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

[X86] Change vXi1 extract_vector_elt lowering to be legal if the index is 0. Add DAG combine to turn scalar_to_vector+extract_vector_elt into extract_subvector. 

We were lowering the last step extract_vector_elt to a bitcast+truncate. Change it to use an extract_vector_elt of index 0 instead. Add isel patterns to do the equivalent of what the bitcast would have done. Plus an isel pattern for an any_extend+extract to prevent some regressions.

Finally add a DAG combine to turn v1i1 scalar_to_vector+extract_vector_elt of 0 into an extract_subvector.

This fixes some of the regressions from D350800.

llvm-svn: 350918
This commit is contained in:
Craig Topper 2019-01-11 05:44:56 +00:00
parent d458ceda24
commit b97885cc2e
8 changed files with 133 additions and 146 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

46
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -16296,34 +16296,25 @@ static SDValue ExtractBitFromMaskVector(SDValue Op, SelectionDAG &DAG,
}
unsigned IdxVal = cast<ConstantSDNode>(Idx)->getZExtValue();
if (IdxVal == 0) // the operation is legal
return Op;
// If the kshift instructions of the correct width aren't natively supported
// then we need to promote the vector to the native size to get the correct
// zeroing behavior.
if (VecVT.getVectorNumElements() < 16) {
VecVT = MVT::v16i1;
Vec = DAG.getNode(ISD::INSERT_SUBVECTOR, dl, MVT::v16i1,
DAG.getUNDEF(VecVT), Vec,
// Extend to natively supported kshift.
unsigned NumElems = VecVT.getVectorNumElements();
MVT WideVecVT = VecVT;
if ((!Subtarget.hasDQI() && NumElems == 8) || NumElems < 8) {
WideVecVT = Subtarget.hasDQI() ? MVT::v8i1 : MVT::v16i1;
Vec = DAG.getNode(ISD::INSERT_SUBVECTOR, dl, WideVecVT,
DAG.getUNDEF(WideVecVT), Vec,
DAG.getIntPtrConstant(0, dl));
}
// Extracts from element 0 are always allowed.
if (IdxVal != 0) {
// Use kshiftr instruction to move to the lower element.
Vec = DAG.getNode(X86ISD::KSHIFTR, dl, VecVT, Vec,
DAG.getConstant(IdxVal, dl, MVT::i8));
}
// Use kshiftr instruction to move to the lower element.
Vec = DAG.getNode(X86ISD::KSHIFTR, dl, WideVecVT, Vec,
DAG.getConstant(IdxVal, dl, MVT::i8));
// Shrink to v16i1 since that's always legal.
if (VecVT.getVectorNumElements() > 16) {
VecVT = MVT::v16i1;
Vec = DAG.getNode(ISD::EXTRACT_SUBVECTOR, dl, VecVT, Vec,
DAG.getIntPtrConstant(0, dl));
}
// Convert to a bitcast+aext/trunc.
MVT CastVT = MVT::getIntegerVT(VecVT.getVectorNumElements());
return DAG.getAnyExtOrTrunc(DAG.getBitcast(CastVT, Vec), dl, EltVT);
return DAG.getNode(ISD::EXTRACT_VECTOR_ELT, dl, Op.getValueType(), Vec,
DAG.getIntPtrConstant(0, dl));
}
SDValue
@ -41413,6 +41404,15 @@ static SDValue combineScalarToVector(SDNode *N, SelectionDAG &DAG) {
return DAG.getNode(ISD::SCALAR_TO_VECTOR, SDLoc(N), MVT::v1i1,
Src.getOperand(0));
// Combine scalar_to_vector of an extract_vector_elt into an extract_subvec.
if (VT == MVT::v1i1 && Src.getOpcode() == ISD::EXTRACT_VECTOR_ELT &&
Src.hasOneUse() && Src.getOperand(0).getValueType().isVector() &&
Src.getOperand(0).getValueType().getVectorElementType() == MVT::i1)
if (auto *C = dyn_cast<ConstantSDNode>(Src.getOperand(1)))
if (C->isNullValue())
return DAG.getNode(ISD::EXTRACT_SUBVECTOR, SDLoc(N), VT,
Src.getOperand(0), Src.getOperand(1));
return SDValue();
}

11
llvm/lib/Target/X86/X86InstrAVX512.td
View File

@ -2889,6 +2889,11 @@ let Predicates = [HasAVX512] in {
(COPY_TO_REGCLASS (MOVZX32rm8 addr:$src), VK8)>;
}
def X86kextract : SDNode<"ISD::EXTRACT_VECTOR_ELT",
SDTypeProfile<1, 2, [SDTCisVT<0, i8>,
SDTCVecEltisVT<1, i1>,
SDTCisPtrTy<2>]>>;
let Predicates = [HasAVX512] in {
multiclass operation_gpr_mask_copy_lowering<RegisterClass maskRC, ValueType maskVT> {
def : Pat<(maskVT (scalar_to_vector GR32:$src)),
@ -2896,6 +2901,12 @@ let Predicates = [HasAVX512] in {
def : Pat<(maskVT (scalar_to_vector GR8:$src)),
(COPY_TO_REGCLASS (INSERT_SUBREG (i32 (IMPLICIT_DEF)), GR8:$src, sub_8bit), maskRC)>;
def : Pat<(i8 (X86kextract maskRC:$src, (iPTR 0))),
(EXTRACT_SUBREG (i32 (COPY_TO_REGCLASS maskRC:$src, GR32)), sub_8bit)>;
def : Pat<(i32 (anyext (i8 (X86kextract maskRC:$src, (iPTR 0))))),
(i32 (COPY_TO_REGCLASS maskRC:$src, GR32))>;
}
defm : operation_gpr_mask_copy_lowering<VK1, v1i1>;

