forked from OSchip/llvm-project
[X86] Add some custom type legalization rules for truncate with -x86-experimental-vector-widening-legalization.
This avoids some nasty shuffles when we have avx512. It will also prevent using zmm truncate instructions when a ymm instruction that zeroes part of an xmm register will do. Also avoid using avx512 truncate instructions when the input is 128 bits or less. These instructions are 2 uops on skx so we can probably find a better single uop shuffle like pshufb. llvm-svn: 346936
This commit is contained in:
Craig Topper
parent
926dbdd601
commit
553ac560aa
|
|
@ -937,6 +937,15 @@ X86TargetLowering::X86TargetLowering(const X86TargetMachine &TM,
|
|||
setOperationAction(ISD::SIGN_EXTEND_VECTOR_INREG, MVT::v4i32, Custom);
|
||||
setOperationAction(ISD::SIGN_EXTEND_VECTOR_INREG, MVT::v8i16, Custom);
|
||||
|
||||
if (ExperimentalVectorWideningLegalization) {
|
||||
setOperationAction(ISD::TRUNCATE, MVT::v2i8, Custom);
|
||||
setOperationAction(ISD::TRUNCATE, MVT::v2i16, Custom);
|
||||
setOperationAction(ISD::TRUNCATE, MVT::v2i32, Custom);
|
||||
setOperationAction(ISD::TRUNCATE, MVT::v4i8, Custom);
|
||||
setOperationAction(ISD::TRUNCATE, MVT::v4i16, Custom);
|
||||
setOperationAction(ISD::TRUNCATE, MVT::v8i8, Custom);
|
||||
}
|
||||
|
||||
// In the customized shift lowering, the legal v4i32/v2i64 cases
|
||||
// in AVX2 will be recognized.
|
||||
for (auto VT : { MVT::v16i8, MVT::v8i16, MVT::v4i32, MVT::v2i64 }) {
|
||||
|
|
@ -17917,6 +17926,10 @@ SDValue X86TargetLowering::LowerTRUNCATE(SDValue Op, SelectionDAG &DAG) const {
|
|||
assert(VT.getVectorNumElements() == InVT.getVectorNumElements() &&
|
||||
"Invalid TRUNCATE operation");
|
||||
|
||||
// If called by the legalizer just return.
|
||||
if (!DAG.getTargetLoweringInfo().isTypeLegal(InVT))
|
||||
return SDValue();
|
||||
|
||||
if (VT.getVectorElementType() == MVT::i1)
|
||||
return LowerTruncateVecI1(Op, DAG, Subtarget);
|
||||
|
||||
|
|
@ -26200,6 +26213,57 @@ void X86TargetLowering::ReplaceNodeResults(SDNode *N,
|
|||
Results.push_back(V);
|
||||
return;
|
||||
}
|
||||
case ISD::TRUNCATE: {
|
||||
MVT VT = N->getSimpleValueType(0);
|
||||
if (getTypeAction(*DAG.getContext(), VT) != TypeWidenVector)
|
||||
return;
|
||||
|
||||
// The generic legalizer will try to widen the input type to the same
|
||||
// number of elements as the widened result type. But this isn't always
|
||||
// the best thing so do some custom legalization to avoid some cases.
|
||||
MVT WidenVT = getTypeToTransformTo(*DAG.getContext(), VT).getSimpleVT();
|
||||
SDValue In = N->getOperand(0);
|
||||
EVT InVT = In.getValueType();
|
||||
|
||||
unsigned InBits = InVT.getSizeInBits();
|
||||
if (128 % InBits == 0) {
|
||||
// 128 bit and smaller inputs should avoid truncate all together and
|
||||
// just use a build_vector that will become a shuffle.
|
||||
// TODO: Widen and use a shuffle directly?
|
||||
MVT InEltVT = InVT.getSimpleVT().getVectorElementType();
|
||||
EVT EltVT = VT.getVectorElementType();
|
||||
unsigned WidenNumElts = WidenVT.getVectorNumElements();
|
||||
SmallVector<SDValue, 16> Ops(WidenNumElts, DAG.getUNDEF(EltVT));
|
||||
// Use the original element count so we don't do more scalar opts than
|
||||
// necessary.
|
||||
unsigned MinElts = VT.getVectorNumElements();
|
||||
for (unsigned i=0; i < MinElts; ++i) {
|
||||
SDValue Val = DAG.getNode(ISD::EXTRACT_VECTOR_ELT, dl, InEltVT, In,
|
||||
DAG.getIntPtrConstant(i, dl));
|
||||
Ops[i] = DAG.getNode(ISD::TRUNCATE, dl, EltVT, Val);
|
||||
}
|
||||
Results.push_back(DAG.getBuildVector(WidenVT, dl, Ops));
|
||||
return;
|
||||
}
|
||||
// With AVX512 there are some cases that can use a target specific
|
||||
// truncate node to go from 256/512 to less than 128 with zeros in the
|
||||
// upper elements of the 128 bit result.
|
||||
if (Subtarget.hasAVX512() && isTypeLegal(InVT)) {
|
||||
// We can use VTRUNC directly if for 256 bits with VLX or for any 512.
|
||||
if ((InBits == 256 && Subtarget.hasVLX()) || InBits == 512) {
|
||||
Results.push_back(DAG.getNode(X86ISD::VTRUNC, dl, WidenVT, In));
|
||||
return;
|
||||
}
|
||||
// There's one case we can widen to 512 bits and use VTRUNC.
|
||||
if (InVT == MVT::v4i64 && VT == MVT::v4i8 && isTypeLegal(MVT::v8i64)) {
|
||||
In = DAG.getNode(ISD::CONCAT_VECTORS, dl, MVT::v8i64, In,
|
||||
DAG.getUNDEF(MVT::v4i64));
|
||||
Results.push_back(DAG.getNode(X86ISD::VTRUNC, dl, WidenVT, In));
|
||||
return;
|
||||
}
|
||||
}
|
||||
return;
|
||||
}
|
||||
case ISD::FP_TO_SINT:
|
||||
case ISD::FP_TO_UINT: {
|
||||
bool IsSigned = N->getOpcode() == ISD::FP_TO_SINT;
|
||||
|
|
|
|||
|
|
@ -1645,9 +1645,8 @@ define <2 x double> @sbto2f64(<2 x double> %a) {
|
|||
; NOVL: # %bb.0:
|
||||
; NOVL-NEXT: vxorpd %xmm1, %xmm1, %xmm1
|
||||
; NOVL-NEXT: vcmpltpd %xmm0, %xmm1, %xmm0
|
||||
; NOVL-NEXT: vpmovqd %zmm0, %ymm0
|
||||
; NOVL-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,2,2,3]
|
||||
; NOVL-NEXT: vcvtdq2pd %xmm0, %xmm0
|
||||
; NOVL-NEXT: vzeroupper
|
||||
; NOVL-NEXT: retq
|
||||
;
|
||||
; VLDQ-LABEL: sbto2f64:
|
||||
|
|
|
|||
|
|
@ -75,27 +75,22 @@ define void @trunc_v8i16_to_v8i8(<16 x i8>* %L, <8 x i8>* %S) nounwind {
|
|||
; AVX512F-LABEL: trunc_v8i16_to_v8i8:
|
||||
; AVX512F: # %bb.0:
|
||||
; AVX512F-NEXT: vmovdqa (%rdi), %xmm0
|
||||
; AVX512F-NEXT: vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
|
||||
; AVX512F-NEXT: vpmovdb %zmm0, %xmm0
|
||||
; AVX512F-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
|
||||
; AVX512F-NEXT: vmovq %xmm0, (%rsi)
|
||||
; AVX512F-NEXT: vzeroupper
|
||||
; AVX512F-NEXT: retq
|
||||
;
|
||||
; AVX512VL-LABEL: trunc_v8i16_to_v8i8:
|
||||
; AVX512VL: # %bb.0:
|
||||
; AVX512VL-NEXT: vmovdqa (%rdi), %xmm0
|
||||
; AVX512VL-NEXT: vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
|
||||
; AVX512VL-NEXT: vpmovdb %zmm0, %xmm0
|
||||
; AVX512VL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
|
||||
; AVX512VL-NEXT: vmovq %xmm0, (%rsi)
|
||||
; AVX512VL-NEXT: vzeroupper
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: trunc_v8i16_to_v8i8:
|
||||
; AVX512BW: # %bb.0:
|
||||
; AVX512BW-NEXT: vmovdqa (%rdi), %xmm0
|
||||
; AVX512BW-NEXT: vpmovwb %zmm0, %ymm0
|
||||
; AVX512BW-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
|
||||
; AVX512BW-NEXT: vmovq %xmm0, (%rsi)
|
||||
; AVX512BW-NEXT: vzeroupper
|
||||
; AVX512BW-NEXT: retq
|
||||
;
|
||||
; AVX512BWVL-LABEL: trunc_v8i16_to_v8i8:
|
||||
|
|
@ -171,9 +166,8 @@ define void @trunc_v4i32_to_v4i16(<8 x i16>* %L, <4 x i16>* %S) nounwind {
|
|||
; AVX512F-LABEL: trunc_v4i32_to_v4i16:
|
||||
; AVX512F: # %bb.0:
|
||||
; AVX512F-NEXT: vmovdqa (%rdi), %xmm0
|
||||
; AVX512F-NEXT: vpmovdw %zmm0, %ymm0
|
||||
; AVX512F-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
|
||||
; AVX512F-NEXT: vmovq %xmm0, (%rsi)
|
||||
; AVX512F-NEXT: vzeroupper
|
||||
; AVX512F-NEXT: retq
|
||||
;
|
||||
; AVX512VL-LABEL: trunc_v4i32_to_v4i16:
|
||||
|
|
@ -185,9 +179,8 @@ define void @trunc_v4i32_to_v4i16(<8 x i16>* %L, <4 x i16>* %S) nounwind {
|
|||
; AVX512BW-LABEL: trunc_v4i32_to_v4i16:
|
||||
; AVX512BW: # %bb.0:
|
||||
; AVX512BW-NEXT: vmovdqa (%rdi), %xmm0
|
||||
; AVX512BW-NEXT: vpmovdw %zmm0, %ymm0
|
||||
; AVX512BW-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
|
||||
; AVX512BW-NEXT: vmovq %xmm0, (%rsi)
|
||||
; AVX512BW-NEXT: vzeroupper
|
||||
; AVX512BW-NEXT: retq
|
||||
;
|
||||
; AVX512BWVL-LABEL: trunc_v4i32_to_v4i16:
|
||||
|
|
@ -233,35 +226,16 @@ define void @trunc_v2i64_to_v2i32(<4 x i32>* %L, <2 x i32>* %S) nounwind {
|
|||
; SSE-NEXT: movq %xmm0, (%rsi)
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX1-LABEL: trunc_v2i64_to_v2i32:
|
||||
; AVX1: # %bb.0:
|
||||
; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = mem[0,2,2,3]
|
||||
; AVX1-NEXT: vmovlps %xmm0, (%rsi)
|
||||
; AVX1-NEXT: retq
|
||||
;
|
||||
; AVX2-SLOW-LABEL: trunc_v2i64_to_v2i32:
|
||||
; AVX2-SLOW: # %bb.0:
|
||||
; AVX2-SLOW-NEXT: vmovaps (%rdi), %xmm0
|
||||
; AVX2-SLOW-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
|
||||
; AVX2-SLOW-NEXT: vmovlps %xmm0, (%rsi)
|
||||
; AVX2-SLOW-NEXT: vzeroupper
|
||||
; AVX2-SLOW-NEXT: retq
|
||||
;
|
||||
; AVX2-FAST-LABEL: trunc_v2i64_to_v2i32:
|
||||
; AVX2-FAST: # %bb.0:
|
||||
; AVX2-FAST-NEXT: vmovaps (%rdi), %xmm0
|
||||
; AVX2-FAST-NEXT: vmovaps {{.*#+}} ymm1 = [0,2,4,6,4,6,6,7]
|
||||
; AVX2-FAST-NEXT: vpermps %ymm0, %ymm1, %ymm0
|
||||
; AVX2-FAST-NEXT: vmovlps %xmm0, (%rsi)
|
||||
; AVX2-FAST-NEXT: vzeroupper
|
||||
; AVX2-FAST-NEXT: retq
|
||||
; AVX-LABEL: trunc_v2i64_to_v2i32:
|
||||
; AVX: # %bb.0:
|
||||
; AVX-NEXT: vpermilps {{.*#+}} xmm0 = mem[0,2,2,3]
|
||||
; AVX-NEXT: vmovlps %xmm0, (%rsi)
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
