ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-06-29 19:28:33 +00:00
Code Issues Packages Projects Releases Wiki Activity
1,892 Commits 776 Branches 40 Tags
4ba9fe186c78f8cfc7664699eaccd7fb1df80e4e
Commit Graph

548 Commits

Author SHA1 Message Date
Ding, Yi
4ba9fe186c Use random scale for init1 2025-05-14 05:42:39 +00:00
Ding, Yi
521471c956 Fix fp8/bf8 B-row 2025-05-13 10:13:18 +00:00
Ding, Yi
178e361101 Fix fp8/bf8; remove duplicated code 2025-05-13 07:52:13 +00:00
aska-0096
79246e6cb8 function pass with inline asm hacky 2025-05-12 16:54:44 +00:00
Ding, Yi
4b19b934e8 fix fp8; fix even/odd 2025-05-12 07:31:28 +00:00
aska-0096
41ea1066ac implement shuffled scale mxfp4gemm, blocker: opsel not effect 2025-05-11 05:54:13 +00:00
aska-0096
6c761bf9b8 tempsave; buggy at passed 4 e8m0 to scaled mfma 2025-05-10 09:57:49 +00:00
aska-0096
0987b0af44 remove unnecessary hacky 2025-05-09 16:07:22 +00:00
aska-0096
7bde4b8d34 Add pipeline v3. Have some runtime issue and register spill 2025-05-09 09:47:22 +00:00
aska-0096
bb043a3202 remove some unnecessary hacky; enable 256x256x256 tilesize 2025-05-09 07:54:28 +00:00
aska-0096
b2efb06315 Spilt the fp4 target. Fix the known bugs. 128x128x128 sanity checked; remove prints 2025-05-08 15:07:33 +00:00
aska-0096
32e6c8aad3 16x16x128 correct; 64x64x128 failed 2025-05-08 09:42:53 +00:00
Ding, Yi
6519ba3aa9 wip3 2025-05-08 07:44:22 +00:00
Ding, Yi
8d51a4ae96 wip2 2025-05-07 09:40:47 +00:00
Ding, Yi
d12b750bb0 wip 2025-05-07 08:17:07 +00:00
carlushuang
4e9b76f88c [CK_TILE] optimize moe sorting kernel, boost large context case up to 20x (#2153) 
* combine 2-3 as single stage

* support zeroing

* improve long tokens

* update specialization

* b16 ws

* 8bit topk optimize

* update 15 example
 2025-05-06 17:32:07 +08:00
jakpiase
0bcb804ad0 [CK_TILE] Remove scratch usage from universal gemm (#2001) 
* moves kbatch condition outside of kernel

* add reviewer comments

* fixes

* fix tests

* fixes after review

---------

Co-authored-by: Adam Osewski <19374865+aosewski@users.noreply.github.com>
 2025-05-05 18:46:44 +02:00
Andriy Roshchenko
79b0bfeb41 MX GEMM - Add FP8 GEMM Tests for Different Layouts (#2152) 
* Add gemm_mx_fp8_bf8 example with row-major B

* Add more overloads of MX MFMA instructions

* Add MK_KN (RRR) tests

* Add KM_NK (CCR) tests

* Add more problem sizes to Large tests

* Add test_gemm_mx to the list of regression tests
 2025-05-01 11:55:48 -06:00
Illia Silin
9a9f59ae69 Revert "Add ck tile examples to package (#1880)" (#2150) 2025-04-30 10:20:16 -07:00
Daniel Su
d9786f3363 Check max-ilp-scheduling compiler option for moe_gemm examples (#2127) 2025-04-28 13:40:22 -07:00
jakpiase
434d19f696 Add ck tile examples to package (#1880) 
* add ck tile examples to package

* Update jenkinsfile

* fix for jenkinsfile

* fix for building ck tile code on non gfx9

* compile ck tile examples only for gfx94

* include ck tile examples in all target

* fix for basic gemm UseStructuredSparsity

* Update CMakeLists.txt

* Update gemm_pipeline_problem.hpp

* add targets to rocm install

---------

Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
 2025-04-28 09:53:19 -07:00
lalala-sh
83394e40d2 fix moe i4 example bug (#2139) 2025-04-28 09:49:31 -07:00
Yi DING
8add2cf45d Fix fp8 convert & add option for basic example (#2129) 2025-04-27 16:26:05 -07:00
Po Yen Chen
3d4d70d2fc Avoid using store_tile_raw() for fp32 tensors (#2072) 2025-04-26 23:07:41 -07:00
joyeamd
41541aff7a SWDEV-52596 for hdim=256, when use splitkv pipeline, two new pipelines need to be added (#2126) 2025-04-25 16:31:09 +08:00
rocking
02ce6d39ea Only generate specific hdim (#2120) 2025-04-24 18:52:58 +08:00
lalala-sh
39ba03f25d Moe gemm activation (#2026) 
* fix useless code and remove usless oob