4
llvm/test/CodeGen/X86/avx512-insert-extract.ll
View File

@ -270,7 +270,7 @@ define i64 @test14(<8 x i64>%a, <8 x i64>%b, i64 %a1, i64 %b1) {
; SKX: ## %bb.0:
; SKX-NEXT: movq %rdi, %rax
; SKX-NEXT: vpcmpgtq %zmm0, %zmm1, %k0
; SKX-NEXT: kshiftrw $4, %k0, %k0
; SKX-NEXT: kshiftrb $4, %k0, %k0
; SKX-NEXT: kmovd %k0, %ecx
; SKX-NEXT: testb $1, %cl
; SKX-NEXT: cmoveq %rsi, %rax
@ -976,7 +976,7 @@ define zeroext i8 @test_extractelement_v4i1(<4 x i32> %a, <4 x i32> %b) {
; SKX-LABEL: test_extractelement_v4i1:
; SKX: ## %bb.0:
; SKX-NEXT: vpcmpnleud %xmm1, %xmm0, %k0
; SKX-NEXT: kshiftrw $3, %k0, %k0
; SKX-NEXT: kshiftrb $3, %k0, %k0
; SKX-NEXT: kmovd %k0, %eax
; SKX-NEXT: andl $1, %eax
; SKX-NEXT: retq

