GitLab

* add a CK_USE_CODEGEN build argument to enable codegen

* fix cmake codegen logic

* update build logic with GPU_ARCHS

* fix the GPU_ARCHS build for codegen

* unset GPU_TARGETS when GPU_ARCHS are set

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

(cherry picked from commit 652a7c04)

* updating CMake

(cherry picked from commit a685822e)

* Legacy support: customized filesystem

* Update cmakefile for python alternative path

* fix build issues

* CK has no boost dependency

* More fixes to issues found on legay systems

* fix clang format issue

* Check if blob is correctly generated in cmake

* fix the python issues

* add a compiler flag for codegen when using alternative python

* use target_link_options instead of target_compile_options

---------
Co-authored-by: illsilin <Illia.Silin@amd.com>

* Legacy support: customized filesystem

* Update cmakefile for python alternative path

* fix build issues

* CK has no boost dependency

* More fixes to issues found on legay systems

* fix clang format issue

* Check if blob is correctly generated in cmake

* fix the python issues

* add a compiler flag for codegen when using alternative python

* use target_link_options instead of target_compile_options

---------
Co-authored-by: illsilin <Illia.Silin@amd.com>

* locate a newwer version of python when -DRHEL=ON flag is set

* allow setting python version on cmake command line

* initial push - altering codegen build

* fix the codegen cmake

* enable codegen build for gfx908 and gfx90a

* enable building codegen with INSTANCES_ONLY=ON

* updating ck_rtc

* remove gpu targets for codegen and rename tests

* make codegen tests dependencies of tests and check targets

---------
Co-authored-by: illsilin <Illia.Silin@amd.com>
Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>

* re-enable fp8 and bf8 for all targets

* restore the fp8 gemm instances

* re-enable conv_3d fp8 on all architectures

* diasble several fp8 gemm instances on all architectures except gfx94

* clang format fix

* Check compiler flags before using

The user's compiler may not support these flags, so check.
Resolves failures on Fedora.
Signed-off-by: Tom Rix <trix@redhat.com>

* fix syntax CMakeLists.txt

Fix syntax in the check_cxx_compiler_flag.

---------
Signed-off-by: Tom Rix <trix@redhat.com>
Co-authored-by: Tom Rix <trix@redhat.com>
Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>

* replace buffer_atomic with global_atomic

* fixed global_atomic_add

* added bf16 atomic_add

* format

* clang-format-12

* clean

* clean

* add guards

* Update gtest.cmake

* enabled splitk_gemm_multi_d

* format

* add ckProfiler

* format

* fixed naming

* format

* clean

* clean

* add guards

* fix clang format

* format

* add kbatch printout

* clean

* Add rocm6.2 related gemm optimization

* Limit bf16 atomic usage

* remove redundant RCR gemm_universal instance

* Add RRR fp8 gemm universal instance

* Bug fix

* Add GPU_TARGET guard to FP8/BF8 target

* bug fix

* update cmake

* remove all fp8/bf8 example if arch not support

* Enable fp8 RRR support in ckProfiler

* limit greedy-reverse flag to gemm_universal in ckProfiler

---------
Co-authored-by: Jing Zhang <jizhan@fb.com>
Co-authored-by: Jing Zhang <jizhan@meta.com>
Co-authored-by: zjing14 <zhangjing14@gmail.com>
Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
Co-authored-by: illsilin <Illia.Silin@amd.com>

* initial push

* cleaned up compiler errors

* removed commented code

* build codegen folder only for gfx9 targets

* remove separate stage for codegen tests from CI

* removed commented code from CMake

---------
Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
Co-authored-by: illsilin <Illia.Silin@amd.com>

* add compiler flags to fix compiler issues

* fix typo.

* disable test_smfmac_op on all devices except gfx942

* specify full path to compiler in CI

A standard option in Fedora packaging that is used to check
the correctness of c++ use of the standard c++ library.
Signed-off-by: Tom Rix <trix@redhat.com>
Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>

