maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[X86] Make lowering of intrinsics with rounding mode stricter so that only valid rounding modes are lowered. Update tests accordingly 

Many of our tests were not using valid rounding mode immediates. Clang verifies this in the frontend when it creates the intrinsics from builtins, but the backend would still lower invalid immediates.

With this change we will now leave them as intrinsics if the immediate is invalid. This will cause an isel selection failure.

llvm-svn: 355789
This commit is contained in:
Craig Topper 2019-03-10 17:20:45 +00:00
parent 0dc8c52d4e
commit 93e15dfacc
10 changed files with 336 additions and 300 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
llvm/lib/Target/X86/MCTargetDesc/X86BaseInfo.h
View File

@ -48,7 +48,8 @@ namespace X86 {
TO_NEG_INF = 1,
TO_POS_INF = 2,
TO_ZERO = 3,
CUR_DIRECTION = 4
CUR_DIRECTION = 4,
NO_EXC = 8
};
/// The constants to describe instr prefixes if there are

97
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -21876,11 +21876,31 @@ SDValue X86TargetLowering::LowerINTRINSIC_WO_CHAIN(SDValue Op,
SelectionDAG &DAG) const {
// Helper to detect if the operand is CUR_DIRECTION rounding mode.
auto isRoundModeCurDirection = [](SDValue Rnd) {
if (!isa<ConstantSDNode>(Rnd))
return false;
if (auto *C = dyn_cast<ConstantSDNode>(Rnd))
return C->getZExtValue() == X86::STATIC_ROUNDING::CUR_DIRECTION;
unsigned Round = cast<ConstantSDNode>(Rnd)->getZExtValue();
return Round == X86::STATIC_ROUNDING::CUR_DIRECTION;
return false;
};
auto isRoundModeSAE = [](SDValue Rnd) {
if (auto *C = dyn_cast<ConstantSDNode>(Rnd))
return C->getZExtValue() == X86::STATIC_ROUNDING::NO_EXC;
return false;
};
auto isRoundModeSAEToX = [](SDValue Rnd) {
if (auto *C = dyn_cast<ConstantSDNode>(Rnd)) {
unsigned Round = C->getZExtValue();
if (Round & X86::STATIC_ROUNDING::NO_EXC) {
// Clear the NO_EXC bit and check remaining bits.
Round ^= X86::STATIC_ROUNDING::NO_EXC;
return Round == X86::STATIC_ROUNDING::TO_NEAREST_INT ||
Round == X86::STATIC_ROUNDING::TO_NEG_INF ||
Round == X86::STATIC_ROUNDING::TO_POS_INF ||
Round == X86::STATIC_ROUNDING::TO_ZERO;
}
}
return false;
};
SDLoc dl(Op);
@ -21896,10 +21916,11 @@ SDValue X86TargetLowering::LowerINTRINSIC_WO_CHAIN(SDValue Op,
unsigned IntrWithRoundingModeOpcode = IntrData->Opc1;
if (IntrWithRoundingModeOpcode != 0) {
SDValue Rnd = Op.getOperand(2);
if (!isRoundModeCurDirection(Rnd)) {
if (isRoundModeSAEToX(Rnd))
return DAG.getNode(IntrWithRoundingModeOpcode, dl, Op.getValueType(),
Op.getOperand(1), Rnd);
}
if (!isRoundModeCurDirection(Rnd))
return SDValue();
}
return DAG.getNode(IntrData->Opc0, dl, Op.getValueType(), Op.getOperand(1));
}
@ -21912,10 +21933,11 @@ SDValue X86TargetLowering::LowerINTRINSIC_WO_CHAIN(SDValue Op,
unsigned IntrWithRoundingModeOpcode = IntrData->Opc1;
if (IntrWithRoundingModeOpcode != 0) {
SDValue Rnd = Op.getOperand(3);
if (!isRoundModeCurDirection(Rnd)) {
if (isRoundModeSAEToX(Rnd))
return DAG.getNode(IntrWithRoundingModeOpcode, dl, Op.getValueType(),
Op.getOperand(1), Src2, Rnd);
}
if (!isRoundModeCurDirection(Rnd))
return SDValue();
}
return DAG.getNode(IntrData->Opc0, dl, Op.getValueType(),
@ -21936,11 +21958,12 @@ SDValue X86TargetLowering::LowerINTRINSIC_WO_CHAIN(SDValue Op,
unsigned IntrWithRoundingModeOpcode = IntrData->Opc1;
if (IntrWithRoundingModeOpcode != 0) {
SDValue Rnd = Op.getOperand(4);
if (!isRoundModeCurDirection(Rnd)) {
if (isRoundModeSAEToX(Rnd))
return DAG.getNode(IntrWithRoundingModeOpcode,
dl, Op.getValueType(),
Src1, Src2, Src3, Rnd);
}
if (!isRoundModeCurDirection(Rnd))
return SDValue();
}
return DAG.getNode(IntrData->Opc0, dl, Op.getValueType(),
@ -21977,12 +22000,13 @@ SDValue X86TargetLowering::LowerINTRINSIC_WO_CHAIN(SDValue Op,
unsigned IntrWithRoundingModeOpcode = IntrData->Opc1;
if (IntrWithRoundingModeOpcode != 0) {
SDValue Rnd = Op.getOperand(4);
if (!isRoundModeCurDirection(Rnd)) {
if (isRoundModeSAEToX(Rnd))
return getVectorMaskingNode(DAG.getNode(IntrWithRoundingModeOpcode,
dl, Op.getValueType(),
Src, Rnd),
Mask, PassThru, Subtarget, DAG);
}
if (!isRoundModeCurDirection(Rnd))
return SDValue();
}
return getVectorMaskingNode(DAG.getNode(IntrData->Opc0, dl, VT, Src),
Mask, PassThru, Subtarget, DAG);
@ -22000,10 +22024,12 @@ SDValue X86TargetLowering::LowerINTRINSIC_WO_CHAIN(SDValue Op,
if (Op.getNumOperands() == (5U + HasRounding)) {
if (HasRounding) {
SDValue Rnd = Op.getOperand(5);
if (!isRoundModeCurDirection(Rnd))
if (isRoundModeSAEToX(Rnd))
return getScalarMaskingNode(DAG.getNode(IntrWithRoundingModeOpcode,
dl, VT, Src1, Src2, Rnd),
Mask, passThru, Subtarget, DAG);
if (!isRoundModeCurDirection(Rnd))
return SDValue();
}
return getScalarMaskingNode(DAG.getNode(IntrData->Opc0, dl, VT, Src1,
Src2),
@ -22015,11 +22041,13 @@ SDValue X86TargetLowering::LowerINTRINSIC_WO_CHAIN(SDValue Op,
SDValue RoundingMode = Op.getOperand(5);
if (HasRounding) {
SDValue Sae = Op.getOperand(6);
if (!isRoundModeCurDirection(Sae))
if (isRoundModeSAE(Sae))
return getScalarMaskingNode(DAG.getNode(IntrWithRoundingModeOpcode,
dl, VT, Src1, Src2,
RoundingMode, Sae),
Mask, passThru, Subtarget, DAG);
if (!isRoundModeCurDirection(Sae))
return SDValue();
}
return getScalarMaskingNode(DAG.getNode(IntrData->Opc0, dl, VT, Src1,
Src2, RoundingMode),
@ -22048,12 +22076,13 @@ SDValue X86TargetLowering::LowerINTRINSIC_WO_CHAIN(SDValue Op,
unsigned IntrWithRoundingModeOpcode = IntrData->Opc1;
if (IntrWithRoundingModeOpcode != 0) {
SDValue Rnd = Op.getOperand(5);
if (!isRoundModeCurDirection(Rnd)) {
if (isRoundModeSAEToX(Rnd))
return getVectorMaskingNode(DAG.getNode(IntrWithRoundingModeOpcode,
dl, Op.getValueType(),
Src1, Src2, Rnd),
Mask, PassThru, Subtarget, DAG);
}
if (!isRoundModeCurDirection(Rnd))
return SDValue();
}
// TODO: Intrinsics should have fast-math-flags to propagate.
return getVectorMaskingNode(DAG.getNode(IntrData->Opc0, dl, VT,Src1,Src2),
@ -22087,10 +22116,12 @@ SDValue X86TargetLowering::LowerINTRINSIC_WO_CHAIN(SDValue Op,
unsigned IntrWithRoundingModeOpcode = IntrData->Opc1;
if (IntrWithRoundingModeOpcode != 0) {
SDValue Rnd = Op.getOperand(6);
if (!isRoundModeCurDirection(Rnd))
if (isRoundModeSAEToX(Rnd))
return getScalarMaskingNode(DAG.getNode(IntrWithRoundingModeOpcode,
dl, VT, Src1, Src2, Src3, Rnd),
Mask, PassThru, Subtarget, DAG);
if (!isRoundModeCurDirection(Rnd))
return SDValue();
}
return getScalarMaskingNode(DAG.getNode(IntrData->Opc0, dl, VT, Src1,
Src2, Src3),
@ -22109,12 +22140,13 @@ SDValue X86TargetLowering::LowerINTRINSIC_WO_CHAIN(SDValue Op,
unsigned IntrWithRoundingModeOpcode = IntrData->Opc1;
if (IntrWithRoundingModeOpcode != 0) {
SDValue Rnd = Op.getOperand(6);
if (!isRoundModeCurDirection(Rnd)) {
if (isRoundModeSAEToX(Rnd))
return getVectorMaskingNode(DAG.getNode(IntrWithRoundingModeOpcode,
dl, Op.getValueType(),
Src1, Src2, Src3, Rnd),
Mask, PassThru, Subtarget, DAG);
}
if (!isRoundModeCurDirection(Rnd))
return SDValue();
}
return getVectorMaskingNode(DAG.getNode(IntrData->Opc0, dl, VT,
Src1, Src2, Src3),
@ -22167,17 +22199,16 @@ SDValue X86TargetLowering::LowerINTRINSIC_WO_CHAIN(SDValue Op,
// First, we check if the intrinsic may have non-default rounding mode,
// (IntrData->Opc1 != 0), then we check the rounding mode operand.
if (IntrData->Opc1 != 0) {
SDValue Rnd = Op.getOperand(4);
if (!isRoundModeCurDirection(Rnd))
Cmp = DAG.getNode(IntrData->Opc1, dl, MaskVT, Op.getOperand(1),
Op.getOperand(2), CC, Rnd);
SDValue Sae = Op.getOperand(4);
if (isRoundModeSAE(Sae))
return DAG.getNode(IntrData->Opc1, dl, MaskVT, Op.getOperand(1),
Op.getOperand(2), CC, Sae);
if (!isRoundModeCurDirection(Sae))
return SDValue();
}
//default rounding mode
if (!Cmp.getNode())
Cmp = DAG.getNode(IntrData->Opc0, dl, MaskVT, Op.getOperand(1),
return DAG.getNode(IntrData->Opc0, dl, MaskVT, Op.getOperand(1),
Op.getOperand(2), CC);
return Cmp;
}
case CMP_MASK_SCALAR_CC: {
SDValue Src1 = Op.getOperand(1);
@ -22187,9 +22218,11 @@ SDValue X86TargetLowering::LowerINTRINSIC_WO_CHAIN(SDValue Op,
SDValue Cmp;
if (IntrData->Opc1 != 0) {
SDValue Rnd = Op.getOperand(5);
if (!isRoundModeCurDirection(Rnd))
Cmp = DAG.getNode(IntrData->Opc1, dl, MVT::v1i1, Src1, Src2, CC, Rnd);
SDValue Sae = Op.getOperand(5);
if (isRoundModeSAE(Sae))
Cmp = DAG.getNode(IntrData->Opc1, dl, MVT::v1i1, Src1, Src2, CC, Sae);
else if (!isRoundModeCurDirection(Sae))
return SDValue();
}
//default rounding mode
if (!Cmp.getNode())
@ -22252,9 +22285,11 @@ SDValue X86TargetLowering::LowerINTRINSIC_WO_CHAIN(SDValue Op,
if (isRoundModeCurDirection(Sae))
FCmp = DAG.getNode(X86ISD::FSETCCM, dl, MVT::v1i1, LHS, RHS,
DAG.getConstant(CondVal, dl, MVT::i8));
else
else if (isRoundModeSAE(Sae))
FCmp = DAG.getNode(X86ISD::FSETCCM_RND, dl, MVT::v1i1, LHS, RHS,
DAG.getConstant(CondVal, dl, MVT::i8), Sae);
else
return SDValue();
// Need to fill with zeros to ensure the bitcast will produce zeroes
// for the upper bits. An EXTRACT_ELEMENT here wouldn't guarantee that.
SDValue Ins = DAG.getNode(ISD::INSERT_SUBVECTOR, dl, MVT::v16i1,

48
llvm/test/CodeGen/X86/avx512-fma-intrinsics-upgrade.ll
View File

@ -227,7 +227,7 @@ define <16 x float> @test_mask_round_vfmadd512_ps_rrb_rne(<16 x float> %a0, <16
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vfmadd132ps {rn-sae}, %zmm1, %zmm2, %zmm0 {%k1}
; CHECK-NEXT: retq
%res = call <16 x float> @llvm.x86.avx512.mask.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i16 %mask, i32 0) nounwind
%res = call <16 x float> @llvm.x86.avx512.mask.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i16 %mask, i32 8) nounwind
ret <16 x float> %res
}
@ -237,7 +237,7 @@ define <16 x float> @test_mask_round_vfmadd512_ps_rrb_rtn(<16 x float> %a0, <16
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vfmadd132ps {rd-sae}, %zmm1, %zmm2, %zmm0 {%k1}
; CHECK-NEXT: retq
%res = call <16 x float> @llvm.x86.avx512.mask.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i16 %mask, i32 1) nounwind
%res = call <16 x float> @llvm.x86.avx512.mask.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i16 %mask, i32 9) nounwind
ret <16 x float> %res
}
@ -247,7 +247,7 @@ define <16 x float> @test_mask_round_vfmadd512_ps_rrb_rtp(<16 x float> %a0, <16
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vfmadd132ps {ru-sae}, %zmm1, %zmm2, %zmm0 {%k1}
; CHECK-NEXT: retq
%res = call <16 x float> @llvm.x86.avx512.mask.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i16 %mask, i32 2) nounwind
%res = call <16 x float> @llvm.x86.avx512.mask.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i16 %mask, i32 10) nounwind
ret <16 x float> %res
}
@ -257,7 +257,7 @@ define <16 x float> @test_mask_round_vfmadd512_ps_rrb_rtz(<16 x float> %a0, <16
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vfmadd132ps {rz-sae}, %zmm1, %zmm2, %zmm0 {%k1}
; CHECK-NEXT: retq
%res = call <16 x float> @llvm.x86.avx512.mask.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i16 %mask, i32 3) nounwind
%res = call <16 x float> @llvm.x86.avx512.mask.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i16 %mask, i32 11) nounwind
ret <16 x float> %res
}
@ -276,7 +276,7 @@ define <16 x float> @test_mask_round_vfmadd512_ps_rrbz_rne(<16 x float> %a0, <16
; CHECK: ## %bb.0:
; CHECK-NEXT: vfmadd213ps {rn-sae}, %zmm2, %zmm1, %zmm0
; CHECK-NEXT: retq
%res = call <16 x float> @llvm.x86.avx512.mask.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i16 -1, i32 0) nounwind
%res = call <16 x float> @llvm.x86.avx512.mask.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i16 -1, i32 8) nounwind
ret <16 x float> %res
}
@ -285,7 +285,7 @@ define <16 x float> @test_mask_round_vfmadd512_ps_rrbz_rtn(<16 x float> %a0, <16
; CHECK: ## %bb.0:
; CHECK-NEXT: vfmadd213ps {rd-sae}, %zmm2, %zmm1, %zmm0
; CHECK-NEXT: retq
%res = call <16 x float> @llvm.x86.avx512.mask.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i16 -1, i32 1) nounwind
%res = call <16 x float> @llvm.x86.avx512.mask.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i16 -1, i32 9) nounwind
ret <16 x float> %res
}
@ -294,7 +294,7 @@ define <16 x float> @test_mask_round_vfmadd512_ps_rrbz_rtp(<16 x float> %a0, <16
; CHECK: ## %bb.0:
; CHECK-NEXT: vfmadd213ps {ru-sae}, %zmm2, %zmm1, %zmm0
; CHECK-NEXT: retq
%res = call <16 x float> @llvm.x86.avx512.mask.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i16 -1, i32 2) nounwind
%res = call <16 x float> @llvm.x86.avx512.mask.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i16 -1, i32 10) nounwind
ret <16 x float> %res
}
@ -303,7 +303,7 @@ define <16 x float> @test_mask_round_vfmadd512_ps_rrbz_rtz(<16 x float> %a0, <16
; CHECK: ## %bb.0:
; CHECK-NEXT: vfmadd213ps {rz-sae}, %zmm2, %zmm1, %zmm0
; CHECK-NEXT: retq
%res = call <16 x float> @llvm.x86.avx512.mask.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i16 -1, i32 3) nounwind
%res = call <16 x float> @llvm.x86.avx512.mask.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i16 -1, i32 11) nounwind
ret <16 x float> %res
}
@ -348,7 +348,7 @@ define <8 x double> @test_mask_round_vfmadd512_pd_rrb_rne(<8 x double> %a0, <8 x
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vfmadd132pd {rn-sae}, %zmm1, %zmm2, %zmm0 {%k1}
; CHECK-NEXT: retq
%res = call <8 x double> @llvm.x86.avx512.mask.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask, i32 0) nounwind
%res = call <8 x double> @llvm.x86.avx512.mask.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask, i32 8) nounwind
ret <8 x double> %res
}
@ -358,7 +358,7 @@ define <8 x double> @test_mask_round_vfmadd512_pd_rrb_rtn(<8 x double> %a0, <8 x
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vfmadd132pd {rd-sae}, %zmm1, %zmm2, %zmm0 {%k1}
; CHECK-NEXT: retq
%res = call <8 x double> @llvm.x86.avx512.mask.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask, i32 1) nounwind
%res = call <8 x double> @llvm.x86.avx512.mask.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask, i32 9) nounwind
ret <8 x double> %res
}
@ -368,7 +368,7 @@ define <8 x double> @test_mask_round_vfmadd512_pd_rrb_rtp(<8 x double> %a0, <8 x
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vfmadd132pd {ru-sae}, %zmm1, %zmm2, %zmm0 {%k1}
; CHECK-NEXT: retq
%res = call <8 x double> @llvm.x86.avx512.mask.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask, i32 2) nounwind
%res = call <8 x double> @llvm.x86.avx512.mask.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask, i32 10) nounwind
ret <8 x double> %res
}
@ -378,7 +378,7 @@ define <8 x double> @test_mask_round_vfmadd512_pd_rrb_rtz(<8 x double> %a0, <8 x
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vfmadd132pd {rz-sae}, %zmm1, %zmm2, %zmm0 {%k1}
; CHECK-NEXT: retq
%res = call <8 x double> @llvm.x86.avx512.mask.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask, i32 3) nounwind
%res = call <8 x double> @llvm.x86.avx512.mask.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask, i32 11) nounwind
ret <8 x double> %res
}
@ -397,7 +397,7 @@ define <8 x double> @test_mask_round_vfmadd512_pd_rrbz_rne(<8 x double> %a0, <8
; CHECK: ## %bb.0:
; CHECK-NEXT: vfmadd213pd {rn-sae}, %zmm2, %zmm1, %zmm0
; CHECK-NEXT: retq
%res = call <8 x double> @llvm.x86.avx512.mask.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 -1, i32 0) nounwind
%res = call <8 x double> @llvm.x86.avx512.mask.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 -1, i32 8) nounwind
ret <8 x double> %res
}
@ -406,7 +406,7 @@ define <8 x double> @test_mask_round_vfmadd512_pd_rrbz_rtn(<8 x double> %a0, <8
; CHECK: ## %bb.0:
; CHECK-NEXT: vfmadd213pd {rd-sae}, %zmm2, %zmm1, %zmm0
; CHECK-NEXT: retq
%res = call <8 x double> @llvm.x86.avx512.mask.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 -1, i32 1) nounwind
%res = call <8 x double> @llvm.x86.avx512.mask.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 -1, i32 9) nounwind
ret <8 x double> %res
}
@ -415,7 +415,7 @@ define <8 x double> @test_mask_round_vfmadd512_pd_rrbz_rtp(<8 x double> %a0, <8
; CHECK: ## %bb.0:
; CHECK-NEXT: vfmadd213pd {ru-sae}, %zmm2, %zmm1, %zmm0
; CHECK-NEXT: retq
%res = call <8 x double> @llvm.x86.avx512.mask.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 -1, i32 2) nounwind
%res = call <8 x double> @llvm.x86.avx512.mask.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 -1, i32 10) nounwind
ret <8 x double> %res
}
@ -424,7 +424,7 @@ define <8 x double> @test_mask_round_vfmadd512_pd_rrbz_rtz(<8 x double> %a0, <8
; CHECK: ## %bb.0:
; CHECK-NEXT: vfmadd213pd {rz-sae}, %zmm2, %zmm1, %zmm0
; CHECK-NEXT: retq
%res = call <8 x double> @llvm.x86.avx512.mask.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 -1, i32 3) nounwind
%res = call <8 x double> @llvm.x86.avx512.mask.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 -1, i32 11) nounwind
ret <8 x double> %res
}
@ -514,7 +514,7 @@ define <8 x double> @test_mask_round_vfnmsub512_pd_rrb_rne(<8 x double> %a0, <8
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vfnmsub132pd {rn-sae}, %zmm1, %zmm2, %zmm0 {%k1}
; CHECK-NEXT: retq
%res = call <8 x double> @llvm.x86.avx512.mask.vfnmsub.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask, i32 0) nounwind
%res = call <8 x double> @llvm.x86.avx512.mask.vfnmsub.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask, i32 8) nounwind
ret <8 x double> %res
}
@ -524,7 +524,7 @@ define <8 x double> @test_mask_round_vfnmsub512_pd_rrb_rtn(<8 x double> %a0, <8
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vfnmsub132pd {rd-sae}, %zmm1, %zmm2, %zmm0 {%k1}
; CHECK-NEXT: retq
%res = call <8 x double> @llvm.x86.avx512.mask.vfnmsub.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask, i32 1) nounwind
%res = call <8 x double> @llvm.x86.avx512.mask.vfnmsub.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask, i32 9) nounwind
ret <8 x double> %res
}
@ -534,7 +534,7 @@ define <8 x double> @test_mask_round_vfnmsub512_pd_rrb_rtp(<8 x double> %a0, <8
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vfnmsub132pd {ru-sae}, %zmm1, %zmm2, %zmm0 {%k1}
; CHECK-NEXT: retq
%res = call <8 x double> @llvm.x86.avx512.mask.vfnmsub.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask, i32 2) nounwind
%res = call <8 x double> @llvm.x86.avx512.mask.vfnmsub.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask, i32 10) nounwind
ret <8 x double> %res
}
@ -544,7 +544,7 @@ define <8 x double> @test_mask_round_vfnmsub512_pd_rrb_rtz(<8 x double> %a0, <8
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vfnmsub132pd {rz-sae}, %zmm1, %zmm2, %zmm0 {%k1}
; CHECK-NEXT: retq
%res = call <8 x double> @llvm.x86.avx512.mask.vfnmsub.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask, i32 3) nounwind
%res = call <8 x double> @llvm.x86.avx512.mask.vfnmsub.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 %mask, i32 11) nounwind
ret <8 x double> %res
}
@ -563,7 +563,7 @@ define <8 x double> @test_mask_round_vfnmsub512_pd_rrbz_rne(<8 x double> %a0, <8
; CHECK: ## %bb.0:
; CHECK-NEXT: vfnmsub213pd {rn-sae}, %zmm2, %zmm1, %zmm0
; CHECK-NEXT: retq
%res = call <8 x double> @llvm.x86.avx512.mask.vfnmsub.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 -1, i32 0) nounwind
%res = call <8 x double> @llvm.x86.avx512.mask.vfnmsub.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 -1, i32 8) nounwind
ret <8 x double> %res
}
@ -572,7 +572,7 @@ define <8 x double> @test_mask_round_vfnmsub512_pd_rrbz_rtn(<8 x double> %a0, <8
; CHECK: ## %bb.0:
; CHECK-NEXT: vfnmsub213pd {rd-sae}, %zmm2, %zmm1, %zmm0
; CHECK-NEXT: retq
%res = call <8 x double> @llvm.x86.avx512.mask.vfnmsub.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 -1, i32 1) nounwind
%res = call <8 x double> @llvm.x86.avx512.mask.vfnmsub.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 -1, i32 9) nounwind
ret <8 x double> %res
}
@ -581,7 +581,7 @@ define <8 x double> @test_mask_round_vfnmsub512_pd_rrbz_rtp(<8 x double> %a0, <8
; CHECK: ## %bb.0:
; CHECK-NEXT: vfnmsub213pd {ru-sae}, %zmm2, %zmm1, %zmm0
; CHECK-NEXT: retq
%res = call <8 x double> @llvm.x86.avx512.mask.vfnmsub.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 -1, i32 2) nounwind
%res = call <8 x double> @llvm.x86.avx512.mask.vfnmsub.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 -1, i32 10) nounwind
ret <8 x double> %res
}
@ -590,7 +590,7 @@ define <8 x double> @test_mask_round_vfnmsub512_pd_rrbz_rtz(<8 x double> %a0, <8
; CHECK: ## %bb.0:
; CHECK-NEXT: vfnmsub213pd {rz-sae}, %zmm2, %zmm1, %zmm0
; CHECK-NEXT: retq
%res = call <8 x double> @llvm.x86.avx512.mask.vfnmsub.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 -1, i32 3) nounwind
%res = call <8 x double> @llvm.x86.avx512.mask.vfnmsub.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i8 -1, i32 11) nounwind
ret <8 x double> %res
}

