diff options
Diffstat (limited to 'lib/Target/X86/X86InstrFragmentsSIMD.td')
| -rw-r--r-- | lib/Target/X86/X86InstrFragmentsSIMD.td | 23 |
1 files changed, 17 insertions, 6 deletions
diff --git a/lib/Target/X86/X86InstrFragmentsSIMD.td b/lib/Target/X86/X86InstrFragmentsSIMD.td index aa088a6..5a093ea 100644 --- a/lib/Target/X86/X86InstrFragmentsSIMD.td +++ b/lib/Target/X86/X86InstrFragmentsSIMD.td @@ -204,17 +204,28 @@ def loadv4f64 : PatFrag<(ops node:$ptr), (v4f64 (load node:$ptr))>; def loadv8i32 : PatFrag<(ops node:$ptr), (v8i32 (load node:$ptr))>; def loadv4i64 : PatFrag<(ops node:$ptr), (v4i64 (load node:$ptr))>; -// Like 'store', but always requires vector alignment. +// Like 'store', but always requires 128-bit vector alignment. def alignedstore : PatFrag<(ops node:$val, node:$ptr), (store node:$val, node:$ptr), [{ return cast<StoreSDNode>(N)->getAlignment() >= 16; }]>; -// Like 'load', but always requires vector alignment. +// Like 'store', but always requires 256-bit vector alignment. +def alignedstore256 : PatFrag<(ops node:$val, node:$ptr), + (store node:$val, node:$ptr), [{ + return cast<StoreSDNode>(N)->getAlignment() >= 32; +}]>; + +// Like 'load', but always requires 128-bit vector alignment. def alignedload : PatFrag<(ops node:$ptr), (load node:$ptr), [{ return cast<LoadSDNode>(N)->getAlignment() >= 16; }]>; +// Like 'load', but always requires 256-bit vector alignment. +def alignedload256 : PatFrag<(ops node:$ptr), (load node:$ptr), [{ + return cast<LoadSDNode>(N)->getAlignment() >= 32; +}]>; + def alignedloadfsf32 : PatFrag<(ops node:$ptr), (f32 (alignedload node:$ptr))>; def alignedloadfsf64 : PatFrag<(ops node:$ptr), @@ -232,13 +243,13 @@ def alignedloadv2i64 : PatFrag<(ops node:$ptr), // 256-bit aligned load pattern fragments def alignedloadv8f32 : PatFrag<(ops node:$ptr), - (v8f32 (alignedload node:$ptr))>; + (v8f32 (alignedload256 node:$ptr))>; def alignedloadv4f64 : PatFrag<(ops node:$ptr), - (v4f64 (alignedload node:$ptr))>; + (v4f64 (alignedload256 node:$ptr))>; def alignedloadv8i32 : PatFrag<(ops node:$ptr), - (v8i32 (alignedload node:$ptr))>; + (v8i32 (alignedload256 node:$ptr))>; def alignedloadv4i64 : PatFrag<(ops node:$ptr), - (v4i64 (alignedload node:$ptr))>; + (v4i64 (alignedload256 node:$ptr))>; // Like 'load', but uses special alignment checks suitable for use in // memory operands in most SSE instructions, which are required to |