0],xmm4[2,3]
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm5 = xmm2[1,0]
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm6 = xmm3[1,0]
|
||||
; CHECK-NEXT: vaddss %xmm5, %xmm6, %xmm5
|
||||
; CHECK-NEXT: vinsertps {{.*#+}} xmm4 = xmm4[0,1],xmm5[0],xmm4[3]
|
||||
; CHECK-NEXT: vpermilps {{.*#+}} xmm2 = xmm2[3,1,2,3]
|
||||
; CHECK-NEXT: vpermilps {{.*#+}} xmm3 = xmm3[3,1,2,3]
|
||||
; CHECK-NEXT: vaddss %xmm2, %xmm3, %xmm2
|
||||
; CHECK-NEXT: vinsertps {{.*#+}} xmm2 = xmm4[0,1,2],xmm2[0]
|
||||
; CHECK-NEXT: vextractf32x4 $2, %zmm1, %xmm3
|
||||
; CHECK-NEXT: vextractf32x4 $2, %zmm0, %xmm4
|
||||
; CHECK-NEXT: vaddss %xmm3, %xmm4, %xmm5
|
||||
; CHECK-NEXT: vmovshdup {{.*#+}} xmm6 = xmm3[1,1,3,3]
|
||||
; CHECK-NEXT: vmovshdup {{.*#+}} xmm7 = xmm4[1,1,3,3]
|
||||
; CHECK-NEXT: vaddss %xmm6, %xmm7, %xmm6
|
||||
; CHECK-NEXT: vinsertps {{.*#+}} xmm5 = xmm5[0],xmm6[0],xmm5[2,3]
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm6 = xmm3[1,0]
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm7 = xmm4[1,0]
|
||||
; CHECK-NEXT: vaddss %xmm6, %xmm7, %xmm6
|
||||
; CHECK-NEXT: vinsertps {{.*#+}} xmm5 = xmm5[0,1],xmm6[0],xmm5[3]
|
||||
; CHECK-NEXT: vpermilps {{.*#+}} xmm3 = xmm3[3,1,2,3]
|
||||
; CHECK-NEXT: vpermilps {{.*#+}} xmm4 = xmm4[3,1,2,3]
|
||||
; CHECK-NEXT: vaddss %xmm3, %xmm4, %xmm3
|
||||
; CHECK-NEXT: vinsertps {{.*#+}} xmm3 = xmm5[0,1,2],xmm3[0]
|
||||
; CHECK-NEXT: vinsertf128 $1, %xmm2, %ymm3, %ymm2
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm1, %xmm3
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm0, %xmm4
|
||||
; CHECK-NEXT: vaddss %xmm3, %xmm4, %xmm5
|
||||
; CHECK-NEXT: vmovshdup {{.*#+}} xmm6 = xmm3[1,1,3,3]
|
||||
; CHECK-NEXT: vmovshdup {{.*#+}} xmm7 = xmm4[1,1,3,3]
|
||||
; CHECK-NEXT: vaddss %xmm6, %xmm7, %xmm6
|
||||
; CHECK-NEXT: vinsertps {{.*#+}} xmm5 = xmm5[0],xmm6[0],xmm5[2,3]
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm6 = xmm3[1,0]
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm7 = xmm4[1,0]
|
||||
; CHECK-NEXT: vaddss %xmm6, %xmm7, %xmm6
|
||||
; CHECK-NEXT: vinsertps {{.*#+}} xmm5 = xmm5[0,1],xmm6[0],xmm5[3]
|
||||
; CHECK-NEXT: vpermilps {{.*#+}} xmm3 = xmm3[3,1,2,3]
|
||||
; CHECK-NEXT: vpermilps {{.*#+}} xmm4 = xmm4[3,1,2,3]
|
||||
; CHECK-NEXT: vaddss %xmm3, %xmm4, %xmm3
|
||||
; CHECK-NEXT: vinsertps {{.*#+}} xmm3 = xmm5[0,1,2],xmm3[0]
|
||||
; CHECK-NEXT: vaddss %xmm1, %xmm0, %xmm4
|
||||
; CHECK-NEXT: vmovshdup {{.*#+}} xmm5 = xmm1[1,1,3,3]
|
||||
; CHECK-NEXT: vmovshdup {{.*#+}} xmm6 = xmm0[1,1,3,3]
