Skip to content

GitLab

Switch branch/tag
  1. 07 Nov, 2023 2 commits
  3. 03 Nov, 2023 2 commits
  5. 02 Nov, 2023 2 commits
  7. 01 Nov, 2023 2 commits
  9. 31 Oct, 2023 3 commits
  11. 30 Oct, 2023 1 commit
    • Illia Silin's avatar
      Enable sccache in the default docker and CI. (#1009) · 4e44a9e8
      Illia Silin authored 
      

* replace ccache with sccache, pin package versions

* put ccache back temporarily to avoid breaking other CI jobs

* add sccashe_wrapper.sh script

* fix the package version syntax

* fix the pymysql package issue

* run sccache_wrapper before build if ccache server found

* set the paths before calling the sccache_wrapper

* use /tmp instead of /usr/local for cache

* try using sccache --start-server instead of wrapper

* try using redis server with sccache

* define SCCACHE_REDIS

* add redis and ping packages, and redis port

* use the new sccache redis server

* do not use sccache with staging compiler

* fix the condition syntax

* add stunnel to redis

* add tunnel verification

* separate caches for different architectures

* fix syntax for the cache tag

* quse double brackets for conditions

* add bash line to the script

* add a switch for sccache and only use it in build stage

* run check_host function when enabling sccache

* fix the invocation tags for sccache

* fix groovy syntax

* set the invocation tag in groovy

* disable sccache in clang-format stage

* try another syntax for invocation tags

* use local sccache server if can't connect to redis

* fix script syntax

* update README

* refresh readme

* readme updates

* remove the timing and verification caveat from readme

---------
Co-authored-by: default avatarLisa Delaney <lisa.delaney@amd.com>
      4e44a9e8
  13. 28 Oct, 2023 1 commit
  15. 26 Oct, 2023 1 commit
  17. 23 Oct, 2023 1 commit
  19. 21 Oct, 2023 1 commit
    • Bartłomiej Kocot's avatar
      Fix cmake dtype check (#989) · ac0e0067
      Bartłomiej Kocot authored 
      * Fix instances dtype check

* Fix source dtypes seletor for examples and tests

* Sync with new cmakefile changes

* Remove not needed ifdefs

* Remove not needed ifdefs
      ac0e0067
  21. 20 Oct, 2023 1 commit
  23. 19 Oct, 2023 5 commits
  25. 18 Oct, 2023 4 commits
    • rocking's avatar
      Layernorm and groupnorm support to save mean and inverse std in forward (#929) · 3696fe1c
      rocking authored 
      * save mean and inverse std in normalization

* Save mean and inverse std in splitK

* Vector save mean and inv std

* Modify instance for save mean and std

* simplify the layernorm example

* Save mean and std in groupnorm example

* Save mean and inv std in ckProfiler and test

* Remove compute data type from base class

* Save mean and inv std in client example

* Add changelog

* clang format

* Fix compile error

* Refine naming

* Avoid error in bf16

* revert changelog
      3696fe1c
    • zjing14's avatar
      fixed math-ci error; suspend a warning (#996) · 58338bb2
      zjing14 authored 
      
Co-authored-by: default avatarJing Zhang <jizha@amd.com>
      58338bb2
    • zjing14's avatar
      Clean DTYPES conditions in CMake (#974) · bf435140
      zjing14 authored 
      

* Add a condition to build fp8 instances

* simplified buffer_load/store

* add bfp8/fp8

* fixed

* remove all f8/bf8 condition include folder

* fixed cmake conditions

* fixed DTYPES=fp16/bfp16

* fix

* fixed buffer_load

* fixed buffer_store

* fix

* clean example cmake files

* fixed ci

* fixed cit

---------
Co-authored-by: default avatarRostyslav Geyyer <rosty.geyyer@amd.com>
Co-authored-by: default avatarJing Zhang <jizha@amd.com>
      bf435140
    • zjing14's avatar
      Add contraction_multi_abd (#972) · 1cc36ba5
      zjing14 authored 
      

