Skip to content

Conversation

@mstankov-amd
Copy link

@mstankov-amd mstankov-amd commented Aug 26, 2025

No description provided.

@mstankov-amd mstankov-amd changed the title Add gfx1150/gfx1151 to hipBLASLt supported architecture list [release/2.8] Add gfx1150/gfx1151 to hipBLASLt supported architecture list Aug 26, 2025
@rocm-repo-management-api
Copy link

rocm-repo-management-api bot commented Aug 27, 2025

Jenkins build for b8bf96307449423ce014ec608fc1a0a1348f8033 commit finished as FAILURE
Links: Blue Ocean view / Build artifacts

@apakbin
Copy link

apakbin commented Aug 28, 2025

@mstankov-amd gfx115x does not seem supported in hipBLASLt CC. @jagadish-amd

@slojosic-amd
Copy link

hipBLASLt support for gfx1150/gfx1151 has been added since ROCm 6.4.1: https://github.com/ROCm/hipBLASLt/blob/release/rocm-rel-6.4/tensilelite/Tensile/Source/lib/include/Tensile/AMDGPU.hpp#L74

@apakbin
Copy link

apakbin commented Sep 15, 2025

you're right @slojosic-amd, it is supported (according to great help from @jagadish-amd who figured it out, it is enabled in 6.4.2). Given this PR also updates the preferred backend, have you benchmarked hipBLASLt versus rocBLAS for perf?

@jagadish-amd
Copy link

probably needs ROCm 6.4.2 condition,

(reference ROCm/hipBLASLt#2067)

@slojosic-amd
Copy link

you're right @slojosic-amd, it is supported (according to great help from @jagadish-amd who figured it out, it is enabled in 6.4.2). Given this PR also updates the preferred backend, have you benchmarked hipBLASLt versus rocBLAS for perf?

hipBLASLt kernel yaml files for gfx1150 and gfx1151 are based on Navi33 yaml files which are again only copy of Navi31 yaml files. We have done some internal testing on Navi31 and it depends from model to model but overall conclusion is that we should change prefered BLAS backend for all RDNA 3/3.5 targets to be hipBLASLt. Please check this PR also: https://github.com/pytorch/pytorch/pull/164744/files

@slojosic-amd
Copy link

probably needs ROCm 6.4.2 condition,

(reference ROCm/hipBLASLt#2067)

Done: 39aaf53

@rocm-repo-management-api
Copy link

rocm-repo-management-api bot commented Oct 24, 2025

Jenkins build for a62940d9960c0905ac7bb1904b7ba29b7963b544 commit finished as NOT_BUILT
Links: Blue Ocean view / Build artifacts

Detected error during Pytorch building:

HIP VERSION: 7.0.51831-7c9236b16
CMake Warning (dev) at /opt/rocm/lib/cmake/hip/hip-config-amd.cmake:98 (message):
   GPU_TARGETS was not set, and system GPU detection was unsuccsessful.
   
   The amdgpu-arch tool failed:
   Error: 'Failed to get device count'
   Output: ''
   
   As a result, --offload-arch will not be set for subsequent
   compilations, and the default architecture
   (gfx906 for dynamic build / gfx942 for static build) will be used

@rocm-repo-management-api
Copy link

rocm-repo-management-api bot commented Oct 24, 2025

Jenkins build for a62940d9960c0905ac7bb1904b7ba29b7963b544 commit finished as FAILURE
Links: Blue Ocean view / Build artifacts

Copy link

@jagadish-amd jagadish-amd left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

lgtm, approved.

@pruthvistony pruthvistony merged commit d631bdb into release/2.8 Oct 27, 2025
5 of 8 checks passed
@pruthvistony pruthvistony deleted the add_gfx115x_to_hipblaslt_list_release_2.8 branch October 27, 2025 14:56
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

6 participants