mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-11 08:50:17 +00:00
e17c0d8008
* Initial adding of generic reduction * Initial adding of generic reduction ... * Updates to make compiling done * clang-format all files * clang-format some files again * Renaming in profiler/include/profile_reduce.hpp * Updates and make BlockWise cases passed * Updates and make ThreadWise and MultiBlockTwoCall cases passed * Remove the support for MUL and NORM1 reduceOp from the profiler and the device instances * Change to replace the dim0_max_vector_size/dim1_max_vector_size template argument in the device reduce classes * format * adding pooling * added max and average pooling * comment out cout and kernel timing * Tiny simplification in profiler/reduce_profiler.cpp * Add example for reduce_blockwise * Tiny updates * Change to pass the ElementWiseOp from device layer to kernel * Fix the vectorDim and vectorSize in Device layer * Enable vector load on both dim0 and dim1 for Threadwise method * Tiny updates * Change to let the user to pass the preUnaryOp and posUnaryOp * Make pooling example work * split device_reduce_instance into two libraries * Tiny update * Replace nanPropaOpt enum by boolean propagate_nan * Simplification in DeviceReduce layer codes * update build * Change to clarify the difference between ck::half_t and half_float::half * Renaming in all the reduction codes * Add VectorSize as template parameter for device layer * Add BetaIsZero as kernel template and as AccDataType for alpha * print * Small updates for pooling * Updates for host_generic_reduction for reference * Update to make AVG pooling pass * Update to make MAX pooling with indices output pass * fix * add OutDst vector store to threadwise reduction and pooling * tweak * turn off check_indices that caused build issue * refactor pooling * clean up * turn off check_indices for building issue for php-compiler * add more tile size for odd C * tweak conv for odd C * update script * clean up elementwise op * add hack in reduction_operator.hpp to avoid compile error. To fix it, need to use element_wise_op in reduction op * Add OutVectorSize as device and kernel tunable, also update to Elementwise Operations * Move reduce operator mapping to host layer file reduction_operator_mapping.hpp from reduction_operator.hpp * Change to the unary operators * Move the definitions of unary operations to element_wise_operation.hpp * re-org files * Refine in device interfaces and multiblock kernels * Split the reduction configurations into instances for specific methods * Update in getTypeString() of device pool2d * Renaming in host and kernel * Tiny update in profiler/src/profiler.cpp * Uncomment in device_operation/CMakeLists.txt to enable the building of all operations * Make check_indices a templated function to remove some linking issue * Renaming in the profiler reduce module * Add support for double Reduction (but disable MultiblockAtomicAdd for double) * Tiny correction of literal string * Rename DevicePoolFwd to DevicePool2dFwd * Split device_reduce_instance_xxx.cpp files according to the data types to speed up compiling * Add comments for lists of configurations, lists of instances and references of add_reduce_instances_xxx * Remove un-used header file gridwise_generic_reduction_wrapper_common.hpp * Renaming and refining in the Reduction codes * Tiny change in the unary operators * Renaming symbols and files * Renaming symbols in the kernels * Move kernel kernel_set_buffer_value to separate file * Add IndexDataType template parameter for kernels and use int32_t as index data type in device layer * Tiny update in the kernels * Remove definition of sqrtf()/isnan()/abs() for half_t due to some ADL issue * Simplify a helper function in device layer * Tiny adjustment in testing data initialization * Renaming in kernel/device/host * Add two testing scripts for reduction * Refine the Unary operators in element_wise_operation.hpp * Update in the reduce profiler module * Update to the reduction testing scripts * reduce compile parallelism * change CI docker to rocm5.0 * remove unused variables * fix build Co-authored-by: Chao Liu <chao.liu2@amd.com>
