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

[X86][SSE] matchShuffleWithSHUFPD - add support for unary shuffles. 

This causes one minor test change but is mainly necessary for an upcoming patch.
This commit is contained in:
Simon Pilgrim 2020-03-10 15:30:56 +00:00
parent 417fe39be5
commit e6a7e3b5e3
2 changed files with 6 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -15942,6 +15942,7 @@ static bool matchShuffleWithSHUFPD(MVT VT, SDValue &V1, SDValue &V2,
// Mask for V8F64: 0/1, 8/9, 2/3, 10/11, 4/5, .. // Mask for V8F64: 0/1, 8/9, 2/3, 10/11, 4/5, ..
// Mask for V4F64; 0/1, 4/5, 2/3, 6/7.. // Mask for V4F64; 0/1, 4/5, 2/3, 6/7..
ShuffleImm = 0; ShuffleImm = 0;
bool UnaryMask = isUndefOrZeroOrInRange(Mask, 0, NumElts);
bool ShufpdMask = true; bool ShufpdMask = true;
bool CommutableMask = true; bool CommutableMask = true;
for (int i = 0; i < NumElts; ++i) { for (int i = 0; i < NumElts; ++i) {
@ -15949,7 +15950,7 @@ static bool matchShuffleWithSHUFPD(MVT VT, SDValue &V1, SDValue &V2,
continue; continue;
if (Mask[i] < 0) if (Mask[i] < 0)
return false; return false;
int Val = (i & 6) + NumElts * (i & 1); int Val = (i & 6) + (UnaryMask ? 0 : (NumElts * (i & 1)));
int CommutVal = (i & 0xe) + NumElts * ((i & 1) ^ 1); int CommutVal = (i & 0xe) + NumElts * ((i & 1) ^ 1);
if (Mask[i] < Val || Mask[i] > Val + 1) if (Mask[i] < Val || Mask[i] > Val + 1)
ShufpdMask = false; ShufpdMask = false;
@ -15961,7 +15962,9 @@ static bool matchShuffleWithSHUFPD(MVT VT, SDValue &V1, SDValue &V2,
if (!ShufpdMask && !CommutableMask) if (!ShufpdMask && !CommutableMask)
return false; return false;
if (!ShufpdMask && CommutableMask) if (UnaryMask)
V2 = V1;
else if (!ShufpdMask && CommutableMask)
std::swap(V1, V2); std::swap(V1, V2);
ForceV1Zero = ZeroLane[0]; ForceV1Zero = ZeroLane[0];

2
llvm/test/CodeGen/X86/sse-intrinsics-fast-isel.ll
View File

@ -2791,7 +2791,7 @@ define void @test_mm_storeh_pi(x86_mmx *%a0, <4 x float> %a1) nounwind {
; ;
; X64-SSE2-LABEL: test_mm_storeh_pi: ; X64-SSE2-LABEL: test_mm_storeh_pi:
; X64-SSE2: # %bb.0: ; X64-SSE2: # %bb.0:
; X64-SSE2-NEXT: pshufd $78, %xmm0, %xmm0 # encoding: [0x66,0x0f,0x70,0xc0,0x4e] ; X64-SSE2-NEXT: shufps $78, %xmm0, %xmm0 # encoding: [0x0f,0xc6,0xc0,0x4e]
; X64-SSE2-NEXT: # xmm0 = xmm0[2,3,0,1] ; X64-SSE2-NEXT: # xmm0 = xmm0[2,3,0,1]
; X64-SSE2-NEXT: movq %xmm0, %rax # encoding: [0x66,0x48,0x0f,0x7e,0xc0] ; X64-SSE2-NEXT: movq %xmm0, %rax # encoding: [0x66,0x48,0x0f,0x7e,0xc0]
; X64-SSE2-NEXT: movq %rax, (%rdi) # encoding: [0x48,0x89,0x07] ; X64-SSE2-NEXT: movq %rax, (%rdi) # encoding: [0x48,0x89,0x07]