|
||||
; CHECK-NEXT: vaddss %xmm5, %xmm6, %xmm5
|
||||
; CHECK-NEXT: vinsertps {{.*#+}} xmm4 = xmm4[0],xmm5[0],xmm4[2,3]
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm5 = xmm1[1,0]
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm6 = xmm0[1,0]
|
||||
; CHECK-NEXT: vaddss %xmm5, %xmm6, %xmm5
|
||||
; CHECK-NEXT: vinsertps {{.*#+}} xmm4 = xmm4[0,1],xmm5[0],xmm4[3]
|
||||
; CHECK-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[3,1,2,3]
|
||||
; CHECK-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,1,2,3]
|
||||
; CHECK-NEXT: vaddss %xmm1, %xmm0, %xmm0
|
||||
; CHECK-NEXT: vinsertps {{.*#+}} xmm0 = xmm4[0,1,2],xmm0[0]
|
||||
; CHECK-NEXT: vinsertf128 $1, %xmm3, %ymm0, %ymm0
|
||||
; CHECK-NEXT: vinsertf64x4 $1, %ymm2, %zmm0, %zmm0
|
||||
; CHECK-NEXT: vaddps %zmm1, %zmm0, %zmm0
|
||||
; CHECK-NEXT: ret{{[l|q]}}
|
||||
%ret = call <16 x float> @llvm.experimental.constrained.fadd.v16f32(<16 x float> %a, <16 x float> %b,
|
||||
metadata !"round.dynamic",
|
||||
|
|
@ -124,35 +36,7 @@ define <16 x float> @f2(<16 x float> %a, <16 x float> %b) #0 {
|
|||
define <8 x double> @f3(<8 x double> %a, <8 x double> %b) #0 {
|
||||
; CHECK-LABEL: f3:
|
||||
; CHECK: # %bb.0:
|
||||
; CHECK-NEXT: vextractf32x4 $3, %zmm1, %xmm2
|
||||
; CHECK-NEXT: vextractf32x4 $3, %zmm0, %xmm3
|
||||
; CHECK-NEXT: vsubsd %xmm2, %xmm3, %xmm4
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm2 = xmm2[1,0]
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm3 = xmm3[1,0]
|
||||
; CHECK-NEXT: vsubsd %xmm2, %xmm3, %xmm2
|
||||
; CHECK-NEXT: vunpcklpd {{.*#+}} xmm2 = xmm4[0],xmm2[0]
|
||||
; CHECK-NEXT: vextractf32x4 $2, %zmm1, %xmm3
|
||||
; CHECK-NEXT: vextractf32x4 $2, %zmm0, %xmm4
|
||||
; CHECK-NEXT: vsubsd %xmm3, %xmm4, %xmm5
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm3 = xmm3[1,0]
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm4 = xmm4[1,0]
|
||||
; CHECK-NEXT: vsubsd %xmm3, %xmm4, %xmm3
|
||||
; CHECK-NEXT: vunpcklpd {{.*#+}} xmm3 = xmm5[0],xmm3[0]
|
||||
; CHECK-NEXT: vinsertf128 $1, %xmm2, %ymm3, %ymm2
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm1, %xmm3
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm0, %xmm4
|
||||
; CHECK-NEXT: vsubsd %xmm3, %xmm4, %xmm5
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm3 = xmm3[1,0]
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm4 = xmm4[1,0]
|
||||
; CHECK-NEXT: vsubsd %xmm3, %xmm4, %xmm3
|
||||
; CHECK-NEXT: vunpcklpd {{.*#+}} xmm3 = xmm5[0],xmm3[0]
|
||||
; CHECK-NEXT: vsubsd %xmm1, %xmm0, %xmm4