82
llvm/test/CodeGen/X86/avx512-mask-op.ll
View File

@ -1281,19 +1281,15 @@ define <8 x i1> @test18(i8 %a, i16 %y) {
; KNL-NEXT: kmovw %edi, %k0
; KNL-NEXT: kmovw %esi, %k1
; KNL-NEXT: kshiftrw $8, %k1, %k2
; KNL-NEXT: kmovw %k2, %eax
; KNL-NEXT: kshiftrw $9, %k1, %k1
; KNL-NEXT: kmovw %k1, %ecx
; KNL-NEXT: kshiftrw $6, %k0, %k1
; KNL-NEXT: kmovw %ecx, %k2
; KNL-NEXT: kxorw %k2, %k1, %k1
; KNL-NEXT: kshiftrw $6, %k0, %k3
; KNL-NEXT: kxorw %k1, %k3, %k1
; KNL-NEXT: kshiftlw $15, %k1, %k1
; KNL-NEXT: kshiftrw $9, %k1, %k1
; KNL-NEXT: kxorw %k1, %k0, %k0
; KNL-NEXT: kshiftlw $9, %k0, %k0
; KNL-NEXT: kshiftrw $9, %k0, %k0
; KNL-NEXT: kmovw %eax, %k1
; KNL-NEXT: kshiftlw $7, %k1, %k1
; KNL-NEXT: kshiftlw $7, %k2, %k1
; KNL-NEXT: korw %k1, %k0, %k1
; KNL-NEXT: vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
; KNL-NEXT: vpmovdw %zmm0, %ymm0
@ -1303,37 +1299,37 @@ define <8 x i1> @test18(i8 %a, i16 %y) {
;
; SKX-LABEL: test18:
; SKX: ## %bb.0:
; SKX-NEXT: kmovd %edi, %k1
; SKX-NEXT: kmovd %esi, %k2
; SKX-NEXT: kshiftrw $8, %k2, %k0
; SKX-NEXT: kshiftrw $9, %k2, %k2
; SKX-NEXT: kshiftrb $6, %k1, %k3
; SKX-NEXT: kxorb %k2, %k3, %k2
; SKX-NEXT: kshiftlb $7, %k2, %k2
; SKX-NEXT: kshiftrb $1, %k2, %k2
; SKX-NEXT: kxorb %k2, %k1, %k1
; SKX-NEXT: kshiftlb $1, %k1, %k1
; SKX-NEXT: kmovd %edi, %k0
; SKX-NEXT: kmovd %esi, %k1
; SKX-NEXT: kshiftrw $8, %k1, %k2
; SKX-NEXT: kshiftrw $9, %k1, %k1
; SKX-NEXT: kshiftrb $6, %k0, %k3
; SKX-NEXT: kxorb %k1, %k3, %k1
; SKX-NEXT: kshiftlb $7, %k1, %k1
; SKX-NEXT: kshiftrb $1, %k1, %k1
; SKX-NEXT: kshiftlb $7, %k0, %k0
; SKX-NEXT: korb %k0, %k1, %k0
; SKX-NEXT: kxorb %k1, %k0, %k0
; SKX-NEXT: kshiftlb $1, %k0, %k0
; SKX-NEXT: kshiftrb $1, %k0, %k0
; SKX-NEXT: kshiftlb $7, %k2, %k1
; SKX-NEXT: korb %k1, %k0, %k0
; SKX-NEXT: vpmovm2w %k0, %xmm0
; SKX-NEXT: retq
;
; AVX512BW-LABEL: test18:
; AVX512BW: ## %bb.0:
; AVX512BW-NEXT: kmovd %edi, %k1
; AVX512BW-NEXT: kmovd %esi, %k2
; AVX512BW-NEXT: kshiftrw $8, %k2, %k0
; AVX512BW-NEXT: kshiftrw $9, %k2, %k2
; AVX512BW-NEXT: kshiftrw $6, %k1, %k3
; AVX512BW-NEXT: kxorw %k2, %k3, %k2
; AVX512BW-NEXT: kshiftlw $15, %k2, %k2
; AVX512BW-NEXT: kshiftrw $9, %k2, %k2
; AVX512BW-NEXT: kxorw %k2, %k1, %k1
; AVX512BW-NEXT: kshiftlw $9, %k1, %k1
; AVX512BW-NEXT: kmovd %edi, %k0
; AVX512BW-NEXT: kmovd %esi, %k1
; AVX512BW-NEXT: kshiftrw $8, %k1, %k2
; AVX512BW-NEXT: kshiftrw $9, %k1, %k1
; AVX512BW-NEXT: kshiftlw $7, %k0, %k0
; AVX512BW-NEXT: korw %k0, %k1, %k0
; AVX512BW-NEXT: kshiftrw $6, %k0, %k3
; AVX512BW-NEXT: kxorw %k1, %k3, %k1
; AVX512BW-NEXT: kshiftlw $15, %k1, %k1
; AVX512BW-NEXT: kshiftrw $9, %k1, %k1
; AVX512BW-NEXT: kxorw %k1, %k0, %k0
; AVX512BW-NEXT: kshiftlw $9, %k0, %k0
; AVX512BW-NEXT: kshiftrw $9, %k0, %k0
; AVX512BW-NEXT: kshiftlw $7, %k2, %k1
; AVX512BW-NEXT: korw %k1, %k0, %k0
; AVX512BW-NEXT: vpmovm2w %k0, %zmm0
; AVX512BW-NEXT: ## kill: def $xmm0 killed $xmm0 killed $zmm0
; AVX512BW-NEXT: vzeroupper
@ -1344,19 +1340,15 @@ define <8 x i1> @test18(i8 %a, i16 %y) {
; AVX512DQ-NEXT: kmovw %edi, %k0
; AVX512DQ-NEXT: kmovw %esi, %k1
; AVX512DQ-NEXT: kshiftrw $8, %k1, %k2
; AVX512DQ-NEXT: kmovw %k2, %eax
; AVX512DQ-NEXT: kshiftrw $9, %k1, %k1
; AVX512DQ-NEXT: kmovw %k1, %ecx
; AVX512DQ-NEXT: kshiftrb $6, %k0, %k1
; AVX512DQ-NEXT: kmovw %ecx, %k2
; AVX512DQ-NEXT: kxorb %k2, %k1, %k1
; AVX512DQ-NEXT: kshiftrb $6, %k0, %k3
; AVX512DQ-NEXT: kxorb %k1, %k3, %k1
; AVX512DQ-NEXT: kshiftlb $7, %k1, %k1
; AVX512DQ-NEXT: kshiftrb $1, %k1, %k1
; AVX512DQ-NEXT: kxorb %k1, %k0, %k0
; AVX512DQ-NEXT: kshiftlb $1, %k0, %k0
; AVX512DQ-NEXT: kshiftrb $1, %k0, %k0
; AVX512DQ-NEXT: kmovw %eax, %k1
; AVX512DQ-NEXT: kshiftlb $7, %k1, %k1
; AVX512DQ-NEXT: kshiftlb $7, %k2, %k1
; AVX512DQ-NEXT: korb %k1, %k0, %k0
; AVX512DQ-NEXT: vpmovm2d %k0, %zmm0
; AVX512DQ-NEXT: vpmovdw %zmm0, %ymm0
@ -1368,16 +1360,16 @@ define <8 x i1> @test18(i8 %a, i16 %y) {
; X86: ## %bb.0:
; X86-NEXT: kmovb {{[0-9]+}}(%esp), %k0
; X86-NEXT: kmovw {{[0-9]+}}(%esp), %k1
; X86-NEXT: kshiftrw $9, %k1, %k2
; X86-NEXT: kshiftrw $8, %k1, %k1
; X86-NEXT: kshiftlb $7, %k1, %k1
; X86-NEXT: kshiftrw $8, %k1, %k2
; X86-NEXT: kshiftrw $9, %k1, %k1
; X86-NEXT: kshiftrb $6, %k0, %k3
; X86-NEXT: kxorb %k2, %k3, %k2
; X86-NEXT: kshiftlb $7, %k2, %k2
; X86-NEXT: kshiftrb $1, %k2, %k2
; X86-NEXT: kxorb %k2, %k0, %k0
; X86-NEXT: kxorb %k1, %k3, %k1
; X86-NEXT: kshiftlb $7, %k1, %k1
; X86-NEXT: kshiftrb $1, %k1, %k1
; X86-NEXT: kxorb %k1, %k0, %k0
; X86-NEXT: kshiftlb $1, %k0, %k0
; X86-NEXT: kshiftrb $1, %k0, %k0
; X86-NEXT: kshiftlb $7, %k2, %k1
; X86-NEXT: korb %k1, %k0, %k0
; X86-NEXT: vpmovm2w %k0, %xmm0
; X86-NEXT: retl