48
llvm/test/CodeGen/X86/avx512-fma-intrinsics.ll
View File

@ -405,7 +405,7 @@ define <16 x float> @test_mask_round_vfmadd512_ps_rrb_rne(<16 x float> %a0, <16
; X64-NEXT: kmovw %edi, %k1 # encoding: [0xc5,0xf8,0x92,0xcf]
; X64-NEXT: vfmadd132ps {rn-sae}, %zmm1, %zmm2, %zmm0 {%k1} # encoding: [0x62,0xf2,0x6d,0x19,0x98,0xc1]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i32 0) nounwind
%res = call <16 x float> @llvm.x86.avx512.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i32 8) nounwind
%bc = bitcast i16 %mask to <16 x i1>
%sel = select <16 x i1> %bc, <16 x float> %res, <16 x float> %a0
ret <16 x float> %sel
@ -423,7 +423,7 @@ define <16 x float> @test_mask_round_vfmadd512_ps_rrb_rtn(<16 x float> %a0, <16
; X64-NEXT: kmovw %edi, %k1 # encoding: [0xc5,0xf8,0x92,0xcf]
; X64-NEXT: vfmadd132ps {rd-sae}, %zmm1, %zmm2, %zmm0 {%k1} # encoding: [0x62,0xf2,0x6d,0x39,0x98,0xc1]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i32 1) nounwind
%res = call <16 x float> @llvm.x86.avx512.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i32 9) nounwind
%bc = bitcast i16 %mask to <16 x i1>
%sel = select <16 x i1> %bc, <16 x float> %res, <16 x float> %a0
ret <16 x float> %sel
@ -441,7 +441,7 @@ define <16 x float> @test_mask_round_vfmadd512_ps_rrb_rtp(<16 x float> %a0, <16
; X64-NEXT: kmovw %edi, %k1 # encoding: [0xc5,0xf8,0x92,0xcf]
; X64-NEXT: vfmadd132ps {ru-sae}, %zmm1, %zmm2, %zmm0 {%k1} # encoding: [0x62,0xf2,0x6d,0x59,0x98,0xc1]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i32 2) nounwind
%res = call <16 x float> @llvm.x86.avx512.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i32 10) nounwind
%bc = bitcast i16 %mask to <16 x i1>
%sel = select <16 x i1> %bc, <16 x float> %res, <16 x float> %a0
ret <16 x float> %sel
@ -459,7 +459,7 @@ define <16 x float> @test_mask_round_vfmadd512_ps_rrb_rtz(<16 x float> %a0, <16
; X64-NEXT: kmovw %edi, %k1 # encoding: [0xc5,0xf8,0x92,0xcf]
; X64-NEXT: vfmadd132ps {rz-sae}, %zmm1, %zmm2, %zmm0 {%k1} # encoding: [0x62,0xf2,0x6d,0x79,0x98,0xc1]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i32 3) nounwind
%res = call <16 x float> @llvm.x86.avx512.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i32 11) nounwind
%bc = bitcast i16 %mask to <16 x i1>
%sel = select <16 x i1> %bc, <16 x float> %res, <16 x float> %a0
ret <16 x float> %sel
@ -490,7 +490,7 @@ define <16 x float> @test_mask_round_vfmadd512_ps_rrbz_rne(<16 x float> %a0, <16
; CHECK: # %bb.0:
; CHECK-NEXT: vfmadd213ps {rn-sae}, %zmm2, %zmm1, %zmm0 # encoding: [0x62,0xf2,0x75,0x18,0xa8,0xc2]
; CHECK-NEXT: ret{{[l|q]}} # encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i32 0) nounwind
%res = call <16 x float> @llvm.x86.avx512.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i32 8) nounwind
ret <16 x float> %res
}
@ -499,7 +499,7 @@ define <16 x float> @test_mask_round_vfmadd512_ps_rrbz_rtn(<16 x float> %a0, <16
; CHECK: # %bb.0:
; CHECK-NEXT: vfmadd213ps {rd-sae}, %zmm2, %zmm1, %zmm0 # encoding: [0x62,0xf2,0x75,0x38,0xa8,0xc2]
; CHECK-NEXT: ret{{[l|q]}} # encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i32 1) nounwind
%res = call <16 x float> @llvm.x86.avx512.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i32 9) nounwind
ret <16 x float> %res
}
@ -508,7 +508,7 @@ define <16 x float> @test_mask_round_vfmadd512_ps_rrbz_rtp(<16 x float> %a0, <16
; CHECK: # %bb.0:
; CHECK-NEXT: vfmadd213ps {ru-sae}, %zmm2, %zmm1, %zmm0 # encoding: [0x62,0xf2,0x75,0x58,0xa8,0xc2]
; CHECK-NEXT: ret{{[l|q]}} # encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i32 2) nounwind
%res = call <16 x float> @llvm.x86.avx512.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i32 10) nounwind
ret <16 x float> %res
}
@ -517,7 +517,7 @@ define <16 x float> @test_mask_round_vfmadd512_ps_rrbz_rtz(<16 x float> %a0, <16
; CHECK: # %bb.0:
; CHECK-NEXT: vfmadd213ps {rz-sae}, %zmm2, %zmm1, %zmm0 # encoding: [0x62,0xf2,0x75,0x78,0xa8,0xc2]
; CHECK-NEXT: ret{{[l|q]}} # encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i32 3) nounwind
%res = call <16 x float> @llvm.x86.avx512.vfmadd.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %a2, i32 11) nounwind
ret <16 x float> %res
}
@ -591,7 +591,7 @@ define <8 x double> @test_mask_round_vfmadd512_pd_rrb_rne(<8 x double> %a0, <8 x
; X64-NEXT: kmovw %edi, %k1 # encoding: [0xc5,0xf8,0x92,0xcf]
; X64-NEXT: vfmadd132pd {rn-sae}, %zmm1, %zmm2, %zmm0 {%k1} # encoding: [0x62,0xf2,0xed,0x19,0x98,0xc1]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <8 x double> @llvm.x86.avx512.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i32 0) nounwind
%res = call <8 x double> @llvm.x86.avx512.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i32 8) nounwind
%bc = bitcast i8 %mask to <8 x i1>
%sel = select <8 x i1> %bc, <8 x double> %res, <8 x double> %a0
ret <8 x double> %sel
@ -610,7 +610,7 @@ define <8 x double> @test_mask_round_vfmadd512_pd_rrb_rtn(<8 x double> %a0, <8 x
; X64-NEXT: kmovw %edi, %k1 # encoding: [0xc5,0xf8,0x92,0xcf]
; X64-NEXT: vfmadd132pd {rd-sae}, %zmm1, %zmm2, %zmm0 {%k1} # encoding: [0x62,0xf2,0xed,0x39,0x98,0xc1]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <8 x double> @llvm.x86.avx512.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i32 1) nounwind
%res = call <8 x double> @llvm.x86.avx512.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i32 9) nounwind
%bc = bitcast i8 %mask to <8 x i1>
%sel = select <8 x i1> %bc, <8 x double> %res, <8 x double> %a0
ret <8 x double> %sel
@ -629,7 +629,7 @@ define <8 x double> @test_mask_round_vfmadd512_pd_rrb_rtp(<8 x double> %a0, <8 x
; X64-NEXT: kmovw %edi, %k1 # encoding: [0xc5,0xf8,0x92,0xcf]
; X64-NEXT: vfmadd132pd {ru-sae}, %zmm1, %zmm2, %zmm0 {%k1} # encoding: [0x62,0xf2,0xed,0x59,0x98,0xc1]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <8 x double> @llvm.x86.avx512.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i32 2) nounwind
%res = call <8 x double> @llvm.x86.avx512.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i32 10) nounwind
%bc = bitcast i8 %mask to <8 x i1>
%sel = select <8 x i1> %bc, <8 x double> %res, <8 x double> %a0
ret <8 x double> %sel
@ -648,7 +648,7 @@ define <8 x double> @test_mask_round_vfmadd512_pd_rrb_rtz(<8 x double> %a0, <8 x
; X64-NEXT: kmovw %edi, %k1 # encoding: [0xc5,0xf8,0x92,0xcf]
; X64-NEXT: vfmadd132pd {rz-sae}, %zmm1, %zmm2, %zmm0 {%k1} # encoding: [0x62,0xf2,0xed,0x79,0x98,0xc1]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <8 x double> @llvm.x86.avx512.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i32 3) nounwind
%res = call <8 x double> @llvm.x86.avx512.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i32 11) nounwind
%bc = bitcast i8 %mask to <8 x i1>
%sel = select <8 x i1> %bc, <8 x double> %res, <8 x double> %a0
ret <8 x double> %sel
@ -680,7 +680,7 @@ define <8 x double> @test_mask_round_vfmadd512_pd_rrbz_rne(<8 x double> %a0, <8
; CHECK: # %bb.0:
; CHECK-NEXT: vfmadd213pd {rn-sae}, %zmm2, %zmm1, %zmm0 # encoding: [0x62,0xf2,0xf5,0x18,0xa8,0xc2]
; CHECK-NEXT: ret{{[l|q]}} # encoding: [0xc3]
%res = call <8 x double> @llvm.x86.avx512.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i32 0) nounwind
%res = call <8 x double> @llvm.x86.avx512.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i32 8) nounwind
ret <8 x double> %res
}
@ -689,7 +689,7 @@ define <8 x double> @test_mask_round_vfmadd512_pd_rrbz_rtn(<8 x double> %a0, <8
; CHECK: # %bb.0:
; CHECK-NEXT: vfmadd213pd {rd-sae}, %zmm2, %zmm1, %zmm0 # encoding: [0x62,0xf2,0xf5,0x38,0xa8,0xc2]
; CHECK-NEXT: ret{{[l|q]}} # encoding: [0xc3]
%res = call <8 x double> @llvm.x86.avx512.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i32 1) nounwind
%res = call <8 x double> @llvm.x86.avx512.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i32 9) nounwind
ret <8 x double> %res
}
@ -698,7 +698,7 @@ define <8 x double> @test_mask_round_vfmadd512_pd_rrbz_rtp(<8 x double> %a0, <8
; CHECK: # %bb.0:
; CHECK-NEXT: vfmadd213pd {ru-sae}, %zmm2, %zmm1, %zmm0 # encoding: [0x62,0xf2,0xf5,0x58,0xa8,0xc2]
; CHECK-NEXT: ret{{[l|q]}} # encoding: [0xc3]
%res = call <8 x double> @llvm.x86.avx512.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i32 2) nounwind
%res = call <8 x double> @llvm.x86.avx512.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i32 10) nounwind
ret <8 x double> %res
}
@ -707,7 +707,7 @@ define <8 x double> @test_mask_round_vfmadd512_pd_rrbz_rtz(<8 x double> %a0, <8
; CHECK: # %bb.0:
; CHECK-NEXT: vfmadd213pd {rz-sae}, %zmm2, %zmm1, %zmm0 # encoding: [0x62,0xf2,0xf5,0x78,0xa8,0xc2]
; CHECK-NEXT: ret{{[l|q]}} # encoding: [0xc3]
%res = call <8 x double> @llvm.x86.avx512.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i32 3) nounwind
%res = call <8 x double> @llvm.x86.avx512.vfmadd.pd.512(<8 x double> %a0, <8 x double> %a1, <8 x double> %a2, i32 11) nounwind
ret <8 x double> %res
}
@ -863,7 +863,7 @@ define <8 x double> @test_mask_round_vfnmsub512_pd_rrb_rne(<8 x double> %a0, <8
; X64-NEXT: retq # encoding: [0xc3]
%1 = fsub <8 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, %a1
%2 = fsub <8 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, %a2
%3 = call <8 x double> @llvm.x86.avx512.vfmadd.pd.512(<8 x double> %a0, <8 x double> %1, <8 x double> %2, i32 0)
%3 = call <8 x double> @llvm.x86.avx512.vfmadd.pd.512(<8 x double> %a0, <8 x double> %1, <8 x double> %2, i32 8)
%4 = bitcast i8 %mask to <8 x i1>
%5 = select <8 x i1> %4, <8 x double> %3, <8 x double> %a0
ret <8 x double> %5
@ -884,7 +884,7 @@ define <8 x double> @test_mask_round_vfnmsub512_pd_rrb_rtn(<8 x double> %a0, <8
; X64-NEXT: retq # encoding: [0xc3]
%1 = fsub <8 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, %a1
%2 = fsub <8 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, %a2
%3 = call <8 x double> @llvm.x86.avx512.vfmadd.pd.512(<8 x double> %a0, <8 x double> %1, <8 x double> %2, i32 1)
%3 = call <8 x double> @llvm.x86.avx512.vfmadd.pd.512(<8 x double> %a0, <8 x double> %1, <8 x double> %2, i32 9)
%4 = bitcast i8 %mask to <8 x i1>
%5 = select <8 x i1> %4, <8 x double> %3, <8 x double> %a0
ret <8 x double> %5
@ -905,7 +905,7 @@ define <8 x double> @test_mask_round_vfnmsub512_pd_rrb_rtp(<8 x double> %a0, <8
; X64-NEXT: retq # encoding: [0xc3]
%1 = fsub <8 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, %a1
%2 = fsub <8 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, %a2
%3 = call <8 x double> @llvm.x86.avx512.vfmadd.pd.512(<8 x double> %a0, <8 x double> %1, <8 x double> %2, i32 2)
%3 = call <8 x double> @llvm.x86.avx512.vfmadd.pd.512(<8 x double> %a0, <8 x double> %1, <8 x double> %2, i32 10)
%4 = bitcast i8 %mask to <8 x i1>
%5 = select <8 x i1> %4, <8 x double> %3, <8 x double> %a0
ret <8 x double> %5
@ -926,7 +926,7 @@ define <8 x double> @test_mask_round_vfnmsub512_pd_rrb_rtz(<8 x double> %a0, <8
; X64-NEXT: retq # encoding: [0xc3]
%1 = fsub <8 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, %a1
%2 = fsub <8 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, %a2
%3 = call <8 x double> @llvm.x86.avx512.vfmadd.pd.512(<8 x double> %a0, <8 x double> %1, <8 x double> %2, i32 3)
%3 = call <8 x double> @llvm.x86.avx512.vfmadd.pd.512(<8 x double> %a0, <8 x double> %1, <8 x double> %2, i32 11)
%4 = bitcast i8 %mask to <8 x i1>
%5 = select <8 x i1> %4, <8 x double> %3, <8 x double> %a0
ret <8 x double> %5
@ -962,7 +962,7 @@ define <8 x double> @test_mask_round_vfnmsub512_pd_rrbz_rne(<8 x double> %a0, <8
; CHECK-NEXT: ret{{[l|q]}} # encoding: [0xc3]
%1 = fsub <8 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, %a1
%2 = fsub <8 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, %a2
%3 = call <8 x double> @llvm.x86.avx512.vfmadd.pd.512(<8 x double> %a0, <8 x double> %1, <8 x double> %2, i32 0)
%3 = call <8 x double> @llvm.x86.avx512.vfmadd.pd.512(<8 x double> %a0, <8 x double> %1, <8 x double> %2, i32 8)
ret <8 x double> %3
}
@ -973,7 +973,7 @@ define <8 x double> @test_mask_round_vfnmsub512_pd_rrbz_rtn(<8 x double> %a0, <8
; CHECK-NEXT: ret{{[l|q]}} # encoding: [0xc3]
%1 = fsub <8 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, %a1
%2 = fsub <8 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, %a2
%3 = call <8 x double> @llvm.x86.avx512.vfmadd.pd.512(<8 x double> %a0, <8 x double> %1, <8 x double> %2, i32 1)
%3 = call <8 x double> @llvm.x86.avx512.vfmadd.pd.512(<8 x double> %a0, <8 x double> %1, <8 x double> %2, i32 9)
ret <8 x double> %3
}
@ -984,7 +984,7 @@ define <8 x double> @test_mask_round_vfnmsub512_pd_rrbz_rtp(<8 x double> %a0, <8
; CHECK-NEXT: ret{{[l|q]}} # encoding: [0xc3]
%1 = fsub <8 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, %a1
%2 = fsub <8 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, %a2
%3 = call <8 x double> @llvm.x86.avx512.vfmadd.pd.512(<8 x double> %a0, <8 x double> %1, <8 x double> %2, i32 2)
%3 = call <8 x double> @llvm.x86.avx512.vfmadd.pd.512(<8 x double> %a0, <8 x double> %1, <8 x double> %2, i32 10)
ret <8 x double> %3
}
@ -995,7 +995,7 @@ define <8 x double> @test_mask_round_vfnmsub512_pd_rrbz_rtz(<8 x double> %a0, <8
; CHECK-NEXT: ret{{[l|q]}} # encoding: [0xc3]
%1 = fsub <8 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, %a1
%2 = fsub <8 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, %a2
%3 = call <8 x double> @llvm.x86.avx512.vfmadd.pd.512(<8 x double> %a0, <8 x double> %1, <8 x double> %2, i32 3)
%3 = call <8 x double> @llvm.x86.avx512.vfmadd.pd.512(<8 x double> %a0, <8 x double> %1, <8 x double> %2, i32 11)
ret <8 x double> %3
}