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm1 = xmm1[1,0]
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
|
||||
; CHECK-NEXT: vsubsd %xmm1, %xmm0, %xmm0
|
||||
; CHECK-NEXT: vunpcklpd {{.*#+}} xmm0 = xmm4[0],xmm0[0]
|
||||
; CHECK-NEXT: vinsertf128 $1, %xmm3, %ymm0, %ymm0
|
||||
; CHECK-NEXT: vinsertf64x4 $1, %ymm2, %zmm0, %zmm0
|
||||
; CHECK-NEXT: vsubpd %zmm1, %zmm0, %zmm0
|
||||
; CHECK-NEXT: ret{{[l|q]}}
|
||||
%ret = call <8 x double> @llvm.experimental.constrained.fsub.v8f64(<8 x double> %a, <8 x double> %b,
|
||||
metadata !"round.dynamic",
|
||||
|
|
@ -163,67 +47,7 @@ define <8 x double> @f3(<8 x double> %a, <8 x double> %b) #0 {
|
|||
define <16 x float> @f4(<16 x float> %a, <16 x float> %b) #0 {
|
||||
; CHECK-LABEL: f4:
|
||||
; CHECK: # %bb.0:
|
||||
; CHECK-NEXT: vextractf32x4 $3, %zmm1, %xmm2
|
||||
; CHECK-NEXT: vextractf32x4 $3, %zmm0, %xmm3
|
||||
; CHECK-NEXT: vsubss %xmm2, %xmm3, %xmm4
|
||||
; CHECK-NEXT: vmovshdup {{.*#+}} xmm5 = xmm2[1,1,3,3]
|
||||
; CHECK-NEXT: vmovshdup {{.*#+}} xmm6 = xmm3[1,1,3,3]
|
||||
; CHECK-NEXT: vsubss %xmm5, %xmm6, %xmm5
|
||||
; CHECK-NEXT: vinsertps {{.*#+}} xmm4 = xmm4[0],xmm5[0],xmm4[2,3]
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm5 = xmm2[1,0]
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm6 = xmm3[1,0]
|
||||
; CHECK-NEXT: vsubss %xmm5, %xmm6, %xmm5
|
||||
; CHECK-NEXT: vinsertps {{.*#+}} xmm4 = xmm4[0,1],xmm5[0],xmm4[3]
|
||||
; CHECK-NEXT: vpermilps {{.*#+}} xmm2 = xmm2[3,1,2,3]
|
||||
; CHECK-NEXT: vpermilps {{.*#+}} xmm3 = xmm3[3,1,2,3]
|
||||
; CHECK-NEXT: vsubss %xmm2, %xmm3, %xmm2
|
||||
; CHECK-NEXT: vinsertps {{.*#+}} xmm2 = xmm4[0,1,2],xmm2[0]
|
||||
; CHECK-NEXT: vextractf32x4 $2, %zmm1, %xmm3
|
||||
; CHECK-NEXT: vextractf32x4 $2, %zmm0, %xmm4
|
||||
; CHECK-NEXT: vsubss %xmm3, %xmm4, %xmm5
|
||||
; CHECK-NEXT: vmovshdup {{.*#+}} xmm6 = xmm3[1,1,3,3]
|
||||
; CHECK-NEXT: vmovshdup {{.*#+}} xmm7 = xmm4[1,1,3,3]
|
||||
; CHECK-NEXT: vsubss %xmm6, %xmm7, %xmm6
|
||||
; CHECK-NEXT: vinsertps {{.*#+}} xmm5 = xmm5[0],xmm6[0],xmm5[2,3]
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm6 = xmm3[1,0]
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm7 = xmm4[1,0]
|
||||
; CHECK-NEXT: vsubss %xmm6, %xmm7, %xmm6
|
||||
; CHECK-NEXT: vinsertps {{.*#+}} xmm5 = xmm5[0,1],xmm6[0],xmm5[3]
|
||||
; CHECK-NEXT: vpermilps {{.*#+}} xmm3 = xmm3[3,1,2,3]
|
||||
; CHECK-NEXT: vpermilps {{.*#+}} xmm4 = xmm4[3,1,2,3]
|
||||
; CHECK-NEXT: vsubss %xmm3, %xmm4, %xmm3
|