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

@ -7300,37 +7300,37 @@ define <64 x i8> @vmov_test17(i64 %x, i32 %y, i32 %z) {
define <8 x i1> @vmov_test18(i8 %a, i16 %y) {
; GENERIC-LABEL: vmov_test18:
; GENERIC: # %bb.0:
; GENERIC-NEXT: kmovd %edi, %k1 # sched: [1:0.33]
; GENERIC-NEXT: kmovd %esi, %k2 # sched: [1:0.33]
; GENERIC-NEXT: kshiftrw $8, %k2, %k0 # sched: [1:1.00]
; GENERIC-NEXT: kshiftrw $9, %k2, %k2 # sched: [1:1.00]
; GENERIC-NEXT: kshiftrb $6, %k1, %k3 # sched: [1:1.00]
; GENERIC-NEXT: kxorb %k2, %k3, %k2 # sched: [1:0.33]
; GENERIC-NEXT: kshiftlb $7, %k2, %k2 # sched: [1:1.00]
; GENERIC-NEXT: kshiftrb $1, %k2, %k2 # sched: [1:1.00]
; GENERIC-NEXT: kxorb %k2, %k1, %k1 # sched: [1:0.33]
; GENERIC-NEXT: kshiftlb $1, %k1, %k1 # sched: [1:1.00]
; GENERIC-NEXT: kmovd %edi, %k0 # sched: [1:0.33]
; GENERIC-NEXT: kmovd %esi, %k1 # sched: [1:0.33]
; GENERIC-NEXT: kshiftrw $8, %k1, %k2 # sched: [1:1.00]
; GENERIC-NEXT: kshiftrw $9, %k1, %k1 # sched: [1:1.00]
; GENERIC-NEXT: kshiftrb $6, %k0, %k3 # sched: [1:1.00]
; GENERIC-NEXT: kxorb %k1, %k3, %k1 # sched: [1:0.33]
; GENERIC-NEXT: kshiftlb $7, %k1, %k1 # sched: [1:1.00]
; GENERIC-NEXT: kshiftrb $1, %k1, %k1 # sched: [1:1.00]
; GENERIC-NEXT: kshiftlb $7, %k0, %k0 # sched: [1:1.00]
; GENERIC-NEXT: korb %k0, %k1, %k0 # sched: [1:0.33]
; GENERIC-NEXT: kxorb %k1, %k0, %k0 # sched: [1:0.33]
; GENERIC-NEXT: kshiftlb $1, %k0, %k0 # sched: [1:1.00]
; GENERIC-NEXT: kshiftrb $1, %k0, %k0 # sched: [1:1.00]
; GENERIC-NEXT: kshiftlb $7, %k2, %k1 # sched: [1:1.00]
; GENERIC-NEXT: korb %k1, %k0, %k0 # sched: [1:0.33]
; GENERIC-NEXT: vpmovm2w %k0, %xmm0 # sched: [1:0.33]
; GENERIC-NEXT: retq # sched: [1:1.00]
;
; SKX-LABEL: vmov_test18:
; SKX: # %bb.0:
; SKX-NEXT: kmovd %edi, %k1 # sched: [1:1.00]
; SKX-NEXT: kmovd %esi, %k2 # sched: [1:1.00]
; SKX-NEXT: kshiftrw $8, %k2, %k0 # sched: [3:1.00]
; SKX-NEXT: kshiftrw $9, %k2, %k2 # sched: [3:1.00]
; SKX-NEXT: kshiftrb $6, %k1, %k3 # sched: [3:1.00]
; SKX-NEXT: kxorb %k2, %k3, %k2 # sched: [1:1.00]
; SKX-NEXT: kshiftlb $7, %k2, %k2 # sched: [3:1.00]
; SKX-NEXT: kshiftrb $1, %k2, %k2 # sched: [3:1.00]
; SKX-NEXT: kxorb %k2, %k1, %k1 # sched: [1:1.00]
; SKX-NEXT: kshiftlb $1, %k1, %k1 # sched: [3:1.00]
; SKX-NEXT: kmovd %edi, %k0 # sched: [1:1.00]
; SKX-NEXT: kmovd %esi, %k1 # sched: [1:1.00]
; SKX-NEXT: kshiftrw $8, %k1, %k2 # sched: [3:1.00]
; SKX-NEXT: kshiftrw $9, %k1, %k1 # sched: [3:1.00]
; SKX-NEXT: kshiftrb $6, %k0, %k3 # sched: [3:1.00]
; SKX-NEXT: kxorb %k1, %k3, %k1 # sched: [1:1.00]
; SKX-NEXT: kshiftlb $7, %k1, %k1 # sched: [3:1.00]
; SKX-NEXT: kshiftrb $1, %k1, %k1 # sched: [3:1.00]
; SKX-NEXT: kshiftlb $7, %k0, %k0 # sched: [3:1.00]
; SKX-NEXT: korb %k0, %k1, %k0 # sched: [1:1.00]
; SKX-NEXT: kxorb %k1, %k0, %k0 # sched: [1:1.00]
; SKX-NEXT: kshiftlb $1, %k0, %k0 # sched: [3:1.00]
; SKX-NEXT: kshiftrb $1, %k0, %k0 # sched: [3:1.00]
; SKX-NEXT: kshiftlb $7, %k2, %k1 # sched: [3:1.00]
; SKX-NEXT: korb %k1, %k0, %k0 # sched: [1:1.00]
; SKX-NEXT: vpmovm2w %k0, %xmm0 # sched: [1:0.25]
; SKX-NEXT: retq # sched: [7:1.00]
%b = bitcast i8 %a to <8 x i1>