144
llvm/test/CodeGen/X86/avx512-intrinsics-upgrade.ll
View File

@ -7194,7 +7194,7 @@ define <16 x float> @test_vsubps_rn(<16 x float> %a0, <16 x float> %a1) {
; CHECK-NEXT: vsubps {rn-sae}, %zmm1, %zmm0, %zmm0 ## encoding: [0x62,0xf1,0x7c,0x18,0x5c,0xc1]
; CHECK-NEXT: ret{{[l|q]}} ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.sub.ps.512(<16 x float> %a0, <16 x float> %a1,
<16 x float> zeroinitializer, i16 -1, i32 0)
<16 x float> zeroinitializer, i16 -1, i32 8)
ret <16 x float> %res
}
@ -7204,7 +7204,7 @@ define <16 x float> @test_vsubps_rd(<16 x float> %a0, <16 x float> %a1) {
; CHECK-NEXT: vsubps {rd-sae}, %zmm1, %zmm0, %zmm0 ## encoding: [0x62,0xf1,0x7c,0x38,0x5c,0xc1]
; CHECK-NEXT: ret{{[l|q]}} ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.sub.ps.512(<16 x float> %a0, <16 x float> %a1,
<16 x float> zeroinitializer, i16 -1, i32 1)
<16 x float> zeroinitializer, i16 -1, i32 9)
ret <16 x float> %res
}
@ -7214,7 +7214,7 @@ define <16 x float> @test_vsubps_ru(<16 x float> %a0, <16 x float> %a1) {
; CHECK-NEXT: vsubps {ru-sae}, %zmm1, %zmm0, %zmm0 ## encoding: [0x62,0xf1,0x7c,0x58,0x5c,0xc1]
; CHECK-NEXT: ret{{[l|q]}} ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.sub.ps.512(<16 x float> %a0, <16 x float> %a1,
<16 x float> zeroinitializer, i16 -1, i32 2)
<16 x float> zeroinitializer, i16 -1, i32 10)
ret <16 x float> %res
}
@ -7224,7 +7224,7 @@ define <16 x float> @test_vsubps_rz(<16 x float> %a0, <16 x float> %a1) {
; CHECK-NEXT: vsubps {rz-sae}, %zmm1, %zmm0, %zmm0 ## encoding: [0x62,0xf1,0x7c,0x78,0x5c,0xc1]
; CHECK-NEXT: ret{{[l|q]}} ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.sub.ps.512(<16 x float> %a0, <16 x float> %a1,
<16 x float> zeroinitializer, i16 -1, i32 3)
<16 x float> zeroinitializer, i16 -1, i32 11)
ret <16 x float> %res
}
@ -7234,7 +7234,7 @@ define <16 x float> @test_vmulps_rn(<16 x float> %a0, <16 x float> %a1) {
; CHECK-NEXT: vmulps {rn-sae}, %zmm1, %zmm0, %zmm0 ## encoding: [0x62,0xf1,0x7c,0x18,0x59,0xc1]
; CHECK-NEXT: ret{{[l|q]}} ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.mul.ps.512(<16 x float> %a0, <16 x float> %a1,
<16 x float> zeroinitializer, i16 -1, i32 0)
<16 x float> zeroinitializer, i16 -1, i32 8)
ret <16 x float> %res
}
@ -7244,7 +7244,7 @@ define <16 x float> @test_vmulps_rd(<16 x float> %a0, <16 x float> %a1) {
; CHECK-NEXT: vmulps {rd-sae}, %zmm1, %zmm0, %zmm0 ## encoding: [0x62,0xf1,0x7c,0x38,0x59,0xc1]
; CHECK-NEXT: ret{{[l|q]}} ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.mul.ps.512(<16 x float> %a0, <16 x float> %a1,
<16 x float> zeroinitializer, i16 -1, i32 1)
<16 x float> zeroinitializer, i16 -1, i32 9)
ret <16 x float> %res
}
@ -7254,7 +7254,7 @@ define <16 x float> @test_vmulps_ru(<16 x float> %a0, <16 x float> %a1) {
; CHECK-NEXT: vmulps {ru-sae}, %zmm1, %zmm0, %zmm0 ## encoding: [0x62,0xf1,0x7c,0x58,0x59,0xc1]
; CHECK-NEXT: ret{{[l|q]}} ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.mul.ps.512(<16 x float> %a0, <16 x float> %a1,
<16 x float> zeroinitializer, i16 -1, i32 2)
<16 x float> zeroinitializer, i16 -1, i32 10)
ret <16 x float> %res
}
@ -7264,7 +7264,7 @@ define <16 x float> @test_vmulps_rz(<16 x float> %a0, <16 x float> %a1) {
; CHECK-NEXT: vmulps {rz-sae}, %zmm1, %zmm0, %zmm0 ## encoding: [0x62,0xf1,0x7c,0x78,0x59,0xc1]
; CHECK-NEXT: ret{{[l|q]}} ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.mul.ps.512(<16 x float> %a0, <16 x float> %a1,
<16 x float> zeroinitializer, i16 -1, i32 3)
<16 x float> zeroinitializer, i16 -1, i32 11)
ret <16 x float> %res
}
@ -7282,7 +7282,7 @@ define <16 x float> @test_vmulps_mask_rn(<16 x float> %a0, <16 x float> %a1, i16
; X64-NEXT: vmulps {rn-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7c,0x99,0x59,0xc1]
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.mul.ps.512(<16 x float> %a0, <16 x float> %a1,
<16 x float> zeroinitializer, i16 %mask, i32 0)
<16 x float> zeroinitializer, i16 %mask, i32 8)
ret <16 x float> %res
}
@ -7299,7 +7299,7 @@ define <16 x float> @test_vmulps_mask_rd(<16 x float> %a0, <16 x float> %a1, i16
; X64-NEXT: vmulps {rd-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7c,0xb9,0x59,0xc1]
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.mul.ps.512(<16 x float> %a0, <16 x float> %a1,
<16 x float> zeroinitializer, i16 %mask, i32 1)
<16 x float> zeroinitializer, i16 %mask, i32 9)
ret <16 x float> %res
}
@ -7316,7 +7316,7 @@ define <16 x float> @test_vmulps_mask_ru(<16 x float> %a0, <16 x float> %a1, i16
; X64-NEXT: vmulps {ru-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7c,0xd9,0x59,0xc1]
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.mul.ps.512(<16 x float> %a0, <16 x float> %a1,
<16 x float> zeroinitializer, i16 %mask, i32 2)
<16 x float> zeroinitializer, i16 %mask, i32 10)
ret <16 x float> %res
}
@ -7333,7 +7333,7 @@ define <16 x float> @test_vmulps_mask_rz(<16 x float> %a0, <16 x float> %a1, i16
; X64-NEXT: vmulps {rz-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7c,0xf9,0x59,0xc1]
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.mul.ps.512(<16 x float> %a0, <16 x float> %a1,
<16 x float> zeroinitializer, i16 %mask, i32 3)
<16 x float> zeroinitializer, i16 %mask, i32 11)
ret <16 x float> %res
}
@ -7353,7 +7353,7 @@ define <16 x float> @test_vmulps_mask_passthru_rn(<16 x float> %a0, <16 x float>
; X64-NEXT: vmovaps %zmm2, %zmm0 ## encoding: [0x62,0xf1,0x7c,0x48,0x28,0xc2]
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.mul.ps.512(<16 x float> %a0, <16 x float> %a1,
<16 x float> %passthru, i16 %mask, i32 0)
<16 x float> %passthru, i16 %mask, i32 8)
ret <16 x float> %res
}
@ -7372,7 +7372,7 @@ define <16 x float> @test_vmulps_mask_passthru_rd(<16 x float> %a0, <16 x float>
; X64-NEXT: vmovaps %zmm2, %zmm0 ## encoding: [0x62,0xf1,0x7c,0x48,0x28,0xc2]
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.mul.ps.512(<16 x float> %a0, <16 x float> %a1,
<16 x float> %passthru, i16 %mask, i32 1)
<16 x float> %passthru, i16 %mask, i32 9)
ret <16 x float> %res
}
@ -7391,7 +7391,7 @@ define <16 x float> @test_vmulps_mask_passthru_ru(<16 x float> %a0, <16 x float>
; X64-NEXT: vmovaps %zmm2, %zmm0 ## encoding: [0x62,0xf1,0x7c,0x48,0x28,0xc2]
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.mul.ps.512(<16 x float> %a0, <16 x float> %a1,
<16 x float> %passthru, i16 %mask, i32 2)
<16 x float> %passthru, i16 %mask, i32 10)
ret <16 x float> %res
}
@ -7410,7 +7410,7 @@ define <16 x float> @test_vmulps_mask_passthru_rz(<16 x float> %a0, <16 x float>
; X64-NEXT: vmovaps %zmm2, %zmm0 ## encoding: [0x62,0xf1,0x7c,0x48,0x28,0xc2]
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.mul.ps.512(<16 x float> %a0, <16 x float> %a1,
<16 x float> %passthru, i16 %mask, i32 3)
<16 x float> %passthru, i16 %mask, i32 11)
ret <16 x float> %res
}
@ -7429,7 +7429,7 @@ define <8 x double> @test_vmulpd_mask_rn(<8 x double> %a0, <8 x double> %a1, i8
; X64-NEXT: vmulpd {rn-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z} ## encoding: [0x62,0xf1,0xfd,0x99,0x59,0xc1]
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <8 x double> @llvm.x86.avx512.mask.mul.pd.512(<8 x double> %a0, <8 x double> %a1,
<8 x double> zeroinitializer, i8 %mask, i32 0)
<8 x double> zeroinitializer, i8 %mask, i32 8)
ret <8 x double> %res
}
@ -7447,7 +7447,7 @@ define <8 x double> @test_vmulpd_mask_rd(<8 x double> %a0, <8 x double> %a1, i8
; X64-NEXT: vmulpd {rd-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z} ## encoding: [0x62,0xf1,0xfd,0xb9,0x59,0xc1]
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <8 x double> @llvm.x86.avx512.mask.mul.pd.512(<8 x double> %a0, <8 x double> %a1,
<8 x double> zeroinitializer, i8 %mask, i32 1)
<8 x double> zeroinitializer, i8 %mask, i32 9)
ret <8 x double> %res
}
@ -7465,7 +7465,7 @@ define <8 x double> @test_vmulpd_mask_ru(<8 x double> %a0, <8 x double> %a1, i8
; X64-NEXT: vmulpd {ru-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z} ## encoding: [0x62,0xf1,0xfd,0xd9,0x59,0xc1]
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <8 x double> @llvm.x86.avx512.mask.mul.pd.512(<8 x double> %a0, <8 x double> %a1,
<8 x double> zeroinitializer, i8 %mask, i32 2)
<8 x double> zeroinitializer, i8 %mask, i32 10)
ret <8 x double> %res
}
@ -7483,7 +7483,7 @@ define <8 x double> @test_vmulpd_mask_rz(<8 x double> %a0, <8 x double> %a1, i8
; X64-NEXT: vmulpd {rz-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z} ## encoding: [0x62,0xf1,0xfd,0xf9,0x59,0xc1]
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <8 x double> @llvm.x86.avx512.mask.mul.pd.512(<8 x double> %a0, <8 x double> %a1,
<8 x double> zeroinitializer, i8 %mask, i32 3)
<8 x double> zeroinitializer, i8 %mask, i32 11)
ret <8 x double> %res
}
@ -7499,7 +7499,7 @@ define <16 x float> @test_mm512_maskz_add_round_ps_rn_sae(<16 x float> %a0, <16
; X64-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; X64-NEXT: vaddps {rn-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7c,0x99,0x58,0xc1]
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.add.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 %mask, i32 0)
%res = call <16 x float> @llvm.x86.avx512.mask.add.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 %mask, i32 8)
ret <16 x float> %res
}
define <16 x float> @test_mm512_maskz_add_round_ps_rd_sae(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
@ -7514,7 +7514,7 @@ define <16 x float> @test_mm512_maskz_add_round_ps_rd_sae(<16 x float> %a0, <16
; X64-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; X64-NEXT: vaddps {rd-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7c,0xb9,0x58,0xc1]
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.add.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 %mask, i32 1)
%res = call <16 x float> @llvm.x86.avx512.mask.add.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 %mask, i32 9)
ret <16 x float> %res
}
define <16 x float> @test_mm512_maskz_add_round_ps_ru_sae(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
@ -7529,7 +7529,7 @@ define <16 x float> @test_mm512_maskz_add_round_ps_ru_sae(<16 x float> %a0, <16
; X64-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; X64-NEXT: vaddps {ru-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7c,0xd9,0x58,0xc1]
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.add.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 %mask, i32 2)
%res = call <16 x float> @llvm.x86.avx512.mask.add.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 %mask, i32 10)
ret <16 x float> %res
}
@ -7545,7 +7545,7 @@ define <16 x float> @test_mm512_maskz_add_round_ps_rz_sae(<16 x float> %a0, <16
; X64-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; X64-NEXT: vaddps {rz-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7c,0xf9,0x58,0xc1]
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.add.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 %mask, i32 3)
%res = call <16 x float> @llvm.x86.avx512.mask.add.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 %mask, i32 11)
ret <16 x float> %res
}
@ -7580,7 +7580,7 @@ define <16 x float> @test_mm512_mask_add_round_ps_rn_sae(<16 x float> %a0, <16 x
; X64-NEXT: vaddps {rn-sae}, %zmm1, %zmm0, %zmm2 {%k1} ## encoding: [0x62,0xf1,0x7c,0x19,0x58,0xd1]
; X64-NEXT: vmovaps %zmm2, %zmm0 ## encoding: [0x62,0xf1,0x7c,0x48,0x28,0xc2]
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.add.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 0)
%res = call <16 x float> @llvm.x86.avx512.mask.add.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 8)
ret <16 x float> %res
}
define <16 x float> @test_mm512_mask_add_round_ps_rd_sae(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask) {
@ -7597,7 +7597,7 @@ define <16 x float> @test_mm512_mask_add_round_ps_rd_sae(<16 x float> %a0, <16 x
; X64-NEXT: vaddps {rd-sae}, %zmm1, %zmm0, %zmm2 {%k1} ## encoding: [0x62,0xf1,0x7c,0x39,0x58,0xd1]
; X64-NEXT: vmovaps %zmm2, %zmm0 ## encoding: [0x62,0xf1,0x7c,0x48,0x28,0xc2]
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.add.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 1)
%res = call <16 x float> @llvm.x86.avx512.mask.add.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 9)
ret <16 x float> %res
}
define <16 x float> @test_mm512_mask_add_round_ps_ru_sae(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask) {
@ -7614,7 +7614,7 @@ define <16 x float> @test_mm512_mask_add_round_ps_ru_sae(<16 x float> %a0, <16 x
; X64-NEXT: vaddps {ru-sae}, %zmm1, %zmm0, %zmm2 {%k1} ## encoding: [0x62,0xf1,0x7c,0x59,0x58,0xd1]
; X64-NEXT: vmovaps %zmm2, %zmm0 ## encoding: [0x62,0xf1,0x7c,0x48,0x28,0xc2]
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.add.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 2)
%res = call <16 x float> @llvm.x86.avx512.mask.add.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 10)
ret <16 x float> %res
}
@ -7632,7 +7632,7 @@ define <16 x float> @test_mm512_mask_add_round_ps_rz_sae(<16 x float> %a0, <16 x
; X64-NEXT: vaddps {rz-sae}, %zmm1, %zmm0, %zmm2 {%k1} ## encoding: [0x62,0xf1,0x7c,0x79,0x58,0xd1]
; X64-NEXT: vmovaps %zmm2, %zmm0 ## encoding: [0x62,0xf1,0x7c,0x48,0x28,0xc2]
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.add.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 3)
%res = call <16 x float> @llvm.x86.avx512.mask.add.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 11)
ret <16 x float> %res
}
@ -7661,7 +7661,7 @@ define <16 x float> @test_mm512_add_round_ps_rn_sae(<16 x float> %a0, <16 x floa
; CHECK: ## %bb.0:
; CHECK-NEXT: vaddps {rn-sae}, %zmm1, %zmm0, %zmm0 ## encoding: [0x62,0xf1,0x7c,0x18,0x58,0xc1]
; CHECK-NEXT: ret{{[l|q]}} ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.add.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 0)
%res = call <16 x float> @llvm.x86.avx512.mask.add.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 8)
ret <16 x float> %res
}
define <16 x float> @test_mm512_add_round_ps_rd_sae(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
@ -7669,7 +7669,7 @@ define <16 x float> @test_mm512_add_round_ps_rd_sae(<16 x float> %a0, <16 x floa
; CHECK: ## %bb.0:
; CHECK-NEXT: vaddps {rd-sae}, %zmm1, %zmm0, %zmm0 ## encoding: [0x62,0xf1,0x7c,0x38,0x58,0xc1]
; CHECK-NEXT: ret{{[l|q]}} ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.add.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 1)
%res = call <16 x float> @llvm.x86.avx512.mask.add.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 9)
ret <16 x float> %res
}
define <16 x float> @test_mm512_add_round_ps_ru_sae(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
@ -7677,7 +7677,7 @@ define <16 x float> @test_mm512_add_round_ps_ru_sae(<16 x float> %a0, <16 x floa
; CHECK: ## %bb.0:
; CHECK-NEXT: vaddps {ru-sae}, %zmm1, %zmm0, %zmm0 ## encoding: [0x62,0xf1,0x7c,0x58,0x58,0xc1]
; CHECK-NEXT: ret{{[l|q]}} ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.add.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 2)
%res = call <16 x float> @llvm.x86.avx512.mask.add.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 10)
ret <16 x float> %res
}
@ -7686,7 +7686,7 @@ define <16 x float> @test_mm512_add_round_ps_rz_sae(<16 x float> %a0, <16 x floa
; CHECK: ## %bb.0:
; CHECK-NEXT: vaddps {rz-sae}, %zmm1, %zmm0, %zmm0 ## encoding: [0x62,0xf1,0x7c,0x78,0x58,0xc1]
; CHECK-NEXT: ret{{[l|q]}} ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.add.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 3)
%res = call <16 x float> @llvm.x86.avx512.mask.add.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 11)
ret <16 x float> %res
}
@ -7714,7 +7714,7 @@ define <16 x float> @test_mm512_mask_sub_round_ps_rn_sae(<16 x float> %a0, <16 x
; X64-NEXT: vsubps {rn-sae}, %zmm1, %zmm0, %zmm2 {%k1} ## encoding: [0x62,0xf1,0x7c,0x19,0x5c,0xd1]
; X64-NEXT: vmovaps %zmm2, %zmm0 ## encoding: [0x62,0xf1,0x7c,0x48,0x28,0xc2]
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.sub.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 0)
%res = call <16 x float> @llvm.x86.avx512.mask.sub.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 8)
ret <16 x float> %res
}
define <16 x float> @test_mm512_mask_sub_round_ps_rd_sae(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask) {
@ -7731,7 +7731,7 @@ define <16 x float> @test_mm512_mask_sub_round_ps_rd_sae(<16 x float> %a0, <16 x
; X64-NEXT: vsubps {rd-sae}, %zmm1, %zmm0, %zmm2 {%k1} ## encoding: [0x62,0xf1,0x7c,0x39,0x5c,0xd1]
; X64-NEXT: vmovaps %zmm2, %zmm0 ## encoding: [0x62,0xf1,0x7c,0x48,0x28,0xc2]
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.sub.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 1)
%res = call <16 x float> @llvm.x86.avx512.mask.sub.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 9)
ret <16 x float> %res
}
define <16 x float> @test_mm512_mask_sub_round_ps_ru_sae(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask) {
@ -7748,7 +7748,7 @@ define <16 x float> @test_mm512_mask_sub_round_ps_ru_sae(<16 x float> %a0, <16 x
; X64-NEXT: vsubps {ru-sae}, %zmm1, %zmm0, %zmm2 {%k1} ## encoding: [0x62,0xf1,0x7c,0x59,0x5c,0xd1]
; X64-NEXT: vmovaps %zmm2, %zmm0 ## encoding: [0x62,0xf1,0x7c,0x48,0x28,0xc2]
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.sub.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 2)
%res = call <16 x float> @llvm.x86.avx512.mask.sub.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 10)
ret <16 x float> %res
}
@ -7766,7 +7766,7 @@ define <16 x float> @test_mm512_mask_sub_round_ps_rz_sae(<16 x float> %a0, <16 x
; X64-NEXT: vsubps {rz-sae}, %zmm1, %zmm0, %zmm2 {%k1} ## encoding: [0x62,0xf1,0x7c,0x79,0x5c,0xd1]
; X64-NEXT: vmovaps %zmm2, %zmm0 ## encoding: [0x62,0xf1,0x7c,0x48,0x28,0xc2]
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.sub.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 3)
%res = call <16 x float> @llvm.x86.avx512.mask.sub.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 11)
ret <16 x float> %res
}
@ -7794,7 +7794,7 @@ define <16 x float> @test_mm512_sub_round_ps_rn_sae(<16 x float> %a0, <16 x floa
; CHECK: ## %bb.0:
; CHECK-NEXT: vsubps {rn-sae}, %zmm1, %zmm0, %zmm0 ## encoding: [0x62,0xf1,0x7c,0x18,0x5c,0xc1]
; CHECK-NEXT: ret{{[l|q]}} ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.sub.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 0)
%res = call <16 x float> @llvm.x86.avx512.mask.sub.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 8)
ret <16 x float> %res
}
define <16 x float> @test_mm512_sub_round_ps_rd_sae(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
@ -7802,7 +7802,7 @@ define <16 x float> @test_mm512_sub_round_ps_rd_sae(<16 x float> %a0, <16 x floa
; CHECK: ## %bb.0:
; CHECK-NEXT: vsubps {rd-sae}, %zmm1, %zmm0, %zmm0 ## encoding: [0x62,0xf1,0x7c,0x38,0x5c,0xc1]
; CHECK-NEXT: ret{{[l|q]}} ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.sub.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 1)
%res = call <16 x float> @llvm.x86.avx512.mask.sub.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 9)
ret <16 x float> %res
}
define <16 x float> @test_mm512_sub_round_ps_ru_sae(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
@ -7810,7 +7810,7 @@ define <16 x float> @test_mm512_sub_round_ps_ru_sae(<16 x float> %a0, <16 x floa
; CHECK: ## %bb.0:
; CHECK-NEXT: vsubps {ru-sae}, %zmm1, %zmm0, %zmm0 ## encoding: [0x62,0xf1,0x7c,0x58,0x5c,0xc1]
; CHECK-NEXT: ret{{[l|q]}} ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.sub.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 2)
%res = call <16 x float> @llvm.x86.avx512.mask.sub.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 10)
ret <16 x float> %res
}
@ -7819,7 +7819,7 @@ define <16 x float> @test_mm512_sub_round_ps_rz_sae(<16 x float> %a0, <16 x floa
; CHECK: ## %bb.0:
; CHECK-NEXT: vsubps {rz-sae}, %zmm1, %zmm0, %zmm0 ## encoding: [0x62,0xf1,0x7c,0x78,0x5c,0xc1]
; CHECK-NEXT: ret{{[l|q]}} ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.sub.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 3)
%res = call <16 x float> @llvm.x86.avx512.mask.sub.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 11)
ret <16 x float> %res
}
@ -7844,7 +7844,7 @@ define <16 x float> @test_mm512_maskz_div_round_ps_rn_sae(<16 x float> %a0, <16
; X64-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; X64-NEXT: vdivps {rn-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7c,0x99,0x5e,0xc1]
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.div.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 %mask, i32 0)
%res = call <16 x float> @llvm.x86.avx512.mask.div.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 %mask, i32 8)
ret <16 x float> %res
}
define <16 x float> @test_mm512_maskz_div_round_ps_rd_sae(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
@ -7859,7 +7859,7 @@ define <16 x float> @test_mm512_maskz_div_round_ps_rd_sae(<16 x float> %a0, <16
; X64-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; X64-NEXT: vdivps {rd-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7c,0xb9,0x5e,0xc1]
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.div.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 %mask, i32 1)
%res = call <16 x float> @llvm.x86.avx512.mask.div.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 %mask, i32 9)
ret <16 x float> %res
}
define <16 x float> @test_mm512_maskz_div_round_ps_ru_sae(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
@ -7874,7 +7874,7 @@ define <16 x float> @test_mm512_maskz_div_round_ps_ru_sae(<16 x float> %a0, <16
; X64-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; X64-NEXT: vdivps {ru-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7c,0xd9,0x5e,0xc1]
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.div.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 %mask, i32 2)
%res = call <16 x float> @llvm.x86.avx512.mask.div.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 %mask, i32 10)
ret <16 x float> %res
}
@ -7890,7 +7890,7 @@ define <16 x float> @test_mm512_maskz_div_round_ps_rz_sae(<16 x float> %a0, <16
; X64-NEXT: kmovw %edi, %k1 ## encoding: [0xc5,0xf8,0x92,0xcf]
; X64-NEXT: vdivps {rz-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z} ## encoding: [0x62,0xf1,0x7c,0xf9,0x5e,0xc1]
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.div.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 %mask, i32 3)
%res = call <16 x float> @llvm.x86.avx512.mask.div.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 %mask, i32 11)
ret <16 x float> %res
}
@ -7925,7 +7925,7 @@ define <16 x float> @test_mm512_mask_div_round_ps_rn_sae(<16 x float> %a0, <16 x
; X64-NEXT: vdivps {rn-sae}, %zmm1, %zmm0, %zmm2 {%k1} ## encoding: [0x62,0xf1,0x7c,0x19,0x5e,0xd1]
; X64-NEXT: vmovaps %zmm2, %zmm0 ## encoding: [0x62,0xf1,0x7c,0x48,0x28,0xc2]
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.div.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 0)
%res = call <16 x float> @llvm.x86.avx512.mask.div.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 8)
ret <16 x float> %res
}
define <16 x float> @test_mm512_mask_div_round_ps_rd_sae(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask) {
@ -7942,7 +7942,7 @@ define <16 x float> @test_mm512_mask_div_round_ps_rd_sae(<16 x float> %a0, <16 x
; X64-NEXT: vdivps {rd-sae}, %zmm1, %zmm0, %zmm2 {%k1} ## encoding: [0x62,0xf1,0x7c,0x39,0x5e,0xd1]
; X64-NEXT: vmovaps %zmm2, %zmm0 ## encoding: [0x62,0xf1,0x7c,0x48,0x28,0xc2]
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.div.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 1)
%res = call <16 x float> @llvm.x86.avx512.mask.div.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 9)
ret <16 x float> %res
}
define <16 x float> @test_mm512_mask_div_round_ps_ru_sae(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask) {
@ -7959,7 +7959,7 @@ define <16 x float> @test_mm512_mask_div_round_ps_ru_sae(<16 x float> %a0, <16 x
; X64-NEXT: vdivps {ru-sae}, %zmm1, %zmm0, %zmm2 {%k1} ## encoding: [0x62,0xf1,0x7c,0x59,0x5e,0xd1]
; X64-NEXT: vmovaps %zmm2, %zmm0 ## encoding: [0x62,0xf1,0x7c,0x48,0x28,0xc2]
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.div.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 2)
%res = call <16 x float> @llvm.x86.avx512.mask.div.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 10)
ret <16 x float> %res
}
@ -7977,7 +7977,7 @@ define <16 x float> @test_mm512_mask_div_round_ps_rz_sae(<16 x float> %a0, <16 x
; X64-NEXT: vdivps {rz-sae}, %zmm1, %zmm0, %zmm2 {%k1} ## encoding: [0x62,0xf1,0x7c,0x79,0x5e,0xd1]
; X64-NEXT: vmovaps %zmm2, %zmm0 ## encoding: [0x62,0xf1,0x7c,0x48,0x28,0xc2]
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.div.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 3)
%res = call <16 x float> @llvm.x86.avx512.mask.div.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float> %src, i16 %mask, i32 11)
ret <16 x float> %res
}
@ -8006,7 +8006,7 @@ define <16 x float> @test_mm512_div_round_ps_rn_sae(<16 x float> %a0, <16 x floa
; CHECK: ## %bb.0:
; CHECK-NEXT: vdivps {rn-sae}, %zmm1, %zmm0, %zmm0 ## encoding: [0x62,0xf1,0x7c,0x18,0x5e,0xc1]
; CHECK-NEXT: ret{{[l|q]}} ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.div.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 0)
%res = call <16 x float> @llvm.x86.avx512.mask.div.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 8)
ret <16 x float> %res
}
define <16 x float> @test_mm512_div_round_ps_rd_sae(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
@ -8014,7 +8014,7 @@ define <16 x float> @test_mm512_div_round_ps_rd_sae(<16 x float> %a0, <16 x floa
; CHECK: ## %bb.0:
; CHECK-NEXT: vdivps {rd-sae}, %zmm1, %zmm0, %zmm0 ## encoding: [0x62,0xf1,0x7c,0x38,0x5e,0xc1]
; CHECK-NEXT: ret{{[l|q]}} ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.div.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 1)
%res = call <16 x float> @llvm.x86.avx512.mask.div.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 9)
ret <16 x float> %res
}
define <16 x float> @test_mm512_div_round_ps_ru_sae(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
@ -8022,7 +8022,7 @@ define <16 x float> @test_mm512_div_round_ps_ru_sae(<16 x float> %a0, <16 x floa
; CHECK: ## %bb.0:
; CHECK-NEXT: vdivps {ru-sae}, %zmm1, %zmm0, %zmm0 ## encoding: [0x62,0xf1,0x7c,0x58,0x5e,0xc1]
; CHECK-NEXT: ret{{[l|q]}} ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.div.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 2)
%res = call <16 x float> @llvm.x86.avx512.mask.div.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 10)
ret <16 x float> %res
}
@ -8031,7 +8031,7 @@ define <16 x float> @test_mm512_div_round_ps_rz_sae(<16 x float> %a0, <16 x floa
; CHECK: ## %bb.0:
; CHECK-NEXT: vdivps {rz-sae}, %zmm1, %zmm0, %zmm0 ## encoding: [0x62,0xf1,0x7c,0x78,0x5e,0xc1]
; CHECK-NEXT: ret{{[l|q]}} ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.div.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 3)
%res = call <16 x float> @llvm.x86.avx512.mask.div.ps.512(<16 x float> %a0, <16 x float> %a1, <16 x float>zeroinitializer, i16 -1, i32 11)
ret <16 x float> %res
}
@ -9066,8 +9066,8 @@ define <2 x double>@test_int_x86_avx512_mask_vfmadd_sd(<2 x double> %x0, <2 x do
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <2 x double> @llvm.x86.avx512.mask.vfmadd.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 -1, i32 4)
%res1 = call <2 x double> @llvm.x86.avx512.mask.vfmadd.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 %x3, i32 4)
%res2 = call <2 x double> @llvm.x86.avx512.mask.vfmadd.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 -1, i32 3)
%res3 = call <2 x double> @llvm.x86.avx512.mask.vfmadd.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 %x3, i32 3)
%res2 = call <2 x double> @llvm.x86.avx512.mask.vfmadd.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 -1, i32 11)
%res3 = call <2 x double> @llvm.x86.avx512.mask.vfmadd.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 %x3, i32 11)
%res4 = fadd <2 x double> %res, %res1
%res5 = fadd <2 x double> %res2, %res3
%res6 = fadd <2 x double> %res4, %res5
@ -9113,8 +9113,8 @@ define <4 x float>@test_int_x86_avx512_mask_vfmadd_ss(<4 x float> %x0, <4 x floa
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <4 x float> @llvm.x86.avx512.mask.vfmadd.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 -1, i32 4)
%res1 = call <4 x float> @llvm.x86.avx512.mask.vfmadd.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 %x3, i32 4)
%res2 = call <4 x float> @llvm.x86.avx512.mask.vfmadd.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 -1, i32 3)
%res3 = call <4 x float> @llvm.x86.avx512.mask.vfmadd.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 %x3, i32 3)
%res2 = call <4 x float> @llvm.x86.avx512.mask.vfmadd.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 -1, i32 11)
%res3 = call <4 x float> @llvm.x86.avx512.mask.vfmadd.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 %x3, i32 11)
%res4 = fadd <4 x float> %res, %res1
%res5 = fadd <4 x float> %res2, %res3
%res6 = fadd <4 x float> %res4, %res5
@ -9145,7 +9145,7 @@ define <2 x double>@test_int_x86_avx512_maskz_vfmadd_sd(<2 x double> %x0, <2 x d
; X64-NEXT: vaddpd %xmm0, %xmm3, %xmm0 ## encoding: [0xc5,0xe1,0x58,0xc0]
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <2 x double> @llvm.x86.avx512.maskz.vfmadd.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 %x3, i32 4)
%res1 = call <2 x double> @llvm.x86.avx512.maskz.vfmadd.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 %x3, i32 3)
%res1 = call <2 x double> @llvm.x86.avx512.maskz.vfmadd.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 %x3, i32 11)
%res2 = fadd <2 x double> %res, %res1
ret <2 x double> %res2
}
@ -9168,7 +9168,7 @@ define <4 x float>@test_int_x86_avx512_maskz_vfmadd_ss(<4 x float> %x0, <4 x flo
; X64-NEXT: ## xmm0 = (xmm1 * xmm0) + xmm2
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <4 x float> @llvm.x86.avx512.maskz.vfmadd.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 %x3, i32 4)
%res1 = call <4 x float> @llvm.x86.avx512.maskz.vfmadd.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 %x3, i32 3)
%res1 = call <4 x float> @llvm.x86.avx512.maskz.vfmadd.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 %x3, i32 11)
%res2 = fadd <4 x float> %res, %res1
ret <4 x float> %res
}
@ -9211,8 +9211,8 @@ define <2 x double>@test_int_x86_avx512_mask3_vfmadd_sd(<2 x double> %x0, <2 x d
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <2 x double> @llvm.x86.avx512.mask3.vfmadd.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 -1, i32 4)
%res1 = call <2 x double> @llvm.x86.avx512.mask3.vfmadd.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 %x3, i32 4)
%res2 = call <2 x double> @llvm.x86.avx512.mask3.vfmadd.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 -1, i32 3)
%res3 = call <2 x double> @llvm.x86.avx512.mask3.vfmadd.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 %x3, i32 3)
%res2 = call <2 x double> @llvm.x86.avx512.mask3.vfmadd.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 -1, i32 11)
%res3 = call <2 x double> @llvm.x86.avx512.mask3.vfmadd.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 %x3, i32 11)
%res4 = fadd <2 x double> %res, %res1
%res5 = fadd <2 x double> %res2, %res3
%res6 = fadd <2 x double> %res4, %res5
@ -9258,8 +9258,8 @@ define <4 x float>@test_int_x86_avx512_mask3_vfmadd_ss(<4 x float> %x0, <4 x flo
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <4 x float> @llvm.x86.avx512.mask3.vfmadd.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 -1, i32 4)
%res1 = call <4 x float> @llvm.x86.avx512.mask3.vfmadd.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 %x3, i32 4)
%res2 = call <4 x float> @llvm.x86.avx512.mask3.vfmadd.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 -1, i32 3)
%res3 = call <4 x float> @llvm.x86.avx512.mask3.vfmadd.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 %x3, i32 3)
%res2 = call <4 x float> @llvm.x86.avx512.mask3.vfmadd.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 -1, i32 11)
%res3 = call <4 x float> @llvm.x86.avx512.mask3.vfmadd.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 %x3, i32 11)
%res4 = fadd <4 x float> %res, %res1
%res5 = fadd <4 x float> %res2, %res3
%res6 = fadd <4 x float> %res4, %res5
@ -9481,8 +9481,8 @@ define <2 x double>@test_int_x86_avx512_mask3_vfmsub_sd(<2 x double> %x0, <2 x d
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <2 x double> @llvm.x86.avx512.mask3.vfmsub.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 -1, i32 4)
%res1 = call <2 x double> @llvm.x86.avx512.mask3.vfmsub.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 %x3, i32 4)
%res2 = call <2 x double> @llvm.x86.avx512.mask3.vfmsub.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 -1, i32 3)
%res3 = call <2 x double> @llvm.x86.avx512.mask3.vfmsub.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 %x3, i32 3)
%res2 = call <2 x double> @llvm.x86.avx512.mask3.vfmsub.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 -1, i32 11)
%res3 = call <2 x double> @llvm.x86.avx512.mask3.vfmsub.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 %x3, i32 11)
%res4 = fadd <2 x double> %res, %res1
%res5 = fadd <2 x double> %res2, %res3
%res6 = fadd <2 x double> %res4, %res5
@ -9528,8 +9528,8 @@ define <4 x float>@test_int_x86_avx512_mask3_vfmsub_ss(<4 x float> %x0, <4 x flo
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <4 x float> @llvm.x86.avx512.mask3.vfmsub.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 -1, i32 4)
%res1 = call <4 x float> @llvm.x86.avx512.mask3.vfmsub.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 %x3, i32 4)
%res2 = call <4 x float> @llvm.x86.avx512.mask3.vfmsub.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 -1, i32 3)
%res3 = call <4 x float> @llvm.x86.avx512.mask3.vfmsub.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 %x3, i32 3)
%res2 = call <4 x float> @llvm.x86.avx512.mask3.vfmsub.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 -1, i32 11)
%res3 = call <4 x float> @llvm.x86.avx512.mask3.vfmsub.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 %x3, i32 11)
%res4 = fadd <4 x float> %res, %res1
%res5 = fadd <4 x float> %res2, %res3
%res6 = fadd <4 x float> %res4, %res5
@ -9575,8 +9575,8 @@ define <2 x double>@test_int_x86_avx512_mask3_vfnmsub_sd(<2 x double> %x0, <2 x
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <2 x double> @llvm.x86.avx512.mask3.vfnmsub.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 -1, i32 4)
%res1 = call <2 x double> @llvm.x86.avx512.mask3.vfnmsub.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 %x3, i32 4)
%res2 = call <2 x double> @llvm.x86.avx512.mask3.vfnmsub.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 -1, i32 3)
%res3 = call <2 x double> @llvm.x86.avx512.mask3.vfnmsub.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 %x3, i32 3)
%res2 = call <2 x double> @llvm.x86.avx512.mask3.vfnmsub.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 -1, i32 11)
%res3 = call <2 x double> @llvm.x86.avx512.mask3.vfnmsub.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 %x3, i32 11)
%res4 = fadd <2 x double> %res, %res1
%res5 = fadd <2 x double> %res2, %res3
%res6 = fadd <2 x double> %res4, %res5
@ -9622,8 +9622,8 @@ define <4 x float>@test_int_x86_avx512_mask3_vfnmsub_ss(<4 x float> %x0, <4 x fl
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <4 x float> @llvm.x86.avx512.mask3.vfnmsub.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 -1, i32 4)
%res1 = call <4 x float> @llvm.x86.avx512.mask3.vfnmsub.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 %x3, i32 4)
%res2 = call <4 x float> @llvm.x86.avx512.mask3.vfnmsub.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 -1, i32 3)
%res3 = call <4 x float> @llvm.x86.avx512.mask3.vfnmsub.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 %x3, i32 3)
%res2 = call <4 x float> @llvm.x86.avx512.mask3.vfnmsub.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 -1, i32 11)
%res3 = call <4 x float> @llvm.x86.avx512.mask3.vfnmsub.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 %x3, i32 11)
%res4 = fadd <4 x float> %res, %res1
%res5 = fadd <4 x float> %res2, %res3
%res6 = fadd <4 x float> %res4, %res5
@ -9740,7 +9740,7 @@ define <16 x float> @test_int_x86_avx512_mask_cvt_dq2ps_512(<16 x i32> %x0, <16
; X64-NEXT: vaddps %zmm0, %zmm1, %zmm0 ## encoding: [0x62,0xf1,0x74,0x48,0x58,0xc0]
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.cvtdq2ps.512(<16 x i32> %x0, <16 x float> %x1, i16 %x2, i32 4)
%res1 = call <16 x float> @llvm.x86.avx512.mask.cvtdq2ps.512(<16 x i32> %x0, <16 x float> %x1, i16 -1, i32 0)
%res1 = call <16 x float> @llvm.x86.avx512.mask.cvtdq2ps.512(<16 x i32> %x0, <16 x float> %x1, i16 -1, i32 8)
%res2 = fadd <16 x float> %res, %res1
ret <16 x float> %res2
}
@ -9764,7 +9764,7 @@ define <16 x float> @test_int_x86_avx512_mask_cvt_udq2ps_512(<16 x i32> %x0, <16
; X64-NEXT: vaddps %zmm0, %zmm1, %zmm0 ## encoding: [0x62,0xf1,0x74,0x48,0x58,0xc0]
; X64-NEXT: retq ## encoding: [0xc3]
%res = call <16 x float> @llvm.x86.avx512.mask.cvtudq2ps.512(<16 x i32> %x0, <16 x float> %x1, i16 %x2, i32 4)
%res1 = call <16 x float> @llvm.x86.avx512.mask.cvtudq2ps.512(<16 x i32> %x0, <16 x float> %x1, i16 -1, i32 0)
%res1 = call <16 x float> @llvm.x86.avx512.mask.cvtudq2ps.512(<16 x i32> %x0, <16 x float> %x1, i16 -1, i32 8)
%res2 = fadd <16 x float> %res, %res1
ret <16 x float> %res2
}

