mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-03-24 09:07:39 +00:00
d184eed823
* initial poc * factor out common parts in operator() * cv4 * rest of the universal gemm pipelines * fix test * remove boilerplate from tile engine * fix example * fix example * format * fix tests build for gemm * remove base pipeline codegen from gemm instance builder * unify v3 logic with the rest of universal gemm pipelines * fix build for multi abd test * fix test gemm multi d * fix build for weight preshuffle * fix grouped gemm test * fix grouped gemm multi d test * fix grouped gemm preshuffle * fix grouped gemm example except for quant * fix gemm preshuffle * fix splitk 2 stage example * fix batched gemm example * fix multid example * fix multiabd example * fix batched gemm test * fixup * fix examples build * fix grouped gemm test build * fix smoke builder
#Multiple ABD GEMM
This folder contains example for Multiple ABD GEMM using ck_tile tile-programming implementation.
build
#in the root of ck_tile
mkdir build && cd build
#you can replace < arch> with the appropriate architecture(for example gfx90a or gfx942) or \
leave it blank
sh ../script/cmake-ck-dev.sh ../ <arch>
#The basic pipeline method on the gemm calculation
make tile_example_gemm_multi_abd_fp16 -j
This will result in an executable build/bin/tile_example_gemm_multi_abd_fp16
example
args:
-m M dimensions - (Default: 3840)
-n N dimensions - (Default: 4096)
-k K dimensions - (Default: 4096)
-as_layout Tensor A layout (default:R)
-bs_layout Tensor B layout (default:C)
-ds_layout Tensor D layout (default:R)
-e_layout Tensor E layout (default:R)
-stride_as Tensor A strides - (Default: 0)
-stride_bs Tensor B strides - (Default: 0)
-stride_e Tensor C strides - (Default: 0)
-stride_ds Tensor D strides - (Default: 0)
-validate 0. No validation, 1. Validation on GPU. (Default: 1)
-warmup Number of iterations before benchmark the kernel. (Default: 10)
-repeat Number of iterations to benchmark the kernel. (Default: 100)
-kbatch kbatch for SplitK. (Default: 1)