[llvm] r343125 - AMDGPU/SI: Change predicate to isCIOnly for 32-bit imm s_buffer_load* patterns
Tom Stellard via llvm-commits
llvm-commits at lists.llvm.org
Wed Sep 26 09:53:37 PDT 2018
Author: tstellar
Date: Wed Sep 26 09:53:36 2018
New Revision: 343125
URL: http://llvm.org/viewvc/llvm-project?rev=343125&view=rev
Log:
AMDGPU/SI: Change predicate to isCIOnly for 32-bit imm s_buffer_load* patterns
Summary:
This is essentially NFC, because the complex pattern used for these patterns
will fail on non-CI, but this makes the pattern consistent with other CI
smrd patterns. It is also a performance improvement, because the pattern
will now fail earlier on non-CI.
Reviewers: arsenm, nhaehnle
Reviewed By: arsenm
Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, tpr, t-tye, llvm-commits
Differential Revision: https://reviews.llvm.org/D52469
Modified:
llvm/trunk/lib/Target/AMDGPU/SMInstructions.td
Modified: llvm/trunk/lib/Target/AMDGPU/SMInstructions.td
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/AMDGPU/SMInstructions.td?rev=343125&r1=343124&r2=343125&view=diff
==============================================================================
--- llvm/trunk/lib/Target/AMDGPU/SMInstructions.td (original)
+++ llvm/trunk/lib/Target/AMDGPU/SMInstructions.td Wed Sep 26 09:53:36 2018
@@ -777,7 +777,7 @@ def : SMRD_Pattern_ci <"S_LOAD_DWORDX16"
class SMLoad_Pattern_ci <string Instr, ValueType vt> : GCNPat <
(vt (SIsbuffer_load v4i32:$sbase, (SMRDBufferImm32 i32:$offset), i1:$glc)),
(!cast<InstSI>(Instr) $sbase, $offset, (as_i1imm $glc))> {
- let OtherPredicates = [isCI]; // should this be isCIOnly?
+ let OtherPredicates = [isCIOnly];
}
def : SMLoad_Pattern_ci <"S_BUFFER_LOAD_DWORD_IMM_ci", i32>;
More information about the llvm-commits
mailing list