24
llvm/test/CodeGen/X86/avx512-intrinsics-x86_64.ll
View File

@ -125,8 +125,8 @@ define i64 @test_x86_avx512_cvtsd2usi64(<2 x double> %a0) {
; CHECK-NEXT: retq
%res = call i64 @llvm.x86.avx512.vcvtsd2usi64(<2 x double> %a0, i32 4)
%res1 = call i64 @llvm.x86.avx512.vcvtsd2usi64(<2 x double> %a0, i32 3)
%res2 = call i64 @llvm.x86.avx512.vcvtsd2usi64(<2 x double> %a0, i32 1)
%res1 = call i64 @llvm.x86.avx512.vcvtsd2usi64(<2 x double> %a0, i32 11)
%res2 = call i64 @llvm.x86.avx512.vcvtsd2usi64(<2 x double> %a0, i32 9)
%res3 = add i64 %res, %res1
%res4 = add i64 %res3, %res2
ret i64 %res4
@ -144,8 +144,8 @@ define i64 @test_x86_avx512_cvtsd2si64(<2 x double> %a0) {
; CHECK-NEXT: retq
%res = call i64 @llvm.x86.avx512.vcvtsd2si64(<2 x double> %a0, i32 4)
%res1 = call i64 @llvm.x86.avx512.vcvtsd2si64(<2 x double> %a0, i32 3)
%res2 = call i64 @llvm.x86.avx512.vcvtsd2si64(<2 x double> %a0, i32 1)
%res1 = call i64 @llvm.x86.avx512.vcvtsd2si64(<2 x double> %a0, i32 11)
%res2 = call i64 @llvm.x86.avx512.vcvtsd2si64(<2 x double> %a0, i32 9)
%res3 = add i64 %res, %res1
%res4 = add i64 %res3, %res2
ret i64 %res4
@ -163,8 +163,8 @@ define i64 @test_x86_avx512_cvtss2usi64(<4 x float> %a0) {
; CHECK-NEXT: retq
%res = call i64 @llvm.x86.avx512.vcvtss2usi64(<4 x float> %a0, i32 4)
%res1 = call i64 @llvm.x86.avx512.vcvtss2usi64(<4 x float> %a0, i32 3)
%res2 = call i64 @llvm.x86.avx512.vcvtss2usi64(<4 x float> %a0, i32 1)
%res1 = call i64 @llvm.x86.avx512.vcvtss2usi64(<4 x float> %a0, i32 11)
%res2 = call i64 @llvm.x86.avx512.vcvtss2usi64(<4 x float> %a0, i32 9)
%res3 = add i64 %res, %res1
%res4 = add i64 %res3, %res2
ret i64 %res4
@ -182,8 +182,8 @@ define i64 @test_x86_avx512_cvtss2si64(<4 x float> %a0) {
; CHECK-NEXT: retq
%res = call i64 @llvm.x86.avx512.vcvtss2si64(<4 x float> %a0, i32 4)
%res1 = call i64 @llvm.x86.avx512.vcvtss2si64(<4 x float> %a0, i32 3)
%res2 = call i64 @llvm.x86.avx512.vcvtss2si64(<4 x float> %a0, i32 1)
%res1 = call i64 @llvm.x86.avx512.vcvtss2si64(<4 x float> %a0, i32 11)
%res2 = call i64 @llvm.x86.avx512.vcvtss2si64(<4 x float> %a0, i32 9)
%res3 = add i64 %res, %res1
%res4 = add i64 %res3, %res2
ret i64 %res4
@ -195,7 +195,7 @@ define <2 x double> @test_x86_avx512_cvtsi2sd64(<2 x double> %a, i64 %b) {
; CHECK: ## %bb.0:
; CHECK-NEXT: vcvtsi2sdq %rdi, {rz-sae}, %xmm0, %xmm0
; CHECK-NEXT: retq
%res = call <2 x double> @llvm.x86.avx512.cvtsi2sd64(<2 x double> %a, i64 %b, i32 3) ; <<<2 x double>> [#uses=1]
%res = call <2 x double> @llvm.x86.avx512.cvtsi2sd64(<2 x double> %a, i64 %b, i32 11) ; <<<2 x double>> [#uses=1]
ret <2 x double> %res
}
declare <2 x double> @llvm.x86.avx512.cvtsi2sd64(<2 x double>, i64, i32) nounwind readnone
@ -205,7 +205,7 @@ define <4 x float> @test_x86_avx512_cvtsi2ss64(<4 x float> %a, i64 %b) {
; CHECK: ## %bb.0:
; CHECK-NEXT: vcvtsi2ssq %rdi, {rz-sae}, %xmm0, %xmm0
; CHECK-NEXT: retq
%res = call <4 x float> @llvm.x86.avx512.cvtsi2ss64(<4 x float> %a, i64 %b, i32 3) ; <<<4 x float>> [#uses=1]
%res = call <4 x float> @llvm.x86.avx512.cvtsi2ss64(<4 x float> %a, i64 %b, i32 11) ; <<<4 x float>> [#uses=1]
ret <4 x float> %res
}
declare <4 x float> @llvm.x86.avx512.cvtsi2ss64(<4 x float>, i64, i32) nounwind readnone
@ -215,7 +215,7 @@ define <4 x float> @_mm_cvt_roundu64_ss (<4 x float> %a, i64 %b) {
; CHECK: ## %bb.0:
; CHECK-NEXT: vcvtusi2ssq %rdi, {rd-sae}, %xmm0, %xmm0
; CHECK-NEXT: retq
%res = call <4 x float> @llvm.x86.avx512.cvtusi642ss(<4 x float> %a, i64 %b, i32 1) ; <<<4 x float>> [#uses=1]
%res = call <4 x float> @llvm.x86.avx512.cvtusi642ss(<4 x float> %a, i64 %b, i32 9) ; <<<4 x float>> [#uses=1]
ret <4 x float> %res
}
@ -234,7 +234,7 @@ define <2 x double> @test_x86_avx512_mm_cvtu64_sd(<2 x double> %a, i64 %b) {
; CHECK: ## %bb.0:
; CHECK-NEXT: vcvtusi2sdq %rdi, {rd-sae}, %xmm0, %xmm0
; CHECK-NEXT: retq
%res = call <2 x double> @llvm.x86.avx512.cvtusi642sd(<2 x double> %a, i64 %b, i32 1) ; <<<2 x double>> [#uses=1]
%res = call <2 x double> @llvm.x86.avx512.cvtusi642sd(<2 x double> %a, i64 %b, i32 9) ; <<<2 x double>> [#uses=1]
ret <2 x double> %res
}

