Skip to content

[offload] Add gfx1012 (Navi 14) to AMDGPU models list #118857

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Dec 6, 2024
Merged

Conversation

mgorny
Copy link
Member

@mgorny mgorny commented Dec 5, 2024

Fixes #118824

@mgorny mgorny requested a review from jhuber6 December 5, 2024 18:44
@llvmbot llvmbot added the offload label Dec 5, 2024
@llvmbot
Copy link
Member

llvmbot commented Dec 5, 2024

@llvm/pr-subscribers-offload

Author: Michał Górny (mgorny)

Changes

Fixes #118824


Full diff: https://github.com/llvm/llvm-project/pull/118857.diff

1 Files Affected:

  • (modified) offload/DeviceRTL/CMakeLists.txt (+1-1)
diff --git a/offload/DeviceRTL/CMakeLists.txt b/offload/DeviceRTL/CMakeLists.txt
index b52305b9516fb1..32a7510be980d8 100644
--- a/offload/DeviceRTL/CMakeLists.txt
+++ b/offload/DeviceRTL/CMakeLists.txt
@@ -44,7 +44,7 @@ set(source_directory ${devicertl_base_directory}/src)
 
 set(all_amdgpu_architectures "gfx700;gfx701;gfx801;gfx803;gfx900;gfx902;gfx906"
                              "gfx908;gfx90a;gfx90c;gfx940;gfx941;gfx942;gfx950;gfx1010"
-                             "gfx1030;gfx1031;gfx1032;gfx1033;gfx1034;gfx1035"
+                             "gfx1012;gfx1030;gfx1031;gfx1032;gfx1033;gfx1034;gfx1035"
                              "gfx1036;gfx1100;gfx1101;gfx1102;gfx1103;gfx1150"
                              "gfx1151;gfx1152;gfx1153")
 set(all_nvptx_architectures "sm_35;sm_37;sm_50;sm_52;sm_53;sm_60;sm_61;sm_62"

@shiltian
Copy link
Contributor

shiltian commented Dec 5, 2024

Do we (ROCm) really support this?

Oh, we do, so I guess it's fine.

@mgorny
Copy link
Member Author

mgorny commented Dec 5, 2024

Do we (ROCm) really support this?

Oh, we do, so I guess it's fine.

Well, at least it compiles and the majority of tests passes. Crash-related tests seem to hang with 100% CPU use for me (or possibly take very long time).

@jhuber6
Copy link
Contributor

jhuber6 commented Dec 5, 2024

Do we (ROCm) really support this?
Oh, we do, so I guess it's fine.

Well, at least it compiles and the majority of tests passes. Crash-related tests seem to hang with 100% CPU use for me (or possibly take very long time).

Offload tests randomly hang, have for a long time.

@shiltian
Copy link
Contributor

shiltian commented Dec 5, 2024

We don't officially support it, but since we already have these unsupported gfx listed here, it doesn't matter adding one or two more...

@mgorny mgorny merged commit b54ba53 into llvm:main Dec 6, 2024
8 checks passed
@mgorny mgorny deleted the gfx1012 branch December 6, 2024 03:24
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

Successfully merging this pull request may close these issues.

[offload] libomptarget :: amdgcn-amd-amdhsa tests are failing on Gentoo
4 participants