projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 741978d) | patch
[AMDGPU] Allow no saddr for global addtid insts
authorSebastian Neubauer <sebastian.neubauer@amd.com>
Tue, 15 Dec 2020 10:15:53 +0000 (11:15 +0100)
committerSebastian Neubauer <sebastian.neubauer@amd.com>
Wed, 16 Dec 2020 09:01:40 +0000 (10:01 +0100)
commit409a2f0f9e4847cd25560bfbddf22ffa11d15237
treea43f00861788299de202edaa119da87def9056b4tree | snapshot
parent741978d727a445fa279d5952a86ea634adb7dc52commit | diff
[AMDGPU] Allow no saddr for global addtid insts

I think the global_load/store_dword_addtid instructions support
switching off the scalar address.
Add assembler and disassembler support for this.

Differential Revision: https://reviews.llvm.org/D93288
llvm/lib/Target/AMDGPU/FLATInstructions.td diff | blob | history
llvm/test/MC/AMDGPU/gfx1030_new.s diff | blob | history
llvm/test/MC/Disassembler/AMDGPU/gfx1030_dasm_new.txt diff | blob | history
Domain: System / Toolchain;