mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-03 05:01:25 +00:00

Files

Cong Ma 245467f359 [CK TILE] Fix bugs in AQuant preshuffle (#2700 )

* [CK TILE] Fix bugs in AQuant preshuffle

- Make Aquant works with block Mx64x256. `M` could be 16, 32, 64
- Make Aquant works with warp 16x16x32 and 32x32x16.

* [CK TILE] Rename Preshuffle to PreshuffleQuant

The new name, PreshuffleQuant, explicitly states the function's purpose:
to preshuffle the quantization matrix.

* [CK TILE Block Scale] Use GemmConfig to save tile properties

- Remove specialization of GemmQuantTypeConfig
- Pass GemmConfig around which contains tile properties. Stop using hard
  coded tile properties in `gemm_calc_aquant()`

* [CK TILE Block Scale] Rename GemmConfig used in block scale

    - Remove unused GemmConfig
    - Rename GemmConfig used in block scale

---------

Co-authored-by: ThomasNing <thomas.ning@amd.com>

2025-08-27 00:05:54 -07:00

CMakeLists.txt

Preshuffle AQ matrix in block scale gemm (#2624 )

2025-08-12 21:32:51 -07:00

gemm_aquant_basic.cpp

[CK TILE] Fix bugs in AQuant preshuffle (#2700 )

2025-08-27 00:05:54 -07:00

gemm_aquant_preshuffle.cpp

[CK TILE] Fix bugs in AQuant preshuffle (#2700 )

2025-08-27 00:05:54 -07:00

gemm_utils.hpp

[CK TILE] Fix bugs in AQuant preshuffle (#2700 )

2025-08-27 00:05:54 -07:00

README.md

invoke script directly (#2687 )

2025-08-19 00:23:07 -07:00

run_gemm_aquant_example.inc

[CK TILE] Fix bugs in AQuant preshuffle (#2700 )

2025-08-27 00:05:54 -07:00

README.md

GEMM Matrix Multiplication

This folder contains example for Block Scale 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
../script/cmake-ck-dev.sh  ../ <arch>
# The aquant pipeline method on the gemm calculation
make tile_example_gemm_aquant_basic -j

This will result in an executable build/bin/tile_example_gemm_aquant_basic

example

args:
          -b    batch size (default:1)
          -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: R)
   -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)
          -e    Absolute error tolerance (default:1e-5)
       -prec    data type. fp16/bf16/fp8/bf8/int8 (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)