* clang format

* fix coredump in e2e test

* fix2

* fix clang format

* fix output oob

* impl int64 but result not correct

* int64 index ok now

* input output all ok

* fix uint32

* revert v1 test

* use uint32

* mork to support 13w tokens

* moe sorting fix moebuf

* fix merge

* update moe api fix aiter build

* fix buid

* fuse silu

* silu ok

* acale ok

* add silu

* change code

* gemm2 ok

* gufusion compatible ok, fix warnings

* gu fusion for m32 m64 ok

* support bf16 cshuffle

* i4 gemm2 ok

* i4 gemm2 ok and i4 gemm1 build

* 16x16 run ok

* change flops; change cshuffle dtype

* fuse gelu silu act in moe gemm1

* fp8 with act ready

* int4 act ready

* remove useless changes

* remove useless code change

* fix clang format

* add the arch limit of int4 moe gemm

* fuse moe activation

* fix fp8 16x16

* fix no quant case

* fix bugs

* fix fp8 gufusion bug

* remove useless comments

* refine activation code & complete moe example

* fix int8 bugs

* merge tkw1

---------

Co-authored-by: coderfeli <coderfeli@163.com>
Co-authored-by: feli <felix.li@amd.com>
Co-authored-by: illsilin <Illia.Silin@amd.com>
Co-authored-by: root <root@hjbog-srdc-51.amd.com>
Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
 2025-04-23 10:35:34 +08:00
Gino Lu
504f563f78 [CK-Tile] warp-gemm support for using V_MFMA_F32_16x16x32_BF16 (#2073) 
* draft v_mfma_f32_16x16x32_bf16

* fix error config and add debug code.

* Solve the CShuffle Problem

* draft v_mfma_f32_16x16x32_bf16

* fix error config and add debug code.

* Solve the CShuffle Problem

* fix error while testing new command

* Finished the feature of new mfma 16*16*32

* Addressed the comment

---------

Co-authored-by: ThomasNing <thomas.ning@amd.com>
 2025-04-22 15:52:36 -07:00
lalala-sh
bcf5bb41be enable do top k weights in moe stage1 gemm (#2094) 
* add switch for mul topk weights

* fix bf16/f16 bugs

* complete
 2025-04-18 10:45:49 +08:00
Andriy Roshchenko
da54464cce MX GEMM - Add MX BF8 example (#2071) 
* Add MX GEMM example for MX BF8

* Verified MX FP8 with 16x16x128 scale builtin

* Verify MX BF8 GEMM with BF16 output
 2025-04-16 15:25:02 -06:00
BingYuan.Zhou
eaf1f0bf3b [flatmm] implement basic fp16 flatmm (#2089) 
* [flatmm] implement basic fp16 flatmm

* fix CI build fail

---------

Co-authored-by: root <root@hjbog-srdc-50.amd.com>
Co-authored-by: solin <bingzhou@amd.com>
 2025-04-16 16:51:17 +08:00
felix
c5975529bb add preshuffle gemm fp16 (#2036) 
* add preshuffle gemm fp16

* clang format and test ok

* Update gemm_multiply_multiply_xdl_fp16_bpreshuffle.cpp

remove useless comments in example

* Update gemm_multiply_multiply_xdl_fp16_bpreshuffle.cpp

remove 2

---------

Co-authored-by: coderfeli <coderfeli@163.com>
 2025-04-16 10:53:21 +08:00
joyeamd
94d47b1680 fmha hdim256 vectorize improve (#2086) 
For hdim 256, will not have vectorized buffer load when seqlen % 256 != 0 and hdim % 256 = 0; this commit tries to solve this condition.
 2025-04-16 09:21:04 +08:00
Andriy Roshchenko
7106976a72 MX GEMM - New GEMM pipeline for MX data types (#2059) 
* Allow selection of mfma_scale instructions

* Read B tensor from LDS to VGPR in chunks of 16 in MFMA order

* Add constexpr and synchronize return type for `get_exponent_value`

* Pass scales by reference and add comments to `mfma_scale_f32_32x32x64`

* Add support for microscaling instructions in `XdlopsGemm`

* Fix `mfma_scale_f32_16x16x128f8f6f4` wrapper

* Remove software implementation of MX GEMM

* Make interface of `intrin_mfma_scale_f32_16x16x128f8f6f4<16, 16>` consistent with the other scale instruction

* Update README

* Updated CHANGELOG

* Remove unused static methods
 2025-04-15 17:17:07 -06:00
Mingtao Gu
56378f810f CK pk_i4_t test failures fix (SWDEV-518629) (#2075) 
* fix pk_i4_v3 tests failures in Unbuntu env.

