Update Blockwise and Gridwise files to support both wave32 & wave64.
1. Calculate WaveSize from template parameter, instead of hard code it to 64, some "64" is also replace with WaveSize
2. Move BN0Shuffled and BK0Shuffled to device side. we can't get correct mfma inst info in host side.
3. Update b_thread_offset_n and b_thread_offset_k in gridwise_gemm_xdl_cshuffle_v3_b_scale.hpp for gfx11. in gfx11, input data is duplicated for each 16 threads, it is different with all of others.
4. Modify a1_threadwise_copy in gridwise_batched_*gemm*gemm for gfx11. for gfx11, we need duplicate input and swizzle A if transposeC isn't enabled.
* Code drop for gtest to test atomic_add for a tensor
* Adding additional test cases
* Fix clang errors in CI pipeline
* Updated test cases
* Fix the Navi card atomic add problem
* solved the define problem
* add more print out traces
* Fix the float4 missing case
* solved the gfx9 errors
* Address the comment
---------
Co-authored-by: Khushbu <khuagarw@amd.com>
Co-authored-by: Thomas Ning <Thomas.Ning@amd.com>
* initial commit for skeleton code
* replaced skeleton code with old streamk b2c map functions from old CK, still need to clean up the code
* fixed up code to match CK Tile convention: data type changes, naming changes, etc.
* change for num_sk_blocks data type
* formatting fix
* minor fixes
* moved reduction argument to template
* resolved comments from PR review: standardizing naming, pruning unneeded code
* resolve errors from merge of device op PR: moved enum to common file
* switching to uint32_t due to implementation constraints: divmod only takes uint32_t and mixing signed and unsigned types causes problems
* unsigned type fix
* add const qualifier
* added documentation for template parameters
* documentation edit
* Adding RapidJson Library
* Adding Json Dumps in all CK_Tile Examples
Not verified yet
* Adding json to cktile Batched Transpose
* adding json dumps to layernorm2d_fwd
* Adding json dump to flatmm_basic
* Adding RapidJson Library
* Adding Json Dumps in all CK_Tile Examples
Not verified yet
* Adding json to cktile Batched Transpose
* adding json dumps to layernorm2d_fwd
* Adding json dump to flatmm_basic
* Adding json in 03_gemm
* Add json dump to 16_batched_gemm
* Add json dump to gemm_multi_d_fp16
* Add json dump to grouped_gemm
* fix fmha_bwd/fwd
* Fix clang-format errors
exclude include/rapidjson in jenkins as its a third-party library
* Saparating function and defination.
* Update Documentation of 03_gemm
* Refactoring as per code review
* Disable fp8 instances on unsupported targets (#2592)
* Restrict building of gemm_universal_preshuffle_f8 instances to specific targets in CMakeLists.txt
* Add condition to skip gemm_xdl_universal_preshuffle_f8 instances for unsupported targets in CMakeLists.txt
* Add conditions to skip unsupported targets for gemm_universal_preshuffle_f8 and gemm_xdl_universal_preshuffle_f8 instances in CMakeLists.txt
* Refine conditions to exclude gemm_universal_preshuffle_f8 instances for unsupported targets in CMakeLists.txt
---------
Co-authored-by: AviralGoelAMD <aviralgoel@amd.com>
* fix clang format
* remove duplicate lines of code from library/src/tensor_operation_instance/gpu/CMakeLists.txt
* Fixing Readme and unifying jsondumps
* adding moe_smoothquant
* adding fused_moe
* Fixing Readme for batched_gemm
* Fixing Readme for grouped_gemm
* adding flatmm
* adding gemm_multi_d_fp16
* adding elementwise
* adding File name when json is dumped
* Fixing Reduce after merge
* adding batched_transpose
* Adding Warptile in Gemm
* Fixing Clang Format
---------
Co-authored-by: Aviral Goel <aviral.goel@amd.com>
Co-authored-by: AviralGoelAMD <aviralgoel@amd.com>
Co-authored-by: illsilin_amdeng <Illia.Silin@amd.com>
* Adding fix for the gfx908 to the GEMM MFMA implementaitons of WarpGemmMfmaBf16Bf16F32M4N64K16 WarpGemmMfmaBf16Bf16F32M64N4K16
* Adding support for offload target gfx9-4-generic
* This duplication here isn't ideal
* Making edits to identify individual compilation issues.