8
llvm/test/CodeGen/X86/masked_gather_scatter.ll
View File

@ -1743,7 +1743,7 @@ define <3 x i32> @test30(<3 x i32*> %base, <3 x i32> %ind, <3 x i1> %mask, <3 x
; SKX-NEXT: vmovq %xmm0, %rax
; SKX-NEXT: vpinsrd $0, (%rax), %xmm3, %xmm3
; SKX-NEXT: .LBB31_2: # %else
; SKX-NEXT: kshiftrw $1, %k0, %k1
; SKX-NEXT: kshiftrb $1, %k0, %k1
; SKX-NEXT: kmovw %k1, %eax
; SKX-NEXT: testb $1, %al
; SKX-NEXT: je .LBB31_4
@ -1751,7 +1751,7 @@ define <3 x i32> @test30(<3 x i32*> %base, <3 x i32> %ind, <3 x i1> %mask, <3 x
; SKX-NEXT: vpextrq $1, %xmm0, %rax
; SKX-NEXT: vpinsrd $1, (%rax), %xmm3, %xmm3
; SKX-NEXT: .LBB31_4: # %else2
; SKX-NEXT: kshiftrw $2, %k0, %k0
; SKX-NEXT: kshiftrb $2, %k0, %k0
; SKX-NEXT: kmovw %k0, %eax
; SKX-NEXT: testb $1, %al
; SKX-NEXT: je .LBB31_6
@ -1781,7 +1781,7 @@ define <3 x i32> @test30(<3 x i32*> %base, <3 x i32> %ind, <3 x i1> %mask, <3 x
; SKX_32-NEXT: vmovd %xmm1, %eax
; SKX_32-NEXT: vpinsrd $0, (%eax), %xmm0, %xmm0
; SKX_32-NEXT: .LBB31_2: # %else
; SKX_32-NEXT: kshiftrw $1, %k0, %k1
; SKX_32-NEXT: kshiftrb $1, %k0, %k1
; SKX_32-NEXT: kmovw %k1, %eax
; SKX_32-NEXT: testb $1, %al
; SKX_32-NEXT: je .LBB31_4
@ -1789,7 +1789,7 @@ define <3 x i32> @test30(<3 x i32*> %base, <3 x i32> %ind, <3 x i1> %mask, <3 x
; SKX_32-NEXT: vpextrd $1, %xmm1, %eax
; SKX_32-NEXT: vpinsrd $1, (%eax), %xmm0, %xmm0
; SKX_32-NEXT: .LBB31_4: # %else2
; SKX_32-NEXT: kshiftrw $2, %k0, %k0
; SKX_32-NEXT: kshiftrb $2, %k0, %k0
; SKX_32-NEXT: kmovw %k0, %eax
; SKX_32-NEXT: testb $1, %al
; SKX_32-NEXT: je .LBB31_6

