r128 dropped in GFX9;
d16 is supported by GFX8/9 only.
See bugs 36094 and 36095:
https://bugs.llvm.org/show_bug.cgi?id=36094 https://bugs.llvm.org/show_bug.cgi?id=36095
Paths
| Differential D42692
[AMDGPU][MC] Added validation of d16 and r128 modifiers of MIMG opcodes ClosedPublic Authored by dp on Jan 30 2018, 9:12 AM.
Details Summary r128 dropped in GFX9; See bugs 36094 and 36095: https://bugs.llvm.org/show_bug.cgi?id=36094 https://bugs.llvm.org/show_bug.cgi?id=36095
Diff Detail Event TimelineHerald added subscribers: t-tye, tpr, dstuttard and 4 others. · View Herald TranscriptJan 30 2018, 9:12 AM
This revision is now accepted and ready to land.Feb 2 2018, 4:19 AM Closed by commit rL324231: [AMDGPU][MC] Added validation of d16 and r128 modifiers of MIMG opcodes (authored by dpreobra). · Explain WhyFeb 5 2018, 4:50 AM This revision was automatically updated to reflect the committed changes.
Revision Contents
Diff 131980 lib/Target/AMDGPU/AsmParser/AMDGPUAsmParser.cpp
test/MC/AMDGPU/mimg.s
|
I don't like this listing of generations. We should add a new r128 subtarget feature bit instead