228
llvm/test/CodeGen/X86/avx512-intrinsics.ll
View File

@ -809,9 +809,9 @@ define <4 x float> @test_sqrt_ss(<4 x float> %a0, <4 x float> %a1, <4 x float> %
; X86-NEXT: vaddps %xmm0, %xmm2, %xmm0
; X86-NEXT: retl
%res0 = call <4 x float> @llvm.x86.avx512.mask.sqrt.ss(<4 x float>%a0, <4 x float> %a1, <4 x float> %a2, i8 %mask, i32 4)
%res1 = call <4 x float> @llvm.x86.avx512.mask.sqrt.ss(<4 x float>%a0, <4 x float> %a1, <4 x float> %a2, i8 %mask, i32 1)
%res2 = call <4 x float> @llvm.x86.avx512.mask.sqrt.ss(<4 x float>%a0, <4 x float> %a1, <4 x float> zeroinitializer, i8 %mask, i32 2)
%res3 = call <4 x float> @llvm.x86.avx512.mask.sqrt.ss(<4 x float>%a0, <4 x float> %a1, <4 x float> zeroinitializer, i8 -1, i32 3)
%res1 = call <4 x float> @llvm.x86.avx512.mask.sqrt.ss(<4 x float>%a0, <4 x float> %a1, <4 x float> %a2, i8 %mask, i32 9)
%res2 = call <4 x float> @llvm.x86.avx512.mask.sqrt.ss(<4 x float>%a0, <4 x float> %a1, <4 x float> zeroinitializer, i8 %mask, i32 10)
%res3 = call <4 x float> @llvm.x86.avx512.mask.sqrt.ss(<4 x float>%a0, <4 x float> %a1, <4 x float> zeroinitializer, i8 -1, i32 11)
%res.1 = fadd <4 x float> %res0, %res1
%res.2 = fadd <4 x float> %res2, %res3
@ -849,9 +849,9 @@ define <2 x double> @test_sqrt_sd(<2 x double> %a0, <2 x double> %a1, <2 x doubl
; X86-NEXT: vaddpd %xmm0, %xmm2, %xmm0
; X86-NEXT: retl
%res0 = call <2 x double> @llvm.x86.avx512.mask.sqrt.sd(<2 x double>%a0, <2 x double> %a1, <2 x double> %a2, i8 %mask, i32 4)
%res1 = call <2 x double> @llvm.x86.avx512.mask.sqrt.sd(<2 x double>%a0, <2 x double> %a1, <2 x double> %a2, i8 %mask, i32 1)
%res2 = call <2 x double> @llvm.x86.avx512.mask.sqrt.sd(<2 x double>%a0, <2 x double> %a1, <2 x double> zeroinitializer, i8 %mask, i32 2)
%res3 = call <2 x double> @llvm.x86.avx512.mask.sqrt.sd(<2 x double>%a0, <2 x double> %a1, <2 x double> zeroinitializer, i8 -1, i32 3)
%res1 = call <2 x double> @llvm.x86.avx512.mask.sqrt.sd(<2 x double>%a0, <2 x double> %a1, <2 x double> %a2, i8 %mask, i32 9)
%res2 = call <2 x double> @llvm.x86.avx512.mask.sqrt.sd(<2 x double>%a0, <2 x double> %a1, <2 x double> zeroinitializer, i8 %mask, i32 10)
%res3 = call <2 x double> @llvm.x86.avx512.mask.sqrt.sd(<2 x double>%a0, <2 x double> %a1, <2 x double> zeroinitializer, i8 -1, i32 11)
%res.1 = fadd <2 x double> %res0, %res1
%res.2 = fadd <2 x double> %res2, %res3
@ -942,8 +942,8 @@ define i32 @test_x86_avx512_cvtsd2usi32(<2 x double> %a0) {
; CHECK-NEXT: ret{{[l|q]}}
%res = call i32 @llvm.x86.avx512.vcvtsd2usi32(<2 x double> %a0, i32 4)
%res1 = call i32 @llvm.x86.avx512.vcvtsd2usi32(<2 x double> %a0, i32 3)
%res2 = call i32 @llvm.x86.avx512.vcvtsd2usi32(<2 x double> %a0, i32 1)
%res1 = call i32 @llvm.x86.avx512.vcvtsd2usi32(<2 x double> %a0, i32 11)
%res2 = call i32 @llvm.x86.avx512.vcvtsd2usi32(<2 x double> %a0, i32 9)
%res3 = add i32 %res, %res1
%res4 = add i32 %res3, %res2
ret i32 %res4
@ -961,8 +961,8 @@ define i32 @test_x86_avx512_cvtsd2si32(<2 x double> %a0) {
; CHECK-NEXT: ret{{[l|q]}}
%res = call i32 @llvm.x86.avx512.vcvtsd2si32(<2 x double> %a0, i32 4)
%res1 = call i32 @llvm.x86.avx512.vcvtsd2si32(<2 x double> %a0, i32 3)
%res2 = call i32 @llvm.x86.avx512.vcvtsd2si32(<2 x double> %a0, i32 1)
%res1 = call i32 @llvm.x86.avx512.vcvtsd2si32(<2 x double> %a0, i32 11)
%res2 = call i32 @llvm.x86.avx512.vcvtsd2si32(<2 x double> %a0, i32 9)
%res3 = add i32 %res, %res1
%res4 = add i32 %res3, %res2
ret i32 %res4
@ -980,8 +980,8 @@ define i32 @test_x86_avx512_cvtss2usi32(<4 x float> %a0) {
; CHECK-NEXT: ret{{[l|q]}}
%res = call i32 @llvm.x86.avx512.vcvtss2usi32(<4 x float> %a0, i32 4)
%res1 = call i32 @llvm.x86.avx512.vcvtss2usi32(<4 x float> %a0, i32 3)
%res2 = call i32 @llvm.x86.avx512.vcvtss2usi32(<4 x float> %a0, i32 1)
%res1 = call i32 @llvm.x86.avx512.vcvtss2usi32(<4 x float> %a0, i32 11)
%res2 = call i32 @llvm.x86.avx512.vcvtss2usi32(<4 x float> %a0, i32 9)
%res3 = add i32 %res, %res1
%res4 = add i32 %res3, %res2
ret i32 %res4
@ -999,8 +999,8 @@ define i32 @test_x86_avx512_cvtss2si32(<4 x float> %a0) {
; CHECK-NEXT: ret{{[l|q]}}
%res = call i32 @llvm.x86.avx512.vcvtss2si32(<4 x float> %a0, i32 4)
%res1 = call i32 @llvm.x86.avx512.vcvtss2si32(<4 x float> %a0, i32 3)
%res2 = call i32 @llvm.x86.avx512.vcvtss2si32(<4 x float> %a0, i32 1)
%res1 = call i32 @llvm.x86.avx512.vcvtss2si32(<4 x float> %a0, i32 11)
%res2 = call i32 @llvm.x86.avx512.vcvtss2si32(<4 x float> %a0, i32 9)
%res3 = add i32 %res, %res1
%res4 = add i32 %res3, %res2
ret i32 %res4
@ -1192,7 +1192,7 @@ define <16 x float> @test_vsubps_rn(<16 x float> %a0, <16 x float> %a1) {
; CHECK: # %bb.0:
; CHECK-NEXT: vsubps {rn-sae}, %zmm1, %zmm0, %zmm0
; CHECK-NEXT: ret{{[l|q]}}
%1 = call <16 x float> @llvm.x86.avx512.sub.ps.512(<16 x float> %a0, <16 x float> %a1, i32 0)
%1 = call <16 x float> @llvm.x86.avx512.sub.ps.512(<16 x float> %a0, <16 x float> %a1, i32 8)
ret <16 x float> %1
}
@ -1201,7 +1201,7 @@ define <16 x float> @test_vsubps_rd(<16 x float> %a0, <16 x float> %a1) {
; CHECK: # %bb.0:
; CHECK-NEXT: vsubps {rd-sae}, %zmm1, %zmm0, %zmm0
; CHECK-NEXT: ret{{[l|q]}}
%1 = call <16 x float> @llvm.x86.avx512.sub.ps.512(<16 x float> %a0, <16 x float> %a1, i32 1)
%1 = call <16 x float> @llvm.x86.avx512.sub.ps.512(<16 x float> %a0, <16 x float> %a1, i32 9)
ret <16 x float> %1
}
@ -1210,7 +1210,7 @@ define <16 x float> @test_vsubps_ru(<16 x float> %a0, <16 x float> %a1) {
; CHECK: # %bb.0:
; CHECK-NEXT: vsubps {ru-sae}, %zmm1, %zmm0, %zmm0
; CHECK-NEXT: ret{{[l|q]}}
%1 = call <16 x float> @llvm.x86.avx512.sub.ps.512(<16 x float> %a0, <16 x float> %a1, i32 2)
%1 = call <16 x float> @llvm.x86.avx512.sub.ps.512(<16 x float> %a0, <16 x float> %a1, i32 10)
ret <16 x float> %1
}
@ -1219,7 +1219,7 @@ define <16 x float> @test_vsubps_rz(<16 x float> %a0, <16 x float> %a1) {
; CHECK: # %bb.0:
; CHECK-NEXT: vsubps {rz-sae}, %zmm1, %zmm0, %zmm0
; CHECK-NEXT: ret{{[l|q]}}
%1 = call <16 x float> @llvm.x86.avx512.sub.ps.512(<16 x float> %a0, <16 x float> %a1, i32 3)
%1 = call <16 x float> @llvm.x86.avx512.sub.ps.512(<16 x float> %a0, <16 x float> %a1, i32 11)
ret <16 x float> %1
}
@ -1228,7 +1228,7 @@ define <16 x float> @test_vmulps_rn(<16 x float> %a0, <16 x float> %a1) {
; CHECK: # %bb.0:
; CHECK-NEXT: vmulps {rn-sae}, %zmm1, %zmm0, %zmm0
; CHECK-NEXT: ret{{[l|q]}}
%1 = call <16 x float> @llvm.x86.avx512.mul.ps.512(<16 x float> %a0, <16 x float> %a1, i32 0)
%1 = call <16 x float> @llvm.x86.avx512.mul.ps.512(<16 x float> %a0, <16 x float> %a1, i32 8)
ret <16 x float> %1
}
@ -1237,7 +1237,7 @@ define <16 x float> @test_vmulps_rd(<16 x float> %a0, <16 x float> %a1) {
; CHECK: # %bb.0:
; CHECK-NEXT: vmulps {rd-sae}, %zmm1, %zmm0, %zmm0
; CHECK-NEXT: ret{{[l|q]}}
%1 = call <16 x float> @llvm.x86.avx512.mul.ps.512(<16 x float> %a0, <16 x float> %a1, i32 1)
%1 = call <16 x float> @llvm.x86.avx512.mul.ps.512(<16 x float> %a0, <16 x float> %a1, i32 9)
ret <16 x float> %1
}
@ -1246,7 +1246,7 @@ define <16 x float> @test_vmulps_ru(<16 x float> %a0, <16 x float> %a1) {
; CHECK: # %bb.0:
; CHECK-NEXT: vmulps {ru-sae}, %zmm1, %zmm0, %zmm0
; CHECK-NEXT: ret{{[l|q]}}
%1 = call <16 x float> @llvm.x86.avx512.mul.ps.512(<16 x float> %a0, <16 x float> %a1, i32 2)
%1 = call <16 x float> @llvm.x86.avx512.mul.ps.512(<16 x float> %a0, <16 x float> %a1, i32 10)
ret <16 x float> %1
}
@ -1255,7 +1255,7 @@ define <16 x float> @test_vmulps_rz(<16 x float> %a0, <16 x float> %a1) {
; CHECK: # %bb.0:
; CHECK-NEXT: vmulps {rz-sae}, %zmm1, %zmm0, %zmm0
; CHECK-NEXT: ret{{[l|q]}}
%1 = call <16 x float> @llvm.x86.avx512.mul.ps.512(<16 x float> %a0, <16 x float> %a1, i32 3)
%1 = call <16 x float> @llvm.x86.avx512.mul.ps.512(<16 x float> %a0, <16 x float> %a1, i32 11)
ret <16 x float> %1
}
@ -1272,7 +1272,7 @@ define <16 x float> @test_vmulps_mask_rn(<16 x float> %a0, <16 x float> %a1, i16
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1
; X86-NEXT: vmulps {rn-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z}
; X86-NEXT: retl
%1 = call <16 x float> @llvm.x86.avx512.mul.ps.512(<16 x float> %a0, <16 x float> %a1, i32 0)
%1 = call <16 x float> @llvm.x86.avx512.mul.ps.512(<16 x float> %a0, <16 x float> %a1, i32 8)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x float> %1, <16 x float> zeroinitializer
ret <16 x float> %3
@ -1290,7 +1290,7 @@ define <16 x float> @test_vmulps_mask_rd(<16 x float> %a0, <16 x float> %a1, i16
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1
; X86-NEXT: vmulps {rd-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z}
; X86-NEXT: retl
%1 = call <16 x float> @llvm.x86.avx512.mul.ps.512(<16 x float> %a0, <16 x float> %a1, i32 1)
%1 = call <16 x float> @llvm.x86.avx512.mul.ps.512(<16 x float> %a0, <16 x float> %a1, i32 9)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x float> %1, <16 x float> zeroinitializer
ret <16 x float> %3
@ -1308,7 +1308,7 @@ define <16 x float> @test_vmulps_mask_ru(<16 x float> %a0, <16 x float> %a1, i16
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1
; X86-NEXT: vmulps {ru-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z}
; X86-NEXT: retl
%1 = call <16 x float> @llvm.x86.avx512.mul.ps.512(<16 x float> %a0, <16 x float> %a1, i32 2)
%1 = call <16 x float> @llvm.x86.avx512.mul.ps.512(<16 x float> %a0, <16 x float> %a1, i32 10)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x float> %1, <16 x float> zeroinitializer
ret <16 x float> %3
@ -1326,7 +1326,7 @@ define <16 x float> @test_vmulps_mask_rz(<16 x float> %a0, <16 x float> %a1, i16
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1
; X86-NEXT: vmulps {rz-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z}
; X86-NEXT: retl
%1 = call <16 x float> @llvm.x86.avx512.mul.ps.512(<16 x float> %a0, <16 x float> %a1, i32 3)
%1 = call <16 x float> @llvm.x86.avx512.mul.ps.512(<16 x float> %a0, <16 x float> %a1, i32 11)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x float> %1, <16 x float> zeroinitializer
ret <16 x float> %3
@ -1347,7 +1347,7 @@ define <16 x float> @test_vmulps_mask_passthru_rn(<16 x float> %a0, <16 x float>
; X86-NEXT: vmulps {rn-sae}, %zmm1, %zmm0, %zmm2 {%k1}
; X86-NEXT: vmovaps %zmm2, %zmm0
; X86-NEXT: retl
%1 = call <16 x float> @llvm.x86.avx512.mul.ps.512(<16 x float> %a0, <16 x float> %a1, i32 0)
%1 = call <16 x float> @llvm.x86.avx512.mul.ps.512(<16 x float> %a0, <16 x float> %a1, i32 8)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x float> %1, <16 x float> %passthru
ret <16 x float> %3
@ -1367,7 +1367,7 @@ define <16 x float> @test_vmulps_mask_passthru_rd(<16 x float> %a0, <16 x float>
; X86-NEXT: vmulps {rd-sae}, %zmm1, %zmm0, %zmm2 {%k1}
; X86-NEXT: vmovaps %zmm2, %zmm0
; X86-NEXT: retl
%1 = call <16 x float> @llvm.x86.avx512.mul.ps.512(<16 x float> %a0, <16 x float> %a1, i32 1)
%1 = call <16 x float> @llvm.x86.avx512.mul.ps.512(<16 x float> %a0, <16 x float> %a1, i32 9)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x float> %1, <16 x float> %passthru
ret <16 x float> %3
@ -1387,7 +1387,7 @@ define <16 x float> @test_vmulps_mask_passthru_ru(<16 x float> %a0, <16 x float>
; X86-NEXT: vmulps {ru-sae}, %zmm1, %zmm0, %zmm2 {%k1}
; X86-NEXT: vmovaps %zmm2, %zmm0
; X86-NEXT: retl
%1 = call <16 x float> @llvm.x86.avx512.mul.ps.512(<16 x float> %a0, <16 x float> %a1, i32 2)
%1 = call <16 x float> @llvm.x86.avx512.mul.ps.512(<16 x float> %a0, <16 x float> %a1, i32 10)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x float> %1, <16 x float> %passthru
ret <16 x float> %3
@ -1407,7 +1407,7 @@ define <16 x float> @test_vmulps_mask_passthru_rz(<16 x float> %a0, <16 x float>
; X86-NEXT: vmulps {rz-sae}, %zmm1, %zmm0, %zmm2 {%k1}
; X86-NEXT: vmovaps %zmm2, %zmm0
; X86-NEXT: retl
%1 = call <16 x float> @llvm.x86.avx512.mul.ps.512(<16 x float> %a0, <16 x float> %a1, i32 3)
%1 = call <16 x float> @llvm.x86.avx512.mul.ps.512(<16 x float> %a0, <16 x float> %a1, i32 11)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x float> %1, <16 x float> %passthru
ret <16 x float> %3
@ -1427,7 +1427,7 @@ define <8 x double> @test_vmulpd_mask_rn(<8 x double> %a0, <8 x double> %a1, i8
; X86-NEXT: kmovw %eax, %k1
; X86-NEXT: vmulpd {rn-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z}
; X86-NEXT: retl
%1 = call <8 x double> @llvm.x86.avx512.mul.pd.512(<8 x double> %a0, <8 x double> %a1, i32 0)
%1 = call <8 x double> @llvm.x86.avx512.mul.pd.512(<8 x double> %a0, <8 x double> %a1, i32 8)
%2 = bitcast i8 %mask to <8 x i1>
%3 = select <8 x i1> %2, <8 x double> %1, <8 x double> zeroinitializer
ret <8 x double> %3
@ -1446,7 +1446,7 @@ define <8 x double> @test_vmulpd_mask_rd(<8 x double> %a0, <8 x double> %a1, i8
; X86-NEXT: kmovw %eax, %k1
; X86-NEXT: vmulpd {rd-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z}
; X86-NEXT: retl
%1 = call <8 x double> @llvm.x86.avx512.mul.pd.512(<8 x double> %a0, <8 x double> %a1, i32 1)
%1 = call <8 x double> @llvm.x86.avx512.mul.pd.512(<8 x double> %a0, <8 x double> %a1, i32 9)
%2 = bitcast i8 %mask to <8 x i1>
%3 = select <8 x i1> %2, <8 x double> %1, <8 x double> zeroinitializer
ret <8 x double> %3
@ -1465,7 +1465,7 @@ define <8 x double> @test_vmulpd_mask_ru(<8 x double> %a0, <8 x double> %a1, i8
; X86-NEXT: kmovw %eax, %k1
; X86-NEXT: vmulpd {ru-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z}
; X86-NEXT: retl
%1 = call <8 x double> @llvm.x86.avx512.mul.pd.512(<8 x double> %a0, <8 x double> %a1, i32 2)
%1 = call <8 x double> @llvm.x86.avx512.mul.pd.512(<8 x double> %a0, <8 x double> %a1, i32 10)
%2 = bitcast i8 %mask to <8 x i1>
%3 = select <8 x i1> %2, <8 x double> %1, <8 x double> zeroinitializer
ret <8 x double> %3
@ -1484,7 +1484,7 @@ define <8 x double> @test_vmulpd_mask_rz(<8 x double> %a0, <8 x double> %a1, i8
; X86-NEXT: kmovw %eax, %k1
; X86-NEXT: vmulpd {rz-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z}
; X86-NEXT: retl
%1 = call <8 x double> @llvm.x86.avx512.mul.pd.512(<8 x double> %a0, <8 x double> %a1, i32 3)
%1 = call <8 x double> @llvm.x86.avx512.mul.pd.512(<8 x double> %a0, <8 x double> %a1, i32 11)
%2 = bitcast i8 %mask to <8 x i1>
%3 = select <8 x i1> %2, <8 x double> %1, <8 x double> zeroinitializer
ret <8 x double> %3
@ -1502,7 +1502,7 @@ define <16 x float> @test_mm512_maskz_add_round_ps_rn_sae(<16 x float> %a0, <16
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1
; X86-NEXT: vaddps {rn-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z}
; X86-NEXT: retl
%1 = call <16 x float> @llvm.x86.avx512.add.ps.512(<16 x float> %a0, <16 x float> %a1, i32 0)
%1 = call <16 x float> @llvm.x86.avx512.add.ps.512(<16 x float> %a0, <16 x float> %a1, i32 8)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x float> %1, <16 x float> zeroinitializer
ret <16 x float> %3
@ -1520,7 +1520,7 @@ define <16 x float> @test_mm512_maskz_add_round_ps_rd_sae(<16 x float> %a0, <16
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1
; X86-NEXT: vaddps {rd-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z}
; X86-NEXT: retl
%1 = call <16 x float> @llvm.x86.avx512.add.ps.512(<16 x float> %a0, <16 x float> %a1, i32 1)
%1 = call <16 x float> @llvm.x86.avx512.add.ps.512(<16 x float> %a0, <16 x float> %a1, i32 9)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x float> %1, <16 x float> zeroinitializer
ret <16 x float> %3
@ -1538,7 +1538,7 @@ define <16 x float> @test_mm512_maskz_add_round_ps_ru_sae(<16 x float> %a0, <16
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1
; X86-NEXT: vaddps {ru-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z}
; X86-NEXT: retl
%1 = call <16 x float> @llvm.x86.avx512.add.ps.512(<16 x float> %a0, <16 x float> %a1, i32 2)
%1 = call <16 x float> @llvm.x86.avx512.add.ps.512(<16 x float> %a0, <16 x float> %a1, i32 10)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x float> %1, <16 x float> zeroinitializer
ret <16 x float> %3
@ -1556,7 +1556,7 @@ define <16 x float> @test_mm512_maskz_add_round_ps_rz_sae(<16 x float> %a0, <16
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1
; X86-NEXT: vaddps {rz-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z}
; X86-NEXT: retl
%1 = call <16 x float> @llvm.x86.avx512.add.ps.512(<16 x float> %a0, <16 x float> %a1, i32 3)
%1 = call <16 x float> @llvm.x86.avx512.add.ps.512(<16 x float> %a0, <16 x float> %a1, i32 11)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x float> %1, <16 x float> zeroinitializer
ret <16 x float> %3
@ -1594,7 +1594,7 @@ define <16 x float> @test_mm512_mask_add_round_ps_rn_sae(<16 x float> %a0, <16 x
; X86-NEXT: vaddps {rn-sae}, %zmm1, %zmm0, %zmm2 {%k1}
; X86-NEXT: vmovaps %zmm2, %zmm0
; X86-NEXT: retl
%1 = call <16 x float> @llvm.x86.avx512.add.ps.512(<16 x float> %a0, <16 x float> %a1, i32 0)
%1 = call <16 x float> @llvm.x86.avx512.add.ps.512(<16 x float> %a0, <16 x float> %a1, i32 8)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x float> %1, <16 x float> %src
ret <16 x float> %3
@ -1614,7 +1614,7 @@ define <16 x float> @test_mm512_mask_add_round_ps_rd_sae(<16 x float> %a0, <16 x
; X86-NEXT: vaddps {rd-sae}, %zmm1, %zmm0, %zmm2 {%k1}
; X86-NEXT: vmovaps %zmm2, %zmm0
; X86-NEXT: retl
%1 = call <16 x float> @llvm.x86.avx512.add.ps.512(<16 x float> %a0, <16 x float> %a1, i32 1)
%1 = call <16 x float> @llvm.x86.avx512.add.ps.512(<16 x float> %a0, <16 x float> %a1, i32 9)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x float> %1, <16 x float> %src
ret <16 x float> %3
