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

[x86] allow narrowing of vector UINT_TO_FP 

As discussed in:
D56864
D58197

Always use the narrow (128-bit) instruction when possible.
We already had the signed int version of this transform.

llvm-svn: 354675
This commit is contained in:
Sanjay Patel 2019-02-22 15:47:45 +00:00
parent 1baf7896cc
commit a9e289174a
3 changed files with 13 additions and 24 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -42016,6 +42016,11 @@ static SDValue combineExtractSubvector(SDNode *N, SelectionDAG &DAG,
InVec.getOperand(0).getValueType() == MVT::v4i32) {
return DAG.getNode(X86ISD::CVTSI2P, SDLoc(N), VT, InVec.getOperand(0));
}
// v2f64 CVTUDQ2PD(v4i32).
if (InOpcode == ISD::UINT_TO_FP &&
InVec.getOperand(0).getValueType() == MVT::v4i32) {
return DAG.getNode(X86ISD::CVTUI2P, SDLoc(N), VT, InVec.getOperand(0));
}
// v2f64 CVTPS2PD(v4f32).
if (InOpcode == ISD::FP_EXTEND &&
InVec.getOperand(0).getValueType() == MVT::v4f32) {

8
llvm/test/CodeGen/X86/vec_int_to_fp-widen.ll
View File

@ -684,9 +684,7 @@ define <2 x double> @uitofp_4i32_to_2f64(<4 x i32> %a) {
;
; AVX512VL-LABEL: uitofp_4i32_to_2f64:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vcvtudq2pd %xmm0, %ymm0
; AVX512VL-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: vcvtudq2pd %xmm0, %xmm0
; AVX512VL-NEXT: retq
;
; AVX512DQ-LABEL: uitofp_4i32_to_2f64:
@ -699,9 +697,7 @@ define <2 x double> @uitofp_4i32_to_2f64(<4 x i32> %a) {
;
; AVX512VLDQ-LABEL: uitofp_4i32_to_2f64:
; AVX512VLDQ: # %bb.0:
; AVX512VLDQ-NEXT: vcvtudq2pd %xmm0, %ymm0
; AVX512VLDQ-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; AVX512VLDQ-NEXT: vzeroupper
; AVX512VLDQ-NEXT: vcvtudq2pd %xmm0, %xmm0
; AVX512VLDQ-NEXT: retq
%cvt = uitofp <4 x i32> %a to <4 x double>
%shuf = shufflevector <4 x double> %cvt, <4 x double> undef, <2 x i32> <i32 0, i32 1>

24
llvm/test/CodeGen/X86/vec_int_to_fp.ll
View File

@ -684,9 +684,7 @@ define <2 x double> @uitofp_4i32_to_2f64(<4 x i32> %a) {
;
; AVX512VL-LABEL: uitofp_4i32_to_2f64:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vcvtudq2pd %xmm0, %ymm0
; AVX512VL-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: vcvtudq2pd %xmm0, %xmm0
; AVX512VL-NEXT: retq
;
; AVX512DQ-LABEL: uitofp_4i32_to_2f64:
@ -699,9 +697,7 @@ define <2 x double> @uitofp_4i32_to_2f64(<4 x i32> %a) {
;
; AVX512VLDQ-LABEL: uitofp_4i32_to_2f64:
; AVX512VLDQ: # %bb.0:
; AVX512VLDQ-NEXT: vcvtudq2pd %xmm0, %ymm0
; AVX512VLDQ-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; AVX512VLDQ-NEXT: vzeroupper
; AVX512VLDQ-NEXT: vcvtudq2pd %xmm0, %xmm0
; AVX512VLDQ-NEXT: retq
%cvt = uitofp <4 x i32> %a to <4 x double>
%shuf = shufflevector <4 x double> %cvt, <4 x double> undef, <2 x i32> <i32 0, i32 1>
@ -5699,9 +5695,7 @@ define double @extract0_uitofp_v4i32_f64(<4 x i32> %x) nounwind {
;
; AVX512VL-LABEL: extract0_uitofp_v4i32_f64:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vcvtudq2pd %xmm0, %ymm0
; AVX512VL-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: vcvtudq2pd %xmm0, %xmm0
; AVX512VL-NEXT: retq
;
; AVX512DQ-LABEL: extract0_uitofp_v4i32_f64:
@ -5714,9 +5708,7 @@ define double @extract0_uitofp_v4i32_f64(<4 x i32> %x) nounwind {
;
; AVX512VLDQ-LABEL: extract0_uitofp_v4i32_f64:
; AVX512VLDQ: # %bb.0:
; AVX512VLDQ-NEXT: vcvtudq2pd %xmm0, %ymm0
; AVX512VLDQ-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; AVX512VLDQ-NEXT: vzeroupper
; AVX512VLDQ-NEXT: vcvtudq2pd %xmm0, %xmm0
; AVX512VLDQ-NEXT: retq
%e = extractelement <4 x i32> %x, i32 0
%r = uitofp i32 %e to double
@ -5855,9 +5847,7 @@ define double @extract3_uitofp_v4i32_f64(<4 x i32> %x) nounwind {
; AVX512VL-LABEL: extract3_uitofp_v4i32_f64:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,1,2,3]
; AVX512VL-NEXT: vcvtudq2pd %xmm0, %ymm0
; AVX512VL-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: vcvtudq2pd %xmm0, %xmm0
; AVX512VL-NEXT: retq
;
; AVX512DQ-LABEL: extract3_uitofp_v4i32_f64:
@ -5871,9 +5861,7 @@ define double @extract3_uitofp_v4i32_f64(<4 x i32> %x) nounwind {
; AVX512VLDQ-LABEL: extract3_uitofp_v4i32_f64:
; AVX512VLDQ: # %bb.0:
; AVX512VLDQ-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,1,2,3]
; AVX512VLDQ-NEXT: vcvtudq2pd %xmm0, %ymm0
; AVX512VLDQ-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; AVX512VLDQ-NEXT: vzeroupper
; AVX512VLDQ-NEXT: vcvtudq2pd %xmm0, %xmm0
; AVX512VLDQ-NEXT: retq
%e = extractelement <4 x i32> %x, i32 3
%r = uitofp i32 %e to double