mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-03 05:01:25 +00:00
15c89e81f0
* initial stub for standalone softmax * start device_softmax_mk_to_mk as a wrapper to device_reduce_mk_to_m * host softmax validates * compiles; to implement beta scaling * use NaN trick to efficiently ignore OOB values during sum of exponentials * freeload device_reduce's utility functions * clean up interface * adding prior value (beta scaling) * remove restriction related to perf considerations * apply clang-format * clean; disable diagnostics * resolve conflicts * add exp wrapper * honor HostTensorDesc interface; allow implicit cast from different vector<T> type * test softmax for fp16/fp32 * update readme * amend commit NaN trick * remove redundant param added during development * format * replace ScalarDataType with AccDataType * separate out test programs by precision type * move softmax sample code to its own folder * format * keep up with recent changes in reduction API * remove extra header
615 B
615 B
Instructions for example_softmax_blockwise
Run example_softmax_blockwise
# -D <xxx> : input 3-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)
example_softmax_blockwise -D 4,128,2048 -v 1 1 1
Result
launch_and_time_kernel: grid_dim {64, 1, 1}, block_dim {256, 1, 1}
Warm up 1 time
Start running 10 times...
Perf: 0.0242877 ms, 259.039 GB/s, DeviceReduceSoftmax<256,M_C8_S1,K_C32_S8,InSrcVectorDim_1_InSrcVectorSize_8_OutDstVectorSize_8>