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

[AVX-512] Add lowering to cvttpd2udq/cvttps2udq for fptoui v2f64/2f32 to 2i32 

This patch adds support for fptoui to 2i32 from both 2f64 and 2f32, building on Simon's change for the signed version in r284459 and using AVX-512 instructions.

If we don't have VLX support we need to use a 512-bit operation for v2f64->v2i32 and extract the result.

It also recognises that cvttpd2udq zeroes the upper 64-bits of the xmm result.

Differential Revision: https://reviews.llvm.org/D26331

llvm-svn: 286345
This commit is contained in:
Craig Topper 2016-11-09 07:48:51 +00:00
parent 731bf9c5d6
commit f334ac19ad
6 changed files with 53 additions and 51 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -1193,6 +1193,7 @@ X86TargetLowering::X86TargetLowering(const X86TargetMachine &TM,
setOperationAction(ISD::FP_TO_UINT, MVT::v16i32, Legal);
setOperationAction(ISD::FP_TO_UINT, MVT::v8i32, Legal);
setOperationAction(ISD::FP_TO_UINT, MVT::v4i32, Legal);
setOperationAction(ISD::FP_TO_UINT, MVT::v2i32, Custom);
setOperationAction(ISD::SINT_TO_FP, MVT::v16i32, Legal);
setOperationAction(ISD::SINT_TO_FP, MVT::v8i1, Custom);
setOperationAction(ISD::SINT_TO_FP, MVT::v16i1, Custom);
@ -22358,12 +22359,16 @@ void X86TargetLowering::ReplaceNodeResults(SDNode *N,
case ISD::FP_TO_UINT: {
bool IsSigned = N->getOpcode() == ISD::FP_TO_SINT;
if (IsSigned && N->getValueType(0) == MVT::v2i32) {
if (N->getValueType(0) == MVT::v2i32) {
assert((IsSigned || Subtarget.hasAVX512()) &&
"Can only handle signed conversion without AVX512");
assert(Subtarget.hasSSE2() && "Requires at least SSE2!");
SDValue Src = N->getOperand(0);
if (Src.getValueType() == MVT::v2f64) {
SDValue Idx = DAG.getIntPtrConstant(0, dl);
SDValue Res = DAG.getNode(X86ISD::CVTTPD2DQ, dl, MVT::v4i32, Src);
SDValue Res = DAG.getNode(IsSigned ? X86ISD::CVTTPD2DQ
: X86ISD::CVTTPD2UDQ,
dl, MVT::v4i32, Src);
Res = DAG.getNode(ISD::EXTRACT_SUBVECTOR, dl, MVT::v2i32, Res, Idx);
Results.push_back(Res);
return;
@ -22372,7 +22377,8 @@ void X86TargetLowering::ReplaceNodeResults(SDNode *N,
SDValue Idx = DAG.getIntPtrConstant(0, dl);
SDValue Res = DAG.getNode(ISD::CONCAT_VECTORS, dl, MVT::v4f32, Src,
DAG.getUNDEF(MVT::v2f32));
Res = DAG.getNode(ISD::FP_TO_SINT, dl, MVT::v4i32, Res);
Res = DAG.getNode(IsSigned ? ISD::FP_TO_SINT
: ISD::FP_TO_UINT, dl, MVT::v4i32, Res);
Res = DAG.getNode(ISD::EXTRACT_SUBVECTOR, dl, MVT::v2i32, Res, Idx);
Results.push_back(Res);
return;
@ -22700,6 +22706,7 @@ const char *X86TargetLowering::getTargetNodeName(unsigned Opcode) const {
case X86ISD::VFPROUND_RND: return "X86ISD::VFPROUND_RND";
case X86ISD::VFPROUNDS_RND: return "X86ISD::VFPROUNDS_RND";
case X86ISD::CVTTPD2DQ: return "X86ISD::CVTTPD2DQ";
case X86ISD::CVTTPD2UDQ: return "X86ISD::CVTTPD2UDQ";
case X86ISD::CVTDQ2PD: return "X86ISD::CVTDQ2PD";
case X86ISD::CVTUDQ2PD: return "X86ISD::CVTUDQ2PD";
case X86ISD::CVT2MASK: return "X86ISD::CVT2MASK";

4
llvm/lib/Target/X86/X86ISelLowering.h
View File

@ -302,8 +302,8 @@ namespace llvm {
// Vector FP round.
VFPROUND, VFPROUND_RND, VFPROUNDS_RND,
// Vector double to signed integer (truncated).
CVTTPD2DQ,
// Vector double to signed/unsigned integer (truncated).
CVTTPD2DQ, CVTTPD2UDQ,
// Vector signed/unsigned integer to double.
CVTDQ2PD, CVTUDQ2PD,

