[PATCH] D65620: [AMDGPU] Use S_DENORM_MODE for gfx10
Matt Arsenault via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Fri Aug 2 11:47:03 PDT 2019
arsenm added inline comments.
================
Comment at: llvm/lib/Target/AMDGPU/SIISelLowering.cpp:7536
+// Returns immeidate value for setting the F32 denorm mode when using the
+// S_DENORM_MODE instruction.
----------------
Typo immeidate
================
Comment at: llvm/lib/Target/AMDGPU/SIISelLowering.cpp:7546
+ int Mode = SPDenormMode | (DPDenormModeDefault << 2);
+ return DAG.getConstant(Mode, SL, MVT::i32);
+}
----------------
Should use getTargetConstant (or I'll end up fixing this for D58232)
================
Comment at: llvm/lib/Target/AMDGPU/SOPInstructions.td:1172
+ SOPP<0x025, (ins i32imm:$simm16), "s_denorm_mode $simm16",
+ [(SIdenorm_mode UIMM4bit:$simm16)]> {
+ let hasSideEffects = 1;
----------------
timm instead of UIMM4bit to match
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D65620/new/
https://reviews.llvm.org/D65620
More information about the llvm-commits
mailing list