mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-14 02:02:46 +00:00
1f7aa130eb
* 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
[ROCm/composable_kernel commit: d184eed823]
#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)