mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-12 09:16:52 +00:00
* Use thread cluster descriptor and explicit M_K 2d descriptor to simply Blockwise Reduction * Change by replacing ReduceDims by NumReduceDims as Device Reduce interface template parameter * Rename the folder name for the pool2d and reduce examples * Update to reduction test scripts * Add Readme for pool2d_fwd and reduce_blockwise examples * Add support for int8_t reduction (ADD/AVG, MIN/MAX/AMAX) * Tiny fix in reduce profiler and tiny update in reduce testing scripts * Tiny fix in testing script profile_reduce_no_index.sh * Tiny fix in testing script profile_reduce_no_index.sh * Add support for bfp16 reduction (using bhalf_t = ushort) * Tiny fix in amd_buffer_addressing.hpp * Tiny change in script/profile_reduce_with_index.sh * Use AccDataType for Beta value and use element_wise::PassThrough * Use type_convert for type converting in host layer reduction * Renaming and refining in Reduction profiler/device layer/examples * Renaming and refining in Reduction profiler/device layer/examples * Renaming all NumReduceDims to NumReduceDim * Fix the leaked type_convert in ThreadwiseTensorSliceTransfer_v2 * Update to testing scripts to add bf16 support * added more static_assert * Remove buggy tunable configurations defined in device_reduce_instance_xxx.hpp * Add static_assert to give compile-time warning for incorrect thread slice-size/vector-size configurations * minor change * Refine and fix (in GetWorkspaceSizeInBytes of MultiBlockPartialReduce) to make int8 completely pass * Tiny renaming in gridwise_2d_reduction_multiblock_partial_reduce.hpp * Tiny fix in script/profile_reduce_no_index.sh * Refine in DeviceReduce layer with regard to using NumInvariantDim/NumReduceDim or InvariantDims/ReduceDims * Generic renaming in host reduction and DeviceReduce layer * Add support for 4-d all dimension reduction in the profiler and add_device_reduce_xxx instances * Use multi-thread and simplification for host Reduction implementation * Add ctest for reduction * Update to clarify the using of data init method in produce_reduce/example_reduce/test_reduce/ * Update to the reduce CTest executables to enable default testing behavior when no command argument * Renaming Co-authored-by: Jianfeng yan <jfyan008@gmail.com>
53 lines
2.1 KiB
Bash
Executable File
53 lines
2.1 KiB
Bash
Executable File
#!/bin/bash
|
|
|
|
## The following will be used for CI
|
|
|
|
set -x
|
|
|
|
## for float
|
|
bin/test_reduce_with_index -D 64,4,280,82 -R 0,1,2,3 0 2
|
|
bin/test_reduce_with_index -D 64,4,280,82 -R 0,1,2 0 2
|
|
bin/test_reduce_with_index -D 64,4,280,82 -R 0,1,3 0 2
|
|
bin/test_reduce_with_index -D 64,4,280,82 -R 0,2,3 0 2
|
|
bin/test_reduce_with_index -D 64,4,280,82 -R 1,2,3 0 2
|
|
bin/test_reduce_with_index -D 64,4,280,82 -R 0 0 2
|
|
bin/test_reduce_with_index -D 64,4,280,82 -R 1 0 2
|
|
bin/test_reduce_with_index -D 64,4,280,82 -R 2 0 2
|
|
bin/test_reduce_with_index -D 64,4,280,82 -R 3 0 2
|
|
|
|
## for float16
|
|
bin/test_reduce_with_index -D 64,4,280,82 -R 0,1,2,3 1 2
|
|
bin/test_reduce_with_index -D 64,4,280,82 -R 0,1,2 1 2
|
|
bin/test_reduce_with_index -D 64,4,280,82 -R 0,1,3 1 2
|
|
bin/test_reduce_with_index -D 64,4,280,82 -R 0,2,3 1 2
|
|
bin/test_reduce_with_index -D 64,4,280,82 -R 1,2,3 1 2
|
|
bin/test_reduce_with_index -D 64,4,280,82 -R 0 1 2
|
|
bin/test_reduce_with_index -D 64,4,280,82 -R 1 1 2
|
|
bin/test_reduce_with_index -D 64,4,280,82 -R 2 1 2
|
|
bin/test_reduce_with_index -D 64,4,280,82 -R 3 1 2
|
|
|
|
## for int8_t
|
|
bin/test_reduce_with_index -D 64,4,280,82 -R 0,1,2,3 3 2
|
|
bin/test_reduce_with_index -D 64,4,280,82 -R 0,1,2 3 2
|
|
bin/test_reduce_with_index -D 64,4,280,82 -R 0,1,3 3 2
|
|
bin/test_reduce_with_index -D 64,4,280,82 -R 0,2,3 3 2
|
|
bin/test_reduce_with_index -D 64,4,280,82 -R 1,2,3 3 2
|
|
bin/test_reduce_with_index -D 64,4,280,82 -R 0 3 2
|
|
bin/test_reduce_with_index -D 64,4,280,82 -R 1 3 2
|
|
bin/test_reduce_with_index -D 64,4,280,82 -R 2 3 2
|
|
bin/test_reduce_with_index -D 64,4,280,82 -R 3 3 2
|
|
|
|
## for bfloat16
|
|
bin/test_reduce_with_index -D 64,4,280,82 -R 0,1,2,3 5 2
|
|
bin/test_reduce_with_index -D 64,4,280,82 -R 0,1,2 5 2
|
|
bin/test_reduce_with_index -D 64,4,280,82 -R 0,1,3 5 2
|
|
bin/test_reduce_with_index -D 64,4,280,82 -R 0,2,3 5 2
|
|
bin/test_reduce_with_index -D 64,4,280,82 -R 1,2,3 5 2
|
|
bin/test_reduce_with_index -D 64,4,280,82 -R 0 5 2
|
|
bin/test_reduce_with_index -D 64,4,280,82 -R 1 5 2
|
|
bin/test_reduce_with_index -D 64,4,280,82 -R 2 5 2
|
|
bin/test_reduce_with_index -D 64,4,280,82 -R 3 5 2
|
|
|
|
set +x
|
|
|