Peter Park
Peter Park
This PR adds two areas of the MI300X tuning guide https://github.com/ROCm/ROCm/pull/3416 and https://github.com/ROCm/ROCm/pull/3372 to `develop`.
This is to align with the expectations of ROCm tool and library repos >The purpose of a changelog is to make it clear to users what has changed since the...
This PR adds missing meta descriptions and keywords to improve CTR and search in the docs portal. This PR also updates metadata written in HTML in `.md` documentation pages to...
Adds fixes in 1. #3668 2. #3663 3. #3670
The AMD SMI API calls `amdsmi_get_gpu_process_isolation` and `amdsmi_clean_gpu_local_data` and the commands `amd-smi set --process-isolation ` do not work. They will be supported in an upcoming release with future driver updates.
The compiler may incorrectly compile a program that uses the `__shfl(var, srcLane, width)` function when one of the parameters to the function is undefined along some path to the function....
**Error when running Omniperf with an application with command line arguments**. As a workaround, create an intermediary script to call the application with the necessary arguments, then call the script...
Expected target peak non-gang performance (~60GB/s) and target peak gang performance (~90GB/s) are not achieved. Both gang and non-gang performance are observed to be limited at 45GB/s. This issue will...
The `KFDEvictTest.QueueTest` is failing on the MI300X platform during KFD (Kernel Fusion Driver) tests, causing the full suite to not execute properly. This issue is suspected to be hardware-related.