mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-04-19 14:29:05 +00:00
63eee2d999
* Tiny fix in dynamic_buffer.hpp to support vectorized AtomicAdd for double type * Update to host layer and host reduction * Merge and remove reduction kernels * Merge and remove reduction device interfaces and update pooling device interface * Merge and remove useless reduction device instances * Update to reduction profiler and reduction ctests * Update to reduction and pooling examples and add one reduction example * Change to reduction examples to let them testable by ctest * Add explicit pass checking for reduction and pooling examples * Explicit assignment of tensor shapes in example reduce_blockwise_two_call * Use atomic_add to repace atomicAdd and add atomic_add for double type * Add reduce ctest support for double data type * Replace to_int_vector() by using c++ std::vector::assign() * Keep DeviceReduceThreadWise separated from DeviceReduceBlockWise * Merge DeviceReduceBlockWise and DeviceReduceMultiBlockAtomicAdd into DeviceReduceMultiBlock * Add GetAtomicOperationZeroValue() support for AtomicMax * Tiny change to reduce example README.md * Fix some tiny issues due to branch merging * Revoke previous change in dynamic_buffer.hpp and add atomic_add for double2_t * Add reduce multiblock_atomic_add instances for fp64 to verify vectorized atomic_add on fp64 * Renaming * Clean the header includings in device_reduce instances header files
Instructions for example_reduce_blockwise
Run example_reduce_blockwise
# -D <xxx> : input 4-d tensor lengths
# -v <x> : verification (0=no, 1=yes)
#arg1: initialization (0=no init, 1=single integer value, 2=scope integer value, 3=decimal value)
#arg2: time kernel (0=no, 1=yes)
./bin/example_reduce_blockwise -D 16,64,32,960 -v 1 1 1
Result
./bin/example_reduce_blockwise -D 16,64,32,960 -v 1 1 1
launch_and_time_kernel: grid_dim {240, 1, 1}, block_dim {256, 1, 1}
Warm up 1 time
Start running 10 times...
Perf: 0.282592 ms, 222.641 GB/s, DeviceReduceBlockWise<256,M_C4_S1,K_C64_S1,InSrcVectorDim_0_InSrcVectorSize_1_OutDstVectorSize_1>
Instructions for example_reduce_blockwise_two_call
Run example_reduce_blockwise_two_call
#arg1: verification (0=no, 1=yes(
#arg2: initialization (0=no init, 1=single integer value, 2=scope integer value, 3=decimal value)
#arg3: time kernel (0=no, 1=yes)
./bin/example_reduce_blockwise_two_call 1 2 1
Result
./bin/example_reduce_blockwise_two_call 1 2 1 launch_and_time_kernel: grid_dim {204800, 1, 1}, block_dim {256, 1, 1} Warm up 1 time Start running 10 times... launch_and_time_kernel: grid_dim {6400, 1, 1}, block_dim {256, 1, 1} Warm up 1 time Start running 10 times... Perf: 2.1791 ms, 771.42 GB/s, DeviceReduceBlockWise<256,M_C32_S1,K_C8_S1,InSrcVectorDim_1_InSrcVectorSize_1_OutDstVectorSize_1> => DeviceReduceBlockWise<256,M_C256_S1,K_C1_S1,InSrcVectorDim_1_InSrcVectorSize_1_OutDstVectorSize_1>