Artem Tamazov

Results 298 comments of Artem Tamazov

@lamb-j Good to know that, Jacob. Thanks.

Basically, this is about actual parallel compilation, because we need it for performance. I recommend re-opening this ticket (I can't).

Installing pfultz2/cget-recipes from source leads to another problem: ```bash # cmake -P install_deps.cmake /usr/local/pip install cget Requirement already satisfied: cget in /usr/local/lib/python3.8/dist-packages (0.2.1) Requirement already satisfied: six>=1.10 in /usr/local/lib/python3.8/site-packages (from...

Try giving the "-mno-code-object-v3" option to clang, please.

Yes, gfx8 and gfx9 ISA differ.

> Solved, I got the solution by using llvm-mc Please publish it here for others who might encounter the same problem.

> @atamazov Because asm sources for gfx8 is not the one I want, I dump the isa code by setting `KMDUMPISA=1` for hcc/hipcc command, and now I get the isa...

Let's close this, https://github.com/ROCm-Developer-Tools/LLVM-AMDGPU-Assembler-Extra/issues/20#issuecomment-489243561

@carlushuang I am not against "non-standard" usage of the preprocessor. However this requires careful and clean design. Please explicitly ask me to review relevant PRs.

Hmm... Perhaps this is not really required, see https://github.com/ROCmSoftwarePlatform/MIOpen/pull/505/files#r502967373