; AVX512F-LABEL: trunc_v2i64_to_v2i32:
|
||||
; AVX512F: # %bb.0:
|
||||
; AVX512F-NEXT: vmovdqa (%rdi), %xmm0
|
||||
; AVX512F-NEXT: vpmovqd %zmm0, %ymm0
|
||||
; AVX512F-NEXT: vmovq %xmm0, (%rsi)
|
||||
; AVX512F-NEXT: vzeroupper
|
||||
; AVX512F-NEXT: vpermilps {{.*#+}} xmm0 = mem[0,2,2,3]
|
||||
; AVX512F-NEXT: vmovlps %xmm0, (%rsi)
|
||||
; AVX512F-NEXT: retq
|
||||
;
|
||||
; AVX512VL-LABEL: trunc_v2i64_to_v2i32:
|
||||
|
|
@ -272,10 +246,8 @@ define void @trunc_v2i64_to_v2i32(<4 x i32>* %L, <2 x i32>* %S) nounwind {
|
|||
;
|
||||
; AVX512BW-LABEL: trunc_v2i64_to_v2i32:
|
||||
; AVX512BW: # %bb.0:
|
||||
; AVX512BW-NEXT: vmovdqa (%rdi), %xmm0
|
||||
; AVX512BW-NEXT: vpmovqd %zmm0, %ymm0
|
||||
; AVX512BW-NEXT: vmovq %xmm0, (%rsi)
|
||||
; AVX512BW-NEXT: vzeroupper
|
||||
; AVX512BW-NEXT: vpermilps {{.*#+}} xmm0 = mem[0,2,2,3]
|
||||
; AVX512BW-NEXT: vmovlps %xmm0, (%rsi)
|
||||
; AVX512BW-NEXT: retq
|
||||
;
|
||||
; AVX512BWVL-LABEL: trunc_v2i64_to_v2i32:
|
||||
|
|
@ -353,9 +325,8 @@ define void @trunc_v4i32_to_v4i8(<16 x i8>* %L, <4 x i8>* %S) nounwind {
|
|||
; AVX512F-LABEL: trunc_v4i32_to_v4i8:
|
||||
; AVX512F: # %bb.0:
|
||||
; AVX512F-NEXT: vmovdqa (%rdi), %xmm0
|
||||
; AVX512F-NEXT: vpmovdb %zmm0, %xmm0
|
||||
; AVX512F-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,4,8,12,u,u,u,u,u,u,u,u,u,u,u,u]
|
||||
; AVX512F-NEXT: vmovd %xmm0, (%rsi)
|
||||
; AVX512F-NEXT: vzeroupper
|
||||
; AVX512F-NEXT: retq
|
||||
;
|
||||
; AVX512VL-LABEL: trunc_v4i32_to_v4i8:
|
||||
|
|
@ -367,9 +338,8 @@ define void @trunc_v4i32_to_v4i8(<16 x i8>* %L, <4 x i8>* %S) nounwind {
|
|||
; AVX512BW-LABEL: trunc_v4i32_to_v4i8:
|
||||
; AVX512BW: # %bb.0:
|
||||
; AVX512BW-NEXT: vmovdqa (%rdi), %xmm0
|
||||
; AVX512BW-NEXT: vpmovdb %zmm0, %xmm0
|
||||
; AVX512BW-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,4,8,12,u,u,u,u,u,u,u,u,u,u,u,u]
|
||||
; AVX512BW-NEXT: vmovd %xmm0, (%rsi)
|
||||
; AVX512BW-NEXT: vzeroupper
|
||||
; AVX512BW-NEXT: retq
|
||||
;
|
||||
; AVX512BWVL-LABEL: trunc_v4i32_to_v4i8:
|
||||
|
|
@ -477,10 +447,9 @@ define void @trunc_v2i64_to_v2i16(<8 x i16>* %L, <2 x i16>* %S) nounwind {
|
|||
;
|
||||
; AVX512F-LABEL: trunc_v2i64_to_v2i16:
|
||||
; AVX512F: # %bb.0:
|
||||
; AVX512F-NEXT: vmovdqa (%rdi), %xmm0
|
||||
; AVX512F-NEXT: vpmovqw %zmm0, %xmm0
|
||||
; AVX512F-NEXT: vpshufd {{.*#+}} xmm0 = mem[0,2,2,3]
|
||||
; AVX512F-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7]
|
||||
; AVX512F-NEXT: vmovd %xmm0, (%rsi)
|
||||
; AVX512F-NEXT: vzeroupper
|
||||
; AVX512F-NEXT: retq
|
||||
;
|
||||
; AVX512VL-LABEL: trunc_v2i64_to_v2i16:
|
||||
|
|
@ -492,9 +461,8 @@ define void @trunc_v2i64_to_v2i16(<8 x i16>* %L, <2 x i16>* %S) nounwind {
|
|||
; AVX512BW-LABEL: trunc_v2i64_to_v2i16:
|
||||
; AVX512BW: # %bb.0:
|
||||
; AVX512BW-NEXT: vmovdqa (%rdi), %xmm0
|
||||
; AVX512BW-NEXT: vpmovqw %zmm0, %xmm0
|
||||
; AVX512BW-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,8,9,8,9,10,11,8,9,10,11,12,13,14,15]
|
||||
; AVX512BW-NEXT: vmovd %xmm0, (%rsi)
|
||||
; AVX512BW-NEXT: vzeroupper
|
||||
; AVX512BW-NEXT: retq
|
||||
;
|
||||
; AVX512BWVL-LABEL: trunc_v2i64_to_v2i16:
|
||||
|
|
|
|||
|
|
@ -381,13 +381,42 @@ define <2 x i64> @trunc_v8i32_to_v8i8_return_v2i64(<8 x i32> %vec) nounwind {
|
|||
; AVX2-NEXT: vzeroupper
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: trunc_v8i32_to_v8i8_return_v2i64:
|
||||
; AVX512: # %bb.0:
|
||||
; AVX512-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
|
||||
; AVX512-NEXT: vpmovdb %zmm0, %xmm0
|
||||
; AVX512-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
|
||||
; AVX512-NEXT: vzeroupper
|
||||
; AVX512-NEXT: retq
|
||||
; AVX512F-LABEL: trunc_v8i32_to_v8i8_return_v2i64:
|
||||
; AVX512F: # %bb.0:
|
||||
; AVX512F-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
|
||||
; AVX512F-NEXT: vpmovdb %zmm0, %xmm0
|
||||
; AVX512F-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
|
||||
; AVX512F-NEXT: vzeroupper
|
||||
; AVX512F-NEXT: retq
|
||||
;
|
||||
; AVX512VL-LABEL: trunc_v8i32_to_v8i8_return_v2i64:
|
||||
; AVX512VL: # %bb.0:
|
||||
; AVX512VL-NEXT: vpmovdb %ymm0, %xmm0
|
||||
; AVX512VL-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
|
||||
; AVX512VL-NEXT: vzeroupper
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: trunc_v8i32_to_v8i8_return_v2i64:
|
||||
; AVX512BW: # %bb.0:
|
||||
; AVX512BW-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
|
||||
; AVX512BW-NEXT: vpmovdb %zmm0, %xmm0
|
||||
; AVX512BW-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
|
||||
; AVX512BW-NEXT: vzeroupper
|
||||
; AVX512BW-NEXT: retq
|
||||
;
|
||||
; AVX512BWVL-LABEL: trunc_v8i32_to_v8i8_return_v2i64:
|
||||
; AVX512BWVL: # %bb.0:
|
||||
; AVX512BWVL-NEXT: vpmovdb %ymm0, %xmm0
|
||||
; AVX512BWVL-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
|
||||
; AVX512BWVL-NEXT: vzeroupper
|
||||
; AVX512BWVL-NEXT: retq
|
||||
;
|
||||
; AVX512VBMIVL-LABEL: trunc_v8i32_to_v8i8_return_v2i64:
|
||||
; AVX512VBMIVL: # %bb.0:
|
||||
; AVX512VBMIVL-NEXT: vpmovdb %ymm0, %xmm0
|
||||
; AVX512VBMIVL-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
|
||||
; AVX512VBMIVL-NEXT: vzeroupper
|
||||
; AVX512VBMIVL-NEXT: retq
|
||||
%truncated.vec = trunc <8 x i32> %vec to <8 x i8>
|
||||
%bc = bitcast <8 x i8> %truncated.vec to i64
|
||||
%result = insertelement <2 x i64> zeroinitializer, i64 %bc, i32 0
|
||||
|
|
@ -536,13 +565,42 @@ define <16 x i8> @trunc_v8i32_to_v8i8_return_v16i8(<8 x i32> %vec) nounwind {
|
|||
; AVX2-NEXT: vzeroupper
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: trunc_v8i32_to_v8i8_return_v16i8:
|
||||
; AVX512: # %bb.0:
|
||||
; AVX512-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
|
||||
; AVX512-NEXT: vpmovdb %zmm0, %xmm0
|
||||
; AVX512-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
|
||||
; AVX512-NEXT: vzeroupper
|
||||
; AVX512-NEXT: retq
|
||||
; AVX512F-LABEL: trunc_v8i32_to_v8i8_return_v16i8:
|
||||
; AVX512F: # %bb.0:
|
||||
; AVX512F-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
|
||||
; AVX512F-NEXT: vpmovdb %zmm0, %xmm0
|
||||
; AVX512F-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
|
||||
; AVX512F-NEXT: vzeroupper
|
||||
; AVX512F-NEXT: retq
|
||||
;
|
||||
; AVX512VL-LABEL: trunc_v8i32_to_v8i8_return_v16i8:
|
||||
; AVX512VL: # %bb.0:
|
||||
; AVX512VL-NEXT: vpmovdb %ymm0, %xmm0
|
||||
; AVX512VL-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
|
||||
; AVX512VL-NEXT: vzeroupper
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: trunc_v8i32_to_v8i8_return_v16i8:
|
||||
; AVX512BW: # %bb.0:
|
||||
; AVX512BW-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
|
||||
; AVX512BW-NEXT: vpmovdb %zmm0, %xmm0
|
||||
; AVX512BW-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
|
||||
; AVX512BW-NEXT: vzeroupper
|
||||
; AVX512BW-NEXT: retq
|
||||
;
|
||||
; AVX512BWVL-LABEL: trunc_v8i32_to_v8i8_return_v16i8:
|
||||
; AVX512BWVL: # %bb.0:
|
||||
; AVX512BWVL-NEXT: vpmovdb %ymm0, %xmm0
|
||||
; AVX512BWVL-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
|
||||
; AVX512BWVL-NEXT: vzeroupper
|
||||
; AVX512BWVL-NEXT: retq
|
||||
;
|
||||
; AVX512VBMIVL-LABEL: trunc_v8i32_to_v8i8_return_v16i8:
|
||||
; AVX512VBMIVL: # %bb.0:
|
||||
; AVX512VBMIVL-NEXT: vpmovdb %ymm0, %xmm0
|
||||
; AVX512VBMIVL-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
|
||||
; AVX512VBMIVL-NEXT: vzeroupper
|
||||
; AVX512VBMIVL-NEXT: retq
|
||||
%truncated = trunc <8 x i32> %vec to <8 x i8>
|
||||
%result = shufflevector <8 x i8> %truncated, <8 x i8> zeroinitializer, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
|
||||
ret <16 x i8> %result
|
||||
|
|
@ -586,13 +644,42 @@ define <2 x i64> @trunc_v4i64_to_v4i16_return_v2i64(<4 x i64> %vec) nounwind {
|
|||
; AVX2-FAST-NEXT: vzeroupper
|
||||
; AVX2-FAST-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: trunc_v4i64_to_v4i16_return_v2i64:
|
||||
; AVX512: # %bb.0:
|
||||
; AVX512-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
|
||||
; AVX512-NEXT: vpmovqw %zmm0, %xmm0
|
||||
; AVX512-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
|
||||
; AVX512-NEXT: vzeroupper
|
||||
; AVX512-NEXT: retq
|
||||
; AVX512F-LABEL: trunc_v4i64_to_v4i16_return_v2i64:
|
||||
; AVX512F: # %bb.0:
|
||||
; AVX512F-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
|
||||
; AVX512F-NEXT: vpmovqw %zmm0, %xmm0
|
||||
; AVX512F-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
|
||||
; AVX512F-NEXT: vzeroupper
|
||||
; AVX512F-NEXT: retq
|
||||
;
|
||||
; AVX512VL-LABEL: trunc_v4i64_to_v4i16_return_v2i64:
|
||||
; AVX512VL: # %bb.0:
|
||||
; AVX512VL-NEXT: vpmovqw %ymm0, %xmm0
|
||||
; AVX512VL-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
|
||||