32
llvm/test/CodeGen/X86/pr33349.ll
View File

@ -12,32 +12,32 @@ target triple = "x86_64-unknown-linux-gnu"
; KNL-NEXT: vptestmd %zmm0, %zmm0, %k0
; KNL-NEXT: kshiftrw $1, %k0, %k1
; KNL-NEXT: kmovw %k1, %eax
; KNL-NEXT: kshiftrw $2, %k0, %k1
; KNL-NEXT: kshiftrw $1, %k1, %k2
; KNL-NEXT: kmovw %k1, %ecx
; KNL-NEXT: testb $1, %al
; KNL-NEXT: fld1
; KNL-NEXT: fldz
; KNL-NEXT: fld %st(0)
; KNL-NEXT: fcmovne %st(2), %st(0)
; KNL-NEXT: kshiftrw $2, %k0, %k1
; KNL-NEXT: kshiftrw $1, %k1, %k2
; KNL-NEXT: kmovw %k2, %eax
; KNL-NEXT: testb $1, %al
; KNL-NEXT: testb $1, %cl
; KNL-NEXT: fld %st(1)
; KNL-NEXT: fcmovne %st(3), %st(0)
; KNL-NEXT: kmovw %k0, %eax
; KNL-NEXT: kmovw %k2, %eax
; KNL-NEXT: testb $1, %al
; KNL-NEXT: fld %st(2)
; KNL-NEXT: fcmovne %st(4), %st(0)
; KNL-NEXT: kmovw %k1, %eax
; KNL-NEXT: kmovw %k0, %eax
; KNL-NEXT: testb $1, %al
; KNL-NEXT: fxch %st(3)
; KNL-NEXT: fcmovne %st(4), %st(0)
; KNL-NEXT: fstp %st(4)
; KNL-NEXT: fxch %st(3)
; KNL-NEXT: fstpt 20(%rdi)
; KNL-NEXT: fxch %st(1)
; KNL-NEXT: fstpt (%rdi)
; KNL-NEXT: fxch %st(1)
; KNL-NEXT: fstpt 30(%rdi)
; KNL-NEXT: fxch %st(1)
; KNL-NEXT: fstpt 20(%rdi)
; KNL-NEXT: fstpt 10(%rdi)
; KNL-NEXT: vzeroupper
; KNL-NEXT: retq
@ -46,20 +46,20 @@ target triple = "x86_64-unknown-linux-gnu"
; SKX: # %bb.0: # %bb
; SKX-NEXT: vpslld $31, %xmm0, %xmm0
; SKX-NEXT: vpmovd2m %xmm0, %k0
; SKX-NEXT: kshiftrb $1, %k0, %k1
; SKX-NEXT: kmovd %k1, %eax
; SKX-NEXT: kshiftrb $2, %k0, %k1
; SKX-NEXT: kshiftrw $1, %k1, %k2
; SKX-NEXT: kmovd %k2, %eax
; SKX-NEXT: kshiftrb $1, %k1, %k2
; SKX-NEXT: kmovd %k1, %ecx
; SKX-NEXT: testb $1, %al
; SKX-NEXT: fld1
; SKX-NEXT: fldz
; SKX-NEXT: fld %st(0)
; SKX-NEXT: fcmovne %st(2), %st(0)
; SKX-NEXT: kmovd %k1, %eax
; SKX-NEXT: testb $1, %al
; SKX-NEXT: testb $1, %cl
; SKX-NEXT: fld %st(1)
; SKX-NEXT: fcmovne %st(3), %st(0)
; SKX-NEXT: kshiftrw $1, %k0, %k1
; SKX-NEXT: kmovd %k1, %eax
; SKX-NEXT: kmovd %k2, %eax
; SKX-NEXT: testb $1, %al
; SKX-NEXT: fld %st(2)
; SKX-NEXT: fcmovne %st(4), %st(0)
@ -71,10 +71,10 @@ target triple = "x86_64-unknown-linux-gnu"
; SKX-NEXT: fxch %st(3)
; SKX-NEXT: fstpt (%rdi)
; SKX-NEXT: fxch %st(1)
; SKX-NEXT: fstpt 10(%rdi)
; SKX-NEXT: fstpt 30(%rdi)
; SKX-NEXT: fxch %st(1)
; SKX-NEXT: fstpt 20(%rdi)
; SKX-NEXT: fstpt 30(%rdi)
; SKX-NEXT: fstpt 10(%rdi)
; SKX-NEXT: retq
bb:
%tmp = select <4 x i1> %m, <4 x x86_fp80> <x86_fp80 0xK3FFF8000000000000000, x86_fp80 0xK3FFF8000000000000000, x86_fp80 0xK3FFF8000000000000000, x86_fp80 0xK3FFF8000000000000000>, <4 x x86_fp80> zeroinitializer

