Skip to content

GitLab

Switch branch/tag
  1. 04 Feb, 2025 2 commits
  3. 03 Feb, 2025 2 commits
  5. 01 Feb, 2025 1 commit
  7. 31 Jan, 2025 9 commits
    • Max Podkorytov's avatar
      re-add group-mode kernels · 81e00bce
      Max Podkorytov authored
      81e00bce
    • Max Podkorytov's avatar
      remove unused cases from smoke test · c657f72b
      Max Podkorytov authored
      c657f72b
    • arai713's avatar
      Codegen hipRTC compilation (#1579) · 2e3183af
      arai713 authored 
      

* updating codegen build for MIOpen access: adding .cmake for codegen component

* updating CMake

* adding in header guards for some headers due to issues with hiprtc compilation in MIOpen

* some more header guards

* putting env file in header guard

* cleaning up some includes

* updated types file for hiprtc purposes

* fixed types file: bit-wise/memcpy issue

* updating multiple utility files to deal with standard header inclusion for hiprtc

* added some more header guards in the utility files, replacing some standard header functionality

* added some more header guards

* fixing some conflicts in utility files, another round of header guards

* fixing errors in data type file

* resolved conflict errors in a few utility files

* added header guards/replicated functionality in device files

* resolved issues with standard headers in device files: device_base and device_grouped_conv_fwd_multiple_abd

* resolved issues with standard headers in device files: device_base.hpp, device_grouped_conv_fwd_multiple_abd.hpp, device_grouped_conv_fwd_multiple_abd_xdl_cshuffle.hpp

* added header guards for gridwise gemm files: gridwise_gemm_multiple_abd_xdl_cshuffle.hpp and gridwise_gemm_multiple_d_xdl_cshuffle.hpp

* fixed issue with numerics header, removed from transform_conv_fwd_to_gemm and added to device_column_to_image_impl, device_grouped_conv_fwd_multiple_abd_xdl_cshuffle, device_grouped_conv_fwd_multiple_abd_xdl_cshuffle_v3, device_image_to_column_impl

* replaced standard header usage and added header guards in block to ctile map and gridwise_gemm_pipeline_selector

* resolved errors in device_gemm_xdl_splitk_c_shuffle files in regards to replacement of standard headers in previous commit

* added replicated functionality for standard header methods in utility files

* replaced standard header functionality in threadwise tensor slice transfer files and added header guards in element_wise_operation.hpp

* temp fix for namespace error in MIOpen

* remove standard header usage in codegen device op

* removed standard header usage in elementwise files, resolved namespace errors

* formatting fix

* changed codegen argument to ON for testing

* temporarily removing codegen compiler flag for testing purposes

* added codegen flag again, set default to ON

* set codegen flag default back to OFF

* replaced enable_if_t standard header usage in data_type.hpp

* added some debug prints to pinpoint issues in MIOpen

* added print outs to debug in MIOpen

* removed debug print outs from device op

* resolved stdexcept include error

* formatting fix

* adding includes to new fp8 file to resolve ck::enable_if_t errors

* made changes to amd_wave_read_first_lane

* updated functionality in type utility file

* fixed end of file issue

* resovled errors in type utility file, added functionality to array utility file

* fixed standard header usage replication in data_type file, resolves error with failing examples on navi3x

* formatting fix

* replaced standard header usage in amd_ck_fp8 file

* added include to random_gen file

* removed and replicated standard header usage from data_type and type_convert files for fp8 changes

* replicated standard unsigned integer types in random_gen

* resolved comments from review: put calls to reinterpret_cast for size_t in header guards

* updated/added copyright headers

* removed duplicate header

* fixed typo in header guard

* updated copyright headers

---------
Co-authored-by: default avatarIllia Silin <98187287+illsilin@users.noreply.github.com>
      2e3183af
    • Illia Silin's avatar
      fix ck_tile gemm scripts (#1851) · 2ab8bf4c
      Illia Silin authored
      2ab8bf4c
    • Max Podkorytov's avatar
      remove readme · b29432f5
      Max Podkorytov authored
      b29432f5
    • Max Podkorytov's avatar
      edit test and benchmark scripts for the new example · 60d0af7e
      Max Podkorytov authored
      60d0af7e
    • Max Podkorytov's avatar
      remove bwd related scripts · 758b2aaa
      Max Podkorytov authored
      758b2aaa
    • Max Podkorytov's avatar
      run clang-format · 37052173
      Max Podkorytov authored
      37052173
    • Illia Silin's avatar
      Enable ck_tile gemms build in CI by default. (#1850) · 7cf89316
      Illia Silin authored 
      * turn on the ck_tile gemm tests by default

* enable ck_tile gemms CI build by default
      7cf89316
  9. 30 Jan, 2025 5 commits
  11. 29 Jan, 2025 13 commits
  13. 28 Jan, 2025 1 commit
  15. 27 Jan, 2025 2 commits
    • Andriy Roshchenko's avatar
      Add OCP FP8 support in CK_TILE (#1829) · 35aebe59
      Andriy Roshchenko authored 
      * Add OCP FP8 to CK_TILE

* Validate OCP FP8 in FMHA FWD under VALID=1
      35aebe59
    • Adam Osewski's avatar
      [CK-Tile] Enable vectorized reads on all layouts & improve perf. (#1835) · 39dc25a9
      Adam Osewski authored 
      

* Refactor universal gemm policy.

* Adapt example to refactor changes.

* Introduce static encoding pattern

* Adding shuffled encoding patterns.

* Fix err in reverse tuple.

* Add transpose_tile2d

* Small refactoring + doc

* Enable reading on contiguous dimension in all layouts.

* Transpose A/B register tile if needed for comp v3 pipeline.

* Take contiguous dim size when calculating dram vector load size.

* A/B smem pack size taken from WarpGemm attributes

* Update B LDS layout and setup tile distribution pattern at class level.

* Fix static assert.

* Fix errors in examples.

* Formatting & fix IsTranspose

* Fix VectorSize & refactor.

* Add error loging messages.

* Fix VecLoadSize and TranspseC for mem pipeline.

* Update unit-tests & disable mem pipeline.

* Clang format

* Update include/ck_tile/core/tensor/tile_window.hpp
Co-authored-by: default avatarjakpiase <jakub.piasecki@amd.com>

* Fix compilation and reviewers comments.

* Refactor unit-test. Fallback to non-universal gemm.

Need to use GemmPipelineAGmemBGmemCRegV1 for now,
since GemmKernel is now supporting also non-K major vector reads.

---------
Co-authored-by: default avatarjakpiase <jakub.piasecki@amd.com>
      39dc25a9
  17. 24 Jan, 2025 2 commits
  19. 22 Jan, 2025 3 commits