12
llvm/lib/Target/X86/X86InstrAVX512.td
View File

@ -6314,8 +6314,8 @@ defm VCVTTPS2UDQ : avx512_cvttps2dq<0x78, "vcvttps2udq", fp_to_uint,
X86cvttp2uiRnd>, PS,
EVEX_CD8<32, CD8VF>;
defm VCVTTPD2UDQ : avx512_cvttpd2dq<0x78, "vcvttpd2udq", fp_to_uint, fp_to_uint,
X86cvttp2uiRnd>, PS, VEX_W,
defm VCVTTPD2UDQ : avx512_cvttpd2dq<0x78, "vcvttpd2udq", fp_to_uint,
X86cvttpd2udq, X86cvttp2uiRnd>, PS, VEX_W,
EVEX_CD8<64, CD8VF>;
defm VCVTUDQ2PD : avx512_cvtdq2pd<0x7A, "vcvtudq2pd", uint_to_fp, X86cvtudq2pd>,
@ -6395,6 +6395,11 @@ def : Pat<(v4i32 (fp_to_uint (v4f64 VR256X:$src1))),
(v8f64 (INSERT_SUBREG (IMPLICIT_DEF),
VR256X:$src1, sub_ymm)))), sub_xmm)>;
def : Pat<(v4i32 (X86cvttpd2udq (v2f64 VR128X:$src))),
(EXTRACT_SUBREG (v8i32 (VCVTTPD2UDQZrr
(v8f64 (INSERT_SUBREG (IMPLICIT_DEF),
VR128X:$src, sub_xmm)))), sub_xmm)>;
def : Pat<(v8f32 (uint_to_fp (v8i32 VR256X:$src1))),
(EXTRACT_SUBREG (v16f32 (VCVTUDQ2PSZrr
(v16i32 (INSERT_SUBREG (IMPLICIT_DEF),
@ -6416,6 +6421,9 @@ let Predicates = [HasAVX512, HasVLX] in {
def : Pat<(X86vzmovl (v2i64 (bitconvert
(v4i32 (X86cvttpd2dq (v2f64 VR128X:$src)))))),
(VCVTTPD2DQZ128rr VR128:$src)>;
def : Pat<(v4i32 (bitconvert (X86vzmovl (v2i64 (bitconvert
(v4i32 (X86cvttpd2udq (v2f64 VR128X:$src)))))))),
(VCVTTPD2UDQZ128rr VR128:$src)>;
}
let Predicates = [HasAVX512] in {

3
llvm/lib/Target/X86/X86InstrFragmentsSIMD.td
View File

@ -70,6 +70,9 @@ def X86cmps : SDNode<"X86ISD::FSETCC", SDTX86Cmps>;
def X86cvttpd2dq: SDNode<"X86ISD::CVTTPD2DQ",
SDTypeProfile<1, 1, [SDTCisVT<0, v4i32>,
SDTCisVT<1, v2f64>]>>;
def X86cvttpd2udq: SDNode<"X86ISD::CVTTPD2UDQ",
SDTypeProfile<1, 1, [SDTCisVT<0, v4i32>,
SDTCisVT<1, v2f64>]>>;
def X86cvtdq2pd: SDNode<"X86ISD::CVTDQ2PD",
SDTypeProfile<1, 1, [SDTCisVT<0, v2f64>,
SDTCisVT<1, v4i32>]>>;

2
llvm/lib/Target/X86/X86IntrinsicsInfo.h
View File

@ -586,7 +586,7 @@ static const IntrinsicData IntrinsicsWithoutChain[] = {
X86_INTRINSIC_DATA(avx512_mask_cvttpd2qq_512, INTR_TYPE_1OP_MASK,
ISD::FP_TO_SINT, X86ISD::CVTTP2SI_RND),
X86_INTRINSIC_DATA(avx512_mask_cvttpd2udq_128, INTR_TYPE_1OP_MASK,
ISD::FP_TO_UINT, 0),
X86ISD::CVTTPD2UDQ, 0),
X86_INTRINSIC_DATA(avx512_mask_cvttpd2udq_256, INTR_TYPE_1OP_MASK,
ISD::FP_TO_UINT, 0),
X86_INTRINSIC_DATA(avx512_mask_cvttpd2udq_512, INTR_TYPE_1OP_MASK,