48
llvm/test/CodeGen/X86/vec_floor.ll
View File

@ -1694,8 +1694,7 @@ define <4 x float> @floor_mask_ss_mask8(<4 x float> %x, <4 x float> %y, <4 x flo
; AVX512F: ## %bb.0:
; AVX512F-NEXT: ## kill: def $xmm1 killed $xmm1 def $zmm1
; AVX512F-NEXT: ## kill: def $xmm0 killed $xmm0 def $zmm0
; AVX512F-NEXT: vcmpeqps %zmm1, %zmm0, %k0
; AVX512F-NEXT: kmovw %k0, %k1
; AVX512F-NEXT: vcmpeqps %zmm1, %zmm0, %k1
; AVX512F-NEXT: vrndscaless $1, %xmm0, %xmm1, %xmm2 {%k1}
; AVX512F-NEXT: vmovaps %xmm2, %xmm0
; AVX512F-NEXT: vzeroupper
@ -1703,8 +1702,7 @@ define <4 x float> @floor_mask_ss_mask8(<4 x float> %x, <4 x float> %y, <4 x flo
;
; AVX512VL-LABEL: floor_mask_ss_mask8:
; AVX512VL: ## %bb.0:
; AVX512VL-NEXT: vcmpeqps %xmm1, %xmm0, %k0
; AVX512VL-NEXT: kmovw %k0, %k1
; AVX512VL-NEXT: vcmpeqps %xmm1, %xmm0, %k1
; AVX512VL-NEXT: vrndscaless $1, %xmm0, %xmm1, %xmm2 {%k1}
; AVX512VL-NEXT: vmovaps %xmm2, %xmm0
; AVX512VL-NEXT: retq
@ -1755,16 +1753,14 @@ define <4 x float> @floor_maskz_ss_mask8(<4 x float> %x, <4 x float> %y) nounwin
; AVX512F: ## %bb.0:
; AVX512F-NEXT: ## kill: def $xmm1 killed $xmm1 def $zmm1
; AVX512F-NEXT: ## kill: def $xmm0 killed $xmm0 def $zmm0
; AVX512F-NEXT: vcmpeqps %zmm1, %zmm0, %k0
; AVX512F-NEXT: kmovw %k0, %k1
; AVX512F-NEXT: vcmpeqps %zmm1, %zmm0, %k1
; AVX512F-NEXT: vrndscaless $1, %xmm0, %xmm1, %xmm0 {%k1} {z}
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: floor_maskz_ss_mask8:
; AVX512VL: ## %bb.0:
; AVX512VL-NEXT: vcmpeqps %xmm1, %xmm0, %k0
; AVX512VL-NEXT: kmovw %k0, %k1
; AVX512VL-NEXT: vcmpeqps %xmm1, %xmm0, %k1
; AVX512VL-NEXT: vrndscaless $1, %xmm0, %xmm1, %xmm0 {%k1} {z}
; AVX512VL-NEXT: retq
%mask1 = fcmp oeq <4 x float> %x, %y
@ -1808,8 +1804,7 @@ define <2 x double> @floor_mask_sd_mask8(<2 x double> %x, <2 x double> %y, <2 x
; AVX512F: ## %bb.0:
; AVX512F-NEXT: ## kill: def $xmm1 killed $xmm1 def $zmm1
; AVX512F-NEXT: ## kill: def $xmm0 killed $xmm0 def $zmm0
; AVX512F-NEXT: vcmpeqpd %zmm1, %zmm0, %k0
; AVX512F-NEXT: kmovw %k0, %k1
; AVX512F-NEXT: vcmpeqpd %zmm1, %zmm0, %k1
; AVX512F-NEXT: vrndscalesd $1, %xmm0, %xmm1, %xmm2 {%k1}
; AVX512F-NEXT: vmovapd %xmm2, %xmm0
; AVX512F-NEXT: vzeroupper
@ -1817,8 +1812,7 @@ define <2 x double> @floor_mask_sd_mask8(<2 x double> %x, <2 x double> %y, <2 x
;
; AVX512VL-LABEL: floor_mask_sd_mask8:
; AVX512VL: ## %bb.0:
; AVX512VL-NEXT: vcmpeqpd %xmm1, %xmm0, %k0
; AVX512VL-NEXT: kmovw %k0, %k1
; AVX512VL-NEXT: vcmpeqpd %xmm1, %xmm0, %k1
; AVX512VL-NEXT: vrndscalesd $1, %xmm0, %xmm1, %xmm2 {%k1}
; AVX512VL-NEXT: vmovapd %xmm2, %xmm0
; AVX512VL-NEXT: retq
@ -1869,16 +1863,14 @@ define <2 x double> @floor_maskz_sd_mask8(<2 x double> %x, <2 x double> %y) noun
; AVX512F: ## %bb.0:
; AVX512F-NEXT: ## kill: def $xmm1 killed $xmm1 def $zmm1
; AVX512F-NEXT: ## kill: def $xmm0 killed $xmm0 def $zmm0
; AVX512F-NEXT: vcmpeqpd %zmm1, %zmm0, %k0
; AVX512F-NEXT: kmovw %k0, %k1
; AVX512F-NEXT: vcmpeqpd %zmm1, %zmm0, %k1
; AVX512F-NEXT: vrndscalesd $1, %xmm0, %xmm1, %xmm0 {%k1} {z}
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: floor_maskz_sd_mask8:
; AVX512VL: ## %bb.0:
; AVX512VL-NEXT: vcmpeqpd %xmm1, %xmm0, %k0
; AVX512VL-NEXT: kmovw %k0, %k1
; AVX512VL-NEXT: vcmpeqpd %xmm1, %xmm0, %k1
; AVX512VL-NEXT: vrndscalesd $1, %xmm0, %xmm1, %xmm0 {%k1} {z}
; AVX512VL-NEXT: retq
