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

[SelectionDAG] Add partial sign-bit support to ComputeNumSignBits for BITCAST nodes 

Only adds support to the existing 'large element' scalar/vector to 'small element' vector bitcasts.

Handle the case where the sign bit extends to only part of the small elements.

llvm-svn: 340169
This commit is contained in:
Simon Pilgrim 2018-08-20 13:05:48 +00:00
parent d882a49742
commit 5b78c9d58d
2 changed files with 30 additions and 24 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
View File

@ -3240,9 +3240,9 @@ unsigned SelectionDAG::ComputeNumSignBits(SDValue Op, const APInt &DemandedElts,
if (VTBits == SrcBits)
return ComputeNumSignBits(N0, DemandedElts, Depth + 1);
bool IsLE = getDataLayout().isLittleEndian();
// Bitcast 'large element' scalar/vector to 'small element' vector.
// TODO: Handle cases other than 'sign splat' when we have a use case.
// Requires handling of DemandedElts and Endianness.
if ((SrcBits % VTBits) == 0) {
assert(Op.getValueType().isVector() && "Expected bitcast to vector");
@ -3252,9 +3252,23 @@ unsigned SelectionDAG::ComputeNumSignBits(SDValue Op, const APInt &DemandedElts,
if (DemandedElts[i])
SrcDemandedElts.setBit(i / Scale);
// Fast case - sign splat can be simply split across the small elements.
Tmp = ComputeNumSignBits(N0, SrcDemandedElts, Depth + 1);
if (Tmp == SrcBits)
return VTBits;
// Slow case - determine how far the sign extends into each sub-element.
Tmp2 = VTBits;
for (unsigned i = 0; i != NumElts; ++i)
if (DemandedElts[i]) {
unsigned SubOffset = i % Scale;
SubOffset = (IsLE ? ((Scale - 1) - SubOffset) : SubOffset);
SubOffset = SubOffset * VTBits;
if (Tmp <= SubOffset)
return 1;
Tmp2 = std::min(Tmp2, Tmp - SubOffset);
}
return Tmp2;
}
break;
}

36
llvm/test/CodeGen/X86/packss.ll
View File

@ -42,40 +42,33 @@ define <4 x i32> @trunc_ashr_v4i64(<4 x i64> %a) nounwind {
define <8 x i16> @trunc_ashr_v4i64_bitcast(<4 x i64> %a0) {
; SSE-LABEL: trunc_ashr_v4i64_bitcast:
; SSE: # %bb.0:
; SSE-NEXT: movdqa %xmm0, %xmm2
; SSE-NEXT: psrad $31, %xmm2
; SSE-NEXT: pshufd {{.*#+}} xmm2 = xmm2[1,3,2,3]
; SSE-NEXT: psrad $17, %xmm0
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,3,2,3]
; SSE-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; SSE-NEXT: movdqa %xmm1, %xmm2
; SSE-NEXT: psrad $31, %xmm2
; SSE-NEXT: pshufd {{.*#+}} xmm2 = xmm2[1,3,2,3]
; SSE-NEXT: psrad $17, %xmm1
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm1[1,3,2,3]
; SSE-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; SSE-NEXT: pslld $16, %xmm1
; SSE-NEXT: psrad $16, %xmm1
; SSE-NEXT: pslld $16, %xmm0
; SSE-NEXT: psrad $16, %xmm0
; SSE-NEXT: movdqa %xmm0, %xmm2
; SSE-NEXT: psrad $31, %xmm2
; SSE-NEXT: pshufd {{.*#+}} xmm2 = xmm2[1,3,2,3]
; SSE-NEXT: psrad $17, %xmm0
; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,3,2,3]
; SSE-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; SSE-NEXT: packssdw %xmm1, %xmm0
; SSE-NEXT: ret{{[l|q]}}
;
; AVX1-LABEL: trunc_ashr_v4i64_bitcast:
; AVX1: # %bb.0:
; AVX1-NEXT: vpsrad $31, %xmm0, %xmm1
; AVX1-NEXT: vpsrad $17, %xmm0, %xmm2
; AVX1-NEXT: vpshufd {{.*#+}} xmm2 = xmm2[1,1,3,3]
; AVX1-NEXT: vpblendw {{.*#+}} xmm1 = xmm2[0,1],xmm1[2,3],xmm2[4,5],xmm1[6,7]
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vpsrad $31, %xmm1, %xmm2
; AVX1-NEXT: vpsrad $17, %xmm1, %xmm1
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[1,1,3,3]
; AVX1-NEXT: vpblendw {{.*#+}} xmm1 = xmm1[0,1],xmm2[2,3],xmm1[4,5],xmm2[6,7]
; AVX1-NEXT: vpsrad $31, %xmm0, %xmm2
; AVX1-NEXT: vpsrad $17, %xmm0, %xmm0
; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[1,1,3,3]
; AVX1-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0,1],xmm2[2,3],xmm0[4,5],xmm2[6,7]
; 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 = xmm1[0],xmm0[0]
; AVX1-NEXT: vpackssdw %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: ret{{[l|q]}}
;
@ -85,9 +78,8 @@ define <8 x i16> @trunc_ashr_v4i64_bitcast(<4 x i64> %a0) {
; AVX2-NEXT: vpsrad $17, %ymm0, %ymm0
; AVX2-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[1,1,3,3,5,5,7,7]
; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
; AVX2-NEXT: vpackssdw %ymm0, %ymm0, %ymm0
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vpackssdw %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: ret{{[l|q]}}
%1 = ashr <4 x i64> %a0, <i64 49, i64 49, i64 49, i64 49>