; AVX512VL-NEXT: vzeroupper
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: trunc_v4i64_to_v4i16_return_v2i64:
|
||||
; AVX512BW: # %bb.0:
|
||||
; AVX512BW-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
|
||||
; AVX512BW-NEXT: vpmovqw %zmm0, %xmm0
|
||||
; AVX512BW-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
|
||||
; AVX512BW-NEXT: vzeroupper
|
||||
; AVX512BW-NEXT: retq
|
||||
;
|
||||
; AVX512BWVL-LABEL: trunc_v4i64_to_v4i16_return_v2i64:
|
||||
; AVX512BWVL: # %bb.0:
|
||||
; AVX512BWVL-NEXT: vpmovqw %ymm0, %xmm0
|
||||
; AVX512BWVL-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
|
||||
; AVX512BWVL-NEXT: vzeroupper
|
||||
; AVX512BWVL-NEXT: retq
|
||||
;
|
||||
; AVX512VBMIVL-LABEL: trunc_v4i64_to_v4i16_return_v2i64:
|
||||
; AVX512VBMIVL: # %bb.0:
|
||||
; AVX512VBMIVL-NEXT: vpmovqw %ymm0, %xmm0
|
||||
; AVX512VBMIVL-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
|
||||
; AVX512VBMIVL-NEXT: vzeroupper
|
||||
; AVX512VBMIVL-NEXT: retq
|
||||
%truncated = trunc <4 x i64> %vec to <4 x i16>
|
||||
%bc = bitcast <4 x i16> %truncated to i64
|
||||
%result = insertelement <2 x i64> zeroinitializer, i64 %bc, i32 0
|
||||
|
|
@ -764,13 +851,42 @@ define <8 x i16> @trunc_v4i64_to_v4i16_return_v8i16(<4 x i64> %vec) nounwind {
|
|||
; AVX2-FAST-NEXT: vzeroupper
|
||||
; AVX2-FAST-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: trunc_v4i64_to_v4i16_return_v8i16:
|
||||
; AVX512: # %bb.0:
|
||||
; AVX512-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
|
||||
; AVX512-NEXT: vpmovqw %zmm0, %xmm0
|
||||
; AVX512-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
|
||||
; AVX512-NEXT: vzeroupper
|
||||
; AVX512-NEXT: retq
|
||||
; AVX512F-LABEL: trunc_v4i64_to_v4i16_return_v8i16:
|
||||
; AVX512F: # %bb.0:
|
||||
; AVX512F-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
|
||||
; AVX512F-NEXT: vpmovqw %zmm0, %xmm0
|
||||
; AVX512F-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
|
||||
; AVX512F-NEXT: vzeroupper
|
||||
; AVX512F-NEXT: retq
|
||||
;
|
||||
; AVX512VL-LABEL: trunc_v4i64_to_v4i16_return_v8i16:
|
||||
; AVX512VL: # %bb.0:
|
||||
; AVX512VL-NEXT: vpmovqw %ymm0, %xmm0
|
||||
; AVX512VL-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
|
||||
; AVX512VL-NEXT: vzeroupper
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: trunc_v4i64_to_v4i16_return_v8i16:
|
||||
; AVX512BW: # %bb.0:
|
||||
; AVX512BW-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
|
||||
; AVX512BW-NEXT: vpmovqw %zmm0, %xmm0
|
||||
; AVX512BW-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
|
||||
; AVX512BW-NEXT: vzeroupper
|
||||
; AVX512BW-NEXT: retq
|
||||
;
|
||||
; AVX512BWVL-LABEL: trunc_v4i64_to_v4i16_return_v8i16:
|
||||
; AVX512BWVL: # %bb.0:
|
||||
; AVX512BWVL-NEXT: vpmovqw %ymm0, %xmm0
|
||||
; AVX512BWVL-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
|
||||
; AVX512BWVL-NEXT: vzeroupper
|
||||
; AVX512BWVL-NEXT: retq
|
||||
;
|
||||
; AVX512VBMIVL-LABEL: trunc_v4i64_to_v4i16_return_v8i16:
|
||||
; AVX512VBMIVL: # %bb.0:
|
||||
; AVX512VBMIVL-NEXT: vpmovqw %ymm0, %xmm0
|
||||
; AVX512VBMIVL-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
|
||||
; AVX512VBMIVL-NEXT: vzeroupper
|
||||
; AVX512VBMIVL-NEXT: retq
|
||||
%truncated = trunc <4 x i64> %vec to <4 x i16>
|
||||
%result = shufflevector <4 x i16> %truncated, <4 x i16> zeroinitializer, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
|
||||
ret <8 x i16> %result
|
||||
|
|
@ -801,17 +917,47 @@ define <16 x i8> @trunc_v4i64_to_v4i8_return_v16i8(<4 x i64> %vec) nounwind {
|
|||
; AVX2-NEXT: vzeroupper
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: trunc_v4i64_to_v4i8_return_v16i8:
|
||||
; AVX512: # %bb.0:
|
||||
; AVX512-NEXT: vextracti128 $1, %ymm0, %xmm1
|
||||
; AVX512-NEXT: vmovdqa {{.*#+}} xmm2 = <0,8,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
|
||||
; AVX512-NEXT: vpshufb %xmm2, %xmm1, %xmm1
|
||||
; AVX512-NEXT: vpshufb %xmm2, %xmm0, %xmm0
|
||||
; AVX512-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
|
||||
; AVX512-NEXT: vpxor %xmm1, %xmm1, %xmm1
|
||||
; AVX512-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3,4,5,6,7]
|
||||
; AVX512-NEXT: vzeroupper
|
||||
; AVX512-NEXT: retq
|
||||
; AVX512F-LABEL: trunc_v4i64_to_v4i8_return_v16i8:
|
||||
; AVX512F: # %bb.0:
|
||||
; AVX512F-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
|
||||
; AVX512F-NEXT: vpmovqb %zmm0, %xmm0
|
||||
; AVX512F-NEXT: vpxor %xmm1, %xmm1, %xmm1
|
||||
; AVX512F-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3,4,5,6,7]
|
||||
; AVX512F-NEXT: vzeroupper
|
||||
; AVX512F-NEXT: retq
|
||||
;
|
||||
; AVX512VL-LABEL: trunc_v4i64_to_v4i8_return_v16i8:
|
||||
; AVX512VL: # %bb.0:
|
||||
; AVX512VL-NEXT: vpmovqb %ymm0, %xmm0
|
||||
; AVX512VL-NEXT: vpxor %xmm1, %xmm1, %xmm1
|
||||
; AVX512VL-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3,4,5,6,7]
|
||||
; AVX512VL-NEXT: vzeroupper
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: trunc_v4i64_to_v4i8_return_v16i8:
|
||||
; AVX512BW: # %bb.0:
|
||||
; AVX512BW-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
|
||||
; AVX512BW-NEXT: vpmovqb %zmm0, %xmm0
|
||||
; AVX512BW-NEXT: vpxor %xmm1, %xmm1, %xmm1
|
||||
; AVX512BW-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3,4,5,6,7]
|
||||
; AVX512BW-NEXT: vzeroupper
|
||||
; AVX512BW-NEXT: retq
|
||||
;
|
||||
; AVX512BWVL-LABEL: trunc_v4i64_to_v4i8_return_v16i8:
|
||||
; AVX512BWVL: # %bb.0:
|
||||
; AVX512BWVL-NEXT: vpmovqb %ymm0, %xmm0
|
||||
; AVX512BWVL-NEXT: vpxor %xmm1, %xmm1, %xmm1
|
||||
; AVX512BWVL-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3,4,5,6,7]
|
||||
; AVX512BWVL-NEXT: vzeroupper
|
||||
; AVX512BWVL-NEXT: retq
|
||||
;
|
||||
; AVX512VBMIVL-LABEL: trunc_v4i64_to_v4i8_return_v16i8:
|
||||
; AVX512VBMIVL: # %bb.0:
|
||||
; AVX512VBMIVL-NEXT: vpmovqb %ymm0, %xmm0
|
||||
; AVX512VBMIVL-NEXT: vpxor %xmm1, %xmm1, %xmm1
|
||||
; AVX512VBMIVL-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3,4,5,6,7]
|
||||
; AVX512VBMIVL-NEXT: vzeroupper
|
||||
; AVX512VBMIVL-NEXT: retq
|
||||
%truncated = trunc <4 x i64> %vec to <4 x i8>
|
||||
%result = shufflevector <4 x i8> %truncated, <4 x i8> zeroinitializer, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 4, i32 5, i32 6, i32 7, i32 5, i32 5, i32 undef, i32 7>
|
||||
ret <16 x i8> %result
|
||||
|
|
@ -1025,13 +1171,10 @@ define void @trunc_v4i64_to_v4i8(<32 x i8>* %L, <4 x i8>* %S) nounwind {
|
|||
;
|
||||
; AVX512F-LABEL: trunc_v4i64_to_v4i8:
|
||||
; AVX512F: # %bb.0:
|
||||
; AVX512F-NEXT: vmovdqa (%rdi), %xmm0
|
||||
; AVX512F-NEXT: vmovdqa 16(%rdi), %xmm1
|
||||
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm2 = <0,8,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
|
||||
; AVX512F-NEXT: vpshufb %xmm2, %xmm1, %xmm1
|
||||
; AVX512F-NEXT: vpshufb %xmm2, %xmm0, %xmm0
|
||||
; AVX512F-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
|
||||
; AVX512F-NEXT: vmovdqa (%rdi), %ymm0
|
||||
; AVX512F-NEXT: vpmovqb %zmm0, %xmm0
|
||||
; AVX512F-NEXT: vmovd %xmm0, (%rsi)
|
||||
; AVX512F-NEXT: vzeroupper
|
||||
; AVX512F-NEXT: retq
|
||||
;
|
||||
; AVX512VL-LABEL: trunc_v4i64_to_v4i8:
|
||||
|
|
@ -1043,13 +1186,10 @@ define void @trunc_v4i64_to_v4i8(<32 x i8>* %L, <4 x i8>* %S) nounwind {
|
|||
;
|
||||
; AVX512BW-LABEL: trunc_v4i64_to_v4i8:
|
||||
; AVX512BW: # %bb.0:
|
||||
; AVX512BW-NEXT: vmovdqa (%rdi), %xmm0
|
||||
; AVX512BW-NEXT: vmovdqa 16(%rdi), %xmm1
|
||||
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm2 = <0,8,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
|
||||
; AVX512BW-NEXT: vpshufb %xmm2, %xmm1, %xmm1
|
||||
; AVX512BW-NEXT: vpshufb %xmm2, %xmm0, %xmm0
|
||||
; AVX512BW-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
|
||||
; AVX512BW-NEXT: vmovdqa (%rdi), %ymm0
|
||||
; AVX512BW-NEXT: vpmovqb %zmm0, %xmm0
|
||||
; AVX512BW-NEXT: vmovd %xmm0, (%rsi)
|
||||
; AVX512BW-NEXT: vzeroupper
|
||||
; AVX512BW-NEXT: retq
|
||||
;
|
||||
; AVX512BWVL-LABEL: trunc_v4i64_to_v4i8:
|
||||
|
|
|
|||
|
|
@ -911,118 +911,12 @@ define <4 x double> @PR34175(<32 x i16>* %p) {
|
|||
}
|
||||
|
||||
define <16 x i8> @trunc_v8i64_to_v8i8_return_v16i8(<8 x i64> %vec) nounwind {
|
||||
; AVX512F-LABEL: trunc_v8i64_to_v8i8_return_v16i8:
|
||||
; AVX512F: # %bb.0:
|
||||
; AVX512F-NEXT: vextracti32x4 $3, %zmm0, %xmm1
|
||||
; AVX512F-NEXT: vpextrq $1, %xmm1, %r8
|
||||
; AVX512F-NEXT: vmovq %xmm1, %r9
|
||||
; AVX512F-NEXT: vextracti32x4 $2, %zmm0, %xmm1
|
||||
; AVX512F-NEXT: vpextrq $1, %xmm1, %r10
|
||||
; AVX512F-NEXT: vmovq %xmm1, %rsi
|
||||
; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm1
|
||||
; AVX512F-NEXT: vpextrq $1, %xmm1, %rdi
|
||||
; AVX512F-NEXT: vmovq %xmm1, %rax
|
||||
; AVX512F-NEXT: vpextrq $1, %xmm0, %rcx