||||
; CHECK-NEXT: vinsertps {{.*#+}} xmm3 = xmm5[0,1,2],xmm3[0]
|
||||
; CHECK-NEXT: vinsertf128 $1, %xmm2, %ymm3, %ymm2
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm1, %xmm3
|
||||
; CHECK-NEXT: vextractf128 $1, %ymm0, %xmm4
|
||||
; CHECK-NEXT: vsubss %xmm3, %xmm4, %xmm5
|
||||
; CHECK-NEXT: vmovshdup {{.*#+}} xmm6 = xmm3[1,1,3,3]
|
||||
; CHECK-NEXT: vmovshdup {{.*#+}} xmm7 = xmm4[1,1,3,3]
|
||||
; CHECK-NEXT: vsubss %xmm6, %xmm7, %xmm6
|
||||
; CHECK-NEXT: vinsertps {{.*#+}} xmm5 = xmm5[0],xmm6[0],xmm5[2,3]
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm6 = xmm3[1,0]
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm7 = xmm4[1,0]
|
||||
; CHECK-NEXT: vsubss %xmm6, %xmm7, %xmm6
|
||||
; CHECK-NEXT: vinsertps {{.*#+}} xmm5 = xmm5[0,1],xmm6[0],xmm5[3]
|
||||
; CHECK-NEXT: vpermilps {{.*#+}} xmm3 = xmm3[3,1,2,3]
|
||||
; CHECK-NEXT: vpermilps {{.*#+}} xmm4 = xmm4[3,1,2,3]
|
||||
; CHECK-NEXT: vsubss %xmm3, %xmm4, %xmm3
|
||||
; CHECK-NEXT: vinsertps {{.*#+}} xmm3 = xmm5[0,1,2],xmm3[0]
|
||||
; CHECK-NEXT: vsubss %xmm1, %xmm0, %xmm4
|
||||
; CHECK-NEXT: vmovshdup {{.*#+}} xmm5 = xmm1[1,1,3,3]
|
||||
; CHECK-NEXT: vmovshdup {{.*#+}} xmm6 = xmm0[1,1,3,3]
|
||||
; CHECK-NEXT: vsubss %xmm5, %xmm6, %xmm5
|
||||
; CHECK-NEXT: vinsertps {{.*#+}} xmm4 = xmm4[0],xmm5[0],xmm4[2,3]
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm5 = xmm1[1,0]
|
||||
; CHECK-NEXT: vpermilpd {{.*#+}} xmm6 = xmm0[1,0]
|
||||
; CHECK-NEXT: vsubss %xmm5, %xmm6, %xmm5
|
||||
; CHECK-NEXT: vinsertps {{.*#+}} xmm4 = xmm4[0,1],xmm5[0],xmm4[3]
|
||||
; CHECK-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[3,1,2,3]
|
||||
; CHECK-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,1,2,3]
|
||||
; CHECK-NEXT: vsubss %xmm1, %xmm0, %xmm0
|
||||
; CHECK-NEXT: vinsertps {{.*#+}} xmm0 = xmm4[0,1,2],xmm0[0]
|
||||
; CHECK-NEXT: vinsertf128 $1, %xmm3, %ymm0, %ymm0
|
||||
; CHECK-NEXT: vinsertf64x4 $1, %ymm2, %zmm0, %zmm0
|
||||
; CHECK-NEXT: vsubps %zmm1, %zmm0, %zmm0
|
||||
; CHECK-NEXT: ret{{[l|q]}}
|
||||
%ret = call <16 x float> @llvm.experimental.constrained.fsub.v16f32(<16 x float> %a, <16 x float> %b,
|
||||
metadata !"round.dynamic",
|
||||
|
|
|
|||
|
|
@ -559,19 +559,14 @@ entry:
|
|||
define <2 x double> @constrained_vector_fadd_v2f64() #0 {
|
||||
; CHECK-LABEL: constrained_vector_fadd_v2f64:
|
||||
; CHECK: # %bb.0: # %entry
|
||||
; CHECK-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
|
||||
; CHECK-NEXT: movsd {{.*#+}} xmm1 = mem[0],zero
|
||||
; CHECK-NEXT: addsd %xmm0, %xmm1