63 lines
3.6 KiB
Bash
Executable File
63 lines
3.6 KiB
Bash
Executable File
#!/bin/bash
|
|
|
|
PRECISION= ##--half
|
|
|
|
if [ $# -ge 1 ] ; then
|
|
NREPEAT=$1
|
|
else
|
|
NREPEAT=1
|
|
fi
|
|
|
|
Operation=4
|
|
|
|
LENGTHS=64,4,280,82
|
|
|
|
## for generic validation
|
|
for op in $Operation; do
|
|
for use_idx in 0 1; do
|
|
set -x
|
|
./bin/ckProfiler reduce $PRECISION -D 64,4,280,82 -R 0 -O $op $CTYPE -v 1 1 $NREPEAT
|
|
./bin/ckProfiler reduce $PRECISION -D 4,64,280,82 -R 0 -O $op $CTYPE -v 1 1 $NREPEAT
|
|
./bin/ckProfiler reduce $PRECISION -D 280,4,64,82 -R 0 -O $op $CTYPE -v 1 1 $NREPEAT
|
|
./bin/ckProfiler reduce $PRECISION -D 64,4,280,82 -R 0,1,2 -O $op $CTYPE -v 1 1 $NREPEAT
|
|
./bin/ckProfiler reduce $PRECISION -D 4,64,280,82 -R 0,1,2 -O $op $CTYPE -v 1 1 $NREPEAT
|
|
./bin/ckProfiler reduce $PRECISION -D 64,280,82,4 -R 0,1,2 -O $op $CTYPE -v 1 1 $NREPEAT
|
|
./bin/ckProfiler reduce $PRECISION -D 700,8192 -R 1 -O $op $CTYPE -v 1 1 $NREPEAT
|
|
./bin/ckProfiler reduce $PRECISION -D 700,1024 -R 1 -O $op $CTYPE -v 1 1 $NREPEAT
|
|
./bin/ckProfiler reduce $PRECISION -D 700,4 -R 1 -O $op $CTYPE -v 1 1 $NREPEAT
|
|
set +x
|
|
done
|
|
done
|
|
|
|
## for performance evaluation (resnet50 NHWC => C)
|
|
for op in $Operation; do
|
|
for use_idx in 0 1; do
|
|
set -x
|
|
./bin/ckProfiler reduce $PRECISION -D 256,14,14,1024 -R 0,1,2 -O $op -I $use_idx -v 1 1 $NREPEAT
|
|
./bin/ckProfiler reduce $PRECISION -D 256,28,28,128 -R 0,1,2 -O $op -I $use_idx -v 1 1 $NREPEAT
|
|
./bin/ckProfiler reduce $PRECISION -D 256,58,58,128 -R 0,1,2 -O $op -I $use_idx -v 1 1 $NREPEAT
|
|
./bin/ckProfiler reduce $PRECISION -D 256,7,7,2048 -R 0,1,2 -O $op -I $use_idx -v 1 1 $NREPEAT
|
|
./bin/ckProfiler reduce $PRECISION -D 256,14,14,256 -R 0,1,2 -O $op -I $use_idx -v 1 1 $NREPEAT
|
|
./bin/ckProfiler reduce $PRECISION -D 256,30,30,256 -R 0,1,2 -O $op -I $use_idx -v 1 1 $NREPEAT
|
|
./bin/ckProfiler reduce $PRECISION -D 256,56,56,256 -R 0,1,2 -O $op -I $use_idx -v 1 1 $NREPEAT
|
|
./bin/ckProfiler reduce $PRECISION -D 256,16,16,512 -R 0,1,2 -O $op -I $use_idx -v 1 1 $NREPEAT
|
|
./bin/ckProfiler reduce $PRECISION -D 256,28,28,512 -R 0,1,2 -O $op -I $use_idx -v 1 1 $NREPEAT
|
|
./bin/ckProfiler reduce $PRECISION -D 256,7,7,512 -R 0,1,2 -O $op -I $use_idx -v 1 1 $NREPEAT
|
|
./bin/ckProfiler reduce $PRECISION -D 256,56,56,64 -R 0,1,2 -O $op -I $use_idx -v 1 1 $NREPEAT
|
|
./bin/ckProfiler reduce $PRECISION -D 256,230,230,3 -R 0,1,2 -O $op -I $use_idx -v 1 1 $NREPEAT
|
|
./bin/ckProfiler reduce $PRECISION -D 128,14,14,1024 -R 0,1,2 -O $op -I $use_idx -v 1 1 $NREPEAT
|
|
./bin/ckProfiler reduce $PRECISION -D 128,28,28,128 -R 0,1,2 -O $op -I $use_idx -v 1 1 $NREPEAT
|
|
./bin/ckProfiler reduce $PRECISION -D 128,58,58,128 -R 0,1,2 -O $op -I $use_idx -v 1 1 $NREPEAT
|
|
./bin/ckProfiler reduce $PRECISION -D 128,7,7,2048 -R 0,1,2 -O $op -I $use_idx -v 1 1 $NREPEAT
|
|
./bin/ckProfiler reduce $PRECISION -D 128,14,14,256 -R 0,1,2 -O $op -I $use_idx -v 1 1 $NREPEAT
|
|
./bin/ckProfiler reduce $PRECISION -D 128,30,30,256 -R 0,1,2 -O $op -I $use_idx -v 1 1 $NREPEAT
|
|
./bin/ckProfiler reduce $PRECISION -D 128,56,56,256 -R 0,1,2 -O $op -I $use_idx -v 1 1 $NREPEAT
|
|
./bin/ckProfiler reduce $PRECISION -D 128,16,16,512 -R 0,1,2 -O $op -I $use_idx -v 1 1 $NREPEAT
|
|
./bin/ckProfiler reduce $PRECISION -D 128,28,28,512 -R 0,1,2 -O $op -I $use_idx -v 1 1 $NREPEAT
|
|
./bin/ckProfiler reduce $PRECISION -D 128,7,7,512 -R 0,1,2 -O $op -I $use_idx -v 1 1 $NREPEAT
|
|
./bin/ckProfiler reduce $PRECISION -D 128,56,56,64 -R 0,1,2 -O $op -I $use_idx -v 1 1 $NREPEAT
|
|
set +x
|
|
done
|
|
done
|
|
|