|
||||
; AVX512F-NEXT: vmovq %xmm0, %rdx
|
||||
; AVX512F-NEXT: vpxor %xmm0, %xmm0, %xmm0
|
||||
; AVX512F-NEXT: vpinsrb $0, %edx, %xmm0, %xmm0
|
||||
; AVX512F-NEXT: vpinsrb $1, %ecx, %xmm0, %xmm0
|
||||
; AVX512F-NEXT: vpinsrb $2, %eax, %xmm0, %xmm0
|
||||
; AVX512F-NEXT: vpinsrb $3, %edi, %xmm0, %xmm0
|
||||
; AVX512F-NEXT: vpinsrb $4, %esi, %xmm0, %xmm0
|
||||
; AVX512F-NEXT: vpinsrb $5, %r10d, %xmm0, %xmm0
|
||||
; AVX512F-NEXT: vpinsrb $6, %r9d, %xmm0, %xmm0
|
||||
; AVX512F-NEXT: vpinsrb $7, %r8d, %xmm0, %xmm0
|
||||
; AVX512F-NEXT: vzeroupper
|
||||
; AVX512F-NEXT: retq
|
||||
;
|
||||
; AVX512VL-LABEL: trunc_v8i64_to_v8i8_return_v16i8:
|
||||
; AVX512VL: # %bb.0:
|
||||
; AVX512VL-NEXT: vextracti32x4 $3, %zmm0, %xmm1
|
||||
; AVX512VL-NEXT: vpextrq $1, %xmm1, %r8
|
||||
; AVX512VL-NEXT: vmovq %xmm1, %r9
|
||||
; AVX512VL-NEXT: vextracti32x4 $2, %zmm0, %xmm1
|
||||
; AVX512VL-NEXT: vpextrq $1, %xmm1, %r10
|
||||
; AVX512VL-NEXT: vmovq %xmm1, %rsi
|
||||
; AVX512VL-NEXT: vextracti128 $1, %ymm0, %xmm1
|
||||
; AVX512VL-NEXT: vpextrq $1, %xmm1, %rdi
|
||||
; AVX512VL-NEXT: vmovq %xmm1, %rax
|
||||
; AVX512VL-NEXT: vpextrq $1, %xmm0, %rcx
|
||||
; AVX512VL-NEXT: vmovq %xmm0, %rdx
|
||||
; AVX512VL-NEXT: vpxor %xmm0, %xmm0, %xmm0
|
||||
; AVX512VL-NEXT: vpinsrb $0, %edx, %xmm0, %xmm0
|
||||
; AVX512VL-NEXT: vpinsrb $1, %ecx, %xmm0, %xmm0
|
||||
; AVX512VL-NEXT: vpinsrb $2, %eax, %xmm0, %xmm0
|
||||
; AVX512VL-NEXT: vpinsrb $3, %edi, %xmm0, %xmm0
|
||||
; AVX512VL-NEXT: vpinsrb $4, %esi, %xmm0, %xmm0
|
||||
; AVX512VL-NEXT: vpinsrb $5, %r10d, %xmm0, %xmm0
|
||||
; AVX512VL-NEXT: vpinsrb $6, %r9d, %xmm0, %xmm0
|
||||
; AVX512VL-NEXT: vpinsrb $7, %r8d, %xmm0, %xmm0
|
||||
; AVX512VL-NEXT: vzeroupper
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: trunc_v8i64_to_v8i8_return_v16i8:
|
||||
; AVX512BW: # %bb.0:
|
||||
; AVX512BW-NEXT: vextracti64x4 $1, %zmm0, %ymm1
|
||||
; AVX512BW-NEXT: vextracti128 $1, %ymm1, %xmm2
|
||||
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm3 = <u,u,0,8,u,u,u,u,u,u,u,u,u,u,u,u>
|
||||
; AVX512BW-NEXT: vpshufb %xmm3, %xmm2, %xmm2
|
||||
; AVX512BW-NEXT: vpshufb %xmm3, %xmm1, %xmm1
|
||||
; AVX512BW-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
|
||||
; AVX512BW-NEXT: vextracti128 $1, %ymm0, %xmm2
|
||||
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm3 = <0,8,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
|
||||
; AVX512BW-NEXT: vpshufb %xmm3, %xmm2, %xmm2
|
||||
; AVX512BW-NEXT: vpshufb %xmm3, %xmm0, %xmm0
|
||||
; AVX512BW-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
|
||||
; AVX512BW-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2,3]
|
||||
; AVX512BW-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
|
||||
; AVX512BW-NEXT: vzeroupper
|
||||
; AVX512BW-NEXT: retq
|
||||
;
|
||||
; AVX512BWVL-LABEL: trunc_v8i64_to_v8i8_return_v16i8:
|
||||
; AVX512BWVL: # %bb.0:
|
||||
; AVX512BWVL-NEXT: vextracti64x4 $1, %zmm0, %ymm1
|
||||
; AVX512BWVL-NEXT: vextracti128 $1, %ymm1, %xmm2
|
||||
; AVX512BWVL-NEXT: vmovdqa {{.*#+}} xmm3 = <u,u,0,8,u,u,u,u,u,u,u,u,u,u,u,u>
|
||||
; AVX512BWVL-NEXT: vpshufb %xmm3, %xmm2, %xmm2
|
||||
; AVX512BWVL-NEXT: vpshufb %xmm3, %xmm1, %xmm1
|
||||
; AVX512BWVL-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
|
||||
; AVX512BWVL-NEXT: vextracti128 $1, %ymm0, %xmm2
|
||||
; AVX512BWVL-NEXT: vmovdqa {{.*#+}} xmm3 = <0,8,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
|
||||
; AVX512BWVL-NEXT: vpshufb %xmm3, %xmm2, %xmm2
|
||||
; AVX512BWVL-NEXT: vpshufb %xmm3, %xmm0, %xmm0
|
||||
; AVX512BWVL-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
|
||||
; AVX512BWVL-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2,3]
|
||||
; AVX512BWVL-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
|
||||
; AVX512BWVL-NEXT: vzeroupper
|
||||
; AVX512BWVL-NEXT: retq
|
||||
;
|
||||
; AVX512VBMI-LABEL: trunc_v8i64_to_v8i8_return_v16i8:
|
||||
; AVX512VBMI: # %bb.0:
|
||||
; AVX512VBMI-NEXT: vextracti64x4 $1, %zmm0, %ymm1
|
||||
; AVX512VBMI-NEXT: vextracti128 $1, %ymm1, %xmm2
|
||||
; AVX512VBMI-NEXT: vmovdqa {{.*#+}} xmm3 = <u,u,0,8,u,u,u,u,u,u,u,u,u,u,u,u>
|
||||
; AVX512VBMI-NEXT: vpshufb %xmm3, %xmm2, %xmm2
|
||||
; AVX512VBMI-NEXT: vpshufb %xmm3, %xmm1, %xmm1
|
||||
; AVX512VBMI-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
|
||||
; AVX512VBMI-NEXT: vextracti128 $1, %ymm0, %xmm2
|
||||
; AVX512VBMI-NEXT: vmovdqa {{.*#+}} xmm3 = <0,8,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
|
||||
; AVX512VBMI-NEXT: vpshufb %xmm3, %xmm2, %xmm2
|
||||
; AVX512VBMI-NEXT: vpshufb %xmm3, %xmm0, %xmm0
|
||||
; AVX512VBMI-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
|
||||
; AVX512VBMI-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2,3]
|
||||
; AVX512VBMI-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
|
||||
; AVX512VBMI-NEXT: vzeroupper
|
||||
; AVX512VBMI-NEXT: retq
|
||||
;
|
||||
; AVX512VBMIVL-LABEL: trunc_v8i64_to_v8i8_return_v16i8:
|
||||
; AVX512VBMIVL: # %bb.0:
|
||||
; AVX512VBMIVL-NEXT: vextracti64x4 $1, %zmm0, %ymm1
|
||||
; AVX512VBMIVL-NEXT: vmovdqa {{.*#+}} ymm2 = <0,8,16,24,32,40,48,56,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
|
||||
; AVX512VBMIVL-NEXT: vpermi2b %ymm1, %ymm0, %ymm2
|
||||
; AVX512VBMIVL-NEXT: vmovq {{.*#+}} xmm0 = xmm2[0],zero
|
||||
; AVX512VBMIVL-NEXT: vzeroupper
|
||||
; AVX512VBMIVL-NEXT: retq
|
||||
; AVX512-LABEL: trunc_v8i64_to_v8i8_return_v16i8:
|
||||
; AVX512: # %bb.0:
|
||||
; AVX512-NEXT: vpmovqb %zmm0, %xmm0
|
||||
; AVX512-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
|
||||
; AVX512-NEXT: vzeroupper
|
||||
; AVX512-NEXT: retq
|
||||
%truncated = trunc <8 x i64> %vec to <8 x i8>
|
||||
%result = shufflevector <8 x i8> %truncated, <8 x i8> zeroinitializer, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
|
||||
ret <16 x i8> %result
|
||||
|
|
|
|||
|
|
@ -1735,99 +1735,14 @@ define <8 x i8> @trunc_packus_v8i64_v8i8(<8 x i64> %a0) {
|
|||
; AVX2-NEXT: vzeroupper
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512F-LABEL: trunc_packus_v8i64_v8i8:
|
||||
; AVX512F: # %bb.0:
|
||||
; AVX512F-NEXT: vpminsq {{.*}}(%rip){1to8}, %zmm0, %zmm0
|
||||
; AVX512F-NEXT: vpxor %xmm1, %xmm1, %xmm1
|
||||
; AVX512F-NEXT: vpmaxsq %zmm1, %zmm0, %zmm0
|
||||
; AVX512F-NEXT: vpextrq $1, %xmm0, %rax
|
||||
; AVX512F-NEXT: vmovq %xmm0, %rcx
|
||||
; AVX512F-NEXT: vmovd %ecx, %xmm1
|
||||
; AVX512F-NEXT: vpinsrb $1, %eax, %xmm1, %xmm1
|
||||
; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm2
|
||||
; AVX512F-NEXT: vmovq %xmm2, %rax
|
||||
; AVX512F-NEXT: vpinsrb $2, %eax, %xmm1, %xmm1
|
||||
; AVX512F-NEXT: vpextrq $1, %xmm2, %rax
|
||||
; AVX512F-NEXT: vpinsrb $3, %eax, %xmm1, %xmm1
|
||||
; AVX512F-NEXT: vextracti32x4 $2, %zmm0, %xmm2
|
||||
; AVX512F-NEXT: vmovq %xmm2, %rax
|
||||
; AVX512F-NEXT: vpinsrb $4, %eax, %xmm1, %xmm1
|
||||
; AVX512F-NEXT: vpextrq $1, %xmm2, %rax
|
||||
; AVX512F-NEXT: vpinsrb $5, %eax, %xmm1, %xmm1
|
||||
; AVX512F-NEXT: vextracti32x4 $3, %zmm0, %xmm0
|
||||
; AVX512F-NEXT: vmovq %xmm0, %rax
|
||||
; AVX512F-NEXT: vpinsrb $6, %eax, %xmm1, %xmm1
|
||||
; AVX512F-NEXT: vpextrq $1, %xmm0, %rax
|
||||
; AVX512F-NEXT: vpinsrb $7, %eax, %xmm1, %xmm0
|
||||
; AVX512F-NEXT: vzeroupper
|
||||
; AVX512F-NEXT: retq
|
||||
;
|
||||
; AVX512VL-LABEL: trunc_packus_v8i64_v8i8:
|
||||
; AVX512VL: # %bb.0:
|
||||
; AVX512VL-NEXT: vpminsq {{.*}}(%rip){1to8}, %zmm0, %zmm0
|
||||
; AVX512VL-NEXT: vpxor %xmm1, %xmm1, %xmm1
|
||||
; AVX512VL-NEXT: vpmaxsq %zmm1, %zmm0, %zmm0
|
||||
; AVX512VL-NEXT: vpextrq $1, %xmm0, %rax
|
||||
; AVX512VL-NEXT: vmovq %xmm0, %rcx
|
||||
; AVX512VL-NEXT: vmovd %ecx, %xmm1
|
||||
; AVX512VL-NEXT: vpinsrb $1, %eax, %xmm1, %xmm1
|
||||
; AVX512VL-NEXT: vextracti128 $1, %ymm0, %xmm2
|
||||
; AVX512VL-NEXT: vmovq %xmm2, %rax
|
||||
; AVX512VL-NEXT: vpinsrb $2, %eax, %xmm1, %xmm1
|
||||
; AVX512VL-NEXT: vpextrq $1, %xmm2, %rax
|
||||
; AVX512VL-NEXT: vpinsrb $3, %eax, %xmm1, %xmm1
|
||||
; AVX512VL-NEXT: vextracti32x4 $2, %zmm0, %xmm2
|
||||
; AVX512VL-NEXT: vmovq %xmm2, %rax
|
||||
; AVX512VL-NEXT: vpinsrb $4, %eax, %xmm1, %xmm1
|
||||
; AVX512VL-NEXT: vpextrq $1, %xmm2, %rax
|
||||
; AVX512VL-NEXT: vpinsrb $5, %eax, %xmm1, %xmm1
|
||||
; AVX512VL-NEXT: vextracti32x4 $3, %zmm0, %xmm0
|
||||
; AVX512VL-NEXT: vmovq %xmm0, %rax
|
||||
; AVX512VL-NEXT: vpinsrb $6, %eax, %xmm1, %xmm1
|
||||
; AVX512VL-NEXT: vpextrq $1, %xmm0, %rax
|
||||
; AVX512VL-NEXT: vpinsrb $7, %eax, %xmm1, %xmm0
|
||||
; AVX512VL-NEXT: vzeroupper
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: trunc_packus_v8i64_v8i8:
|
||||
; AVX512BW: # %bb.0:
|
||||
; AVX512BW-NEXT: vpminsq {{.*}}(%rip){1to8}, %zmm0, %zmm0
|
||||
; AVX512BW-NEXT: vpxor %xmm1, %xmm1, %xmm1