@ -1634,7 +1634,7 @@ define <16 x float> @test_mm512_mask_add_round_ps_ru_sae(<16 x float> %a0, <16 x
; X86-NEXT: vaddps {ru-sae}, %zmm1, %zmm0, %zmm2 {%k1}
; X86-NEXT: vmovaps %zmm2, %zmm0
; X86-NEXT: retl
%1 = call <16 x float> @llvm.x86.avx512.add.ps.512(<16 x float> %a0, <16 x float> %a1, i32 2)
%1 = call <16 x float> @llvm.x86.avx512.add.ps.512(<16 x float> %a0, <16 x float> %a1, i32 10)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x float> %1, <16 x float> %src
ret <16 x float> %3
@ -1654,7 +1654,7 @@ define <16 x float> @test_mm512_mask_add_round_ps_rz_sae(<16 x float> %a0, <16 x
; X86-NEXT: vaddps {rz-sae}, %zmm1, %zmm0, %zmm2 {%k1}
; X86-NEXT: vmovaps %zmm2, %zmm0
; X86-NEXT: retl
%1 = call <16 x float> @llvm.x86.avx512.add.ps.512(<16 x float> %a0, <16 x float> %a1, i32 3)
%1 = call <16 x float> @llvm.x86.avx512.add.ps.512(<16 x float> %a0, <16 x float> %a1, i32 11)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x float> %1, <16 x float> %src
ret <16 x float> %3
@ -1685,7 +1685,7 @@ define <16 x float> @test_mm512_add_round_ps_rn_sae(<16 x float> %a0, <16 x floa
; CHECK: # %bb.0:
; CHECK-NEXT: vaddps {rn-sae}, %zmm1, %zmm0, %zmm0
; CHECK-NEXT: ret{{[l|q]}}
%1 = call <16 x float> @llvm.x86.avx512.add.ps.512(<16 x float> %a0, <16 x float> %a1, i32 0)
%1 = call <16 x float> @llvm.x86.avx512.add.ps.512(<16 x float> %a0, <16 x float> %a1, i32 8)
ret <16 x float> %1
}
@ -1694,7 +1694,7 @@ define <16 x float> @test_mm512_add_round_ps_rd_sae(<16 x float> %a0, <16 x floa
; CHECK: # %bb.0:
; CHECK-NEXT: vaddps {rd-sae}, %zmm1, %zmm0, %zmm0
; CHECK-NEXT: ret{{[l|q]}}
%1 = call <16 x float> @llvm.x86.avx512.add.ps.512(<16 x float> %a0, <16 x float> %a1, i32 1)
%1 = call <16 x float> @llvm.x86.avx512.add.ps.512(<16 x float> %a0, <16 x float> %a1, i32 9)
ret <16 x float> %1
}
@ -1703,7 +1703,7 @@ define <16 x float> @test_mm512_add_round_ps_ru_sae(<16 x float> %a0, <16 x floa
; CHECK: # %bb.0:
; CHECK-NEXT: vaddps {ru-sae}, %zmm1, %zmm0, %zmm0
; CHECK-NEXT: ret{{[l|q]}}
%1 = call <16 x float> @llvm.x86.avx512.add.ps.512(<16 x float> %a0, <16 x float> %a1, i32 2)
%1 = call <16 x float> @llvm.x86.avx512.add.ps.512(<16 x float> %a0, <16 x float> %a1, i32 10)
ret <16 x float> %1
}
@ -1712,7 +1712,7 @@ define <16 x float> @test_mm512_add_round_ps_rz_sae(<16 x float> %a0, <16 x floa
; CHECK: # %bb.0:
; CHECK-NEXT: vaddps {rz-sae}, %zmm1, %zmm0, %zmm0
; CHECK-NEXT: ret{{[l|q]}}
%1 = call <16 x float> @llvm.x86.avx512.add.ps.512(<16 x float> %a0, <16 x float> %a1, i32 3)
%1 = call <16 x float> @llvm.x86.avx512.add.ps.512(<16 x float> %a0, <16 x float> %a1, i32 11)
ret <16 x float> %1
}
@ -1740,7 +1740,7 @@ define <16 x float> @test_mm512_mask_sub_round_ps_rn_sae(<16 x float> %a0, <16 x
; X86-NEXT: vsubps {rn-sae}, %zmm1, %zmm0, %zmm2 {%k1}
; X86-NEXT: vmovaps %zmm2, %zmm0
; X86-NEXT: retl
%1 = call <16 x float> @llvm.x86.avx512.sub.ps.512(<16 x float> %a0, <16 x float> %a1, i32 0)
%1 = call <16 x float> @llvm.x86.avx512.sub.ps.512(<16 x float> %a0, <16 x float> %a1, i32 8)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x float> %1, <16 x float> %src
ret <16 x float> %3
@ -1760,7 +1760,7 @@ define <16 x float> @test_mm512_mask_sub_round_ps_rd_sae(<16 x float> %a0, <16 x
; X86-NEXT: vsubps {rd-sae}, %zmm1, %zmm0, %zmm2 {%k1}
; X86-NEXT: vmovaps %zmm2, %zmm0
; X86-NEXT: retl
%1 = call <16 x float> @llvm.x86.avx512.sub.ps.512(<16 x float> %a0, <16 x float> %a1, i32 1)
%1 = call <16 x float> @llvm.x86.avx512.sub.ps.512(<16 x float> %a0, <16 x float> %a1, i32 9)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x float> %1, <16 x float> %src
ret <16 x float> %3
@ -1780,7 +1780,7 @@ define <16 x float> @test_mm512_mask_sub_round_ps_ru_sae(<16 x float> %a0, <16 x
; X86-NEXT: vsubps {ru-sae}, %zmm1, %zmm0, %zmm2 {%k1}
; X86-NEXT: vmovaps %zmm2, %zmm0
; X86-NEXT: retl
%1 = call <16 x float> @llvm.x86.avx512.sub.ps.512(<16 x float> %a0, <16 x float> %a1, i32 2)
%1 = call <16 x float> @llvm.x86.avx512.sub.ps.512(<16 x float> %a0, <16 x float> %a1, i32 10)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x float> %1, <16 x float> %src
ret <16 x float> %3
@ -1800,7 +1800,7 @@ define <16 x float> @test_mm512_mask_sub_round_ps_rz_sae(<16 x float> %a0, <16 x
; X86-NEXT: vsubps {rz-sae}, %zmm1, %zmm0, %zmm2 {%k1}
; X86-NEXT: vmovaps %zmm2, %zmm0
; X86-NEXT: retl
%1 = call <16 x float> @llvm.x86.avx512.sub.ps.512(<16 x float> %a0, <16 x float> %a1, i32 3)
%1 = call <16 x float> @llvm.x86.avx512.sub.ps.512(<16 x float> %a0, <16 x float> %a1, i32 11)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x float> %1, <16 x float> %src
ret <16 x float> %3
@ -1831,7 +1831,7 @@ define <16 x float> @test_mm512_sub_round_ps_rn_sae(<16 x float> %a0, <16 x floa
; CHECK: # %bb.0:
; CHECK-NEXT: vsubps {rn-sae}, %zmm1, %zmm0, %zmm0
; CHECK-NEXT: ret{{[l|q]}}
%1 = call <16 x float> @llvm.x86.avx512.sub.ps.512(<16 x float> %a0, <16 x float> %a1, i32 0)
%1 = call <16 x float> @llvm.x86.avx512.sub.ps.512(<16 x float> %a0, <16 x float> %a1, i32 8)
ret <16 x float> %1
}
@ -1840,7 +1840,7 @@ define <16 x float> @test_mm512_sub_round_ps_rd_sae(<16 x float> %a0, <16 x floa
; CHECK: # %bb.0:
; CHECK-NEXT: vsubps {rd-sae}, %zmm1, %zmm0, %zmm0
; CHECK-NEXT: ret{{[l|q]}}
%1 = call <16 x float> @llvm.x86.avx512.sub.ps.512(<16 x float> %a0, <16 x float> %a1, i32 1)
%1 = call <16 x float> @llvm.x86.avx512.sub.ps.512(<16 x float> %a0, <16 x float> %a1, i32 9)
ret <16 x float> %1
}
@ -1849,7 +1849,7 @@ define <16 x float> @test_mm512_sub_round_ps_ru_sae(<16 x float> %a0, <16 x floa
; CHECK: # %bb.0:
; CHECK-NEXT: vsubps {ru-sae}, %zmm1, %zmm0, %zmm0
; CHECK-NEXT: ret{{[l|q]}}
%1 = call <16 x float> @llvm.x86.avx512.sub.ps.512(<16 x float> %a0, <16 x float> %a1, i32 2)
%1 = call <16 x float> @llvm.x86.avx512.sub.ps.512(<16 x float> %a0, <16 x float> %a1, i32 10)
ret <16 x float> %1
}
@ -1858,7 +1858,7 @@ define <16 x float> @test_mm512_sub_round_ps_rz_sae(<16 x float> %a0, <16 x floa
; CHECK: # %bb.0:
; CHECK-NEXT: vsubps {rz-sae}, %zmm1, %zmm0, %zmm0
; CHECK-NEXT: ret{{[l|q]}}
%1 = call <16 x float> @llvm.x86.avx512.sub.ps.512(<16 x float> %a0, <16 x float> %a1, i32 3)
%1 = call <16 x float> @llvm.x86.avx512.sub.ps.512(<16 x float> %a0, <16 x float> %a1, i32 11)
ret <16 x float> %1
}
@ -1883,7 +1883,7 @@ define <16 x float> @test_mm512_maskz_div_round_ps_rn_sae(<16 x float> %a0, <16
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1
; X86-NEXT: vdivps {rn-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z}
; X86-NEXT: retl
%1 = call <16 x float> @llvm.x86.avx512.div.ps.512(<16 x float> %a0, <16 x float> %a1, i32 0)
%1 = call <16 x float> @llvm.x86.avx512.div.ps.512(<16 x float> %a0, <16 x float> %a1, i32 8)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x float> %1, <16 x float> zeroinitializer
ret <16 x float> %3
@ -1901,7 +1901,7 @@ define <16 x float> @test_mm512_maskz_div_round_ps_rd_sae(<16 x float> %a0, <16
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1
; X86-NEXT: vdivps {rd-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z}
; X86-NEXT: retl
%1 = call <16 x float> @llvm.x86.avx512.div.ps.512(<16 x float> %a0, <16 x float> %a1, i32 1)
%1 = call <16 x float> @llvm.x86.avx512.div.ps.512(<16 x float> %a0, <16 x float> %a1, i32 9)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x float> %1, <16 x float> zeroinitializer
ret <16 x float> %3
@ -1919,7 +1919,7 @@ define <16 x float> @test_mm512_maskz_div_round_ps_ru_sae(<16 x float> %a0, <16
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1
; X86-NEXT: vdivps {ru-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z}
; X86-NEXT: retl
%1 = call <16 x float> @llvm.x86.avx512.div.ps.512(<16 x float> %a0, <16 x float> %a1, i32 2)
%1 = call <16 x float> @llvm.x86.avx512.div.ps.512(<16 x float> %a0, <16 x float> %a1, i32 10)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x float> %1, <16 x float> zeroinitializer
ret <16 x float> %3
@ -1937,7 +1937,7 @@ define <16 x float> @test_mm512_maskz_div_round_ps_rz_sae(<16 x float> %a0, <16
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1
; X86-NEXT: vdivps {rz-sae}, %zmm1, %zmm0, %zmm0 {%k1} {z}
; X86-NEXT: retl
%1 = call <16 x float> @llvm.x86.avx512.div.ps.512(<16 x float> %a0, <16 x float> %a1, i32 3)
%1 = call <16 x float> @llvm.x86.avx512.div.ps.512(<16 x float> %a0, <16 x float> %a1, i32 11)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x float> %1, <16 x float> zeroinitializer
ret <16 x float> %3
@ -1975,7 +1975,7 @@ define <16 x float> @test_mm512_mask_div_round_ps_rn_sae(<16 x float> %a0, <16 x
; X86-NEXT: vdivps {rn-sae}, %zmm1, %zmm0, %zmm2 {%k1}
; X86-NEXT: vmovaps %zmm2, %zmm0
; X86-NEXT: retl
%1 = call <16 x float> @llvm.x86.avx512.div.ps.512(<16 x float> %a0, <16 x float> %a1, i32 0)
%1 = call <16 x float> @llvm.x86.avx512.div.ps.512(<16 x float> %a0, <16 x float> %a1, i32 8)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x float> %1, <16 x float> %src
ret <16 x float> %3
@ -1995,7 +1995,7 @@ define <16 x float> @test_mm512_mask_div_round_ps_rd_sae(<16 x float> %a0, <16 x
; X86-NEXT: vdivps {rd-sae}, %zmm1, %zmm0, %zmm2 {%k1}
; X86-NEXT: vmovaps %zmm2, %zmm0
; X86-NEXT: retl
%1 = call <16 x float> @llvm.x86.avx512.div.ps.512(<16 x float> %a0, <16 x float> %a1, i32 1)
%1 = call <16 x float> @llvm.x86.avx512.div.ps.512(<16 x float> %a0, <16 x float> %a1, i32 9)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x float> %1, <16 x float> %src
ret <16 x float> %3
@ -2015,7 +2015,7 @@ define <16 x float> @test_mm512_mask_div_round_ps_ru_sae(<16 x float> %a0, <16 x
; X86-NEXT: vdivps {ru-sae}, %zmm1, %zmm0, %zmm2 {%k1}
; X86-NEXT: vmovaps %zmm2, %zmm0
; X86-NEXT: retl
%1 = call <16 x float> @llvm.x86.avx512.div.ps.512(<16 x float> %a0, <16 x float> %a1, i32 2)
%1 = call <16 x float> @llvm.x86.avx512.div.ps.512(<16 x float> %a0, <16 x float> %a1, i32 10)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x float> %1, <16 x float> %src
ret <16 x float> %3
@ -2035,7 +2035,7 @@ define <16 x float> @test_mm512_mask_div_round_ps_rz_sae(<16 x float> %a0, <16 x
; X86-NEXT: vdivps {rz-sae}, %zmm1, %zmm0, %zmm2 {%k1}
; X86-NEXT: vmovaps %zmm2, %zmm0
; X86-NEXT: retl
%1 = call <16 x float> @llvm.x86.avx512.div.ps.512(<16 x float> %a0, <16 x float> %a1, i32 3)
%1 = call <16 x float> @llvm.x86.avx512.div.ps.512(<16 x float> %a0, <16 x float> %a1, i32 11)
%2 = bitcast i16 %mask to <16 x i1>
%3 = select <16 x i1> %2, <16 x float> %1, <16 x float> %src
ret <16 x float> %3
@ -2066,7 +2066,7 @@ define <16 x float> @test_mm512_div_round_ps_rn_sae(<16 x float> %a0, <16 x floa
; CHECK: # %bb.0:
; CHECK-NEXT: vdivps {rn-sae}, %zmm1, %zmm0, %zmm0
; CHECK-NEXT: ret{{[l|q]}}
%1 = call <16 x float> @llvm.x86.avx512.div.ps.512(<16 x float> %a0, <16 x float> %a1, i32 0)
%1 = call <16 x float> @llvm.x86.avx512.div.ps.512(<16 x float> %a0, <16 x float> %a1, i32 8)
ret <16 x float> %1
}
@ -2075,7 +2075,7 @@ define <16 x float> @test_mm512_div_round_ps_rd_sae(<16 x float> %a0, <16 x floa
; CHECK: # %bb.0:
; CHECK-NEXT: vdivps {rd-sae}, %zmm1, %zmm0, %zmm0
; CHECK-NEXT: ret{{[l|q]}}
%1 = call <16 x float> @llvm.x86.avx512.div.ps.512(<16 x float> %a0, <16 x float> %a1, i32 1)
%1 = call <16 x float> @llvm.x86.avx512.div.ps.512(<16 x float> %a0, <16 x float> %a1, i32 9)
ret <16 x float> %1
}
@ -2084,7 +2084,7 @@ define <16 x float> @test_mm512_div_round_ps_ru_sae(<16 x float> %a0, <16 x floa
; CHECK: # %bb.0:
; CHECK-NEXT: vdivps {ru-sae}, %zmm1, %zmm0, %zmm0
; CHECK-NEXT: ret{{[l|q]}}
%1 = call <16 x float> @llvm.x86.avx512.div.ps.512(<16 x float> %a0, <16 x float> %a1, i32 2)
%1 = call <16 x float> @llvm.x86.avx512.div.ps.512(<16 x float> %a0, <16 x float> %a1, i32 10)
ret <16 x float> %1
}
@ -2093,7 +2093,7 @@ define <16 x float> @test_mm512_div_round_ps_rz_sae(<16 x float> %a0, <16 x floa
; CHECK: # %bb.0:
; CHECK-NEXT: vdivps {rz-sae}, %zmm1, %zmm0, %zmm0
; CHECK-NEXT: ret{{[l|q]}}
%1 = call <16 x float> @llvm.x86.avx512.div.ps.512(<16 x float> %a0, <16 x float> %a1, i32 3)
%1 = call <16 x float> @llvm.x86.avx512.div.ps.512(<16 x float> %a0, <16 x float> %a1, i32 11)
ret <16 x float> %1
}
@ -2314,7 +2314,7 @@ define <4 x float> @test_mask_add_ss_rn(<4 x float> %a0, <4 x float> %a1, <4 x f
; X86-NEXT: vaddss {rn-sae}, %xmm1, %xmm0, %xmm2 {%k1}
; X86-NEXT: vmovaps %xmm2, %xmm0
; X86-NEXT: retl
%res = call <4 x float> @llvm.x86.avx512.mask.add.ss.round(<4 x float>%a0, <4 x float> %a1, <4 x float> %a2, i8 %mask, i32 0)
%res = call <4 x float> @llvm.x86.avx512.mask.add.ss.round(<4 x float>%a0, <4 x float> %a1, <4 x float> %a2, i8 %mask, i32 8)
ret <4 x float> %res
}
@ -2333,7 +2333,7 @@ define <4 x float> @test_mask_add_ss_rd(<4 x float> %a0, <4 x float> %a1, <4 x f
; X86-NEXT: vaddss {rd-sae}, %xmm1, %xmm0, %xmm2 {%k1}
; X86-NEXT: vmovaps %xmm2, %xmm0
; X86-NEXT: retl
%res = call <4 x float> @llvm.x86.avx512.mask.add.ss.round(<4 x float>%a0, <4 x float> %a1, <4 x float> %a2, i8 %mask, i32 1)
%res = call <4 x float> @llvm.x86.avx512.mask.add.ss.round(<4 x float>%a0, <4 x float> %a1, <4 x float> %a2, i8 %mask, i32 9)
ret <4 x float> %res
}
@ -2352,7 +2352,7 @@ define <4 x float> @test_mask_add_ss_ru(<4 x float> %a0, <4 x float> %a1, <4 x f
; X86-NEXT: vaddss {ru-sae}, %xmm1, %xmm0, %xmm2 {%k1}
; X86-NEXT: vmovaps %xmm2, %xmm0
; X86-NEXT: retl
%res = call <4 x float> @llvm.x86.avx512.mask.add.ss.round(<4 x float>%a0, <4 x float> %a1, <4 x float> %a2, i8 %mask, i32 2)
%res = call <4 x float> @llvm.x86.avx512.mask.add.ss.round(<4 x float>%a0, <4 x float> %a1, <4 x float> %a2, i8 %mask, i32 10)
ret <4 x float> %res
}
@ -2371,7 +2371,7 @@ define <4 x float> @test_mask_add_ss_rz(<4 x float> %a0, <4 x float> %a1, <4 x f
; X86-NEXT: vaddss {rz-sae}, %xmm1, %xmm0, %xmm2 {%k1}
; X86-NEXT: vmovaps %xmm2, %xmm0
; X86-NEXT: retl
%res = call <4 x float> @llvm.x86.avx512.mask.add.ss.round(<4 x float>%a0, <4 x float> %a1, <4 x float> %a2, i8 %mask, i32 3)
%res = call <4 x float> @llvm.x86.avx512.mask.add.ss.round(<4 x float>%a0, <4 x float> %a1, <4 x float> %a2, i8 %mask, i32 11)
ret <4 x float> %res
}
@ -2407,7 +2407,7 @@ define <4 x float> @test_maskz_add_ss_rn(<4 x float> %a0, <4 x float> %a1, i8 %m
; X86-NEXT: kmovw %eax, %k1
; X86-NEXT: vaddss {rn-sae}, %xmm1, %xmm0, %xmm0 {%k1} {z}
; X86-NEXT: retl
%res = call <4 x float> @llvm.x86.avx512.mask.add.ss.round(<4 x float>%a0, <4 x float> %a1, <4 x float> zeroinitializer, i8 %mask, i32 0)
%res = call <4 x float> @llvm.x86.avx512.mask.add.ss.round(<4 x float>%a0, <4 x float> %a1, <4 x float> zeroinitializer, i8 %mask, i32 8)
ret <4 x float> %res
}
@ -2416,7 +2416,7 @@ define <4 x float> @test_add_ss_rn(<4 x float> %a0, <4 x float> %a1) {
; CHECK: # %bb.0:
; CHECK-NEXT: vaddss {rn-sae}, %xmm1, %xmm0, %xmm0
; CHECK-NEXT: ret{{[l|q]}}
%res = call <4 x float> @llvm.x86.avx512.mask.add.ss.round(<4 x float>%a0, <4 x float> %a1, <4 x float> zeroinitializer, i8 -1, i32 0)
%res = call <4 x float> @llvm.x86.avx512.mask.add.ss.round(<4 x float>%a0, <4 x float> %a1, <4 x float> zeroinitializer, i8 -1, i32 8)
ret <4 x float> %res
}
@ -2485,7 +2485,7 @@ define <2 x double> @test_mask_add_sd_rn(<2 x double> %a0, <2 x double> %a1, <2
; X86-NEXT: vaddsd {rn-sae}, %xmm1, %xmm0, %xmm2 {%k1}
; X86-NEXT: vmovapd %xmm2, %xmm0
; X86-NEXT: retl
%res = call <2 x double> @llvm.x86.avx512.mask.add.sd.round(<2 x double>%a0, <2 x double> %a1, <2 x double> %a2, i8 %mask, i32 0)
%res = call <2 x double> @llvm.x86.avx512.mask.add.sd.round(<2 x double>%a0, <2 x double> %a1, <2 x double> %a2, i8 %mask, i32 8)
ret <2 x double> %res
}
@ -2504,7 +2504,7 @@ define <2 x double> @test_mask_add_sd_rd(<2 x double> %a0, <2 x double> %a1, <2
; X86-NEXT: vaddsd {rd-sae}, %xmm1, %xmm0, %xmm2 {%k1}
; X86-NEXT: vmovapd %xmm2, %xmm0
; X86-NEXT: retl
%res = call <2 x double> @llvm.x86.avx512.mask.add.sd.round(<2 x double>%a0, <2 x double> %a1, <2 x double> %a2, i8 %mask, i32 1)
%res = call <2 x double> @llvm.x86.avx512.mask.add.sd.round(<2 x double>%a0, <2 x double> %a1, <2 x double> %a2, i8 %mask, i32 9)
ret <2 x double> %res
}
@ -2523,7 +2523,7 @@ define <2 x double> @test_mask_add_sd_ru(<2 x double> %a0, <2 x double> %a1, <2
; X86-NEXT: vaddsd {ru-sae}, %xmm1, %xmm0, %xmm2 {%k1}
; X86-NEXT: vmovapd %xmm2, %xmm0
; X86-NEXT: retl
%res = call <2 x double> @llvm.x86.avx512.mask.add.sd.round(<2 x double>%a0, <2 x double> %a1, <2 x double> %a2, i8 %mask, i32 2)
%res = call <2 x double> @llvm.x86.avx512.mask.add.sd.round(<2 x double>%a0, <2 x double> %a1, <2 x double> %a2, i8 %mask, i32 10)
ret <2 x double> %res
}
@ -2542,7 +2542,7 @@ define <2 x double> @test_mask_add_sd_rz(<2 x double> %a0, <2 x double> %a1, <2
; X86-NEXT: vaddsd {rz-sae}, %xmm1, %xmm0, %xmm2 {%k1}
; X86-NEXT: vmovapd %xmm2, %xmm0
; X86-NEXT: retl
%res = call <2 x double> @llvm.x86.avx512.mask.add.sd.round(<2 x double>%a0, <2 x double> %a1, <2 x double> %a2, i8 %mask, i32 3)
%res = call <2 x double> @llvm.x86.avx512.mask.add.sd.round(<2 x double>%a0, <2 x double> %a1, <2 x double> %a2, i8 %mask, i32 11)
ret <2 x double> %res
}
@ -2578,7 +2578,7 @@ define <2 x double> @test_maskz_add_sd_rn(<2 x double> %a0, <2 x double> %a1, i8
; X86-NEXT: kmovw %eax, %k1
; X86-NEXT: vaddsd {rn-sae}, %xmm1, %xmm0, %xmm0 {%k1} {z}
; X86-NEXT: retl
%res = call <2 x double> @llvm.x86.avx512.mask.add.sd.round(<2 x double>%a0, <2 x double> %a1, <2 x double> zeroinitializer, i8 %mask, i32 0)
