Commit Graph

7 Commits

Author SHA1 Message Date
linqunAMD
e78a897ec0 [CK] Add command option instance_index and param_mask to run partial ck test (#2889)
* [CK] Add command option instance_index and param_mask to run partial ck test

Many CK test are instance test. it will loop all instance in the instance library. It causes test often out-of-time if we run test on simulator/emulator.
This PR add option instance_index and param_mask to reduce the workload of instance test

instance_index: only run test 1 available instance with specified index.
param_mask: filter the embedded parameter with specified mask

* fix CI error

* fix clang format

---------

Co-authored-by: illsilin_amdeng <Illia.Silin@amd.com>
2025-09-30 08:24:40 -07:00
linqunAMD
321627aec5 Extend XDL kernel to Support RDNA3/4 - Part 4 (#2724)
* Fix example

* fix build error

* update pk_i4 & moe test case

* fix all instance build (examples)

* fix batched_gemm_gemm (example)

* disable example_gemm_bias_softmax_gemm_permute on gfx11

* remove unnecessary disable gfx11

* update tests

* update tests2
2025-09-12 08:17:07 -07:00
Adam Osewski
061ac0649c Polished Grouped GEMM APIs and new BF16 instances (#1600)
* Few small fixes.

* New GroupedGemm instances (BF16)

* Unify and refactor GroupedGEMM device API.

* Adapt changes to new API.

* Adapt grouped gemm profiler.

* Accept multiple kbatches for grouped gemm profiler.

- delete obsolete two stage as it is now covered by grouped gemm

* Update unit test for grouped gemm.

* Fix thresholds for BF16 and F8. Unblock tests.

* Fix few instances.

* Multiple small fixes.

* Adapt to new API, check dynamic casting.

* Uncomment few data types in grouped gemm profiler.

* Fix call to SetDeviceArgs.

* Fix profile grouped gemm multiply tile loop.

* Fix grouped gemm tile loop kernel args in client examples.

* Review comments.
2024-11-27 13:02:44 +01:00
jakpiase
3e3471d5d2 Add unit tests for grouped gemm two stage (#1256)
* add unit tests for grouped gemm two stage

* add reviewers suggestions

---------

Co-authored-by: Adam Osewski <19374865+aosewski@users.noreply.github.com>
2024-05-15 10:03:39 +02:00
Illia Silin
886d9eeb99 Add an option to change the number of warm-up cycles and iterations. (#1124)
* allow setting the number of warmup cycles and iterations for profiler

* fix the gemm_splitk and grouped_gemm examples
2024-01-09 09:43:08 -08:00
Bartłomiej Kocot
595d23be14 Fix transform and instances for grouped conv bwd data (#848)
* Fix transform and instances for grouped conv bwd data

* Add instances for small K and small C

* Remove workaround after fix

* Fix interface tests
2023-08-22 11:25:41 -05:00
Adam Osewski
70e4eb567f Multiple fixes to GroupedGemm+SplitK (#707)
* Add license header.

* Reduce number of logged output. Add constant initialization.

* Add functional tests for grouped_gemm with different kbatch value.

* Add debug log informations + remove unused code.

* Don't pass kbatch to CalculateKPadded.

* Turn on logging in grouped gemm and gemm splitk profiler

* Debug: limit number of test cases to run;

* Log more information and initialize with constant value.

* Turn on DEBUG_LOG

* Add more debug log informations.

* Limit the number of instances to compile.

* Use GridwiseGemmPipeline

* Use KBatch to calculate K0

* Multiple DebugLog messages.

* Unit tests for multiple KBatch values.

* Refactoring

* Disable logging
* extract out of if statement KBatch update.

* Uncomment instances.

* Disable DebugLog.

* Use Kbatch when calculate KPadded.

* Fix CGridDesc padding.

* Use available helper functions.

* Uncomment code commented for debuggin.

* Remove unnecessary debug log messages.

* Uncomment previously commented code for debug purposes.

* Add KBatch info to profiler output summary log.

* Add gtests for gemm splitk using ckProfiler API.

* Add more test-cases for different data layout.

* Add more test cases for gemm splitk

* Remove old test.

* Unit tests for MKNK ggemm interface.

* Fix and add more unit-tests.

* Constepxr everything!

* Increase error threshold for fp16 and splitk.

Since we're using fp16 atomic add for splitk there's a
known precision loss.

---------

Co-authored-by: Adam Osewski <aosewski@amd.com>
Co-authored-by: zjing14 <zhangjing14@gmail.com>
2023-05-30 07:09:06 -05:00