|
||||
; AVX512BW-NEXT: vpmaxsq %zmm1, %zmm0, %zmm0
|
||||
; AVX512BW-NEXT: vextracti64x4 $1, %zmm0, %ymm1
|
||||
; AVX512BW-NEXT: vextracti128 $1, %ymm1, %xmm2
|
||||
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm3 = <u,u,0,8,u,u,u,u,u,u,u,u,u,u,u,u>
|
||||
; AVX512BW-NEXT: vpshufb %xmm3, %xmm2, %xmm2
|
||||
; AVX512BW-NEXT: vpshufb %xmm3, %xmm1, %xmm1
|
||||
; AVX512BW-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
|
||||
; AVX512BW-NEXT: vextracti128 $1, %ymm0, %xmm2
|
||||
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm3 = <0,8,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
|
||||
; AVX512BW-NEXT: vpshufb %xmm3, %xmm2, %xmm2
|
||||
; AVX512BW-NEXT: vpshufb %xmm3, %xmm0, %xmm0
|
||||
; AVX512BW-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
|
||||
; AVX512BW-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2,3]
|
||||
; AVX512BW-NEXT: vzeroupper
|
||||
; AVX512BW-NEXT: retq
|
||||
;
|
||||
; AVX512BWVL-LABEL: trunc_packus_v8i64_v8i8:
|
||||
; AVX512BWVL: # %bb.0:
|
||||
; AVX512BWVL-NEXT: vpminsq {{.*}}(%rip){1to8}, %zmm0, %zmm0
|
||||
; AVX512BWVL-NEXT: vpxor %xmm1, %xmm1, %xmm1
|
||||
; AVX512BWVL-NEXT: vpmaxsq %zmm1, %zmm0, %zmm0
|
||||
; AVX512BWVL-NEXT: vextracti64x4 $1, %zmm0, %ymm1
|
||||
; AVX512BWVL-NEXT: vextracti128 $1, %ymm1, %xmm2
|
||||
; AVX512BWVL-NEXT: vmovdqa {{.*#+}} xmm3 = <u,u,0,8,u,u,u,u,u,u,u,u,u,u,u,u>
|
||||
; AVX512BWVL-NEXT: vpshufb %xmm3, %xmm2, %xmm2
|
||||
; AVX512BWVL-NEXT: vpshufb %xmm3, %xmm1, %xmm1
|
||||
; AVX512BWVL-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
|
||||
; AVX512BWVL-NEXT: vextracti128 $1, %ymm0, %xmm2
|
||||
; AVX512BWVL-NEXT: vmovdqa {{.*#+}} xmm3 = <0,8,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
|
||||
; AVX512BWVL-NEXT: vpshufb %xmm3, %xmm2, %xmm2
|
||||
; AVX512BWVL-NEXT: vpshufb %xmm3, %xmm0, %xmm0
|
||||
; AVX512BWVL-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
|
||||
; AVX512BWVL-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2,3]
|
||||
; AVX512BWVL-NEXT: vzeroupper
|
||||
; AVX512BWVL-NEXT: retq
|
||||
; AVX512-LABEL: trunc_packus_v8i64_v8i8:
|
||||
; AVX512: # %bb.0:
|
||||
; AVX512-NEXT: vpminsq {{.*}}(%rip){1to8}, %zmm0, %zmm0
|
||||
; AVX512-NEXT: vpxor %xmm1, %xmm1, %xmm1
|
||||
; AVX512-NEXT: vpmaxsq %zmm1, %zmm0, %zmm0
|
||||
; AVX512-NEXT: vpmovqb %zmm0, %xmm0
|
||||
; AVX512-NEXT: vzeroupper
|
||||
; AVX512-NEXT: retq
|
||||
%1 = icmp slt <8 x i64> %a0, <i64 255, i64 255, i64 255, i64 255, i64 255, i64 255, i64 255, i64 255>
|
||||
%2 = select <8 x i1> %1, <8 x i64> %a0, <8 x i64> <i64 255, i64 255, i64 255, i64 255, i64 255, i64 255, i64 255, i64 255>
|
||||
%3 = icmp sgt <8 x i64> %2, zeroinitializer
|
||||
|
|
@ -3022,7 +2937,7 @@ define <8 x i8> @trunc_packus_v8i32_v8i8(<8 x i32> %a0) {
|
|||
; AVX512VL-NEXT: vpminsd {{.*}}(%rip){1to8}, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpxor %xmm1, %xmm1, %xmm1
|
||||
; AVX512VL-NEXT: vpmaxsd %ymm1, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpmovdb %zmm0, %xmm0
|
||||
; AVX512VL-NEXT: vpmovdb %ymm0, %xmm0
|
||||
; AVX512VL-NEXT: vzeroupper
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
|
|
@ -3041,7 +2956,7 @@ define <8 x i8> @trunc_packus_v8i32_v8i8(<8 x i32> %a0) {
|
|||
; AVX512BWVL-NEXT: vpminsd {{.*}}(%rip){1to8}, %ymm0, %ymm0
|
||||
; AVX512BWVL-NEXT: vpxor %xmm1, %xmm1, %xmm1
|
||||
; AVX512BWVL-NEXT: vpmaxsd %ymm1, %ymm0, %ymm0
|
||||
; AVX512BWVL-NEXT: vpmovdb %zmm0, %xmm0
|
||||
; AVX512BWVL-NEXT: vpmovdb %ymm0, %xmm0
|
||||
; AVX512BWVL-NEXT: vzeroupper
|
||||
; AVX512BWVL-NEXT: retq
|
||||
%1 = icmp slt <8 x i32> %a0, <i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255>
|
||||
|
|
|
|||
|
|
@ -1633,95 +1633,13 @@ define <8 x i8> @trunc_ssat_v8i64_v8i8(<8 x i64> %a0) {
|
|||
; AVX2-NEXT: vzeroupper
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512F-LABEL: trunc_ssat_v8i64_v8i8:
|
||||
; AVX512F: # %bb.0:
|
||||
; AVX512F-NEXT: vpminsq {{.*}}(%rip){1to8}, %zmm0, %zmm0
|
||||
; AVX512F-NEXT: vpmaxsq {{.*}}(%rip){1to8}, %zmm0, %zmm0
|
||||
; AVX512F-NEXT: vpextrq $1, %xmm0, %rax
|
||||
; AVX512F-NEXT: vmovq %xmm0, %rcx
|
||||
; AVX512F-NEXT: vmovd %ecx, %xmm1
|
||||
; AVX512F-NEXT: vpinsrb $1, %eax, %xmm1, %xmm1
|
||||
; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm2
|
||||
; AVX512F-NEXT: vmovq %xmm2, %rax
|
||||
; AVX512F-NEXT: vpinsrb $2, %eax, %xmm1, %xmm1
|
||||
; AVX512F-NEXT: vpextrq $1, %xmm2, %rax
|
||||
; AVX512F-NEXT: vpinsrb $3, %eax, %xmm1, %xmm1
|
||||
; AVX512F-NEXT: vextracti32x4 $2, %zmm0, %xmm2
|
||||
; AVX512F-NEXT: vmovq %xmm2, %rax
|
||||
; AVX512F-NEXT: vpinsrb $4, %eax, %xmm1, %xmm1
|
||||
; AVX512F-NEXT: vpextrq $1, %xmm2, %rax
|
||||
; AVX512F-NEXT: vpinsrb $5, %eax, %xmm1, %xmm1
|
||||
; AVX512F-NEXT: vextracti32x4 $3, %zmm0, %xmm0
|
||||
; AVX512F-NEXT: vmovq %xmm0, %rax
|
||||
; AVX512F-NEXT: vpinsrb $6, %eax, %xmm1, %xmm1
|
||||
; AVX512F-NEXT: vpextrq $1, %xmm0, %rax
|
||||
; AVX512F-NEXT: vpinsrb $7, %eax, %xmm1, %xmm0
|
||||
; AVX512F-NEXT: vzeroupper
|
||||
; AVX512F-NEXT: retq
|
||||
;
|
||||
; AVX512VL-LABEL: trunc_ssat_v8i64_v8i8:
|
||||
; AVX512VL: # %bb.0:
|
||||
; AVX512VL-NEXT: vpminsq {{.*}}(%rip){1to8}, %zmm0, %zmm0
|
||||
; AVX512VL-NEXT: vpmaxsq {{.*}}(%rip){1to8}, %zmm0, %zmm0
|
||||
; AVX512VL-NEXT: vpextrq $1, %xmm0, %rax
|
||||
; AVX512VL-NEXT: vmovq %xmm0, %rcx
|
||||
; AVX512VL-NEXT: vmovd %ecx, %xmm1
|
||||
; AVX512VL-NEXT: vpinsrb $1, %eax, %xmm1, %xmm1
|
||||
; AVX512VL-NEXT: vextracti128 $1, %ymm0, %xmm2
|
||||
; AVX512VL-NEXT: vmovq %xmm2, %rax
|
||||
; AVX512VL-NEXT: vpinsrb $2, %eax, %xmm1, %xmm1
|
||||
; AVX512VL-NEXT: vpextrq $1, %xmm2, %rax
|
||||
; AVX512VL-NEXT: vpinsrb $3, %eax, %xmm1, %xmm1
|
||||
; AVX512VL-NEXT: vextracti32x4 $2, %zmm0, %xmm2
|
||||
; AVX512VL-NEXT: vmovq %xmm2, %rax
|
||||
; AVX512VL-NEXT: vpinsrb $4, %eax, %xmm1, %xmm1
|
||||
; AVX512VL-NEXT: vpextrq $1, %xmm2, %rax
|
||||
; AVX512VL-NEXT: vpinsrb $5, %eax, %xmm1, %xmm1
|
||||
; AVX512VL-NEXT: vextracti32x4 $3, %zmm0, %xmm0
|
||||
; AVX512VL-NEXT: vmovq %xmm0, %rax
|
||||
; AVX512VL-NEXT: vpinsrb $6, %eax, %xmm1, %xmm1
|
||||
; AVX512VL-NEXT: vpextrq $1, %xmm0, %rax
|
||||
; AVX512VL-NEXT: vpinsrb $7, %eax, %xmm1, %xmm0
|
||||
; AVX512VL-NEXT: vzeroupper
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: trunc_ssat_v8i64_v8i8:
|
||||
; AVX512BW: # %bb.0:
|
||||
; AVX512BW-NEXT: vpminsq {{.*}}(%rip){1to8}, %zmm0, %zmm0
|
||||
; AVX512BW-NEXT: vpmaxsq {{.*}}(%rip){1to8}, %zmm0, %zmm0
|
||||
; AVX512BW-NEXT: vextracti64x4 $1, %zmm0, %ymm1
|
||||
; AVX512BW-NEXT: vextracti128 $1, %ymm1, %xmm2
|
||||
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm3 = <u,u,0,8,u,u,u,u,u,u,u,u,u,u,u,u>
|
||||
; AVX512BW-NEXT: vpshufb %xmm3, %xmm2, %xmm2
|
||||
; AVX512BW-NEXT: vpshufb %xmm3, %xmm1, %xmm1
|
||||
; AVX512BW-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
|
||||
; AVX512BW-NEXT: vextracti128 $1, %ymm0, %xmm2
|
||||
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm3 = <0,8,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
|
||||
; AVX512BW-NEXT: vpshufb %xmm3, %xmm2, %xmm2
|
||||
; AVX512BW-NEXT: vpshufb %xmm3, %xmm0, %xmm0
|
||||
; AVX512BW-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
|
||||
; AVX512BW-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2,3]
|
||||
; AVX512BW-NEXT: vzeroupper
|
||||
; AVX512BW-NEXT: retq
|
||||
;
|
||||
; AVX512BWVL-LABEL: trunc_ssat_v8i64_v8i8:
|
||||
; AVX512BWVL: # %bb.0:
|
||||
; AVX512BWVL-NEXT: vpminsq {{.*}}(%rip){1to8}, %zmm0, %zmm0
|
||||
; AVX512BWVL-NEXT: vpmaxsq {{.*}}(%rip){1to8}, %zmm0, %zmm0
|
||||
; AVX512BWVL-NEXT: vextracti64x4 $1, %zmm0, %ymm1
|
||||
; AVX512BWVL-NEXT: vextracti128 $1, %ymm1, %xmm2
|
||||
; AVX512BWVL-NEXT: vmovdqa {{.*#+}} xmm3 = <u,u,0,8,u,u,u,u,u,u,u,u,u,u,u,u>
|
||||
; AVX512BWVL-NEXT: vpshufb %xmm3, %xmm2, %xmm2
|
||||
; AVX512BWVL-NEXT: vpshufb %xmm3, %xmm1, %xmm1
|
||||
; AVX512BWVL-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
|
||||
; AVX512BWVL-NEXT: vextracti128 $1, %ymm0, %xmm2
|
||||
; AVX512BWVL-NEXT: vmovdqa {{.*#+}} xmm3 = <0,8,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
|
||||
; AVX512BWVL-NEXT: vpshufb %xmm3, %xmm2, %xmm2
|
||||
; AVX512BWVL-NEXT: vpshufb %xmm3, %xmm0, %xmm0
|
||||
; AVX512BWVL-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
|
||||
; AVX512BWVL-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2,3]
|
||||
; AVX512BWVL-NEXT: vzeroupper
|
||||
; AVX512BWVL-NEXT: retq
|
||||
; AVX512-LABEL: trunc_ssat_v8i64_v8i8:
|
||||
; AVX512: # %bb.0:
|
||||
; AVX512-NEXT: vpminsq {{.*}}(%rip){1to8}, %zmm0, %zmm0
|
||||
; AVX512-NEXT: vpmaxsq {{.*}}(%rip){1to8}, %zmm0, %zmm0
|
||||
; AVX512-NEXT: vpmovqb %zmm0, %xmm0
|
||||
; AVX512-NEXT: vzeroupper
|