* add a build parameter to build only XNACK targets

* use ENABLE_ASAN_PACKAGING flag to set targets for ASAN builds

---------
Co-authored-by: Bartłomiej Kocot <barkocot@amd.com>

* set individual gpu targets for instances, examples, tests

* fix path to hip compiler

* fix path to hip compiler once more

* aggregate device macros in ck_tile config header

* fix the cmake logic for instances

* fix clang format

* add gfx900 and gfx906 to default set of targets

* code clean-up

* remove the profiling output samples

* add rocm6.1 docker and make it default for CI

* fix typo

* move the rocm6.1 image into public dockerhub repo

* enable gfx940

* switch between intrinsic mfma routines on mi100/200 and mi300

* fix mfma_int8 on MI300

* disable 2 int8 examples on MI300

* Update cmake-ck-dev.sh

* restore gitignore file

* modify Jenkinsfile to the internal repo

* Bump rocm-docs-core from 0.24.0 to 0.29.0 in /docs/sphinx

Bumps [rocm-docs-core](https://github.com/RadeonOpenCompute/rocm-docs-core) from 0.24.0 to 0.29.0.
- [Release notes](https://github.com/RadeonOpenCompute/rocm-docs-core/releases)
- [Changelog](https://github.com/RadeonOpenCompute/rocm-docs-core/blob/develop/CHANGELOG.md)
- [Commits](https://github.com/RadeonOpenCompute/rocm-docs-core/compare/v0.24.0...v0.29.0

)

---
updated-dependencies:
- dependency-name: rocm-docs-core
  dependency-type: direct:production
  update-type: version-update:semver-minor
...
Signed-off-by: dependabot[bot] <support@github.com>

* initial enablement of gfx950

* fix clang format

* disable examples 31 and 41 int8 on gfx950

* add code

* fix build wip

* fix xx

* now can build

* naming

* minor fix

* wip fix

* fix macro for exp2; fix warpgemm a/b in transposedC

* unify as tuple_array

* Update the required Python version to 3.9

* Update executable name in test scripts

* re-structure tuple/array to avoid spill

* Merge function templates

* Fix format

* Add constraint to array<> ctor

* Re-use function

* Some minor changes

* remove wrong code in store_raw()

* fix compile issue in transpose

* Rename enum
Rename 'cood_transform_enum' to 'coord_transform_enum'

* let more integral_constant->constant, and formating

* make sure thread_buffer can be tuple/array

* temp fix buffer_store spill

* not using custom data type by default, now we can have ISA-level same code as opt_padding

* fix compile error, fp8 not ready now

* fix fp8 duplicated move/shift/and/or problem

* Default use CK_TILE_FLOAT_TO_FP8_STOCHASTIC rounding mode

* fix scratch in fp8 kernel

* update some readme

* fix merge from upstream

* sync with upstream

* sync upstream again

* sync 22

* remove unused

* fix clang-format

* update README of ck_tile example

* fix several issue

* let python version to be 3.8 as minimal

* remove ck_tile example from default cmake target like all/install/check

* remove mistake

* 1).support receipe in generate.py 2).use simplified mask type 3).change left/right to pass into karg

* fix some bug in group-mode masking and codegen. update README

* F8 quantization for FMHA forward (#1224)

* Add SAccElementFunction, PComputeElementFunction, OAccElementFunction in pipeline

* Add element function to fmha api

* Adjust P elementwise function

* Fix bug of elementwise op, our elementwise op is not inout

* Add some elementwise op, prepare to quantization

* Let generate.py can generate different elementwise function

* To prevent compiler issue, remove the elementwise function we have not used.

* Remove f8 pipeline, we should share the same pipeline even in f8

* Remove remove_cvref_t

* Avoid warning

* Fix wrong fp8 QK/KV block gemm setting

* Check fp8 rounding error in check_err()

* Set fp8 rounding error for check_err()

* Use CK_TILE_FLOAT_TO_FP8_STANDARD as default fp8 rounding mode

* 1. codgen the f8 api and kernel
2. f8 host code

* prevent warning in filter mode

* Remove not-in-use elementwise function kargs

* Remove more not-in-use elementwise function kargs

* Small refinements in C++ source files

* Use conditional_t<> to simplify code

* Support heterogeneous argument for binary function types

* Re-use already-existing scales<> functor template

* Fix wrong value produced by saturating

* Generalize the composes<> template

* Unify saturates<> implementation

* Fix type errors in composes<>

* Extend less_equal<>

* Reuse the existing template less_equal<> in check_err()

* Add equal<float> & equal<double>

* Rename check_err() parameter

* Rename check_err() parameter

* Add FIXME comment for adding new macro in future

* Remove unnecessary cast to void

* Eliminate duplicated code

* Avoid dividing api pool into more than 2 groups

* Use more clear variable names

* Use affirmative condition in if stmt

* Remove blank lines

* Donot perfect forwarding in composes<>

* To fix compile error, revert generate.py back to 4439cc107dd90302d68a6494bdd33113318709f8

* Fix bug of p element function

* Add compute element op to host softmax

* Remove element function in api interface

* Extract user parameter

* Rename pscale and oscale variable

* rename f8 to fp8

* rename more f8 to fp8

* Add pipeline::operator() without element_functor

* 1. Remove deprecated pipeline enum
2. Refine host code parameter

* Use quantization range as input

* 1. Rename max_dtype to dtype_max.
2. Rename scale to scale_s
3.Add init description

* Refine description

* prevent early return

* unify _squant kernel name in cpp, update README

* Adjust the default range.