|
||||
; CHECK-NEXT: addsd {{.*}}(%rip), %xmm0
|
||||
; CHECK-NEXT: unpcklpd {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; CHECK-NEXT: movapd {{.*#+}} xmm0 = [1.7976931348623157E+308,1.7976931348623157E+308]
|
||||
; CHECK-NEXT: addpd {{.*}}(%rip), %xmm0
|
||||
; CHECK-NEXT: retq
|
||||
;
|
||||
; AVX-LABEL: constrained_vector_fadd_v2f64:
|
||||
; AVX: # %bb.0: # %entry
|
||||
; AVX-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
|
||||
; AVX-NEXT: vaddsd {{.*}}(%rip), %xmm0, %xmm1
|
||||
; AVX-NEXT: vaddsd {{.*}}(%rip), %xmm0, %xmm0
|
||||
; AVX-NEXT: vunpcklpd {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; AVX-NEXT: vmovapd {{.*#+}} xmm0 = [1.7976931348623157E+308,1.7976931348623157E+308]
|
||||
; AVX-NEXT: vaddpd {{.*}}(%rip), %xmm0, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
entry:
|
||||
%add = call <2 x double> @llvm.experimental.constrained.fadd.v2f64(
|
||||
|
|
@ -618,24 +613,22 @@ entry:
|
|||
define <3 x double> @constrained_vector_fadd_v3f64() #0 {
|
||||
; CHECK-LABEL: constrained_vector_fadd_v3f64:
|
||||
; CHECK: # %bb.0: # %entry
|
||||
; CHECK-NEXT: xorpd %xmm2, %xmm2
|
||||
; CHECK-NEXT: movsd {{.*#+}} xmm1 = mem[0],zero
|
||||
; CHECK-NEXT: addsd %xmm1, %xmm2
|
||||
; CHECK-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
|
||||
; CHECK-NEXT: addsd %xmm1, %xmm0
|
||||
; CHECK-NEXT: movapd {{.*#+}} xmm0 = [1.7976931348623157E+308,1.7976931348623157E+308]
|
||||
; CHECK-NEXT: addpd {{.*}}(%rip), %xmm0
|
||||
; CHECK-NEXT: xorpd %xmm1, %xmm1
|
||||
; CHECK-NEXT: addsd {{.*}}(%rip), %xmm1
|
||||
; CHECK-NEXT: movsd %xmm2, -{{[0-9]+}}(%rsp)
|
||||
; CHECK-NEXT: movsd %xmm1, -{{[0-9]+}}(%rsp)
|
||||
; CHECK-NEXT: movapd %xmm0, %xmm1
|
||||
; CHECK-NEXT: unpckhpd {{.*#+}} xmm1 = xmm1[1],xmm0[1]
|
||||
; CHECK-NEXT: fldl -{{[0-9]+}}(%rsp)
|
||||
; CHECK-NEXT: retq
|
||||
;
|
||||
; AVX-LABEL: constrained_vector_fadd_v3f64:
|
||||
; AVX: # %bb.0: # %entry
|
||||
; AVX-NEXT: vxorpd %xmm0, %xmm0, %xmm0
|
||||
; AVX-NEXT: vmovsd {{.*#+}} xmm1 = mem[0],zero
|
||||
; AVX-NEXT: vaddsd %xmm0, %xmm1, %xmm0
|
||||
; AVX-NEXT: vaddsd {{.*}}(%rip), %xmm1, %xmm2
|
||||
; AVX-NEXT: vaddsd {{.*}}(%rip), %xmm1, %xmm1
|
||||
; AVX-NEXT: vunpcklpd {{.*#+}} xmm1 = xmm1[0],xmm2[0]
|
||||
; AVX-NEXT: vaddsd {{.*}}(%rip), %xmm0, %xmm0
|
||||
; AVX-NEXT: vmovapd {{.*#+}} xmm1 = [1.7976931348623157E+308,1.7976931348623157E+308]
|
||||
; AVX-NEXT: vaddpd {{.*}}(%rip), %xmm1, %xmm1
|
||||
; AVX-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