||||
; AVX512-NEXT: retq
|
||||
%1 = icmp slt <8 x i64> %a0, <i64 127, i64 127, i64 127, i64 127, i64 127, i64 127, i64 127, i64 127>
|
||||
%2 = select <8 x i1> %1, <8 x i64> %a0, <8 x i64> <i64 127, i64 127, i64 127, i64 127, i64 127, i64 127, i64 127, i64 127>
|
||||
%3 = icmp sgt <8 x i64> %2, <i64 -128, i64 -128, i64 -128, i64 -128, i64 -128, i64 -128, i64 -128, i64 -128>
|
||||
|
|
@ -2975,7 +2893,7 @@ define <8 x i8> @trunc_ssat_v8i32_v8i8(<8 x i32> %a0) {
|
|||
; AVX512VL: # %bb.0:
|
||||
; AVX512VL-NEXT: vpminsd {{.*}}(%rip){1to8}, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpmaxsd {{.*}}(%rip){1to8}, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpmovdb %zmm0, %xmm0
|
||||
; AVX512VL-NEXT: vpmovdb %ymm0, %xmm0
|
||||
; AVX512VL-NEXT: vzeroupper
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
|
|
@ -2993,7 +2911,7 @@ define <8 x i8> @trunc_ssat_v8i32_v8i8(<8 x i32> %a0) {
|
|||
; AVX512BWVL: # %bb.0:
|
||||
; AVX512BWVL-NEXT: vpminsd {{.*}}(%rip){1to8}, %ymm0, %ymm0
|
||||
; AVX512BWVL-NEXT: vpmaxsd {{.*}}(%rip){1to8}, %ymm0, %ymm0
|
||||
; AVX512BWVL-NEXT: vpmovdb %zmm0, %xmm0
|
||||
; AVX512BWVL-NEXT: vpmovdb %ymm0, %xmm0
|
||||
; AVX512BWVL-NEXT: vzeroupper
|
||||
; AVX512BWVL-NEXT: retq
|
||||
%1 = icmp slt <8 x i32> %a0, <i32 127, i32 127, i32 127, i32 127, i32 127, i32 127, i32 127, i32 127>
|
||||
|
|
|
|||
|
|
@ -1216,91 +1216,12 @@ define <8 x i8> @trunc_usat_v8i64_v8i8(<8 x i64> %a0) {
|
|||
; AVX2-NEXT: vzeroupper
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512F-LABEL: trunc_usat_v8i64_v8i8:
|
||||
; AVX512F: # %bb.0:
|
||||
; AVX512F-NEXT: vpminuq {{.*}}(%rip){1to8}, %zmm0, %zmm0
|
||||
; AVX512F-NEXT: vpextrq $1, %xmm0, %rax
|
||||
; AVX512F-NEXT: vmovq %xmm0, %rcx
|
||||
; AVX512F-NEXT: vmovd %ecx, %xmm1
|
||||
; AVX512F-NEXT: vpinsrb $1, %eax, %xmm1, %xmm1
|
||||
; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm2
|
||||
; AVX512F-NEXT: vmovq %xmm2, %rax
|
||||
; AVX512F-NEXT: vpinsrb $2, %eax, %xmm1, %xmm1
|
||||
; AVX512F-NEXT: vpextrq $1, %xmm2, %rax
|
||||
; AVX512F-NEXT: vpinsrb $3, %eax, %xmm1, %xmm1
|
||||
; AVX512F-NEXT: vextracti32x4 $2, %zmm0, %xmm2
|
||||
; AVX512F-NEXT: vmovq %xmm2, %rax
|
||||
; AVX512F-NEXT: vpinsrb $4, %eax, %xmm1, %xmm1
|
||||
; AVX512F-NEXT: vpextrq $1, %xmm2, %rax
|
||||
; AVX512F-NEXT: vpinsrb $5, %eax, %xmm1, %xmm1
|
||||
; AVX512F-NEXT: vextracti32x4 $3, %zmm0, %xmm0
|
||||
; AVX512F-NEXT: vmovq %xmm0, %rax
|
||||
; AVX512F-NEXT: vpinsrb $6, %eax, %xmm1, %xmm1
|
||||
; AVX512F-NEXT: vpextrq $1, %xmm0, %rax
|
||||
; AVX512F-NEXT: vpinsrb $7, %eax, %xmm1, %xmm0
|
||||
; AVX512F-NEXT: vzeroupper
|
||||
; AVX512F-NEXT: retq
|
||||
;
|
||||
; AVX512VL-LABEL: trunc_usat_v8i64_v8i8:
|
||||
; AVX512VL: # %bb.0:
|
||||
; AVX512VL-NEXT: vpminuq {{.*}}(%rip){1to8}, %zmm0, %zmm0
|
||||
; AVX512VL-NEXT: vpextrq $1, %xmm0, %rax
|
||||
; AVX512VL-NEXT: vmovq %xmm0, %rcx
|
||||
; AVX512VL-NEXT: vmovd %ecx, %xmm1
|
||||
; AVX512VL-NEXT: vpinsrb $1, %eax, %xmm1, %xmm1
|
||||
; AVX512VL-NEXT: vextracti128 $1, %ymm0, %xmm2
|
||||
; AVX512VL-NEXT: vmovq %xmm2, %rax
|
||||
; AVX512VL-NEXT: vpinsrb $2, %eax, %xmm1, %xmm1
|
||||
; AVX512VL-NEXT: vpextrq $1, %xmm2, %rax
|
||||
; AVX512VL-NEXT: vpinsrb $3, %eax, %xmm1, %xmm1
|
||||
; AVX512VL-NEXT: vextracti32x4 $2, %zmm0, %xmm2
|
||||
; AVX512VL-NEXT: vmovq %xmm2, %rax
|
||||
; AVX512VL-NEXT: vpinsrb $4, %eax, %xmm1, %xmm1
|
||||
; AVX512VL-NEXT: vpextrq $1, %xmm2, %rax
|
||||
; AVX512VL-NEXT: vpinsrb $5, %eax, %xmm1, %xmm1
|
||||
; AVX512VL-NEXT: vextracti32x4 $3, %zmm0, %xmm0
|
||||
; AVX512VL-NEXT: vmovq %xmm0, %rax
|
||||
; AVX512VL-NEXT: vpinsrb $6, %eax, %xmm1, %xmm1
|
||||
; AVX512VL-NEXT: vpextrq $1, %xmm0, %rax
|
||||
; AVX512VL-NEXT: vpinsrb $7, %eax, %xmm1, %xmm0
|
||||
; AVX512VL-NEXT: vzeroupper
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: trunc_usat_v8i64_v8i8:
|
||||
; AVX512BW: # %bb.0:
|
||||
; AVX512BW-NEXT: vpminuq {{.*}}(%rip){1to8}, %zmm0, %zmm0
|
||||
; AVX512BW-NEXT: vextracti64x4 $1, %zmm0, %ymm1
|
||||
; AVX512BW-NEXT: vextracti128 $1, %ymm1, %xmm2
|
||||
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm3 = <u,u,0,8,u,u,u,u,u,u,u,u,u,u,u,u>
|
||||
; AVX512BW-NEXT: vpshufb %xmm3, %xmm2, %xmm2
|
||||
; AVX512BW-NEXT: vpshufb %xmm3, %xmm1, %xmm1
|
||||
; AVX512BW-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
|
||||
; AVX512BW-NEXT: vextracti128 $1, %ymm0, %xmm2
|
||||
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm3 = <0,8,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
|
||||
; AVX512BW-NEXT: vpshufb %xmm3, %xmm2, %xmm2
|
||||
; AVX512BW-NEXT: vpshufb %xmm3, %xmm0, %xmm0
|
||||
; AVX512BW-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
|
||||
; AVX512BW-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2,3]
|
||||
; AVX512BW-NEXT: vzeroupper
|
||||
; AVX512BW-NEXT: retq
|
||||
;
|
||||
; AVX512BWVL-LABEL: trunc_usat_v8i64_v8i8:
|
||||
; AVX512BWVL: # %bb.0:
|
||||
; AVX512BWVL-NEXT: vpminuq {{.*}}(%rip){1to8}, %zmm0, %zmm0
|
||||
; AVX512BWVL-NEXT: vextracti64x4 $1, %zmm0, %ymm1
|
||||
; AVX512BWVL-NEXT: vextracti128 $1, %ymm1, %xmm2
|
||||
; AVX512BWVL-NEXT: vmovdqa {{.*#+}} xmm3 = <u,u,0,8,u,u,u,u,u,u,u,u,u,u,u,u>
|
||||
; AVX512BWVL-NEXT: vpshufb %xmm3, %xmm2, %xmm2
|
||||
; AVX512BWVL-NEXT: vpshufb %xmm3, %xmm1, %xmm1
|
||||
; AVX512BWVL-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
|
||||
; AVX512BWVL-NEXT: vextracti128 $1, %ymm0, %xmm2
|
||||
; AVX512BWVL-NEXT: vmovdqa {{.*#+}} xmm3 = <0,8,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
|
||||
; AVX512BWVL-NEXT: vpshufb %xmm3, %xmm2, %xmm2
|
||||
; AVX512BWVL-NEXT: vpshufb %xmm3, %xmm0, %xmm0
|
||||
; AVX512BWVL-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
|
||||
; AVX512BWVL-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2,3]
|
||||
; AVX512BWVL-NEXT: vzeroupper
|
||||
; AVX512BWVL-NEXT: retq
|
||||
; AVX512-LABEL: trunc_usat_v8i64_v8i8:
|
||||
; AVX512: # %bb.0:
|
||||
; AVX512-NEXT: vpminuq {{.*}}(%rip){1to8}, %zmm0, %zmm0
|
||||
; AVX512-NEXT: vpmovqb %zmm0, %xmm0
|
||||
; AVX512-NEXT: vzeroupper
|
||||
; AVX512-NEXT: retq
|
||||
%1 = icmp ult <8 x i64> %a0, <i64 255, i64 255, i64 255, i64 255, i64 255, i64 255, i64 255, i64 255>
|
||||
%2 = select <8 x i1> %1, <8 x i64> %a0, <8 x i64> <i64 255, i64 255, i64 255, i64 255, i64 255, i64 255, i64 255, i64 255>
|
||||
%3 = trunc <8 x i64> %2 to <8 x i8>
|
||||
|
|
@ -2110,7 +2031,7 @@ define <8 x i8> @trunc_usat_v8i32_v8i8(<8 x i32> %a0) {
|
|||
; AVX512VL-LABEL: trunc_usat_v8i32_v8i8:
|
||||
; AVX512VL: # %bb.0:
|
||||
; AVX512VL-NEXT: vpminud {{.*}}(%rip){1to8}, %ymm0, %ymm0
|
||||
; AVX512VL-NEXT: vpmovdb %zmm0, %xmm0
|
||||
; AVX512VL-NEXT: vpmovdb %ymm0, %xmm0
|
||||
; AVX512VL-NEXT: vzeroupper
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
|
|
@ -2125,7 +2046,7 @@ define <8 x i8> @trunc_usat_v8i32_v8i8(<8 x i32> %a0) {
|
|||
; AVX512BWVL-LABEL: trunc_usat_v8i32_v8i8:
|
||||
; AVX512BWVL: # %bb.0:
|
||||
; AVX512BWVL-NEXT: vpminud {{.*}}(%rip){1to8}, %ymm0, %ymm0
|
||||
; AVX512BWVL-NEXT: vpmovdb %zmm0, %xmm0
|
||||
; AVX512BWVL-NEXT: vpmovdb %ymm0, %xmm0
|
||||
; AVX512BWVL-NEXT: vzeroupper
|
||||
; AVX512BWVL-NEXT: retq
|
||||
%1 = icmp ult <8 x i32> %a0, <i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255, i32 255>
|
||||
|
|
|
|||
|
|
@ -1562,15 +1562,41 @@ define <8 x i16> @trunc2x4i64_8i16(<4 x i64> %a, <4 x i64> %b) {
|
|||
; AVX2-FAST-NEXT: vzeroupper
|
||||
; AVX2-FAST-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: trunc2x4i64_8i16:
|
||||
; AVX512: # %bb.0: # %entry
|
||||
; AVX512-NEXT: # kill: def $ymm1 killed $ymm1 def $zmm1
|
||||
; AVX512-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
|
||||
; AVX512-NEXT: vpmovqw %zmm0, %xmm0
|
||||
; AVX512-NEXT: vpmovqw %zmm1, %xmm1
|
||||
; AVX512-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; AVX512-NEXT: vzeroupper
|
||||
; AVX512-NEXT: retq
|
||||
; AVX512F-LABEL: trunc2x4i64_8i16:
|
||||
; AVX512F: # %bb.0: # %entry
|
||||
; AVX512F-NEXT: # kill: def $ymm1 killed $ymm1 def $zmm1
|
||||
; AVX512F-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
|
||||
; AVX512F-NEXT: vpmovqw %zmm0, %xmm0
|
||||
; AVX512F-NEXT: vpmovqw %zmm1, %xmm1
|
||||
; AVX512F-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; AVX512F-NEXT: vzeroupper
|
||||
; AVX512F-NEXT: retq
|
||||
;
|
||||
; AVX512VL-LABEL: trunc2x4i64_8i16:
|
||||
; AVX512VL: # %bb.0: # %entry
|
||||
; AVX512VL-NEXT: vpmovqw %ymm0, %xmm0
|
||||
; AVX512VL-NEXT: vpmovqw %ymm1, %xmm1
|
||||
; AVX512VL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; AVX512VL-NEXT: vzeroupper
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: trunc2x4i64_8i16:
|
||||
; AVX512BW: # %bb.0: # %entry
|
||||
