omniperf
omniperf copied to clipboard
Advanced Profiling and Analytics for AMD Hardware
This PR aligns Omniperf's documentation with other ROCm components for publication on rocm.docs.amd.com. - Move docs/ to root. - Update Sphinx build config. - Structure docs for Diataxis. - Convert...
**Is your feature request related to a problem? Please describe.** Currently, filtering by dispatch ID requires global dispatch IDs across all kernel launches of an application, making it difficult to...
**Describe the bug** E.g., if you try to compare two kernels from two different runs: ``` omniperf analyze -p workloads/stream/MI300A_A1/ -k 0 -p workloads/stream-copy/MI300A_A1/ -k 1 ``` only the first...
Bumps [pillow](https://github.com/python-pillow/Pillow) from 9.5.0 to 10.3.0. Release notes Sourced from pillow's releases. 10.3.0 https://pillow.readthedocs.io/en/stable/releasenotes/10.3.0.html Changes CVE-2024-28219: Use strncpy to avoid buffer overflow #7928 [@hugovk] Use functools.lru_cache for hopper() #7912 [@hugovk]...
Using latest omniperf to run some xla tests. GPU -mi300 ``` omniperf profile -n scatt -- /grok/grok-1-rocm/xla/bazel-bin/xla/service/gpu/tests/select_and_scatter_test --gtest_filter=SelectAndScatterTest.SelectAndScatterPerformance ``` ``` ___ _ __ / _ \ _ __ ___ _...
**Describe the bug** When profiling a workload with very high arithmetic intensity, the peak ALU line stops in the middle of the chart while the data points appear further right....
**Describe the bug** The height of the items in the Kernel dropdown is too big (150 pixels!). **To Reproduce** omniperf analyze -p --gui click Kernel menu drop-down **Expected behavior** The...
**Is your feature request related to a problem? Please describe.** It can be cumbersome to type all the block fields you'd like to see in the omniperf output. It is...