* add gridwise_multi_abd

* move element_op into RunRead

* merge element_wise op with data read

* add multiABD example

* allow packed elementwise_op

* changed example

* clean

* clean

* add is_detected

* fix

* minor fix

* add scaleAdd_vec4 example

* init commit for contraction_multi_ABD

* add examples

* add examples of multiA and broadcast

* update example

* fixed comments

* Update cmake-ck-dev.sh

* Update cmake-ck-dev.sh

* Add comments into the example

* Update CMakeLists.txt

---------
Co-authored-by: default avatarJing Zhang <jizha@amd.com>
      1cc36ba5
  27. 17 Oct, 2023 2 commits
  29. 16 Oct, 2023 2 commits
    • zjing14's avatar
      workaround with float (#992) · 39430bfd
      zjing14 authored 
      
Co-authored-by: default avatarJing Zhang <jizha@amd.com>
      39430bfd
    • Illia Silin's avatar
      Add hipTensor build and test to CK CI. (#990) · 707ad002
      Illia Silin authored 
      * add a hipTensor test to CI

* use jenkins git plugin

* change hipTensor folder location in CI

* change the git method for hipTensor

* run tests usign ctest

* check the hipTensor contents

* only build hipTensor on MI100/200

* pull hipTensor as zip archive

* fix jenkins syntax

* add path to the CK installation

* combine build commands into one shell

* change jenkins syntax for CK installer path

* try different syntax

* allow unzip overwrite

* fix jenkins file syntax

* remove any old versions of hipTensor before building

* add option to select hipTensor branch for testing
      707ad002
  31. 13 Oct, 2023 2 commits
  33. 12 Oct, 2023 2 commits
  35. 11 Oct, 2023 2 commits
    • zjing14's avatar
      Revert "Grouped Gemm with looping over the tiles. (#788)" (#982) · c99323be
      zjing14 authored 
      This reverts commit a4f72a31.
      c99323be
    • Adam Osewski's avatar
      Grouped Gemm with looping over the tiles. (#788) · a4f72a31
      Adam Osewski authored 
      

* Introduce LocalBlockToCTileMap.

* Change the signature of CalculateBottomIndex() function which now does
not accept any argument. The B2C map which is already passed as an
argument to the kernel Run function is calculating block's local id
already outside at kernel entry point __global__ function.
The LocalB2C map stores as members local block ID.

* Use LocalBlockToCTile map in device ops.

* First draft of tile loop work distribution.

* Fix typo.

* Simplify kernel arguments.

Calculate descriptors & B2C maps on the device.

* Use looping kernel.

* Fix B2C constructor.

* Fix Navi21 errors.

* Calculate tile start/end in device kernel.

* Change Run API to accept user provided workspace buffer.

* Add new line at EOF.

* Move Gemm KernelArguments to device op interface.

* Remove unused code.

* Update API.

* Launch grid size which is min of occupancy vs tile count

* Get back to use constant memory for gemm descriptors.

* Remove unused code.

* Add default virtual method implementation.

* Update comments to conform with doxygen style.

* Fix doc style and unused parameters.

* Add thread cluster lengths to kernel name.

* Remove old splitk impl and replace it with tile looping one.

* Modify instances.

* set KPerBlock to 64
* maximize wherever possible vector load size.

* Fix instances cluster lengths.

* Change comment style.

* Use 128b store where possible in instances.

* Update test cases, since KPerBlock has doubled.

* Update output stream operator for Sequence.

* Add pipeline version to GroupedGEMM device op type string.

* Fix pipeline version type logging.

* Fix input tensors type after merge.

* Fix compiler error.

* Fix output stream operator for Pipeline version.

* Store using 128b.

* Set of instances with kpb 32/64

* Limit number of instances

* Remove commented out instances.

* Fix function name.

* Limit the number of instances.

Add pipline version to the regular instances

* Change thr cluster layout for reading B tensor.

* disabled failed instances

---------
Co-authored-by: default avatarAdam Osewski <aosewski@amd.com>
Co-authored-by: default avatarzjing14 <zhangjing14@gmail.com>
Co-authored-by: default avatarJing Zhang <jizha@amd.com>
      a4f72a31
  37. 10 Oct, 2023 2 commits
  39. 05 Oct, 2023 2 commits