; AVX512BW-NEXT: # kill: def $ymm1 killed $ymm1 def $zmm1
|
||||
; AVX512BW-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
|
||||
; AVX512BW-NEXT: vpmovqw %zmm0, %xmm0
|
||||
; AVX512BW-NEXT: vpmovqw %zmm1, %xmm1
|
||||
; AVX512BW-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; AVX512BW-NEXT: vzeroupper
|
||||
; AVX512BW-NEXT: retq
|
||||
;
|
||||
; AVX512BWVL-LABEL: trunc2x4i64_8i16:
|
||||
; AVX512BWVL: # %bb.0: # %entry
|
||||
; AVX512BWVL-NEXT: vpmovqw %ymm0, %xmm0
|
||||
; AVX512BWVL-NEXT: vpmovqw %ymm1, %xmm1
|
||||
; AVX512BWVL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; AVX512BWVL-NEXT: vzeroupper
|
||||
; AVX512BWVL-NEXT: retq
|
||||
entry:
|
||||
%0 = trunc <4 x i64> %a to <4 x i16>
|
||||
%1 = trunc <4 x i64> %b to <4 x i16>
|
||||
|
|
@ -1584,71 +1610,15 @@ define <4 x i32> @trunc2x2i64_4i32(<2 x i64> %a, <2 x i64> %b) {
|
|||
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX1-LABEL: trunc2x2i64_4i32:
|
||||
; AVX1: # %bb.0: # %entry
|
||||
; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
|
||||
; AVX1-NEXT: retq
|
||||
; AVX-LABEL: trunc2x2i64_4i32:
|
||||
; AVX: # %bb.0: # %entry
|
||||
; AVX-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
; AVX2-SLOW-LABEL: trunc2x2i64_4i32:
|
||||
; AVX2-SLOW: # %bb.0: # %entry
|
||||
; AVX2-SLOW-NEXT: # kill: def $xmm1 killed $xmm1 def $ymm1
|
||||
; AVX2-SLOW-NEXT: # kill: def $xmm0 killed $xmm0 def $ymm0
|
||||
; AVX2-SLOW-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
|
||||
; AVX2-SLOW-NEXT: vpermilps {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
|
||||
; AVX2-SLOW-NEXT: vmovlhps {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; AVX2-SLOW-NEXT: vzeroupper
|
||||
; AVX2-SLOW-NEXT: retq
|
||||
;
|
||||
; AVX2-FAST-LABEL: trunc2x2i64_4i32:
|
||||
; AVX2-FAST: # %bb.0: # %entry
|
||||
; AVX2-FAST-NEXT: # kill: def $xmm1 killed $xmm1 def $ymm1
|
||||
; AVX2-FAST-NEXT: # kill: def $xmm0 killed $xmm0 def $ymm0
|
||||
; AVX2-FAST-NEXT: vmovaps {{.*#+}} ymm2 = [0,2,4,6,4,6,6,7]
|
||||
; AVX2-FAST-NEXT: vpermps %ymm0, %ymm2, %ymm0
|
||||
; AVX2-FAST-NEXT: vpermps %ymm1, %ymm2, %ymm1
|
||||
; AVX2-FAST-NEXT: vmovlhps {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; AVX2-FAST-NEXT: vzeroupper
|
||||
; AVX2-FAST-NEXT: retq
|
||||
;
|
||||
; AVX512F-LABEL: trunc2x2i64_4i32:
|
||||
; AVX512F: # %bb.0: # %entry
|
||||
; AVX512F-NEXT: # kill: def $xmm1 killed $xmm1 def $zmm1
|
||||
; AVX512F-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
|
||||
; AVX512F-NEXT: vpmovqd %zmm0, %ymm0
|
||||
; AVX512F-NEXT: vpmovqd %zmm1, %ymm1
|
||||
; AVX512F-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; AVX512F-NEXT: vzeroupper
|
||||
; AVX512F-NEXT: retq
|
||||
;
|
||||
; AVX512VL-LABEL: trunc2x2i64_4i32:
|
||||
; AVX512VL: # %bb.0: # %entry
|
||||
; AVX512VL-NEXT: # kill: def $xmm1 killed $xmm1 def $ymm1
|
||||
; AVX512VL-NEXT: # kill: def $xmm0 killed $xmm0 def $ymm0
|
||||
; AVX512VL-NEXT: vpmovqd %ymm0, %xmm0
|
||||
; AVX512VL-NEXT: vpmovqd %ymm1, %xmm1
|
||||
; AVX512VL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; AVX512VL-NEXT: vzeroupper
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: trunc2x2i64_4i32:
|
||||
; AVX512BW: # %bb.0: # %entry
|
||||
; AVX512BW-NEXT: # kill: def $xmm1 killed $xmm1 def $zmm1
|
||||
; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
|
||||
; AVX512BW-NEXT: vpmovqd %zmm0, %ymm0
|
||||
; AVX512BW-NEXT: vpmovqd %zmm1, %ymm1
|
||||
; AVX512BW-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; AVX512BW-NEXT: vzeroupper
|
||||
; AVX512BW-NEXT: retq
|
||||
;
|
||||
; AVX512BWVL-LABEL: trunc2x2i64_4i32:
|
||||
; AVX512BWVL: # %bb.0: # %entry
|
||||
; AVX512BWVL-NEXT: # kill: def $xmm1 killed $xmm1 def $ymm1
|
||||
; AVX512BWVL-NEXT: # kill: def $xmm0 killed $xmm0 def $ymm0
|
||||
; AVX512BWVL-NEXT: vpmovqd %ymm0, %xmm0
|
||||
; AVX512BWVL-NEXT: vpmovqd %ymm1, %xmm1
|
||||
; AVX512BWVL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; AVX512BWVL-NEXT: vzeroupper
|
||||
; AVX512BWVL-NEXT: retq
|
||||
; AVX512-LABEL: trunc2x2i64_4i32:
|
||||
; AVX512: # %bb.0: # %entry
|
||||
; AVX512-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
|
||||
; AVX512-NEXT: retq
|
||||
entry:
|
||||
%0 = trunc <2 x i64> %a to <2 x i32>
|
||||
%1 = trunc <2 x i64> %b to <2 x i32>
|
||||
|
|
@ -1663,60 +1633,17 @@ define i64 @trunc2i64_i64(<2 x i64> %inval) {
|
|||
; SSE-NEXT: movq %xmm0, %rax
|
||||
; SSE-NEXT: retq
|
||||
;
|
||||
; AVX1-LABEL: trunc2i64_i64:
|
||||
; AVX1: # %bb.0: # %entry
|
||||
; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
|
||||
; AVX1-NEXT: vmovq %xmm0, %rax
|
||||
; AVX1-NEXT: retq
|
||||
; AVX-LABEL: trunc2i64_i64:
|
||||
; AVX: # %bb.0: # %entry
|
||||
; AVX-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
|
||||
; AVX-NEXT: vmovq %xmm0, %rax
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
; AVX2-SLOW-LABEL: trunc2i64_i64:
|
||||
; AVX2-SLOW: # %bb.0: # %entry
|
||||
; AVX2-SLOW-NEXT: # kill: def $xmm0 killed $xmm0 def $ymm0
|
||||
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
|
||||
; AVX2-SLOW-NEXT: vmovq %xmm0, %rax
|
||||
; AVX2-SLOW-NEXT: vzeroupper
|
||||
; AVX2-SLOW-NEXT: retq
|
||||
;
|
||||
; AVX2-FAST-LABEL: trunc2i64_i64:
|
||||
; AVX2-FAST: # %bb.0: # %entry
|
||||
; AVX2-FAST-NEXT: # kill: def $xmm0 killed $xmm0 def $ymm0
|
||||
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} ymm1 = [0,2,4,6,4,6,6,7]
|
||||
; AVX2-FAST-NEXT: vpermd %ymm0, %ymm1, %ymm0
|
||||
; AVX2-FAST-NEXT: vmovq %xmm0, %rax
|
||||
; AVX2-FAST-NEXT: vzeroupper
|
||||
; AVX2-FAST-NEXT: retq
|
||||
;
|
||||
; AVX512F-LABEL: trunc2i64_i64:
|
||||
; AVX512F: # %bb.0: # %entry
|
||||
; AVX512F-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
|
||||
; AVX512F-NEXT: vpmovqd %zmm0, %ymm0
|
||||
; AVX512F-NEXT: vmovq %xmm0, %rax
|
||||
; AVX512F-NEXT: vzeroupper
|
||||
; AVX512F-NEXT: retq
|
||||
;
|
||||
; AVX512VL-LABEL: trunc2i64_i64:
|
||||
; AVX512VL: # %bb.0: # %entry
|
||||
; AVX512VL-NEXT: # kill: def $xmm0 killed $xmm0 def $ymm0
|
||||
; AVX512VL-NEXT: vpmovqd %ymm0, %xmm0
|
||||
; AVX512VL-NEXT: vmovq %xmm0, %rax
|
||||
; AVX512VL-NEXT: vzeroupper
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: trunc2i64_i64:
|
||||
; AVX512BW: # %bb.0: # %entry
|
||||
; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
|
||||
; AVX512BW-NEXT: vpmovqd %zmm0, %ymm0
|
||||
; AVX512BW-NEXT: vmovq %xmm0, %rax
|
||||
; AVX512BW-NEXT: vzeroupper
|
||||
; AVX512BW-NEXT: retq
|
||||
;
|
||||
; AVX512BWVL-LABEL: trunc2i64_i64:
|
||||
; AVX512BWVL: # %bb.0: # %entry
|
||||
; AVX512BWVL-NEXT: # kill: def $xmm0 killed $xmm0 def $ymm0
|
||||
; AVX512BWVL-NEXT: vpmovqd %ymm0, %xmm0
|
||||
; AVX512BWVL-NEXT: vmovq %xmm0, %rax
|
||||
; AVX512BWVL-NEXT: vzeroupper
|
||||
; AVX512BWVL-NEXT: retq
|
||||
; AVX512-LABEL: trunc2i64_i64:
|
||||
; AVX512: # %bb.0: # %entry
|
||||
; AVX512-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
|
||||
; AVX512-NEXT: vmovq %xmm0, %rax
|
||||
; AVX512-NEXT: retq
|
||||
entry:
|
||||
%0 = trunc <2 x i64> %inval to <2 x i32>
|
||||
%1 = bitcast <2 x i32> %0 to i64
|
||||
|
|
@ -1751,61 +1678,21 @@ define <8 x i16> @trunc2x4i32_8i16(<4 x i32> %a, <4 x i32> %b) {
|
|||
; SSE41-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; SSE41-NEXT: retq
|
||||
;
|
||||
; AVX1-LABEL: trunc2x4i32_8i16:
|
||||
; AVX1: # %bb.0: # %entry
|
||||
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
|
||||
; AVX1-NEXT: vpshufb %xmm2, %xmm0, %xmm0
|
||||
; AVX1-NEXT: vpshufb %xmm2, %xmm1, %xmm1
|
||||
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; AVX1-NEXT: retq
|
||||
; AVX-LABEL: trunc2x4i32_8i16:
|
||||
; AVX: # %bb.0: # %entry
|
||||
; AVX-NEXT: vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
|
||||
; AVX-NEXT: vpshufb %xmm2, %xmm1, %xmm1
|
||||
; AVX-NEXT: vpshufb %xmm2, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
; AVX2-LABEL: trunc2x4i32_8i16:
|
||||
; AVX2: # %bb.0: # %entry
|
||||
; AVX2-NEXT: vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15,16,17,20,21,24,25,28,29,24,25,28,29,28,29,30,31]
|
||||
; AVX2-NEXT: vpshufb %xmm2, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpshufb %xmm2, %xmm1, %xmm1
|
||||
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512F-LABEL: trunc2x4i32_8i16:
|
||||
; AVX512F: # %bb.0: # %entry
|
||||
; AVX512F-NEXT: # kill: def $xmm1 killed $xmm1 def $zmm1
|
||||
; AVX512F-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
|
||||
; AVX512F-NEXT: vpmovdw %zmm0, %ymm0
|
||||
; AVX512F-NEXT: vpmovdw %zmm1, %ymm1
|
||||
; AVX512F-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; AVX512F-NEXT: vzeroupper
|
||||
; AVX512F-NEXT: retq
|
||||
;
|
||||
; AVX512VL-LABEL: trunc2x4i32_8i16:
|
||||
; AVX512VL: # %bb.0: # %entry
|