|
||||
; AVX-NEXT: retq
|
||||
entry:
|
||||
|
|
@ -651,29 +644,23 @@ entry:
|
|||
define <4 x double> @constrained_vector_fadd_v4f64() #0 {
|
||||
; CHECK-LABEL: constrained_vector_fadd_v4f64:
|
||||
; CHECK: # %bb.0: # %entry
|
||||
; CHECK-NEXT: movsd {{.*#+}} xmm1 = mem[0],zero
|
||||
; CHECK-NEXT: movsd {{.*#+}} xmm2 = mem[0],zero
|
||||
; CHECK-NEXT: addsd %xmm1, %xmm2
|
||||
; CHECK-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
|
||||
; CHECK-NEXT: addsd %xmm1, %xmm0
|
||||
; CHECK-NEXT: unpcklpd {{.*#+}} xmm0 = xmm0[0],xmm2[0]
|
||||
; CHECK-NEXT: movsd {{.*#+}} xmm2 = mem[0],zero
|
||||
; CHECK-NEXT: addsd %xmm1, %xmm2
|
||||
; CHECK-NEXT: addsd {{.*}}(%rip), %xmm1
|
||||
; CHECK-NEXT: unpcklpd {{.*#+}} xmm1 = xmm1[0],xmm2[0]
|
||||
; CHECK-NEXT: movapd {{.*#+}} xmm1 = [1.7976931348623157E+308,1.7976931348623157E+308]
|
||||
; CHECK-NEXT: movapd {{.*#+}} xmm0 = [1.0E+0,1.0000000000000001E-1]
|
||||
; CHECK-NEXT: addpd %xmm1, %xmm0
|
||||
; CHECK-NEXT: addpd {{.*}}(%rip), %xmm1
|
||||
; CHECK-NEXT: retq
|
||||
;
|
||||
; AVX-LABEL: constrained_vector_fadd_v4f64:
|
||||
; AVX: # %bb.0: # %entry
|
||||
; AVX-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
|
||||
; AVX-NEXT: vaddsd {{.*}}(%rip), %xmm0, %xmm1
|
||||
; AVX-NEXT: vaddsd {{.*}}(%rip), %xmm0, %xmm2
|
||||
; AVX-NEXT: vunpcklpd {{.*#+}} xmm1 = xmm2[0],xmm1[0]
|
||||
; AVX-NEXT: vaddsd {{.*}}(%rip), %xmm0, %xmm2
|
||||
; AVX-NEXT: vaddsd {{.*}}(%rip), %xmm0, %xmm0
|
||||
; AVX-NEXT: vunpcklpd {{.*#+}} xmm0 = xmm0[0],xmm2[0]
|
||||
; AVX-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
|
||||
; AVX-NEXT: retq
|
||||
; AVX1-LABEL: constrained_vector_fadd_v4f64:
|
||||
; AVX1: # %bb.0: # %entry
|
||||
; AVX1-NEXT: vmovapd {{.*#+}} ymm0 = [1.7976931348623157E+308,1.7976931348623157E+308,1.7976931348623157E+308,1.7976931348623157E+308]
|
||||
; AVX1-NEXT: vaddpd {{.*}}(%rip), %ymm0, %ymm0
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: constrained_vector_fadd_v4f64:
|
||||
; AVX512: # %bb.0: # %entry
|
||||
; AVX512-NEXT: vbroadcastsd {{.*#+}} ymm0 = [1.7976931348623157E+308,1.7976931348623157E+308,1.7976931348623157E+308,1.7976931348623157E+308]
|
||||
; AVX512-NEXT: vaddpd {{.*}}(%rip), %ymm0, %ymm0
|
||||
; AVX512-NEXT: retq
|
||||
entry:
|
||||
%add = call <4 x double> @llvm.experimental.constrained.fadd.v4f64(
|
||||
<4 x double> <double 0x7FEFFFFFFFFFFFFF, double 0x7FEFFFFFFFFFFFFF,
|
||||
|
|
@ -709,19 +696,14 @@ entry:
|
|||
define <2 x double> @constrained_vector_fsub_v2f64() #0 {
