* turn on -O3 compiler flag explicitly
* change cmake syntax for CI
* modify cmake line breaks in jenkinsfile
[ROCm/composable_kernel commit: 6896c3b0ae]
* add daily build with mainline compiler
* fix the compiler paths for ci
* remove the -flto flag
* build with clang by default
[ROCm/composable_kernel commit: afe4622014]
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.
[ROCm/composable_kernel commit: bc4bf9bd03]
* 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: Jing Zhang <jizha@amd.com>
Co-authored-by: Jing Zhang <jizhan@amd.com>
Co-authored-by: zjing14 <zhangjing14@gmail.com>
[ROCm/composable_kernel commit: a2969aa8b6]
* spolit the static library into several
* update lib paths and fix client example
* do not use device_mha_operarions for client examples
* use appropriate libs to link to client examples
* remove the gpu/transpose path from the list
* try fixing clinet examples 3,4,9
* add necessary libs for client examples
* fix the layernorm client example
* fix the client examples 23 and 24
* fix typo
* add interface library and refresh clang format
[ROCm/composable_kernel commit: 7965d66a81]
* 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
[ROCm/composable_kernel commit: 627054b941]
* Introduce multiABD api and deprecate multiD
* Replace multiD with multiABD
* Mark structures as deprecated
* Change doxygen deprecated to note to avoid warnings
[ROCm/composable_kernel commit: f2398f612d]
* 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
[ROCm/composable_kernel commit: 454cf7bd1f]
* 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
[ROCm/composable_kernel commit: 49e52bb357]
* 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: Jing Zhang <jizha@amd.com>
[ROCm/composable_kernel commit: 3af8c81a72]
* 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: Po Yen Chen <PoYen.Chen@amd.com>
[ROCm/composable_kernel commit: a3d9a2cd42]
* Add support for mixed precision in contraction scale and bilinear (#936)
* Extract common functionality to separate files
* Reference contraction: Remove incorrect consts from type_converts
* Reference contraction: Add missing type_convert for dst value
* Reference contraction: Fix incorrect order of B matrix dimensions
* Add support for mixed precision in contraction scale and bilinear
* Move using statements from instances to a common file
* Move using statements from examples to a common file
* Fix the order of B matrix dimensions across examples and profiler
* Fix the computation of error threshold
* Make ComputeDataType an optional argument
* Include possible DataType -> ComputeDataType casting error in the threshold
* Remove commented code
* Make the ComputeDataType an optional argument in instance
---------
Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
[ROCm/composable_kernel commit: 4ef704d8a6]
* Disable the SLP vectorizer to prevent unnecessary wait
* Add comment to the reason of adding flag
* Fix wording
[ROCm/composable_kernel commit: db4461c142]
* Enable gfx942 support for DeviceGemmXdl<> device op
* Enable gfx941 support for DeviceGemmXdl<> device op
[ROCm/composable_kernel commit: 675b69782b]
* Add support for groups in Img2Col/Col2Img
* Fix interface test
* Fix interface test G to N
* Improve performance
* Change gemm layout to 3d
* Fixes
[ROCm/composable_kernel commit: 2e824c6d46]
* 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>
[ROCm/composable_kernel commit: 4e44a9e8da]