* Minor fix for blob txt files not being created.
* Fixing compilation issues.
* Fixing ordering bug.
* Adding python profiling functionality.
* Setting individual build as default.
* Setting gpu target filtering for tile engine to gfx90a, gfx942 and gfx950.
* update the default running parameters and settings
* Fixing bug with benchmarking, shifting file generation to build instead of config.
* Updating fixes.
* Fixing json output and parsing.
* Disable ccache for tile engine gemm ops because we dont need it.
* Removing duplicate type definition.
* Improving json printing.
* Add the flexibility of different layout and more warp tile support
* Fix extra flag in name of individual kernels.
* Fixing bug with booleans.
* Solve the first patch of the post merge conflict
* Compilation fixes, and cosmetic improvements.
* Yet again compilation fixes after latest changes from develop.
* Fixing python benchmarking script.
---------
Co-authored-by: Vidyasagar Ananthan <vidyasagar.ananthan@amd.com>
Co-authored-by: Vidyasagar Ananthan <vanantha@amd.com>
* This change introduces new pipelines with Intrawave scheduler and block gemm primitives that loads the scale tensor to registers to perform dequantization post MFMA on C tensor in registers.
Scale tensor data, BQ is spliced across threads in registers and not stored in LDS.
Current support is for the following combinations, but it should be fairly straightforward to extend support to more formats.
fp8, fp8 -> f32
bf8, bf8 -> f32
fp8, i4 -> f32
bf8, i4 -> f32
Group size can go down to as low as K length of underlying WarpGemm primitive.
* Solve merge conflict
* [CK TILE] Update CHANGELOG.md
---------
Co-authored-by: Vijay Krishnamoorthy <vjkrish@fb.com>
Co-authored-by: ThomasNing <thomas.ning@amd.com>
Co-authored-by: Cong Ma <congma13@amd.com>
The performance of Aquant has increased after enabling transposed C.
Do not need to exchange AQ elements among lanes after enabling
transposed C as one thread only holds data from one row.
* add gemm unit tests for int4, int8 datatypes
* minor changes based on reviews
---------
Co-authored-by: msaffari-amd <msaffari@banff-cyxtera-s78-2.ctr.dcgpu>
* feat(check_err): add a variable to adjust number of incorrect values to print
* feat(host_tensor): add printing capability for fp8 bf8 int8 int4
* fix(gemm_utils): update acceptable data type
* fix(host_tensor): print both 4 bit ints in pk_int4_t
* refactor(HostTensor): define pk_int4_t_to_int8x2_t and fix typo in vector_type.hpp
* feat(host_tensor): add print first n elements functions
In #2443, a helper function was added test new print functionality, but it used auto for the function parameter types.
We need to support c++17 for downstream libraries, so we cannot use auto there. This PR replaces it witht the equivalent function template implementation.
* [CK TILE] Fix bugs in AQuant preshuffle
- Make Aquant works with block Mx64x256. `M` could be 16, 32, 64
- Make Aquant works with warp 16x16x32 and 32x32x16.
* [CK TILE] Rename Preshuffle to PreshuffleQuant
The new name, PreshuffleQuant, explicitly states the function's purpose:
to preshuffle the quantization matrix.