* Refine error message and bias range

* Add fp8 benchmark and smoke test

* fix fp8 swizzle_factor=4 case

---------
Co-authored-by: Po Yen Chen <PoYen.Chen@amd.com>
Co-authored-by: carlushuang <carlus.huang@amd.com>

---------
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: illsilin <Illia.Silin@amd.com>
Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
Co-authored-by: Jing Zhang <jizha@amd.com>
Co-authored-by: zjing14 <zhangjing14@gmail.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Po-Yen, Chen <PoYen.Chen@amd.com>
Co-authored-by: rocking <ChunYu.Lai@amd.com>

* pass XDL and WMMA macros to libs that use CK

* update config.h after XDL and WMMA macros get set

* parse examples inside the add_example_executable function

* fix the example 64 cmake file

* add xdl flag to the gemm_bias_softmax_gemm_permute example

* add filtering of tests based on architecture type

* enable test_grouped_gemm for gfx9 only

* enable test_transpose only for gfx9

* only linnk test_transpose if it gets built

* split the gemm instances by architectures

* split gemm_bilinear,grouped_conv_bwd_weight instances by targets

* split instances by architecture

* split grouped_conv instances by architecture

* fix clang format

* fix the if-else logic in group_conv headers

* small fix for grouped convolution instances

* fix the grouped conv bwd weight dl instances

* fix client examples

* only enable client examples 3 and 4 on gfx9

* set the gfx9 macro

* make sure the architecture macros are set by cmake

* use separate set of xdl/wmma flags for host code

* sinmplify the main cmake file

* add conv_fwd_bf8 instance declaration

* enable compilation of INSTANCES_ONLY for Windows

* suppress ROCMChecks warnings on GoogleTests

* suppress -Wfloat-equal warning on GoogleTests

---------
Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>

* ROCm 6.0 replaces all __HIP_PLATFORM_HCC__ with __HIP_PLATFORM_AMD__

* make it backward compatible

* Update .clang-tidy

* Update ClangTidy.cmake

Copied from the llvm-project LLVM_PARALLEL_*_JOBS

Concurrent linking can break the build as well as having too many
compile jobs for the avaiable memory.  These options allow the user
to fine tune the build to fit within their machines memory
constraints.

An example use on linux is
COMPILE_JOBS=`cat /proc/cpuinfo | grep -m 1 'cpu cores' | awk '{ print $4 }'`
if [ ${COMPILE_JOBS}x = x ]; then
  COMPILE_JOBS=1
fi
BUILD_MEM=4
MEM_KB=0
MEM_KB=`cat /proc/meminfo | grep MemTotal | awk '{ print $2 }'`
MEM_MB=`eval "expr ${MEM_KB} / 1024"`
MEM_GB=`eval "expr ${MEM_MB} / 1024"`
COMPILE_JOBS_MEM=`eval "expr 1 + ${MEM_GB} / ${BUILD_MEM}"`
if [ "$COMPILE_JOBS_MEM" -lt "$COMPILE_JOBS" ]; then
  COMPILE_JOBS=$COMPILE_JOBS_MEM
fi
LINK_MEM=32
LINK_JOBS=`eval "expr 1 + ${MEM_GB} / ${LINK_MEM}"`

cmake -G Ninja -DCK_PARALLEL_LINK_JOBS=$LINK_JOBS
               -DCK_PARALLEL_COMPILE_JOBS=$COMPILE_JOBS
Signed-off-by: Tom Rix <trix@redhat.com>

* add daily build with mainline compiler

* fix the compiler paths for ci

* remove the -flto flag

* build with clang by default

* 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: Lisa Delaney <lisa.delaney@amd.com>

* 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: Rostyslav Geyyer <rosty.geyyer@amd.com>
Co-authored-by: Jing Zhang <jizha@amd.com>

* split ckProfiler gfx9 package into gfx90 and gfx94

* use lower case for package names