||||
; AVX512VL-NEXT: # kill: def $xmm1 killed $xmm1 def $ymm1
|
||||
; AVX512VL-NEXT: # kill: def $xmm0 killed $xmm0 def $ymm0
|
||||
; AVX512VL-NEXT: vpmovdw %ymm0, %xmm0
|
||||
; AVX512VL-NEXT: vpmovdw %ymm1, %xmm1
|
||||
; AVX512VL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; AVX512VL-NEXT: vzeroupper
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: trunc2x4i32_8i16:
|
||||
; AVX512BW: # %bb.0: # %entry
|
||||
; AVX512BW-NEXT: # kill: def $xmm1 killed $xmm1 def $zmm1
|
||||
; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
|
||||
; AVX512BW-NEXT: vpmovdw %zmm0, %ymm0
|
||||
; AVX512BW-NEXT: vpmovdw %zmm1, %ymm1
|
||||
; AVX512BW-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; AVX512BW-NEXT: vzeroupper
|
||||
; AVX512BW-NEXT: retq
|
||||
;
|
||||
; AVX512BWVL-LABEL: trunc2x4i32_8i16:
|
||||
; AVX512BWVL: # %bb.0: # %entry
|
||||
; AVX512BWVL-NEXT: # kill: def $xmm1 killed $xmm1 def $ymm1
|
||||
; AVX512BWVL-NEXT: # kill: def $xmm0 killed $xmm0 def $ymm0
|
||||
; AVX512BWVL-NEXT: vpmovdw %ymm0, %xmm0
|
||||
; AVX512BWVL-NEXT: vpmovdw %ymm1, %xmm1
|
||||
; AVX512BWVL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; AVX512BWVL-NEXT: vzeroupper
|
||||
; AVX512BWVL-NEXT: retq
|
||||
; AVX512-LABEL: trunc2x4i32_8i16:
|
||||
; AVX512: # %bb.0: # %entry
|
||||
; AVX512-NEXT: vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
|
||||
; AVX512-NEXT: vpshufb %xmm2, %xmm1, %xmm1
|
||||
; AVX512-NEXT: vpshufb %xmm2, %xmm0, %xmm0
|
||||
; AVX512-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; AVX512-NEXT: retq
|
||||
entry:
|
||||
%0 = trunc <4 x i32> %a to <4 x i16>
|
||||
%1 = trunc <4 x i32> %b to <4 x i16>
|
||||
|
|
@ -1841,37 +1728,11 @@ define i64 @trunc4i32_i64(<4 x i32> %inval) {
|
|||
; AVX-NEXT: vmovq %xmm0, %rax
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
; AVX512F-LABEL: trunc4i32_i64:
|
||||
; AVX512F: # %bb.0: # %entry
|
||||
; AVX512F-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
|
||||
; AVX512F-NEXT: vpmovdw %zmm0, %ymm0
|
||||
; AVX512F-NEXT: vmovq %xmm0, %rax
|
||||
; AVX512F-NEXT: vzeroupper
|
||||
; AVX512F-NEXT: retq
|
||||
;
|
||||
; AVX512VL-LABEL: trunc4i32_i64:
|
||||
; AVX512VL: # %bb.0: # %entry
|
||||
; AVX512VL-NEXT: # kill: def $xmm0 killed $xmm0 def $ymm0
|
||||
; AVX512VL-NEXT: vpmovdw %ymm0, %xmm0
|
||||
; AVX512VL-NEXT: vmovq %xmm0, %rax
|
||||
; AVX512VL-NEXT: vzeroupper
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: trunc4i32_i64:
|
||||
; AVX512BW: # %bb.0: # %entry
|
||||
; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
|
||||
; AVX512BW-NEXT: vpmovdw %zmm0, %ymm0
|
||||
; AVX512BW-NEXT: vmovq %xmm0, %rax
|
||||
; AVX512BW-NEXT: vzeroupper
|
||||
; AVX512BW-NEXT: retq
|
||||
;
|
||||
; AVX512BWVL-LABEL: trunc4i32_i64:
|
||||
; AVX512BWVL: # %bb.0: # %entry
|
||||
; AVX512BWVL-NEXT: # kill: def $xmm0 killed $xmm0 def $ymm0
|
||||
; AVX512BWVL-NEXT: vpmovdw %ymm0, %xmm0
|
||||
; AVX512BWVL-NEXT: vmovq %xmm0, %rax
|
||||
; AVX512BWVL-NEXT: vzeroupper
|
||||
; AVX512BWVL-NEXT: retq
|
||||
; AVX512-LABEL: trunc4i32_i64:
|
||||
; AVX512: # %bb.0: # %entry
|
||||
; AVX512-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
|
||||
; AVX512-NEXT: vmovq %xmm0, %rax
|
||||
; AVX512-NEXT: retq
|
||||
entry:
|
||||
%0 = trunc <4 x i32> %inval to <4 x i16>
|
||||
%1 = bitcast <4 x i16> %0 to i64
|
||||
|
|
@ -1906,54 +1767,18 @@ define <16 x i8> @trunc2x8i16_16i8(<8 x i16> %a, <8 x i16> %b) {
|
|||
; AVX-LABEL: trunc2x8i16_16i8:
|
||||
; AVX: # %bb.0: # %entry
|
||||
; AVX-NEXT: vmovdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
|
||||
; AVX-NEXT: vpshufb %xmm2, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpshufb %xmm2, %xmm1, %xmm1
|
||||
; AVX-NEXT: vpshufb %xmm2, %xmm0, %xmm0
|
||||
; AVX-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
; AVX512F-LABEL: trunc2x8i16_16i8:
|
||||
; AVX512F: # %bb.0: # %entry
|
||||
; AVX512F-NEXT: # kill: def $xmm1 killed $xmm1 def $ymm1
|
||||
; AVX512F-NEXT: # kill: def $xmm0 killed $xmm0 def $ymm0
|
||||
; AVX512F-NEXT: vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
|
||||
; AVX512F-NEXT: vpmovdb %zmm0, %xmm0
|
||||
; AVX512F-NEXT: vpmovzxwd {{.*#+}} zmm1 = ymm1[0],zero,ymm1[1],zero,ymm1[2],zero,ymm1[3],zero,ymm1[4],zero,ymm1[5],zero,ymm1[6],zero,ymm1[7],zero,ymm1[8],zero,ymm1[9],zero,ymm1[10],zero,ymm1[11],zero,ymm1[12],zero,ymm1[13],zero,ymm1[14],zero,ymm1[15],zero
|
||||
; AVX512F-NEXT: vpmovdb %zmm1, %xmm1
|
||||
; AVX512F-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; AVX512F-NEXT: vzeroupper
|
||||
; AVX512F-NEXT: retq
|
||||
;
|
||||
; AVX512VL-LABEL: trunc2x8i16_16i8:
|
||||
; AVX512VL: # %bb.0: # %entry
|
||||
; AVX512VL-NEXT: # kill: def $xmm1 killed $xmm1 def $ymm1
|
||||
; AVX512VL-NEXT: # kill: def $xmm0 killed $xmm0 def $ymm0
|
||||
; AVX512VL-NEXT: vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
|
||||
; AVX512VL-NEXT: vpmovdb %zmm0, %xmm0
|
||||
; AVX512VL-NEXT: vpmovzxwd {{.*#+}} zmm1 = ymm1[0],zero,ymm1[1],zero,ymm1[2],zero,ymm1[3],zero,ymm1[4],zero,ymm1[5],zero,ymm1[6],zero,ymm1[7],zero,ymm1[8],zero,ymm1[9],zero,ymm1[10],zero,ymm1[11],zero,ymm1[12],zero,ymm1[13],zero,ymm1[14],zero,ymm1[15],zero
|
||||
; AVX512VL-NEXT: vpmovdb %zmm1, %xmm1
|
||||
; AVX512VL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; AVX512VL-NEXT: vzeroupper
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: trunc2x8i16_16i8:
|
||||
; AVX512BW: # %bb.0: # %entry
|
||||
; AVX512BW-NEXT: # kill: def $xmm1 killed $xmm1 def $zmm1
|
||||
; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
|
||||
; AVX512BW-NEXT: vpmovwb %zmm0, %ymm0
|
||||
; AVX512BW-NEXT: vpmovwb %zmm1, %ymm1
|
||||
; AVX512BW-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; AVX512BW-NEXT: vzeroupper
|
||||
; AVX512BW-NEXT: retq
|
||||
;
|
||||
; AVX512BWVL-LABEL: trunc2x8i16_16i8:
|
||||
; AVX512BWVL: # %bb.0: # %entry
|
||||
; AVX512BWVL-NEXT: # kill: def $xmm1 killed $xmm1 def $ymm1
|
||||
; AVX512BWVL-NEXT: # kill: def $xmm0 killed $xmm0 def $ymm0
|
||||
; AVX512BWVL-NEXT: vpmovwb %ymm0, %xmm0
|
||||
; AVX512BWVL-NEXT: vpmovwb %ymm1, %xmm1
|
||||
; AVX512BWVL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; AVX512BWVL-NEXT: vzeroupper
|
||||
; AVX512BWVL-NEXT: retq
|
||||
; AVX512-LABEL: trunc2x8i16_16i8:
|
||||
; AVX512: # %bb.0: # %entry
|
||||
; AVX512-NEXT: vmovdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
|
||||
; AVX512-NEXT: vpshufb %xmm2, %xmm1, %xmm1
|
||||
; AVX512-NEXT: vpshufb %xmm2, %xmm0, %xmm0
|
||||
; AVX512-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
|
||||
; AVX512-NEXT: retq
|
||||
entry:
|
||||
%0 = trunc <8 x i16> %a to <8 x i8>
|
||||
%1 = trunc <8 x i16> %b to <8 x i8>
|
||||
|
|
@ -1988,39 +1813,11 @@ define i64 @trunc8i16_i64(<8 x i16> %inval) {
|
|||
; AVX-NEXT: vmovq %xmm0, %rax
|
||||
; AVX-NEXT: retq
|
||||
;
|
||||
; AVX512F-LABEL: trunc8i16_i64:
|
||||
; AVX512F: # %bb.0: # %entry
|
||||
; AVX512F-NEXT: # kill: def $xmm0 killed $xmm0 def $ymm0
|
||||
; AVX512F-NEXT: vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
|
||||
; AVX512F-NEXT: vpmovdb %zmm0, %xmm0
|
||||
; AVX512F-NEXT: vmovq %xmm0, %rax
|
||||
; AVX512F-NEXT: vzeroupper
|
||||
; AVX512F-NEXT: retq
|
||||
;
|
||||
; AVX512VL-LABEL: trunc8i16_i64:
|
||||
; AVX512VL: # %bb.0: # %entry
|
||||
; AVX512VL-NEXT: # kill: def $xmm0 killed $xmm0 def $ymm0
|
||||
; AVX512VL-NEXT: vpmovzxwd {{.*#+}} zmm0 = ymm0[0],zero,ymm0[1],zero,ymm0[2],zero,ymm0[3],zero,ymm0[4],zero,ymm0[5],zero,ymm0[6],zero,ymm0[7],zero,ymm0[8],zero,ymm0[9],zero,ymm0[10],zero,ymm0[11],zero,ymm0[12],zero,ymm0[13],zero,ymm0[14],zero,ymm0[15],zero
|
||||
; AVX512VL-NEXT: vpmovdb %zmm0, %xmm0
|
||||
; AVX512VL-NEXT: vmovq %xmm0, %rax
|
||||
; AVX512VL-NEXT: vzeroupper
|
||||
; AVX512VL-NEXT: retq
|
||||
;
|
||||
; AVX512BW-LABEL: trunc8i16_i64:
|
||||
; AVX512BW: # %bb.0: # %entry
|
||||
; AVX512BW-NEXT: # kill: def $xmm0 killed $xmm0 def $zmm0
|
||||
; AVX512BW-NEXT: vpmovwb %zmm0, %ymm0
|
||||
; AVX512BW-NEXT: vmovq %xmm0, %rax
|
||||
; AVX512BW-NEXT: vzeroupper
|
||||
; AVX512BW-NEXT: retq
|
||||
;
|
||||
; AVX512BWVL-LABEL: trunc8i16_i64:
|
||||
; AVX512BWVL: # %bb.0: # %entry
|
||||
; AVX512BWVL-NEXT: # kill: def $xmm0 killed $xmm0 def $ymm0
|
||||
; AVX512BWVL-NEXT: vpmovwb %ymm0, %xmm0
|
||||
; AVX512BWVL-NEXT: vmovq %xmm0, %rax
|
||||
; AVX512BWVL-NEXT: vzeroupper
|
||||
; AVX512BWVL-NEXT: retq
|
||||
; AVX512-LABEL: trunc8i16_i64:
|
||||
; AVX512: # %bb.0: # %entry
|
||||
; AVX512-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
|
||||
; AVX512-NEXT: vmovq %xmm0, %rax
|
||||
; AVX512-NEXT: retq
|
||||
entry:
|
||||
%0 = trunc <8 x i16> %inval to <8 x i8>
|
||||
%1 = bitcast <8 x i8> %0 to i64
|
||||
|
|
|
|||
Loading…
Reference in New Issue