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

[x86] Start improving the matching of unpck instructions based on test 

cases from Halide folks. This initial step was extracted from
a prototype change by Clay Wood to try and address regressions found
with Halide and the new vector shuffle lowering.

llvm-svn: 221779
This commit is contained in:
Chandler Carruth 2014-11-12 10:05:18 +00:00
parent 9b70a919db
commit 0c922fcec5
3 changed files with 13 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -9046,6 +9046,12 @@ static SDValue lowerV8I16VectorShuffle(SDValue Op, SDValue V1, SDValue V2,
Mask, Subtarget, DAG))
return V;
// Use dedicated unpack instructions for masks that match their pattern.
if (isShuffleEquivalent(Mask, 0, 8, 1, 9, 2, 10, 3, 11))
return DAG.getNode(X86ISD::UNPCKL, DL, MVT::v8i16, V1, V2);
if (isShuffleEquivalent(Mask, 4, 12, 5, 13, 6, 14, 7, 15))
return DAG.getNode(X86ISD::UNPCKH, DL, MVT::v8i16, V1, V2);
if (Subtarget->hasSSE41())
if (SDValue Blend = lowerVectorShuffleAsBlend(DL, MVT::v8i16, V1, V2, Mask,
Subtarget, DAG))

17
llvm/test/CodeGen/X86/vector-shuffle-128-v8.ll
View File

@ -885,16 +885,12 @@ define <8 x i16> @shuffle_v8i16_0c1d2e3f(<8 x i16> %a, <8 x i16> %b) {
define <8 x i16> @shuffle_v8i16_4c5d6e7f(<8 x i16> %a, <8 x i16> %b) {
; SSE-LABEL: shuffle_v8i16_4c5d6e7f:
; SSE: # BB#0:
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
; SSE-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; SSE-NEXT: punpckhwd {{.*#+}} xmm0 = xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
; SSE-NEXT: retq
;
; AVX-LABEL: shuffle_v8i16_4c5d6e7f:
; AVX: # BB#0:
; AVX-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
; AVX-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
; AVX-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; AVX-NEXT: vpunpckhwd {{.*#+}} xmm0 = xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
; AVX-NEXT: retq
%shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
ret <8 x i16> %shuffle
@ -992,16 +988,13 @@ define <8 x i16> @shuffle_v8i16_8091a2b3(<8 x i16> %a, <8 x i16> %b) {
define <8 x i16> @shuffle_v8i16_c4d5e6f7(<8 x i16> %a, <8 x i16> %b) {
; SSE-LABEL: shuffle_v8i16_c4d5e6f7:
; SSE: # BB#0:
; SSE-NEXT: pshufd {{.*#+}} xmm2 = xmm0[2,3,0,1]
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm1[2,3,0,1]
; SSE-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; SSE-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
; SSE-NEXT: movdqa %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: shuffle_v8i16_c4d5e6f7:
; AVX: # BB#0:
; AVX-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
; AVX-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
; AVX-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
; AVX-NEXT: vpunpckhwd {{.*#+}} xmm0 = xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
; AVX-NEXT: retq
%shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 12, i32 4, i32 13, i32 5, i32 14, i32 6, i32 15, i32 7>
ret <8 x i16> %shuffle

5
llvm/test/CodeGen/X86/vector-zext.ll
View File

@ -39,9 +39,8 @@ define <8 x i32> @zext_8i16_to_8i32(<8 x i16> %A) nounwind uwtable readnone ssp
;
; AVX1-LABEL: zext_8i16_to_8i32:
; AVX1: # BB#0: # %entry
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
; AVX1-NEXT: vpxor %xmm2, %xmm2, %xmm2
; AVX1-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
; AVX1-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX1-NEXT: vpunpckhwd {{.*#+}} xmm1 = xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
; AVX1-NEXT: vpmovzxwd %xmm0, %xmm0
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT: retq