|
||||
; CHECK-LABEL: constrained_vector_fsub_v2f64:
|
||||
; CHECK: # %bb.0: # %entry
|
||||
; CHECK-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
|
||||
; CHECK-NEXT: movapd %xmm0, %xmm1
|
||||
; CHECK-NEXT: subsd {{.*}}(%rip), %xmm1
|
||||
; CHECK-NEXT: subsd {{.*}}(%rip), %xmm0
|
||||
; CHECK-NEXT: unpcklpd {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; CHECK-NEXT: movapd {{.*#+}} xmm0 = [-1.7976931348623157E+308,-1.7976931348623157E+308]
|
||||
; CHECK-NEXT: subpd {{.*}}(%rip), %xmm0
|
||||
; CHECK-NEXT: retq
|
||||
;
|
||||
; AVX-LABEL: constrained_vector_fsub_v2f64:
|
||||
; AVX: # %bb.0: # %entry
|
||||
; AVX-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
|
||||
; AVX-NEXT: vsubsd {{.*}}(%rip), %xmm0, %xmm1
|
||||
; AVX-NEXT: vsubsd {{.*}}(%rip), %xmm0, %xmm0
|
||||
; AVX-NEXT: vunpcklpd {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; AVX-NEXT: vmovapd {{.*#+}} xmm0 = [-1.7976931348623157E+308,-1.7976931348623157E+308]
|
||||
; AVX-NEXT: vsubpd {{.*}}(%rip), %xmm0, %xmm0
|
||||
; AVX-NEXT: retq
|
||||
entry:
|
||||
%sub = call <2 x double> @llvm.experimental.constrained.fsub.v2f64(
|
||||
|
|
@ -771,12 +753,12 @@ define <3 x double> @constrained_vector_fsub_v3f64() #0 {
|
|||
; CHECK: # %bb.0: # %entry
|
||||
; CHECK-NEXT: xorpd %xmm0, %xmm0
|
||||
; CHECK-NEXT: movsd {{.*#+}} xmm1 = mem[0],zero
|
||||
; CHECK-NEXT: movapd %xmm1, %xmm2
|
||||
; CHECK-NEXT: subsd %xmm0, %xmm2
|
||||
; CHECK-NEXT: movapd %xmm1, %xmm0
|
||||
; CHECK-NEXT: subsd {{.*}}(%rip), %xmm0
|
||||
; CHECK-NEXT: subsd {{.*}}(%rip), %xmm1
|
||||
; CHECK-NEXT: movsd %xmm2, -{{[0-9]+}}(%rsp)
|
||||
; CHECK-NEXT: subsd %xmm0, %xmm1
|
||||
; CHECK-NEXT: movapd {{.*#+}} xmm0 = [-1.7976931348623157E+308,-1.7976931348623157E+308]
|
||||
; CHECK-NEXT: subpd {{.*}}(%rip), %xmm0
|
||||
; CHECK-NEXT: movsd %xmm1, -{{[0-9]+}}(%rsp)
|
||||
; CHECK-NEXT: movapd %xmm0, %xmm1
|
||||
; CHECK-NEXT: unpckhpd {{.*#+}} xmm1 = xmm1[1],xmm0[1]
|
||||
; CHECK-NEXT: fldl -{{[0-9]+}}(%rsp)
|
||||
; CHECK-NEXT: retq
|
||||
;
|
||||
|
|
@ -785,9 +767,8 @@ define <3 x double> @constrained_vector_fsub_v3f64() #0 {
|
|||
; AVX-NEXT: vxorpd %xmm0, %xmm0, %xmm0
|
||||
; AVX-NEXT: vmovsd {{.*#+}} xmm1 = mem[0],zero
|
||||
; AVX-NEXT: vsubsd %xmm0, %xmm1, %xmm0
|
||||
; AVX-NEXT: vsubsd {{.*}}(%rip), %xmm1, %xmm2
|
||||
; AVX-NEXT: vsubsd {{.*}}(%rip), %xmm1, %xmm1
|
||||
; AVX-NEXT: vunpcklpd {{.*#+}} xmm1 = xmm1[0],xmm2[0]
|
||||
; AVX-NEXT: vmovapd {{.*#+}} xmm1 = [-1.7976931348623157E+308,-1.7976931348623157E+308]