%res = call <2 x double> @llvm.x86.avx512.mask.add.sd.round(<2 x double>%a0, <2 x double> %a1, <2 x double> zeroinitializer, i8 %mask, i32 8)
ret <2 x double> %res
}
@ -2587,7 +2587,7 @@ define <2 x double> @test_add_sd_rn(<2 x double> %a0, <2 x double> %a1) {
; CHECK: # %bb.0:
; CHECK-NEXT: vaddsd {rn-sae}, %xmm1, %xmm0, %xmm0
; CHECK-NEXT: ret{{[l|q]}}
%res = call <2 x double> @llvm.x86.avx512.mask.add.sd.round(<2 x double>%a0, <2 x double> %a1, <2 x double> zeroinitializer, i8 -1, i32 0)
%res = call <2 x double> @llvm.x86.avx512.mask.add.sd.round(<2 x double>%a0, <2 x double> %a1, <2 x double> zeroinitializer, i8 -1, i32 8)
ret <2 x double> %res
}
@ -2921,7 +2921,7 @@ define <4 x float> @test_x86_avx512_cvtsi2ss32(<4 x float> %a, i32 %b) {
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: vcvtsi2ssl %eax, {rz-sae}, %xmm0, %xmm0
; X86-NEXT: retl
%res = call <4 x float> @llvm.x86.avx512.cvtsi2ss32(<4 x float> %a, i32 %b, i32 3) ; <<<4 x float>> [#uses=1]
%res = call <4 x float> @llvm.x86.avx512.cvtsi2ss32(<4 x float> %a, i32 %b, i32 11) ; <<<4 x float>> [#uses=1]
ret <4 x float> %res
}
declare <4 x float> @llvm.x86.avx512.cvtsi2ss32(<4 x float>, i32, i32) nounwind readnone
@ -2937,7 +2937,7 @@ define <4 x float> @test_x86_avx512__mm_cvt_roundu32_ss (<4 x float> %a, i32 %b)
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: vcvtusi2ssl %eax, {rd-sae}, %xmm0, %xmm0
; X86-NEXT: retl
%res = call <4 x float> @llvm.x86.avx512.cvtusi2ss(<4 x float> %a, i32 %b, i32 1) ; <<<4 x float>> [#uses=1]
%res = call <4 x float> @llvm.x86.avx512.cvtusi2ss(<4 x float> %a, i32 %b, i32 9) ; <<<4 x float>> [#uses=1]
ret <4 x float> %res
}
@ -2955,7 +2955,7 @@ define <4 x float> @test_x86_avx512__mm_cvt_roundu32_ss_mem(<4 x float> %a, i32*
; X86-NEXT: vcvtusi2ssl %eax, {rd-sae}, %xmm0, %xmm0
; X86-NEXT: retl
%b = load i32, i32* %ptr
%res = call <4 x float> @llvm.x86.avx512.cvtusi2ss(<4 x float> %a, i32 %b, i32 1) ; <<<4 x float>> [#uses=1]
%res = call <4 x float> @llvm.x86.avx512.cvtusi2ss(<4 x float> %a, i32 %b, i32 9) ; <<<4 x float>> [#uses=1]
ret <4 x float> %res
}
@ -3266,8 +3266,8 @@ define <8 x double>@test_int_x86_avx512_mask_scalef_pd_512(<8 x double> %x0, <8
; X86-NEXT: vscalefpd {rn-sae}, %zmm1, %zmm0, %zmm0
; X86-NEXT: vaddpd %zmm0, %zmm2, %zmm0
; X86-NEXT: retl
%res = call <8 x double> @llvm.x86.avx512.mask.scalef.pd.512(<8 x double> %x0, <8 x double> %x1, <8 x double> %x2, i8 %x3, i32 3)
%res1 = call <8 x double> @llvm.x86.avx512.mask.scalef.pd.512(<8 x double> %x0, <8 x double> %x1, <8 x double> %x2, i8 -1, i32 0)
%res = call <8 x double> @llvm.x86.avx512.mask.scalef.pd.512(<8 x double> %x0, <8 x double> %x1, <8 x double> %x2, i8 %x3, i32 11)
%res1 = call <8 x double> @llvm.x86.avx512.mask.scalef.pd.512(<8 x double> %x0, <8 x double> %x1, <8 x double> %x2, i8 -1, i32 8)
%res2 = fadd <8 x double> %res, %res1
ret <8 x double> %res2
}
@ -3289,8 +3289,8 @@ define <16 x float>@test_int_x86_avx512_mask_scalef_ps_512(<16 x float> %x0, <16
; X86-NEXT: vscalefps {rn-sae}, %zmm1, %zmm0, %zmm0
; X86-NEXT: vaddps %zmm0, %zmm2, %zmm0
; X86-NEXT: retl
%res = call <16 x float> @llvm.x86.avx512.mask.scalef.ps.512(<16 x float> %x0, <16 x float> %x1, <16 x float> %x2, i16 %x3, i32 2)
%res1 = call <16 x float> @llvm.x86.avx512.mask.scalef.ps.512(<16 x float> %x0, <16 x float> %x1, <16 x float> %x2, i16 -1, i32 0)
%res = call <16 x float> @llvm.x86.avx512.mask.scalef.ps.512(<16 x float> %x0, <16 x float> %x1, <16 x float> %x2, i16 %x3, i32 10)
%res1 = call <16 x float> @llvm.x86.avx512.mask.scalef.ps.512(<16 x float> %x0, <16 x float> %x1, <16 x float> %x2, i16 -1, i32 8)
%res2 = fadd <16 x float> %res, %res1
ret <16 x float> %res2
}
@ -4164,7 +4164,7 @@ define <16 x float>@test_int_x86_avx512_mask_cvt_dq2ps_512(<16 x i32> %x0, <16 x
%cvt = sitofp <16 x i32> %x0 to <16 x float>
%1 = bitcast i16 %x2 to <16 x i1>
%2 = select <16 x i1> %1, <16 x float> %cvt, <16 x float> %x1
%3 = call <16 x float> @llvm.x86.avx512.sitofp.round.v16f32.v16i32(<16 x i32> %x0, i32 0)
%3 = call <16 x float> @llvm.x86.avx512.sitofp.round.v16f32.v16i32(<16 x i32> %x0, i32 8)
%res2 = fadd <16 x float> %2, %3
ret <16 x float> %res2
}
@ -4189,7 +4189,7 @@ define <8 x i32>@test_int_x86_avx512_mask_cvt_pd2dq_512(<8 x double> %x0, <8 x i
; X86-NEXT: vpaddd %ymm0, %ymm1, %ymm0
; X86-NEXT: retl
%res = call <8 x i32> @llvm.x86.avx512.mask.cvtpd2dq.512(<8 x double> %x0, <8 x i32> %x1, i8 %x2, i32 4)
%res1 = call <8 x i32> @llvm.x86.avx512.mask.cvtpd2dq.512(<8 x double> %x0, <8 x i32> %x1, i8 -1, i32 0)
%res1 = call <8 x i32> @llvm.x86.avx512.mask.cvtpd2dq.512(<8 x double> %x0, <8 x i32> %x1, i8 -1, i32 8)
%res2 = add <8 x i32> %res, %res1
ret <8 x i32> %res2
}
@ -4214,7 +4214,7 @@ define <8 x float>@test_int_x86_avx512_mask_cvt_pd2ps_512(<8 x double> %x0, <8 x
; X86-NEXT: vaddps %ymm0, %ymm1, %ymm0
; X86-NEXT: retl
%res = call <8 x float> @llvm.x86.avx512.mask.cvtpd2ps.512(<8 x double> %x0, <8 x float> %x1, i8 %x2, i32 4)
%res1 = call <8 x float> @llvm.x86.avx512.mask.cvtpd2ps.512(<8 x double> %x0, <8 x float> %x1, i8 -1, i32 2)
%res1 = call <8 x float> @llvm.x86.avx512.mask.cvtpd2ps.512(<8 x double> %x0, <8 x float> %x1, i8 -1, i32 10)
%res2 = fadd <8 x float> %res, %res1
ret <8 x float> %res2
}
@ -4238,8 +4238,8 @@ define <8 x i32>@test_int_x86_avx512_mask_cvt_pd2udq_512(<8 x double> %x0, <8 x
; X86-NEXT: vcvtpd2udq {rn-sae}, %zmm0, %ymm0
; X86-NEXT: vpaddd %ymm0, %ymm1, %ymm0
; X86-NEXT: retl
%res = call <8 x i32> @llvm.x86.avx512.mask.cvtpd2udq.512(<8 x double> %x0, <8 x i32> %x1, i8 %x2, i32 2)
%res1 = call <8 x i32> @llvm.x86.avx512.mask.cvtpd2udq.512(<8 x double> %x0, <8 x i32> %x1, i8 -1, i32 0)
%res = call <8 x i32> @llvm.x86.avx512.mask.cvtpd2udq.512(<8 x double> %x0, <8 x i32> %x1, i8 %x2, i32 10)
%res1 = call <8 x i32> @llvm.x86.avx512.mask.cvtpd2udq.512(<8 x double> %x0, <8 x i32> %x1, i8 -1, i32 8)
%res2 = add <8 x i32> %res, %res1
ret <8 x i32> %res2
}
@ -4262,8 +4262,8 @@ define <16 x i32>@test_int_x86_avx512_mask_cvt_ps2dq_512(<16 x float> %x0, <16 x
; X86-NEXT: vcvtps2dq {rn-sae}, %zmm0, %zmm0
; X86-NEXT: vpaddd %zmm0, %zmm1, %zmm0
; X86-NEXT: retl
%res = call <16 x i32> @llvm.x86.avx512.mask.cvtps2dq.512(<16 x float> %x0, <16 x i32> %x1, i16 %x2, i32 2)
%res1 = call <16 x i32> @llvm.x86.avx512.mask.cvtps2dq.512(<16 x float> %x0, <16 x i32> %x1, i16 -1, i32 0)
%res = call <16 x i32> @llvm.x86.avx512.mask.cvtps2dq.512(<16 x float> %x0, <16 x i32> %x1, i16 %x2, i32 10)
%res1 = call <16 x i32> @llvm.x86.avx512.mask.cvtps2dq.512(<16 x float> %x0, <16 x i32> %x1, i16 -1, i32 8)
%res2 = add <16 x i32> %res, %res1
ret <16 x i32> %res2
}
@ -4311,8 +4311,8 @@ define <16 x i32>@test_int_x86_avx512_mask_cvt_ps2udq_512(<16 x float> %x0, <16
; X86-NEXT: vcvtps2udq {rn-sae}, %zmm0, %zmm0
; X86-NEXT: vpaddd %zmm0, %zmm1, %zmm0
; X86-NEXT: retl
%res = call <16 x i32> @llvm.x86.avx512.mask.cvtps2udq.512(<16 x float> %x0, <16 x i32> %x1, i16 %x2, i32 2)
%res1 = call <16 x i32> @llvm.x86.avx512.mask.cvtps2udq.512(<16 x float> %x0, <16 x i32> %x1, i16 -1, i32 0)
%res = call <16 x i32> @llvm.x86.avx512.mask.cvtps2udq.512(<16 x float> %x0, <16 x i32> %x1, i16 %x2, i32 10)
%res1 = call <16 x i32> @llvm.x86.avx512.mask.cvtps2udq.512(<16 x float> %x0, <16 x i32> %x1, i16 -1, i32 8)
%res2 = add <16 x i32> %res, %res1
ret <16 x i32> %res2
}
@ -4363,7 +4363,7 @@ define <16 x float>@test_int_x86_avx512_mask_cvt_udq2ps_512(<16 x i32> %x0, <16
%cvt = uitofp <16 x i32> %x0 to <16 x float>
%1 = bitcast i16 %x2 to <16 x i1>
%2 = select <16 x i1> %1, <16 x float> %cvt, <16 x float> %x1
%3 = call <16 x float> @llvm.x86.avx512.uitofp.round.v16f32.v16i32(<16 x i32> %x0, i32 0)
%3 = call <16 x float> @llvm.x86.avx512.uitofp.round.v16f32.v16i32(<16 x i32> %x0, i32 8)
%res2 = fadd <16 x float> %2, %3
ret <16 x float> %res2
}
@ -4990,7 +4990,7 @@ define <4 x float>@test_int_x86_avx512_mask_cvt_sd2ss_round(<4 x float> %x0,<2 x
; X86-NEXT: vcvtsd2ss {rn-sae}, %xmm1, %xmm0, %xmm0
; X86-NEXT: vaddps %xmm0, %xmm2, %xmm0
; X86-NEXT: retl
%res = call <4 x float> @llvm.x86.avx512.mask.cvtsd2ss.round(<4 x float> %x0, <2 x double> %x1, <4 x float> %x2, i8 %x3, i32 3)
%res = call <4 x float> @llvm.x86.avx512.mask.cvtsd2ss.round(<4 x float> %x0, <2 x double> %x1, <4 x float> %x2, i8 %x3, i32 11)
%res1 = call <4 x float> @llvm.x86.avx512.mask.cvtsd2ss.round(<4 x float> %x0, <2 x double> %x1, <4 x float> %x2, i8 -1, i32 8)
%res2 = fadd <4 x float> %res, %res1
ret <4 x float> %res2
@ -5712,12 +5712,12 @@ define <2 x double>@test_int_x86_avx512_mask_vfmadd_sd(<2 x double> %x0, <2 x do
%14 = extractelement <2 x double> %x0, i64 0
%15 = extractelement <2 x double> %x1, i64 0
%16 = extractelement <2 x double> %x2, i64 0
%17 = call double @llvm.x86.avx512.vfmadd.f64(double %14, double %15, double %16, i32 3)
%17 = call double @llvm.x86.avx512.vfmadd.f64(double %14, double %15, double %16, i32 11)
%18 = insertelement <2 x double> %x0, double %17, i64 0
%19 = extractelement <2 x double> %x0, i64 0
%20 = extractelement <2 x double> %x1, i64 0
%21 = extractelement <2 x double> %x2, i64 0
%22 = call double @llvm.x86.avx512.vfmadd.f64(double %19, double %20, double %21, i32 3)
%22 = call double @llvm.x86.avx512.vfmadd.f64(double %19, double %20, double %21, i32 11)
%23 = bitcast i8 %x3 to <8 x i1>
%24 = extractelement <8 x i1> %23, i64 0
%25 = select i1 %24, double %22, double %19
@ -5775,12 +5775,12 @@ define <4 x float>@test_int_x86_avx512_mask_vfmadd_ss(<4 x float> %x0, <4 x floa
%14 = extractelement <4 x float> %x0, i64 0
%15 = extractelement <4 x float> %x1, i64 0
%16 = extractelement <4 x float> %x2, i64 0
%17 = call float @llvm.x86.avx512.vfmadd.f32(float %14, float %15, float %16, i32 3)
%17 = call float @llvm.x86.avx512.vfmadd.f32(float %14, float %15, float %16, i32 11)
%18 = insertelement <4 x float> %x0, float %17, i64 0
%19 = extractelement <4 x float> %x0, i64 0
%20 = extractelement <4 x float> %x1, i64 0
%21 = extractelement <4 x float> %x2, i64 0
%22 = call float @llvm.x86.avx512.vfmadd.f32(float %19, float %20, float %21, i32 3)
%22 = call float @llvm.x86.avx512.vfmadd.f32(float %19, float %20, float %21, i32 11)
%23 = bitcast i8 %x3 to <8 x i1>
%24 = extractelement <8 x i1> %23, i64 0
%25 = select i1 %24, float %22, float %19
@ -5821,7 +5821,7 @@ define <2 x double>@test_int_x86_avx512_maskz_vfmadd_sd(<2 x double> %x0, <2 x d
%9 = extractelement <2 x double> %x0, i64 0
%10 = extractelement <2 x double> %x1, i64 0
%11 = extractelement <2 x double> %x2, i64 0
%12 = call double @llvm.x86.avx512.vfmadd.f64(double %9, double %10, double %11, i32 3)
%12 = call double @llvm.x86.avx512.vfmadd.f64(double %9, double %10, double %11, i32 11)
%13 = bitcast i8 %x3 to <8 x i1>
%14 = extractelement <8 x i1> %13, i64 0
%15 = select i1 %14, double %12, double 0.000000e+00
@ -5857,7 +5857,7 @@ define <4 x float>@test_int_x86_avx512_maskz_vfmadd_ss(<4 x float> %x0, <4 x flo
%9 = extractelement <4 x float> %x0, i64 0
%10 = extractelement <4 x float> %x1, i64 0
%11 = extractelement <4 x float> %x2, i64 0
%12 = call float @llvm.x86.avx512.vfmadd.f32(float %9, float %10, float %11, i32 3)
%12 = call float @llvm.x86.avx512.vfmadd.f32(float %9, float %10, float %11, i32 11)
%13 = bitcast i8 %x3 to <8 x i1>
%14 = extractelement <8 x i1> %13, i64 0
%15 = select i1 %14, float %12, float 0.000000e+00
@ -5913,12 +5913,12 @@ define <2 x double>@test_int_x86_avx512_mask3_vfmadd_sd(<2 x double> %x0, <2 x d
%14 = extractelement <2 x double> %x0, i64 0
%15 = extractelement <2 x double> %x1, i64 0
%16 = extractelement <2 x double> %x2, i64 0
%17 = call double @llvm.x86.avx512.vfmadd.f64(double %14, double %15, double %16, i32 3)
%17 = call double @llvm.x86.avx512.vfmadd.f64(double %14, double %15, double %16, i32 11)
%18 = insertelement <2 x double> %x2, double %17, i64 0
%19 = extractelement <2 x double> %x0, i64 0
%20 = extractelement <2 x double> %x1, i64 0
%21 = extractelement <2 x double> %x2, i64 0
%22 = call double @llvm.x86.avx512.vfmadd.f64(double %19, double %20, double %21, i32 3)
%22 = call double @llvm.x86.avx512.vfmadd.f64(double %19, double %20, double %21, i32 11)
%23 = bitcast i8 %x3 to <8 x i1>
%24 = extractelement <8 x i1> %23, i64 0
%25 = select i1 %24, double %22, double %21
@ -5976,12 +5976,12 @@ define <4 x float>@test_int_x86_avx512_mask3_vfmadd_ss(<4 x float> %x0, <4 x flo
%14 = extractelement <4 x float> %x0, i64 0
%15 = extractelement <4 x float> %x1, i64 0
%16 = extractelement <4 x float> %x2, i64 0
%17 = call float @llvm.x86.avx512.vfmadd.f32(float %14, float %15, float %16, i32 3)
%17 = call float @llvm.x86.avx512.vfmadd.f32(float %14, float %15, float %16, i32 11)
%18 = insertelement <4 x float> %x2, float %17, i64 0
%19 = extractelement <4 x float> %x0, i64 0
%20 = extractelement <4 x float> %x1, i64 0
%21 = extractelement <4 x float> %x2, i64 0
%22 = call float @llvm.x86.avx512.vfmadd.f32(float %19, float %20, float %21, i32 3)
%22 = call float @llvm.x86.avx512.vfmadd.f32(float %19, float %20, float %21, i32 11)
%23 = bitcast i8 %x3 to <8 x i1>
%24 = extractelement <8 x i1> %23, i64 0
%25 = select i1 %24, float %22, float %21
@ -6220,14 +6220,14 @@ define <2 x double>@test_int_x86_avx512_mask3_vfmsub_sd(<2 x double> %x0, <2 x d
%19 = extractelement <2 x double> %x0, i64 0
%20 = extractelement <2 x double> %x1, i64 0
%21 = extractelement <2 x double> %18, i64 0
%22 = call double @llvm.x86.avx512.vfmadd.f64(double %19, double %20, double %21, i32 3)
%22 = call double @llvm.x86.avx512.vfmadd.f64(double %19, double %20, double %21, i32 11)
%23 = extractelement <2 x double> %x2, i64 0
%24 = insertelement <2 x double> %x2, double %22, i64 0
%25 = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, %x2
%26 = extractelement <2 x double> %x0, i64 0
%27 = extractelement <2 x double> %x1, i64 0
%28 = extractelement <2 x double> %25, i64 0
%29 = call double @llvm.x86.avx512.vfmadd.f64(double %26, double %27, double %28, i32 3)
%29 = call double @llvm.x86.avx512.vfmadd.f64(double %26, double %27, double %28, i32 11)
%30 = extractelement <2 x double> %x2, i64 0
%31 = bitcast i8 %x3 to <8 x i1>
%32 = extractelement <8 x i1> %31, i64 0
@ -6291,14 +6291,14 @@ define <4 x float>@test_int_x86_avx512_mask3_vfmsub_ss(<4 x float> %x0, <4 x flo
%19 = extractelement <4 x float> %x0, i64 0
%20 = extractelement <4 x float> %x1, i64 0
%21 = extractelement <4 x float> %18, i64 0
%22 = call float @llvm.x86.avx512.vfmadd.f32(float %19, float %20, float %21, i32 3)
%22 = call float @llvm.x86.avx512.vfmadd.f32(float %19, float %20, float %21, i32 11)
%23 = extractelement <4 x float> %x2, i64 0
%24 = insertelement <4 x float> %x2, float %22, i64 0
%25 = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %x2
%26 = extractelement <4 x float> %x0, i64 0
%27 = extractelement <4 x float> %x1, i64 0
%28 = extractelement <4 x float> %25, i64 0
%29 = call float @llvm.x86.avx512.vfmadd.f32(float %26, float %27, float %28, i32 3)
%29 = call float @llvm.x86.avx512.vfmadd.f32(float %26, float %27, float %28, i32 11)
%30 = extractelement <4 x float> %x2, i64 0
%31 = bitcast i8 %x3 to <8 x i1>
%32 = extractelement <8 x i1> %31, i64 0
@ -6365,7 +6365,7 @@ define <2 x double>@test_int_x86_avx512_mask3_vfnmsub_sd(<2 x double> %x0, <2 x
%22 = extractelement <2 x double> %20, i64 0
%23 = extractelement <2 x double> %x1, i64 0
%24 = extractelement <2 x double> %21, i64 0
%25 = call double @llvm.x86.avx512.vfmadd.f64(double %22, double %23, double %24, i32 3)
%25 = call double @llvm.x86.avx512.vfmadd.f64(double %22, double %23, double %24, i32 11)
%26 = extractelement <2 x double> %x2, i64 0
%27 = insertelement <2 x double> %x2, double %25, i64 0
%28 = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, %x0
@ -6373,7 +6373,7 @@ define <2 x double>@test_int_x86_avx512_mask3_vfnmsub_sd(<2 x double> %x0, <2 x
%30 = extractelement <2 x double> %28, i64 0
%31 = extractelement <2 x double> %x1, i64 0
%32 = extractelement <2 x double> %29, i64 0
%33 = call double @llvm.x86.avx512.vfmadd.f64(double %30, double %31, double %32, i32 3)
%33 = call double @llvm.x86.avx512.vfmadd.f64(double %30, double %31, double %32, i32 11)
%34 = extractelement <2 x double> %x2, i64 0
%35 = bitcast i8 %x3 to <8 x i1>
%36 = extractelement <8 x i1> %35, i64 0
@ -6440,7 +6440,7 @@ define <4 x float>@test_int_x86_avx512_mask3_vfnmsub_ss(<4 x float> %x0, <4 x fl
%22 = extractelement <4 x float> %20, i64 0
%23 = extractelement <4 x float> %x1, i64 0
%24 = extractelement <4 x float> %21, i64 0
%25 = call float @llvm.x86.avx512.vfmadd.f32(float %22, float %23, float %24, i32 3)
%25 = call float @llvm.x86.avx512.vfmadd.f32(float %22, float %23, float %24, i32 11)
%26 = extractelement <4 x float> %x2, i64 0
%27 = insertelement <4 x float> %x2, float %25, i64 0
%28 = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %x0
@ -6448,7 +6448,7 @@ define <4 x float>@test_int_x86_avx512_mask3_vfnmsub_ss(<4 x float> %x0, <4 x fl
%30 = extractelement <4 x float> %28, i64 0
%31 = extractelement <4 x float> %x1, i64 0
%32 = extractelement <4 x float> %29, i64 0
%33 = call float @llvm.x86.avx512.vfmadd.f32(float %30, float %31, float %32, i32 3)
%33 = call float @llvm.x86.avx512.vfmadd.f32(float %30, float %31, float %32, i32 11)
%34 = extractelement <4 x float> %x2, i64 0
%35 = bitcast i8 %x3 to <8 x i1>
%36 = extractelement <8 x i1> %35, i64 0