* fix pk_i4_t tests failure on Unbuntu issues.

* some fixed.

---------

Co-authored-by: mtgu0705 <mtgu@amd.com>
 2025-04-14 16:58:57 +08:00
jakpiase
6c61f4d237 [CK_TILE] Add 2:4 structured sparsity support for fp16 gemm (#1957) 
* add structured sparsity fp16 support for gemm

* added reviewer suggestions

* update changelog

* update changelog

* add reviewers suggestions

* Minor fix

* clang fix

* fix doxygen
 2025-04-11 12:18:26 +02:00
slippedJim
5f885d2b7a add fmha fwd splitkv receipt for aiter c++ api (#2068) 
* add s_randval for c++ api

* Fix bug of bias in splitkv

---------

Co-authored-by: rocking <ChunYu.Lai@amd.com>
 2025-04-10 23:21:13 +08:00
Illia Silin
3e6d21adeb enable gfx115x support (#2065) 2025-04-09 10:06:42 -07:00
slippedJim
5a22b61de5 Add new receipt (#2055) 2025-04-07 14:18:01 +08:00
Thomas Ning
50d1f8ff90 Add the MI355 support for CK TILE GEMM (#2046) 
* Get the root cause of the ck tile gemm failing on mi355

* Fix the ck tile gemm on MI355

* delete the debug info
 2025-04-03 11:48:54 -07:00
aledudek
9329432f6c Post-merge changes for fully async args copy in ck grouped gemm (#1991) 
* Post-merge changes for fully async args copy in ck grouped gemm

* Post-merge documentation and naming changes

* Build fix and updated changelog

* Revised comments
 2025-04-03 13:35:43 +02:00
Muhammed Emin Ozturk
dd4c12b155 f8/bf16 GEMM Stream-K (#1879) 2025-03-31 20:30:17 -06:00
rocking
8a20b62e91 Reduce redundant space in bias tensor (#2024) 
Co-authored-by: Po Yen Chen <PoYen.Chen@amd.com>
 2025-03-28 21:58:06 +08:00
felix
a82f338fb9 hotfix fix sorting int64 (#2025) 
* fix sorting int64

* clang format

* fix example issue

* update WA issue #

---------

Co-authored-by: coderfeli <coderfeli@163.com>
Co-authored-by: carlushuang <carlus.huang@amd.com>
 2025-03-28 11:31:52 +08:00
felix
36d50de50e ckmoe: change cmake; use smaller shape for i4 (#2027) 
* change cmake; use smaller shape for i4

* fix pki4 run

* fix typo

* fix runtime arch logic for moe_gemm2 example

---------

Co-authored-by: coderfeli <coderfeli@163.com>
Co-authored-by: illsilin <Illia.Silin@amd.com>
 2025-03-27 09:04:31 -07:00
Illia Silin
23a949706c Disable all pk_i4 tests for all targets except gfx942/950. (#2022) 
* only build gemm_fp8_pk_i4 examples for gfx942/950

* fix cmake logic

* moved the architecture check to IsSupported function

* Revert "moved the architecture check to IsSupported function"

This reverts commit 056d2a08b3.

* disable all pk_i4 tests for targets other than gfx942/950

* fix cmake logic
 2025-03-26 15:15:57 -07:00
Illia Silin
99b2bbc1d6 Make sure gemm_fp8_pk_i4 examples only build and run on gfx942/950. (#2010) 
* only build gemm_fp8_pk_i4 examples for gfx942/950

* fix cmake logic

* moved the architecture check to IsSupported function

* Revert "moved the architecture check to IsSupported function"

This reverts commit 056d2a08b3.
 2025-03-25 14:43:38 -07:00
Andriy Roshchenko
72d888821c MX GEMM examples with FP8, FP16, and E8M0 scales (#2016) 
* Add `scalar_type` specification for E8M0 exponent

* Specialize `nnvb_data_t_selector` for E8M0 exponent

* Remove partial specializations for `scalar_type` of `non_native_vector_base` template

* Reword command line helper string

* Create MX GEMM examples for different scales
 2025-03-25 15:33:03 -06:00
ruanjm
d49abdaa87 [CK_TILE] Improve RMS/Layer Normalization 2 Pass Pipeline Performance (#1861) 
* 50ms -> 28ms

* Fix bug in non fuse_add_store cases

* Fine tuned setting for 2 pass pipeline

* adjust workload

* remove unnecessary change

* add layernorm

* Adding output quant and unquant results at the same time.

* fix test

* fix format

* tune for cases 128x640 and 128x1024

* bug ifx
 2025-03-25 20:09:45 +08:00
Andriy Roshchenko
6660dc6b8e Introduce MX GEMM for FP8 data type (#2000) 2025-03-24 15:41:07 -06:00