Skip to content

GitLab

Switch branch/tag
  1. 04 Dec, 2023 3 commits
  3. 03 Dec, 2023 1 commit
    • Bartlomiej Wroblewski's avatar
      Add support for double buffering in direct load GEMM kernel (#1052) · bc4bf9bd
      Bartlomiej Wroblewski authored 
      This PR introduces support for double buffering in LDS into GEMM kernels that use direct load instructions.

Direct loads now use inline asm instead of intrinsics. Usage of intrinsics results in compiler adding additional waitcnt instructions what breaks possible load/compute overlap in case of double buffering.

Usage of inline asm results in the need to use sched_barrier in order to make sure that compiler cannot incorrectly reschedule instructions since it does not know the data dependencies between global->LDS and LDS->registers.
      bc4bf9bd
  5. 01 Dec, 2023 2 commits
  7. 30 Nov, 2023 4 commits
  9. 29 Nov, 2023 1 commit
    • arai713's avatar
      Disable transpose device op for MI300 (#1050) · a2969aa8
      arai713 authored 
      

* added working example for 5D input using 1D kernel

* example with 5D input tensor and 2d kernel - not working: issues with arguments

* added updated version of 3d device op - changed descriptors/dims

* added example file to check kernel

* fixed descriptor and isSupportedArgument stride problem

* added and modified kernel for 3d - updated tids/loop

* adding some more 5d example files

* fixed some issues

* changes made for testing

* working version: fixed error in stride for A, still a bit inefficient

* cleaned up formatting/comments

* updating formatting

* more formatting fixes

* fixing cmake, adding back gpu targets in cmake script

* adding client example

* added instances for client example

* fixed errors in client example

* implemented client ex with device_elementwise.hpp and device_elementwise_3d_impl.hpp

* removed extra files

* minor formatting and naming fixes

* adding test files and profiler

* fixing minor error

* minor fix

* removed unneccesary comments, renamed files

* updated instance list for client example, added different layout example

* removing instances

* fixed error in instance generation

* remove comments

* update profiler and client example tensor layouts

* fixed errors in test/profiler

* updated vector dim access to enable vector load

* updated test/profiler files

* updated example with 1d kernel

* updating profiler

* renamed files

* disabled device op for MI300

* skip  elementwise_permute_2d on gfx94x

* Update CMakeLists.txt

* fixing CMake - disabling some GPU targets

---------
Co-authored-by: default avatarJing Zhang <jizha@amd.com>
Co-authored-by: default avatarJing Zhang <jizhan@amd.com>
Co-authored-by: default avatarzjing14 <zhangjing14@gmail.com>
      a2969aa8
  11. 28 Nov, 2023 3 commits
  13. 27 Nov, 2023 2 commits
  15. 25 Nov, 2023 1 commit
    • Bartlomiej Wroblewski's avatar
      Add basic support for direct loads from global to LDS (#999) · 627054b9
      Bartlomiej Wroblewski authored 
      * Add basic support for direct loads from global to LDS

* Clean the code and comments

* Add support for fp16

* Add comments

* Add check for thread cluster lengths

* Align non-direct-load fp16 example

* Small fixes

* Extend IsSupported to check for supported GPU gens

* Build examples only on the supported HW

* Do not throw when instance not supported in 04 example

* Review: Apply review suggestions

* Review: small fix

* Review: small fix
      627054b9
  17. 17 Nov, 2023 1 commit
  19. 16 Nov, 2023 2 commits
  21. 15 Nov, 2023 2 commits
  23. 14 Nov, 2023 1 commit
  25. 13 Nov, 2023 2 commits
    • Rostyslav Geyyer's avatar
      Add conv bwd weight client example (#1005) · 5356c4a9
      Rostyslav Geyyer authored 
      * Add conv bwd weight client example

* Update instance selector

* Fake the conversion

* Bring the conversion back
      5356c4a9
    • arai713's avatar
      Hip tensor permute (#1002) · 454cf7bd
      arai713 authored 
      * adding files for F32 example

