mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-04-20 06:49:15 +00:00
634634f5c0
* First checkpoint * Second checkpoint - hot loop scheduler * Third checkpoint - init main operator * Fourth checkpoint - main loop ready * Fifth checkpoint - main loop fix * Sixth checkpoint - ReadWritecompFunc * Seventh checkpoint - Tail finished * [CK_TILE] Blockwise gemm pipeline v5 complete * Working * Working fixes 2 * Rename v5 to v77 temporarily * Data type adjustment * Data type adjustment 2 * [CK_TILE] Blockwise Gemm pipeline v5 add tests * [CK_TILE] Fix calculation error * TEMP: check pipeline * Fix name to V6 * naming and documentation changes * WIP dump * Try fixing v1 * Failing tests v5 * Debugging * Changes v2 * F16 tests working great * Working BlockwiseGemmPipelineV5 as V6 * Cleanup and format * Merging changes part1 * [CK_TILE] Blockwise Gemm Pipeline Comp V5/V6 * Remove commented code * Fix gfx950 build issues * Fix file formatting * Review changes, more concat info, add bf16 bf8 tests * Fix formatting * Add bf16 and bf8 tests --------- Co-authored-by: Adam Osewski <Adam.Osewski@amd.com>
GEMM Matrix Multiplication
This folder contains example for GEMM using ck_tile tile-programming implementation. Currently, it only supports the basic feature of the CK Tile GEMM, but creates the placeholders for the future support on different GEMM pipeline and different GEMM modules. In the near future, we will gradually migrate all the GEMM features from old CK to CK Tile.
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
../script/cmake-ck-dev.sh ../ <arch>
# The basic pipeline method on the gemm calculation
make tile_example_gemm_basic -j`nproc`
# The memory bound pipeline on the gemm calculation
make tile_example_gemm_universal -j`nproc`
# The weight preshuffle pipeline on the gemm calculation
make tile_example_gemm_weight_preshuffle -j`nproc`
This will result in an executable build/bin/tile_example_gemm_basic & build/bin/tile_example_gemm_universal
example
args:
-m m dimension (default:1024)
-n n dimension (default:2048)
-k k dimension (default:64)
-a_layout Tensor A data layout (default: R)
-b_layout Tensor B data layout (default: C)
-c_layout Tensor C data layout (default: R)
-stride_a Tensor A stride (default:0)
-stride_b Tensor B stride (default:0)
-stride_c Tensor C stride (default:0)
-v 0. No validation, 1. Validation on CPU, 2. Validation on GPU (default:2)
-prec data type. fp16/bf16/fp8/bf8 (default:fp16)
-warmup number of iterations before benchmark the kernel (default:50)
-repeat number of iterations to benchmark the kernel (default:100)
-timer gpu:gpu timer, cpu:cpu timer (default:gpu)
-split_k splitK value (default:1)
-init 0:random, 1:linear, 2:constant(1) (default:0)
-persistent 0:non-persistent, 1:persistent (default:0)
-json 0: No Json, 1: Dump Results in Json format (default:0)
-jsonfile json file name to dump results (default:gemm.json)