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

[DAG] Add SimplifyDemandedBits support for BITREVERSE 

Pulled out of D58017 while I continue to investigate the BSWAP regression on PPC

llvm-svn: 360534
This commit is contained in:
Simon Pilgrim 2019-05-11 20:56:05 +00:00
parent 3fa632a112
commit 605a840747
3 changed files with 11 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
View File

@ -1268,6 +1268,16 @@ bool TargetLowering::SimplifyDemandedBits(
}
break;
}
case ISD::BITREVERSE: {
SDValue Src = Op.getOperand(0);
APInt DemandedSrcBits = DemandedBits.reverseBits();
if (SimplifyDemandedBits(Src, DemandedSrcBits, DemandedElts, Known2, TLO,
Depth + 1))
return true;
Known.One = Known2.One.reverseBits();
Known.Zero = Known2.Zero.reverseBits();
break;
}
case ISD::SIGN_EXTEND_INREG: {
SDValue Op0 = Op.getOperand(0);
EVT ExVT = cast<VTSDNode>(Op.getOperand(1))->getVT();

3
llvm/test/CodeGen/AMDGPU/bitreverse.ll
View File

@ -36,7 +36,6 @@ define amdgpu_kernel void @s_brev_i16(i16 addrspace(1)* noalias %out, i16 %val)
; FLAT-NEXT: s_mov_b32 s7, 0xf000
; FLAT-NEXT: s_mov_b32 s6, -1
; FLAT-NEXT: s_waitcnt lgkmcnt(0)
; FLAT-NEXT: s_and_b32 s0, s0, 0xffff
; FLAT-NEXT: s_brev_b32 s0, s0
; FLAT-NEXT: s_lshr_b32 s0, s0, 16
; FLAT-NEXT: v_mov_b32_e32 v0, s0
@ -1020,7 +1019,7 @@ define float @missing_truncate_promote_bitreverse(i32 %arg) {
; FLAT-LABEL: missing_truncate_promote_bitreverse:
; FLAT: ; %bb.0: ; %bb
; FLAT-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; FLAT-NEXT: v_bfrev_b32_sdwa v0, v0 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_0
; FLAT-NEXT: v_bfrev_b32_e32 v0, v0
; FLAT-NEXT: v_cvt_f32_f16_sdwa v0, v0 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1
; FLAT-NEXT: s_setpc_b64 s[30:31]
bb:

2
llvm/test/CodeGen/X86/combine-bitreverse.ll
View File

@ -40,7 +40,6 @@ define i32 @test_bitreverse_bitreverse(i32 %a0) nounwind {
define <4 x i32> @test_demandedbits_bitreverse(<4 x i32> %a0) nounwind {
; X86-LABEL: test_demandedbits_bitreverse:
; X86: # %bb.0:
; X86-NEXT: por {{\.LCPI.*}}, %xmm0
; X86-NEXT: pxor %xmm1, %xmm1
; X86-NEXT: movdqa %xmm0, %xmm2
; X86-NEXT: punpckhbw {{.*#+}} xmm2 = xmm2[8],xmm1[8],xmm2[9],xmm1[9],xmm2[10],xmm1[10],xmm2[11],xmm1[11],xmm2[12],xmm1[12],xmm2[13],xmm1[13],xmm2[14],xmm1[14],xmm2[15],xmm1[15]
@ -79,7 +78,6 @@ define <4 x i32> @test_demandedbits_bitreverse(<4 x i32> %a0) nounwind {
;
; X64-LABEL: test_demandedbits_bitreverse:
; X64: # %bb.0:
; X64-NEXT: vpor {{.*}}(%rip), %xmm0, %xmm0
; X64-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[3,2,1,0,7,6,5,4,11,10,9,8,15,14,13,12]
; X64-NEXT: vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
; X64-NEXT: vpand %xmm1, %xmm0, %xmm2