* adding functioning implementation with scalar multiplication and unary operator support

* added fp 16 type check in unary square

* updating scalar multiplication as an operator

* functioning version with scalar operator

* changing strides for col major

* updated column major implementation

* working column major implementation

* cleaned up comments, rearranged/renamed files
      454cf7bd
  27. 11 Nov, 2023 1 commit
  29. 10 Nov, 2023 2 commits
    • Bartłomiej Kocot's avatar
      Support multi AB for grouped conv fwd xdl (#1027) · 49e52bb3
      Bartłomiej Kocot authored 
      * Support multi AB for grouped conv fwd xdl

* Add instances

* Add client example

* Add example

* Add interface test

* Minor fixes

Minor fixes

Minor fixes

* Comment fixes

* Fixes

* Reference fix

* Test xdl fixes

* Improve multi_ab interface test
      49e52bb3
    • rocking's avatar
      Backward of gamma and beta for layernorm and groupnorm (#1013) · 1db75603
      rocking authored 
      * Add layernorm backward reference code

* Add groupnorm backward reference code

* Add example

* clang format

* Fixc bug of reference layernorm and groupnorm

* Fix naming

* Refine naming

* Add device op for normalization bwd gamma and beta

* Refine template parameter

* Add bwd gamma & beta of kernel

* 1. Add groupnorm example
2. Refine layernorm naming

* Narrow down the static check for performance

* Refine variable name
      1db75603
  31. 09 Nov, 2023 3 commits
    • Illia Silin's avatar
      add linker script to QA builds (#1030) · 68f2b5e7
      Illia Silin authored
      68f2b5e7
    • arai713's avatar
      Transpose 3d (#984) · 3af8c81a
      arai713 authored 
      

* added working example for 5D input using 1D kernel

* example with 5D input tensor and 2d kernel - not working: issues with arguments

* added updated version of 3d device op - changed descriptors/dims

* added example file to check kernel

* fixed descriptor and isSupportedArgument stride problem

* added and modified kernel for 3d - updated tids/loop

* adding some more 5d example files

* fixed some issues

* changes made for testing

* working version: fixed error in stride for A, still a bit inefficient

* cleaned up formatting/comments

* updating formatting

* more formatting fixes

* fixing cmake, adding back gpu targets in cmake script

* adding client example

* added instances for client example

* fixed errors in client example

* implemented client ex with device_elementwise.hpp and device_elementwise_3d_impl.hpp

* removed extra files

* minor formatting and naming fixes

* adding test files and profiler

* fixing minor error

* minor fix

* removed unneccesary comments, renamed files

* updated instance list for client example, added different layout example

* removing instances

* fixed error in instance generation

* remove comments

* update profiler and client example tensor layouts

* fixed errors in test/profiler

* updated vector dim access to enable vector load

* updated test/profiler files

* updated example with 1d kernel

* updating profiler

* renamed files

---------
Co-authored-by: default avatarJing Zhang <jizha@amd.com>
      3af8c81a
    • rocking's avatar
      Layernorm4d (#1022) · a3d9a2cd
      rocking authored 
      

* Rename folder

* Add layernorm 4d fwd example

* Rename original layernorm example

* Add layernorm 4d f16  test

* Add layernorm4d_fwd client example

* Support layernorm4D in ckProfiler

* Rename groupnorm to groupnorm fwd in example

* Rename layernorm and group fwd in test

* Rename normalization to normalization_fwd (instances)

* Add fwd to DeviceNormalization

* Rename external api header

* Rename folder, because we can also add bwd in this folder

* Add fwd in layernorm and groupnorm (profiler

* Fix compile error

---------
Co-authored-by: default avatarPo Yen Chen <PoYen.Chen@amd.com>
      a3d9a2cd
  33. 08 Nov, 2023 1 commit
  35. 07 Nov, 2023 2 commits
  37. 03 Nov, 2023 2 commits
  39. 02 Nov, 2023 2 commits
  41. 01 Nov, 2023 2 commits