|
||||
; AVX-NEXT: vsubpd {{.*}}(%rip), %xmm1, %xmm1
|
||||
; AVX-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
|
||||
; AVX-NEXT: retq
|
||||
entry:
|
||||
|
|
@ -803,29 +784,23 @@ entry:
|
|||
define <4 x double> @constrained_vector_fsub_v4f64() #0 {
|
||||
; CHECK-LABEL: constrained_vector_fsub_v4f64:
|
||||
; CHECK: # %bb.0: # %entry
|
||||
; CHECK-NEXT: movsd {{.*#+}} xmm1 = mem[0],zero
|
||||
; CHECK-NEXT: movapd %xmm1, %xmm2
|
||||
; CHECK-NEXT: subsd {{.*}}(%rip), %xmm2
|
||||
; CHECK-NEXT: movapd {{.*#+}} xmm1 = [-1.7976931348623157E+308,-1.7976931348623157E+308]
|
||||
; CHECK-NEXT: movapd %xmm1, %xmm0
|
||||
; CHECK-NEXT: subsd {{.*}}(%rip), %xmm0
|
||||
; CHECK-NEXT: unpcklpd {{.*#+}} xmm0 = xmm0[0],xmm2[0]
|
||||
; CHECK-NEXT: movapd %xmm1, %xmm2
|
||||
; CHECK-NEXT: subsd {{.*}}(%rip), %xmm2
|
||||
; CHECK-NEXT: subsd {{.*}}(%rip), %xmm1
|
||||
; CHECK-NEXT: unpcklpd {{.*#+}} xmm1 = xmm1[0],xmm2[0]
|
||||
; CHECK-NEXT: subpd {{.*}}(%rip), %xmm0
|
||||
; CHECK-NEXT: subpd {{.*}}(%rip), %xmm1
|
||||
; CHECK-NEXT: retq
|
||||
;
|
||||
; AVX-LABEL: constrained_vector_fsub_v4f64:
|
||||
; AVX: # %bb.0: # %entry
|
||||
; AVX-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
|
||||
; AVX-NEXT: vsubsd {{.*}}(%rip), %xmm0, %xmm1
|
||||
; AVX-NEXT: vsubsd {{.*}}(%rip), %xmm0, %xmm2
|
||||
; AVX-NEXT: vunpcklpd {{.*#+}} xmm1 = xmm2[0],xmm1[0]
|
||||
; AVX-NEXT: vsubsd {{.*}}(%rip), %xmm0, %xmm2
|
||||
; AVX-NEXT: vsubsd {{.*}}(%rip), %xmm0, %xmm0
|
||||
; AVX-NEXT: vunpcklpd {{.*#+}} xmm0 = xmm0[0],xmm2[0]
|
||||
; AVX-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
|
||||
; AVX-NEXT: retq
|
||||
; AVX1-LABEL: constrained_vector_fsub_v4f64:
|
||||
; AVX1: # %bb.0: # %entry
|
||||
; AVX1-NEXT: vmovapd {{.*#+}} ymm0 = [-1.7976931348623157E+308,-1.7976931348623157E+308,-1.7976931348623157E+308,-1.7976931348623157E+308]
|
||||
; AVX1-NEXT: vsubpd {{.*}}(%rip), %ymm0, %ymm0
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: constrained_vector_fsub_v4f64:
|
||||
; AVX512: # %bb.0: # %entry
|
||||
; AVX512-NEXT: vbroadcastsd {{.*#+}} ymm0 = [-1.7976931348623157E+308,-1.7976931348623157E+308,-1.7976931348623157E+308,-1.7976931348623157E+308]
|
||||
; AVX512-NEXT: vsubpd {{.*}}(%rip), %ymm0, %ymm0
|
||||
; AVX512-NEXT: retq
|
||||
entry:
|
||||
%sub = call <4 x double> @llvm.experimental.constrained.fsub.v4f64(
|
||||
<4 x double> <double 0xFFEFFFFFFFFFFFFF, double 0xFFEFFFFFFFFFFFFF,
|
||||
|
|
|
|||
Loading…
Reference in New Issue