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

[X86] Remove unnecessary isel pattern for MOVLPSmr. 

This was identical to a pattern for MOVPQI2QImr with a bitcast
as an input. But we should be able to turn MOVPQI2QImr into
MOVLPSmr in the execution domain fixup pass so we shouldn't
need this.

llvm-svn: 365224
This commit is contained in:
Craig Topper 2019-07-05 17:31:25 +00:00
parent 652ad423bb
commit 8a93952a5c
1 changed files with 0 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
llvm/lib/Target/X86/X86InstrSSE.td
View File

@ -657,11 +657,6 @@ def MOVLPDmr : PDI<0x13, MRMDestMem, (outs), (ins f64mem:$dst, VR128:$src),
} // SchedRW } // SchedRW
let Predicates = [UseSSE1] in { let Predicates = [UseSSE1] in {
// (store (vector_shuffle (load addr), v2, <4, 5, 2, 3>), addr) using MOVLPS
def : Pat<(store (i64 (extractelt (bc_v2i64 (v4f32 VR128:$src2)),
(iPTR 0))), addr:$src1),
(MOVLPSmr addr:$src1, VR128:$src2)>;
// This pattern helps select MOVLPS on SSE1 only targets. With SSE2 we'll // This pattern helps select MOVLPS on SSE1 only targets. With SSE2 we'll
// end up with a movsd or blend instead of shufp. // end up with a movsd or blend instead of shufp.
// No need for aligned load, we're only loading 64-bits. // No need for aligned load, we're only loading 64-bits.