mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-06-30 11:47:48 +00:00
15d7637f89
GH-2368 Minor edits GH-2368 Adding missing READMEs and standardization. resolving readme updates GH-2368 Minor improvements to documentation. Improving some readmes. Further improvement for readmes. Cleaned up the documentation in 'client_example' (#2468) Update for PR Update ACRONYMS.md to remove trivial terms Update ACRONYMS.md to provide detailed explanations for BF16 and BF8 formats Apply suggestion from @spolifroni-amd Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com> Apply suggestion from @spolifroni-amd Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com> Update README.md to clarify CK Tile API description and remove outdated references to the Tile Engine. revise 37_transpose readme revise 36_copy readme Remove references to the Tile Engine in README files for 19_gemm_multi_d and 35_batched_transpose, and update distribution links for clarity. Remove references to the Tile Engine in multiple README files and update distribution links for consistency and clarity. Remove references to the Tile Engine in README files across multiple examples
GEMM with CK Tile
This example demonstrates matrix multiplication (GEMM) using the CK Tile programming model, focusing on tile-based parallelism and modular kernel design.
Algorithm and Math
GEMM computes:
C = A \times B
where A is [M, K], B is [K, N], and C is [M, N].
- Tilewise GEMM: Each thread block computes a tile of
Cby loading tiles ofAandB, performing blockwise matrix multiply-accumulate, and writing results back.
Tile Programming Model
- Tiles: Each thread block processes a tile of
C. - Pipeline: Modular design allows swapping different memory/computation pipelines (e.g., basic, memory-bound).
Features
- Flexible Layouts: Supports row/column-major and custom strides for
A,B,C. - Batching: Batched GEMM supported.
- Precision: Supports fp16, bf16, fp8, bf8.
- Validation: CPU/GPU validation and error tolerance options.
Build & Run
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)
Source Structure
- Kernels:
gemm_basic.cpp,universal_gemm.cpp(different pipelines) - Utils:
gemm_utils.hpp(helper functions) - Build:
CMakeLists.txt,run_gemm_example.inc - Scripts:
script/(build and run helpers)
Related CK Tile Examples
- 01_fmha: Fused multi-head attention (FMHA)
- 02_layernorm2d: Tile-programming LayerNorm
- 16_batched_gemm: Batched GEMM with tiles
For distribution, see include/ck_tile/tile_program/tile_distribution/.