mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-03 21:21:22 +00:00
39dc25a9b8
* Refactor universal gemm policy. * Adapt example to refactor changes. * Introduce static encoding pattern * Adding shuffled encoding patterns. * Fix err in reverse tuple. * Add transpose_tile2d * Small refactoring + doc * Enable reading on contiguous dimension in all layouts. * Transpose A/B register tile if needed for comp v3 pipeline. * Take contiguous dim size when calculating dram vector load size. * A/B smem pack size taken from WarpGemm attributes * Update B LDS layout and setup tile distribution pattern at class level. * Fix static assert. * Fix errors in examples. * Formatting & fix IsTranspose * Fix VectorSize & refactor. * Add error loging messages. * Fix VecLoadSize and TranspseC for mem pipeline. * Update unit-tests & disable mem pipeline. * Clang format * Update include/ck_tile/core/tensor/tile_window.hpp Co-authored-by: jakpiase <jakub.piasecki@amd.com> * Fix compilation and reviewers comments. * Refactor unit-test. Fallback to non-universal gemm. Need to use GemmPipelineAGmemBGmemCRegV1 for now, since GemmKernel is now supporting also non-K major vector reads. --------- Co-authored-by: jakpiase <jakub.piasecki@amd.com>
Batched GEMM
This folder contains example for batched 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>
make tile_example_batched_gemm -j
This will result in an executable build/bin/tile_example_batched_gemm
example
args:
-m m dimension (default:256)
-n n dimension (default:128)
-k k dimension (default:128)
-a_layout A tensor data layout (default:R) (R for Row, C for Col)
-b_layout B tensor data layout (default:R) (R for Row, C for Col)
-c_layout C tensor data layout (default:R) (R for Row, C for Col)
-stride_a Tensor A stride (default:128)
-stride_b Tensor B stride (default:128)
-stride_c Tensor C stride (default:128)
-batch_stride_a Batch A stride (default:32768)
-batch_stride_b Batch B stride (default:16384)
-batch_stride_c Batch C stride (default:32768)
-batch_count Batch count (default:16)
-v 0. No validation, 1. Validation on CPU, 2. Validation on GPU (default:2)
-e Absolute error tolerance (default:1e-5)
-prec data type. fp16/bf16/fp8/bf8 (default:fp16)
-warmup number of iterations before benchmark the kernel (default:10)
-repeat number of iterations to benchmark the kernel (default:100)
-timer gpu:gpu timer, cpu:cpu timer (default:gpu)