diff options
Diffstat (limited to 'llvm/lib/Target/X86/X86InstrSSE.td')
| -rw-r--r-- | llvm/lib/Target/X86/X86InstrSSE.td | 26 |
1 files changed, 15 insertions, 11 deletions
diff --git a/llvm/lib/Target/X86/X86InstrSSE.td b/llvm/lib/Target/X86/X86InstrSSE.td index f74ca9dd7bf..5a87314c324 100644 --- a/llvm/lib/Target/X86/X86InstrSSE.td +++ b/llvm/lib/Target/X86/X86InstrSSE.td @@ -1115,15 +1115,19 @@ def STMXCSR : PSI<0xAE, MRM3m, (outs), (ins i32mem:$dst), // load of an all-zeros value if folding it would be beneficial. // FIXME: Change encoding to pseudo! let isReMaterializable = 1, isAsCheapAsAMove = 1, canFoldAsLoad = 1, - isCodeGenOnly = 1 in -def V_SET0 : PSI<0x57, MRMInitReg, (outs VR128:$dst), (ins), "", + isCodeGenOnly = 1 in { +def V_SET0PS : PSI<0x57, MRMInitReg, (outs VR128:$dst), (ins), "", + [(set VR128:$dst, (v4f32 immAllZerosV))]>; +def V_SET0PD : PDI<0x57, MRMInitReg, (outs VR128:$dst), (ins), "", + [(set VR128:$dst, (v2f64 immAllZerosV))]>; +let ExeDomain = SSEPackedInt in +def V_SET0PI : PDI<0xEF, MRMInitReg, (outs VR128:$dst), (ins), "", [(set VR128:$dst, (v4i32 immAllZerosV))]>; +} -def : Pat<(v2i64 immAllZerosV), (V_SET0)>; -def : Pat<(v8i16 immAllZerosV), (V_SET0)>; -def : Pat<(v16i8 immAllZerosV), (V_SET0)>; -def : Pat<(v2f64 immAllZerosV), (V_SET0)>; -def : Pat<(v4f32 immAllZerosV), (V_SET0)>; +def : Pat<(v2i64 immAllZerosV), (V_SET0PI)>; +def : Pat<(v8i16 immAllZerosV), (V_SET0PI)>; +def : Pat<(v16i8 immAllZerosV), (V_SET0PI)>; def : Pat<(f32 (vector_extract (v4f32 VR128:$src), (iPTR 0))), (f32 (EXTRACT_SUBREG (v4f32 VR128:$src), x86_subreg_ss))>; @@ -3026,14 +3030,14 @@ let Predicates = [HasSSE2] in { let AddedComplexity = 15 in { // Zeroing a VR128 then do a MOVS{S|D} to the lower bits. def : Pat<(v2f64 (X86vzmovl (v2f64 (scalar_to_vector FR64:$src)))), - (MOVSDrr (v2f64 (V_SET0)), FR64:$src)>; + (MOVSDrr (v2f64 (V_SET0PS)), FR64:$src)>; def : Pat<(v4f32 (X86vzmovl (v4f32 (scalar_to_vector FR32:$src)))), - (MOVSSrr (v4f32 (V_SET0)), FR32:$src)>; + (MOVSSrr (v4f32 (V_SET0PS)), FR32:$src)>; def : Pat<(v4f32 (X86vzmovl (v4f32 VR128:$src))), - (MOVSSrr (v4f32 (V_SET0)), + (MOVSSrr (v4f32 (V_SET0PS)), (f32 (EXTRACT_SUBREG (v4f32 VR128:$src), x86_subreg_ss)))>; def : Pat<(v4i32 (X86vzmovl (v4i32 VR128:$src))), - (MOVSSrr (v4i32 (V_SET0)), + (MOVSSrr (v4i32 (V_SET0PI)), (EXTRACT_SUBREG (v4i32 VR128:$src), x86_subreg_ss))>; } |