70
llvm/test/CodeGen/X86/vec_fp_to_int.ll
View File

@ -407,33 +407,19 @@ define <4 x i32> @fptoui_2f64_to_4i32(<2 x double> %a) {
;
; AVX512F-LABEL: fptoui_2f64_to_4i32:
; AVX512F: # BB#0:
; AVX512F-NEXT: vcvttsd2usi %xmm0, %rax
; AVX512F-NEXT: vmovq %rax, %xmm1
; AVX512F-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
; AVX512F-NEXT: vcvttsd2usi %xmm0, %rax
; AVX512F-NEXT: vmovq %rax, %xmm0
; AVX512F-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
; AVX512F-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX512F-NEXT: # kill: %XMM0<def> %XMM0<kill> %ZMM0<def>
; AVX512F-NEXT: vcvttpd2udq %zmm0, %ymm0
; AVX512F-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: fptoui_2f64_to_4i32:
; AVX512VL: # BB#0:
; AVX512VL-NEXT: vcvttsd2usi %xmm0, %rax
; AVX512VL-NEXT: vmovq %rax, %xmm1
; AVX512VL-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
; AVX512VL-NEXT: vcvttsd2usi %xmm0, %rax
; AVX512VL-NEXT: vmovq %rax, %xmm0
; AVX512VL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
; AVX512VL-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX512VL-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
; AVX512VL-NEXT: vcvttpd2udq %xmm0, %xmm0
; AVX512VL-NEXT: retq
;
; AVX512VLDQ-LABEL: fptoui_2f64_to_4i32:
; AVX512VLDQ: # BB#0:
; AVX512VLDQ-NEXT: vcvttpd2uqq %xmm0, %xmm0
; AVX512VLDQ-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX512VLDQ-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
; AVX512VLDQ-NEXT: vcvttpd2udq %xmm0, %xmm0
; AVX512VLDQ-NEXT: retq
%cvt = fptoui <2 x double> %a to <2 x i32>
%ext = shufflevector <2 x i32> %cvt, <2 x i32> zeroinitializer, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
@ -491,30 +477,19 @@ define <4 x i32> @fptoui_2f64_to_2i32(<2 x double> %a) {
;
; AVX512F-LABEL: fptoui_2f64_to_2i32:
; AVX512F: # BB#0:
; AVX512F-NEXT: vcvttsd2usi %xmm0, %rax
; AVX512F-NEXT: vmovq %rax, %xmm1
; AVX512F-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
; AVX512F-NEXT: vcvttsd2usi %xmm0, %rax
; AVX512F-NEXT: vmovq %rax, %xmm0
; AVX512F-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
; AVX512F-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX512F-NEXT: # kill: %XMM0<def> %XMM0<kill> %ZMM0<def>
; AVX512F-NEXT: vcvttpd2udq %zmm0, %ymm0
; AVX512F-NEXT: # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: fptoui_2f64_to_2i32:
; AVX512VL: # BB#0:
; AVX512VL-NEXT: vcvttsd2usi %xmm0, %rax
; AVX512VL-NEXT: vmovq %rax, %xmm1
; AVX512VL-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
; AVX512VL-NEXT: vcvttsd2usi %xmm0, %rax
; AVX512VL-NEXT: vmovq %rax, %xmm0
; AVX512VL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
; AVX512VL-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX512VL-NEXT: vcvttpd2udq %xmm0, %xmm0
; AVX512VL-NEXT: retq
;
; AVX512VLDQ-LABEL: fptoui_2f64_to_2i32:
; AVX512VLDQ: # BB#0:
; AVX512VLDQ-NEXT: vcvttpd2uqq %xmm0, %xmm0
; AVX512VLDQ-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX512VLDQ-NEXT: vcvttpd2udq %xmm0, %xmm0
; AVX512VLDQ-NEXT: retq
%cvt = fptoui <2 x double> %a to <2 x i32>
%ext = shufflevector <2 x i32> %cvt, <2 x i32> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
@ -1250,15 +1225,24 @@ define <2 x i32> @fptoui_2f32_to_2i32(<2 x float> %a) {
; AVX-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm2[0],xmm0[0]
; AVX-NEXT: retq
;
; AVX512-LABEL: fptoui_2f32_to_2i32:
; AVX512: # BB#0:
; AVX512-NEXT: vcvttss2usi %xmm0, %rax
; AVX512-NEXT: vmovq %rax, %xmm1
; AVX512-NEXT: vmovshdup {{.*#+}} xmm0 = xmm0[1,1,3,3]
; AVX512-NEXT: vcvttss2usi %xmm0, %rax
; AVX512-NEXT: vmovq %rax, %xmm0
; AVX512-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
; AVX512-NEXT: retq
; AVX512F-LABEL: fptoui_2f32_to_2i32:
; AVX512F: # BB#0:
; AVX512F-NEXT: # kill: %XMM0<def> %XMM0<kill> %ZMM0<def>
; AVX512F-NEXT: vcvttps2udq %zmm0, %zmm0
; AVX512F-NEXT: vpmovzxdq {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: fptoui_2f32_to_2i32:
; AVX512VL: # BB#0:
; AVX512VL-NEXT: vcvttps2udq %xmm0, %xmm0
; AVX512VL-NEXT: vpmovzxdq {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero
; AVX512VL-NEXT: retq
;
; AVX512VLDQ-LABEL: fptoui_2f32_to_2i32:
; AVX512VLDQ: # BB#0:
; AVX512VLDQ-NEXT: vcvttps2udq %xmm0, %xmm0
; AVX512VLDQ-NEXT: vpmovzxdq {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero
; AVX512VLDQ-NEXT: retq
%cvt = fptoui <2 x float> %a to <2 x i32>
ret <2 x i32> %cvt
}