%mask1 = fcmp oeq <2 x double> %x, %y
@ -2766,8 +2758,7 @@ define <4 x float> @ceil_mask_ss_mask8(<4 x float> %x, <4 x float> %y, <4 x floa
; AVX512F: ## %bb.0:
; AVX512F-NEXT: ## kill: def $xmm1 killed $xmm1 def $zmm1
; AVX512F-NEXT: ## kill: def $xmm0 killed $xmm0 def $zmm0
; AVX512F-NEXT: vcmpeqps %zmm1, %zmm0, %k0
; AVX512F-NEXT: kmovw %k0, %k1
; AVX512F-NEXT: vcmpeqps %zmm1, %zmm0, %k1
; AVX512F-NEXT: vrndscaless $2, %xmm0, %xmm1, %xmm2 {%k1}
; AVX512F-NEXT: vmovaps %xmm2, %xmm0
; AVX512F-NEXT: vzeroupper
@ -2775,8 +2766,7 @@ define <4 x float> @ceil_mask_ss_mask8(<4 x float> %x, <4 x float> %y, <4 x floa
;
; AVX512VL-LABEL: ceil_mask_ss_mask8:
; AVX512VL: ## %bb.0:
; AVX512VL-NEXT: vcmpeqps %xmm1, %xmm0, %k0
; AVX512VL-NEXT: kmovw %k0, %k1
; AVX512VL-NEXT: vcmpeqps %xmm1, %xmm0, %k1
; AVX512VL-NEXT: vrndscaless $2, %xmm0, %xmm1, %xmm2 {%k1}
; AVX512VL-NEXT: vmovaps %xmm2, %xmm0
; AVX512VL-NEXT: retq
@ -2827,16 +2817,14 @@ define <4 x float> @ceil_maskz_ss_mask8(<4 x float> %x, <4 x float> %y) nounwind
; AVX512F: ## %bb.0:
; AVX512F-NEXT: ## kill: def $xmm1 killed $xmm1 def $zmm1
; AVX512F-NEXT: ## kill: def $xmm0 killed $xmm0 def $zmm0
; AVX512F-NEXT: vcmpeqps %zmm1, %zmm0, %k0
; AVX512F-NEXT: kmovw %k0, %k1
; AVX512F-NEXT: vcmpeqps %zmm1, %zmm0, %k1
; AVX512F-NEXT: vrndscaless $2, %xmm0, %xmm1, %xmm0 {%k1} {z}
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: ceil_maskz_ss_mask8:
; AVX512VL: ## %bb.0:
; AVX512VL-NEXT: vcmpeqps %xmm1, %xmm0, %k0
; AVX512VL-NEXT: kmovw %k0, %k1
; AVX512VL-NEXT: vcmpeqps %xmm1, %xmm0, %k1
; AVX512VL-NEXT: vrndscaless $2, %xmm0, %xmm1, %xmm0 {%k1} {z}
; AVX512VL-NEXT: retq
%mask1 = fcmp oeq <4 x float> %x, %y
@ -2880,8 +2868,7 @@ define <2 x double> @ceil_mask_sd_mask8(<2 x double> %x, <2 x double> %y, <2 x d
; AVX512F: ## %bb.0:
; AVX512F-NEXT: ## kill: def $xmm1 killed $xmm1 def $zmm1
; AVX512F-NEXT: ## kill: def $xmm0 killed $xmm0 def $zmm0
; AVX512F-NEXT: vcmpeqpd %zmm1, %zmm0, %k0
; AVX512F-NEXT: kmovw %k0, %k1
; AVX512F-NEXT: vcmpeqpd %zmm1, %zmm0, %k1
; AVX512F-NEXT: vrndscalesd $2, %xmm0, %xmm1, %xmm2 {%k1}
; AVX512F-NEXT: vmovapd %xmm2, %xmm0
; AVX512F-NEXT: vzeroupper
@ -2889,8 +2876,7 @@ define <2 x double> @ceil_mask_sd_mask8(<2 x double> %x, <2 x double> %y, <2 x d
;
; AVX512VL-LABEL: ceil_mask_sd_mask8:
; AVX512VL: ## %bb.0:
; AVX512VL-NEXT: vcmpeqpd %xmm1, %xmm0, %k0
; AVX512VL-NEXT: kmovw %k0, %k1
; AVX512VL-NEXT: vcmpeqpd %xmm1, %xmm0, %k1
; AVX512VL-NEXT: vrndscalesd $2, %xmm0, %xmm1, %xmm2 {%k1}
; AVX512VL-NEXT: vmovapd %xmm2, %xmm0
; AVX512VL-NEXT: retq
@ -2941,16 +2927,14 @@ define <2 x double> @ceil_maskz_sd_mask8(<2 x double> %x, <2 x double> %y) nounw
; AVX512F: ## %bb.0:
; AVX512F-NEXT: ## kill: def $xmm1 killed $xmm1 def $zmm1
; AVX512F-NEXT: ## kill: def $xmm0 killed $xmm0 def $zmm0
; AVX512F-NEXT: vcmpeqpd %zmm1, %zmm0, %k0
; AVX512F-NEXT: kmovw %k0, %k1
; AVX512F-NEXT: vcmpeqpd %zmm1, %zmm0, %k1
; AVX512F-NEXT: vrndscalesd $2, %xmm0, %xmm1, %xmm0 {%k1} {z}
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: ceil_maskz_sd_mask8:
; AVX512VL: ## %bb.0:
; AVX512VL-NEXT: vcmpeqpd %xmm1, %xmm0, %k0
; AVX512VL-NEXT: kmovw %k0, %k1
; AVX512VL-NEXT: vcmpeqpd %xmm1, %xmm0, %k1
; AVX512VL-NEXT: vrndscalesd $2, %xmm0, %xmm1, %xmm0 {%k1} {z}
; AVX512VL-NEXT: retq
%mask1 = fcmp oeq <2 x double> %x, %y