8
llvm/test/CodeGen/X86/avx512dq-intrinsics-upgrade.ll
View File

@ -587,7 +587,7 @@ define <8 x double>@test_int_x86_avx512_mask_cvt_qq2pd_512(<8 x i64> %x0, <8 x d
; X64-NEXT: vaddpd %zmm0, %zmm1, %zmm0 # encoding: [0x62,0xf1,0xf5,0x48,0x58,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <8 x double> @llvm.x86.avx512.mask.cvtqq2pd.512(<8 x i64> %x0, <8 x double> %x1, i8 %x2, i32 4)
%res1 = call <8 x double> @llvm.x86.avx512.mask.cvtqq2pd.512(<8 x i64> %x0, <8 x double> %x1, i8 -1, i32 0)
%res1 = call <8 x double> @llvm.x86.avx512.mask.cvtqq2pd.512(<8 x i64> %x0, <8 x double> %x1, i8 -1, i32 8)
%res2 = fadd <8 x double> %res, %res1
ret <8 x double> %res2
}
@ -611,7 +611,7 @@ define <8 x float> @test_int_x86_avx512_mask_cvt_qq2ps_512(<8 x i64> %x0, <8 x f
; X64-NEXT: vaddps %ymm0, %ymm1, %ymm0 # encoding: [0xc5,0xf4,0x58,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <8 x float> @llvm.x86.avx512.mask.cvtqq2ps.512(<8 x i64> %x0, <8 x float> %x1, i8 %x2, i32 4)
%res1 = call <8 x float> @llvm.x86.avx512.mask.cvtqq2ps.512(<8 x i64> %x0, <8 x float> %x1, i8 -1, i32 0)
%res1 = call <8 x float> @llvm.x86.avx512.mask.cvtqq2ps.512(<8 x i64> %x0, <8 x float> %x1, i8 -1, i32 8)
%res2 = fadd <8 x float> %res, %res1
ret <8 x float> %res2
}
@ -635,7 +635,7 @@ define <8 x double> @test_int_x86_avx512_mask_cvt_uqq2pd_512(<8 x i64> %x0, <8 x
; X64-NEXT: vaddpd %zmm0, %zmm1, %zmm0 # encoding: [0x62,0xf1,0xf5,0x48,0x58,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <8 x double> @llvm.x86.avx512.mask.cvtuqq2pd.512(<8 x i64> %x0, <8 x double> %x1, i8 %x2, i32 4)
%res1 = call <8 x double> @llvm.x86.avx512.mask.cvtuqq2pd.512(<8 x i64> %x0, <8 x double> %x1, i8 -1, i32 0)
%res1 = call <8 x double> @llvm.x86.avx512.mask.cvtuqq2pd.512(<8 x i64> %x0, <8 x double> %x1, i8 -1, i32 8)
%res2 = fadd <8 x double> %res, %res1
ret <8 x double> %res2
}
@ -659,7 +659,7 @@ define <8 x float> @test_int_x86_avx512_mask_cvt_uqq2ps_512(<8 x i64> %x0, <8 x
; X64-NEXT: vaddps %ymm0, %ymm1, %ymm0 # encoding: [0xc5,0xf4,0x58,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <8 x float> @llvm.x86.avx512.mask.cvtuqq2ps.512(<8 x i64> %x0, <8 x float> %x1, i8 %x2, i32 4)
%res1 = call <8 x float> @llvm.x86.avx512.mask.cvtuqq2ps.512(<8 x i64> %x0, <8 x float> %x1, i8 -1, i32 0)
%res1 = call <8 x float> @llvm.x86.avx512.mask.cvtuqq2ps.512(<8 x i64> %x0, <8 x float> %x1, i8 -1, i32 8)
%res2 = fadd <8 x float> %res, %res1
ret <8 x float> %res2
}

24
llvm/test/CodeGen/X86/avx512dq-intrinsics.ll
View File

@ -134,8 +134,8 @@ define <8 x i64>@test_int_x86_avx512_mask_cvt_pd2qq_512(<8 x double> %x0, <8 x i
; X64-NEXT: vcvtpd2qq {rn-sae}, %zmm0, %zmm0 # encoding: [0x62,0xf1,0xfd,0x18,0x7b,0xc0]
; X64-NEXT: vpaddq %zmm0, %zmm1, %zmm0 # encoding: [0x62,0xf1,0xf5,0x48,0xd4,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <8 x i64> @llvm.x86.avx512.mask.cvtpd2qq.512(<8 x double> %x0, <8 x i64> %x1, i8 %x2, i32 2)
%res1 = call <8 x i64> @llvm.x86.avx512.mask.cvtpd2qq.512(<8 x double> %x0, <8 x i64> %x1, i8 -1, i32 0)
%res = call <8 x i64> @llvm.x86.avx512.mask.cvtpd2qq.512(<8 x double> %x0, <8 x i64> %x1, i8 %x2, i32 10)
%res1 = call <8 x i64> @llvm.x86.avx512.mask.cvtpd2qq.512(<8 x double> %x0, <8 x i64> %x1, i8 -1, i32 8)
%res2 = add <8 x i64> %res, %res1
ret <8 x i64> %res2
}
@ -158,8 +158,8 @@ define <8 x i64>@test_int_x86_avx512_mask_cvt_pd2uqq_512(<8 x double> %x0, <8 x
; X64-NEXT: vcvtpd2uqq {rn-sae}, %zmm0, %zmm0 # encoding: [0x62,0xf1,0xfd,0x18,0x79,0xc0]
; X64-NEXT: vpaddq %zmm0, %zmm1, %zmm0 # encoding: [0x62,0xf1,0xf5,0x48,0xd4,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <8 x i64> @llvm.x86.avx512.mask.cvtpd2uqq.512(<8 x double> %x0, <8 x i64> %x1, i8 %x2, i32 2)
%res1 = call <8 x i64> @llvm.x86.avx512.mask.cvtpd2uqq.512(<8 x double> %x0, <8 x i64> %x1, i8 -1, i32 0)
%res = call <8 x i64> @llvm.x86.avx512.mask.cvtpd2uqq.512(<8 x double> %x0, <8 x i64> %x1, i8 %x2, i32 10)
%res1 = call <8 x i64> @llvm.x86.avx512.mask.cvtpd2uqq.512(<8 x double> %x0, <8 x i64> %x1, i8 -1, i32 8)
%res2 = add <8 x i64> %res, %res1
ret <8 x i64> %res2
}
@ -182,8 +182,8 @@ define <8 x i64>@test_int_x86_avx512_mask_cvt_ps2qq_512(<8 x float> %x0, <8 x i6
; X64-NEXT: vcvtps2qq {rn-sae}, %ymm0, %zmm0 # encoding: [0x62,0xf1,0x7d,0x18,0x7b,0xc0]
; X64-NEXT: vpaddq %zmm0, %zmm1, %zmm0 # encoding: [0x62,0xf1,0xf5,0x48,0xd4,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <8 x i64> @llvm.x86.avx512.mask.cvtps2qq.512(<8 x float> %x0, <8 x i64> %x1, i8 %x2, i32 2)
%res1 = call <8 x i64> @llvm.x86.avx512.mask.cvtps2qq.512(<8 x float> %x0, <8 x i64> %x1, i8 -1, i32 0)
%res = call <8 x i64> @llvm.x86.avx512.mask.cvtps2qq.512(<8 x float> %x0, <8 x i64> %x1, i8 %x2, i32 10)
%res1 = call <8 x i64> @llvm.x86.avx512.mask.cvtps2qq.512(<8 x float> %x0, <8 x i64> %x1, i8 -1, i32 8)
%res2 = add <8 x i64> %res, %res1
ret <8 x i64> %res2
}
@ -206,8 +206,8 @@ define <8 x i64>@test_int_x86_avx512_mask_cvt_ps2uqq_512(<8 x float> %x0, <8 x i
; X64-NEXT: vcvtps2uqq {rn-sae}, %ymm0, %zmm0 # encoding: [0x62,0xf1,0x7d,0x18,0x79,0xc0]
; X64-NEXT: vpaddq %zmm0, %zmm1, %zmm0 # encoding: [0x62,0xf1,0xf5,0x48,0xd4,0xc0]
; X64-NEXT: retq # encoding: [0xc3]
%res = call <8 x i64> @llvm.x86.avx512.mask.cvtps2uqq.512(<8 x float> %x0, <8 x i64> %x1, i8 %x2, i32 2)
%res1 = call <8 x i64> @llvm.x86.avx512.mask.cvtps2uqq.512(<8 x float> %x0, <8 x i64> %x1, i8 -1, i32 0)
%res = call <8 x i64> @llvm.x86.avx512.mask.cvtps2uqq.512(<8 x float> %x0, <8 x i64> %x1, i8 %x2, i32 10)
%res1 = call <8 x i64> @llvm.x86.avx512.mask.cvtps2uqq.512(<8 x float> %x0, <8 x i64> %x1, i8 -1, i32 8)
%res2 = add <8 x i64> %res, %res1
ret <8 x i64> %res2
}
@ -233,7 +233,7 @@ define <8 x double>@test_int_x86_avx512_mask_cvt_qq2pd_512(<8 x i64> %x0, <8 x d
%cvt = sitofp <8 x i64> %x0 to <8 x double>
%1 = bitcast i8 %x2 to <8 x i1>
%2 = select <8 x i1> %1, <8 x double> %cvt, <8 x double> %x1
%3 = call <8 x double> @llvm.x86.avx512.sitofp.round.v8f64.v8i64(<8 x i64> %x0, i32 0)
%3 = call <8 x double> @llvm.x86.avx512.sitofp.round.v8f64.v8i64(<8 x i64> %x0, i32 8)
%res2 = fadd <8 x double> %2, %3
ret <8 x double> %res2
}
@ -275,7 +275,7 @@ define <8 x float>@test_int_x86_avx512_mask_cvt_qq2ps_512(<8 x i64> %x0, <8 x fl
%cvt = sitofp <8 x i64> %x0 to <8 x float>
%1 = bitcast i8 %x2 to <8 x i1>
%2 = select <8 x i1> %1, <8 x float> %cvt, <8 x float> %x1
%3 = call <8 x float> @llvm.x86.avx512.sitofp.round.v8f32.v8i64(<8 x i64> %x0, i32 0)
%3 = call <8 x float> @llvm.x86.avx512.sitofp.round.v8f32.v8i64(<8 x i64> %x0, i32 8)
%res2 = fadd <8 x float> %2, %3
ret <8 x float> %res2
}
@ -397,7 +397,7 @@ define <8 x double>@test_int_x86_avx512_mask_cvt_uqq2pd_512(<8 x i64> %x0, <8 x
%cvt = uitofp <8 x i64> %x0 to <8 x double>
%1 = bitcast i8 %x2 to <8 x i1>
%2 = select <8 x i1> %1, <8 x double> %cvt, <8 x double> %x1
%3 = call <8 x double> @llvm.x86.avx512.uitofp.round.v8f64.v8i64(<8 x i64> %x0, i32 0)
%3 = call <8 x double> @llvm.x86.avx512.uitofp.round.v8f64.v8i64(<8 x i64> %x0, i32 8)
%res2 = fadd <8 x double> %2, %3
ret <8 x double> %res2
}
@ -439,7 +439,7 @@ define <8 x float>@test_int_x86_avx512_mask_cvt_uqq2ps_512(<8 x i64> %x0, <8 x f
%cvt = uitofp <8 x i64> %x0 to <8 x float>
%1 = bitcast i8 %x2 to <8 x i1>
%2 = select <8 x i1> %1, <8 x float> %cvt, <8 x float> %x1
%3 = call <8 x float> @llvm.x86.avx512.uitofp.round.v8f32.v8i64(<8 x i64> %x0, i32 0)
%3 = call <8 x float> @llvm.x86.avx512.uitofp.round.v8f32.v8i64(<8 x i64> %x0, i32 8)
%res2 = fadd <8 x float> %2, %3
ret <8 x float> %res2
}

12
llvm/test/CodeGen/X86/fma-fneg-combine.ll
View File

@ -61,7 +61,7 @@ define <16 x float> @test5(<16 x float> %a, <16 x float> %b, <16 x float> %c) {
; CHECK-NEXT: retq
entry:
%sub.i = fsub <16 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %c
%0 = tail call <16 x float> @llvm.x86.avx512.vfmadd.ps.512(<16 x float> %a, <16 x float> %b, <16 x float> %sub.i, i32 2) #2
%0 = tail call <16 x float> @llvm.x86.avx512.vfmadd.ps.512(<16 x float> %a, <16 x float> %b, <16 x float> %sub.i, i32 10) #2
ret <16 x float> %0
}
@ -71,7 +71,7 @@ define <16 x float> @test6(<16 x float> %a, <16 x float> %b, <16 x float> %c) {
; CHECK-NEXT: vfmadd213ps {ru-sae}, %zmm2, %zmm1, %zmm0
; CHECK-NEXT: retq
entry:
%0 = tail call <16 x float> @llvm.x86.avx512.mask.vfnmsub.ps.512(<16 x float> %a, <16 x float> %b, <16 x float> %c, i16 -1, i32 2) #2
%0 = tail call <16 x float> @llvm.x86.avx512.mask.vfnmsub.ps.512(<16 x float> %a, <16 x float> %b, <16 x float> %c, i16 -1, i32 10) #2
%sub.i = fsub <16 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %0
ret <16 x float> %sub.i
}
@ -238,7 +238,7 @@ define <16 x float> @test14(<16 x float> %a, <16 x float> %b, <16 x float> %c, i
; KNL-NEXT: vpxord {{.*}}(%rip){1to16}, %zmm0, %zmm0
; KNL-NEXT: retq
entry:
%0 = tail call <16 x float> @llvm.x86.avx512.mask.vfnmsub.ps.512(<16 x float> %a, <16 x float> %b, <16 x float> %c, i16 %mask, i32 2) #2
%0 = tail call <16 x float> @llvm.x86.avx512.mask.vfnmsub.ps.512(<16 x float> %a, <16 x float> %b, <16 x float> %c, i16 %mask, i32 10) #2
%sub.i = fsub <16 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %0
ret <16 x float> %sub.i
}
@ -266,9 +266,9 @@ define <16 x float> @test15(<16 x float> %a, <16 x float> %b, <16 x float> %c, i
entry:
%bc = bitcast i16 %mask to <16 x i1>
%sub.i = fsub <16 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %a
%0 = tail call <16 x float> @llvm.x86.avx512.vfmadd.ps.512(<16 x float> %sub.i, <16 x float> %b, <16 x float> %c, i32 2)
%0 = tail call <16 x float> @llvm.x86.avx512.vfmadd.ps.512(<16 x float> %sub.i, <16 x float> %b, <16 x float> %c, i32 10)
%sel = select <16 x i1> %bc, <16 x float> %0, <16 x float> %sub.i
%1 = tail call <16 x float> @llvm.x86.avx512.vfmadd.ps.512(<16 x float> %sel, <16 x float> %sub.i, <16 x float> %c, i32 1)
%1 = tail call <16 x float> @llvm.x86.avx512.vfmadd.ps.512(<16 x float> %sel, <16 x float> %sub.i, <16 x float> %c, i32 9)
%sel2 = select <16 x i1> %bc, <16 x float> %1, <16 x float> %sel
ret <16 x float> %sel2
}
@ -286,7 +286,7 @@ define <16 x float> @test16(<16 x float> %a, <16 x float> %b, <16 x float> %c, i
; KNL-NEXT: vfmsubadd132ps {rd-sae}, %zmm1, %zmm2, %zmm0 {%k1}
; KNL-NEXT: retq
%sub.i = fsub <16 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %c
%res = call <16 x float> @llvm.x86.avx512.vfmaddsub.ps.512(<16 x float> %a, <16 x float> %b, <16 x float> %sub.i, i32 1)
%res = call <16 x float> @llvm.x86.avx512.vfmaddsub.ps.512(<16 x float> %a, <16 x float> %b, <16 x float> %sub.i, i32 9)
%bc = bitcast i16 %mask to <16 x i1>
%sel = select <16 x i1> %bc, <16 x float> %res, <16 x float> %a
ret <16 x float> %sel