* [CK TILE Block Scale] Use GemmConfig to save tile properties
- Remove specialization of GemmQuantTypeConfig
- Pass GemmConfig around which contains tile properties. Stop using hard
coded tile properties in `gemm_calc_aquant()`
* [CK TILE Block Scale] Rename GemmConfig used in block scale
- Remove unused GemmConfig
- Rename GemmConfig used in block scale
---------
Co-authored-by: ThomasNing <thomas.ning@amd.com>
* Add CSV-driven convolution test pipeline
- Add test_grouped_convnd_fwd_dataset_xdl.cpp with CSV reader functionality
- Add complete dataset generation toolchain in test_data/
- Add Jenkins integration with RUN_CONV_COMPREHENSIVE_DATASET parameter
- Ready for comprehensive convolution testing with scalable datasets
* Update convolution test dataset generation pipeline
* add 2d, 3d dataset csv files
* Remove CSV test dataset files from repository
* Update generate_test_dataset.sh
* Fix channel division for MIOpen to CK conversion
* Remove unnecessary test files
* Fix clang-format-18 formatting issues
* TEST: Enable comprehensive dataset tests by default
* Fix test_data path in Jenkins - build runs from build directory
* Add Python dependencies and debug output for CSV generation
* Remove Python package installation - not needed
* Add better debugging for generate_test_dataset.sh execution
* Fix Jenkinsfile syntax error - escape dollar signs
* Add PyTorch to Docker image for convolution test dataset generation
- Install PyTorch CPU version for lightweight model execution
- Fixes Jenkins CI failures where CSV files were empty due to missing PyTorch
- Model generation scripts require PyTorch to extract convolution parameters
* Add debugging to understand Jenkins directory structure and CSV file status
- Print current working directory
- List CSV files in test_data directory
- Show line counts of CSV files
- Will help diagnose why tests fail in Jenkins
* Fix clang-format-18 formatting issues
- Applied clang-format-18 to test file
- Fixed brace placement and whitespace issues
* Add detailed debugging for CSV dataset investigation
- Check generated_datasets directory contents
- List all CSV files with line counts
- Show first 5 lines of main CSV file
- Applied clang-format-18 formatting
- This will help identify why CSV files are empty in Jenkins
* keep testing add pytorch installation in shell script
* Use virtual environment for PyTorch installation
- Jenkins user doesn't have permission to write to /.local
- Create virtual environment in current directory (./pytorch_venv)
- Install PyTorch in virtual environment to avoid permission issues
- Use PYTHON_CMD variable to run all Python scripts with correct interpreter
- Virtual environment will be reused if it already exists
* Remove debug code and reduce verbose logging in Jenkins
- Remove bash -x and debug commands from Jenkinsfile execute_args
- Remove all debug system() calls and getcwd from C++ test file
- Remove unistd.h include that was only needed for getcwd
- Remove debug print in CSV parser
- Add set +x to generate_test_dataset.sh to disable command echo
- Redirect Python script stdout to /dev/null for cleaner output
This makes Jenkins logs much cleaner while still showing progress messages.
* install gpu torch
* Clean up and optimize comprehensive dataset test pipeline
- Reorder Jenkinsfile execution: build -> generate data -> run test
- Remove commented-out debug code from generate_test_dataset.sh
- Ensure all files end with proper newline character (POSIX compliance)
- Keep useful status messages while removing development debug prints
- Set MAX_ITERATIONS=0 for unlimited test generation in production
* Add configuration modes to reduce test execution time
- Add --mode option (half/full) to generate_model_configs.py
- half mode (default): ~278 configs (224 2D + 54 3D) -> ~1,058 total tests
- full mode: ~807 configs (672 2D + 135 3D) -> ~3,093 total tests
- Update generate_test_dataset.sh to use CONFIG_MODE environment variable
- Keeps all model types but reduces parameter combinations intelligently
- Fixes Jenkins timeout issue (was running 3,669 tests taking 17+ hours)
- Default half mode should complete in ~4-5 hours instead of 17+ hours
* Add small mode for quick testing of comprehensive dataset
* jenkins pipeline test done
* jenkins test done
* Trigger CI build
* remove test comment and update data generation option as half
---------
Co-authored-by: Bartłomiej Kocot <barkocot@amd.com>
* Remove some unnecessary calls to create_args in basic and universal GEMM tests
* Remove unnecessary include statements in universal GEMM tests
* Improve compilation time of basic GEMM tests by only compiling the precision variants that we need
* Universal GEMM PrecType should be the same as CDataType
* Improve compilation time of universal GEMM tests by only compiling the precision variants that we need
* Revert to constexpr when defining some constants
