RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-19 11:02:59 +02:00
Code Issues Projects Releases Wiki Activity

[SelectionDAG] Add support for vector demandedelts in XOR opcodes

Browse Source 
llvm-svn: 286075
This commit is contained in:
Simon Pilgrim 2016-11-06 16:49:19 +00:00
parent ad8582a1b0
commit 6ff3359a0b
2 changed files with 6 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
lib/CodeGen/SelectionDAG/SelectionDAG.cpp
View File

@ -2153,8 +2153,10 @@ void SelectionDAG::computeKnownBits(SDValue Op, APInt &KnownZero,
KnownOne |= KnownOne2;
break;
case ISD::XOR: {
computeKnownBits(Op.getOperand(1), KnownZero, KnownOne, Depth+1);
computeKnownBits(Op.getOperand(0), KnownZero2, KnownOne2, Depth+1);
computeKnownBits(Op.getOperand(1), KnownZero, KnownOne, DemandedElts,
Depth + 1);
computeKnownBits(Op.getOperand(0), KnownZero2, KnownOne2, DemandedElts,
Depth + 1);
// Output known-0 bits are known if clear or set in both the LHS & RHS.
APInt KnownZeroOut = (KnownZero & KnownZero2) | (KnownOne & KnownOne2);

12
test/CodeGen/X86/known-bits-vector.ll
View File

@ -119,11 +119,7 @@ define <4 x float> @knownbits_mask_xor_shuffle_uitofp(<4 x i32> %a0) nounwind {
; X32-NEXT: vpand {{\.LCPI.*}}, %xmm0, %xmm0
; X32-NEXT: vpxor {{\.LCPI.*}}, %xmm0, %xmm0
; X32-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[2,2,3,3]
; X32-NEXT: vpblendw {{.*#+}} xmm1 = xmm0[0],mem[1],xmm0[2],mem[3],xmm0[4],mem[5],xmm0[6],mem[7]
; X32-NEXT: vpsrld $16, %xmm0, %xmm0
; X32-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0],mem[1],xmm0[2],mem[3],xmm0[4],mem[5],xmm0[6],mem[7]
; X32-NEXT: vaddps {{\.LCPI.*}}, %xmm0, %xmm0
; X32-NEXT: vaddps %xmm0, %xmm1, %xmm0
; X32-NEXT: vcvtdq2ps %xmm0, %xmm0
; X32-NEXT: retl
;
; X64-LABEL: knownbits_mask_xor_shuffle_uitofp:
@ -131,11 +127,7 @@ define <4 x float> @knownbits_mask_xor_shuffle_uitofp(<4 x i32> %a0) nounwind {
; X64-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
; X64-NEXT: vpxor {{.*}}(%rip), %xmm0, %xmm0
; X64-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[2,2,3,3]
; X64-NEXT: vpblendw {{.*#+}} xmm1 = xmm0[0],mem[1],xmm0[2],mem[3],xmm0[4],mem[5],xmm0[6],mem[7]
; X64-NEXT: vpsrld $16, %xmm0, %xmm0
; X64-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0],mem[1],xmm0[2],mem[3],xmm0[4],mem[5],xmm0[6],mem[7]
; X64-NEXT: vaddps {{.*}}(%rip), %xmm0, %xmm0
; X64-NEXT: vaddps %xmm0, %xmm1, %xmm0
; X64-NEXT: vcvtdq2ps %xmm0, %xmm0
; X64-NEXT: retq
%1 = and <4 x i32> %a0, <i32 -1, i32 -1, i32 255, i32 4085>
%2 = xor <4 x i32> %1, <i32 65535, i32 65535, i32 65535, i32 65535>