ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-11 17:00:18 +00:00
Code Issues Packages Projects Releases Wiki Activity
1,192 Commits 739 Branches 38 Tags
8e97e85ac6cdb71903d3ac46a7e82f8350eb0ce5
Commit Graph

1192 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
dependabot[bot]
8e97e85ac6 Bump rocm-docs-core from 0.35.1 to 0.36.0 in /docs/sphinx (#1194) 
Bumps [rocm-docs-core](https://github.com/RadeonOpenCompute/rocm-docs-core) from 0.35.1 to 0.36.0.
- [Release notes](https://github.com/RadeonOpenCompute/rocm-docs-core/releases)
- [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md)
- [Commits](https://github.com/RadeonOpenCompute/rocm-docs-core/compare/v0.35.1...v0.36.0)

---
updated-dependencies:
- dependency-name: rocm-docs-core
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2024-03-12 08:21:14 -07:00
Bartłomiej Kocot
42fc8eddd2 Fix warnings during wrapper docs generation (#1192) 
* Fix warnings during wrapper docs generation

* Fixes
 2024-03-08 17:13:03 -08:00
zjing14
1837040a9c Navi3 rel (#1176) 
* wmma_op + unit test

* add arch limitation to wmma test

* change arch limitation

* Refactor + Add all type unit test(int4 compile failed)

* Add f32_16x16x16_bf16 unit test

* tempsave

* tempsave

* tempsave

* runtime bug, cannot find symbol

* workaround for incorrect HIP warpSize return value

* debugging

* tempsave

* Correctness OK, waiting for optimization

* Tidy up + format

* temp save

* temp save, reproduce the v_bfi_b32 issue

* add inline asm for wmmaop test

* tidy up

* clean some debug purpose code

* discard some codes

* clang format

* clang format

* compiler issue fixed + increase tile size

* navi3x_multipleD+example

* temp save

* workable

* batchedgemm[OK], groupconv[debug]

* groupconv: Sanity check[OK], Performance[Bad]

* navi3x_groupconv_need_optimization

* create necessary files

* save progress

* Add Inter-Row thread transfer

* save progress

* save debugging progress

* sanity check pass

* fix a host tensor bug and clean up flash-attn code

* format

* cancel unnecessary change

* cancel unnecessary change

* cancel unnecessary change

* temp save, add asm backend flag to amd_wmma

* Mat-A LDS Bypass sanity pass

* temp save

* gemm sanity fix

* Porting new blockwise gemm to flash attention

* Example branch provide to compiler team

* tempsave

* Fix a bug

* batched gemm ported

* conv A-skip lds ported

* Skip B-Lds real gemm

* Skip B Lds Gemm + MulD

* batched gemm, conv, skip b lds

* format

* Attn, skip b lds

* Change GridwiseOp nam

* fix a typo caused bug

* Skip A_Lds sanity pass, Skip B_Lds scratch occured

* Bug found, intra-row permute off caused

* bug found

* a fix

* disable buffer load due to incorrect 3rd dword

* update fmha config, no scratch generated

* update 3rd dword

* fmha config update

* FMHA, add support to gfx1101/gfx1102

* Merge origin dev (#2)

* [Navi3x] Fix Gridwise_multiple_d operation (#649)

* Add CMake Option "USE_OPT_NAVI3X"

* fix bug

* standardize docs (#655)

* Separate bibtex requirement from rocm-docs-core (#656)

* separate bibtex requirement from rocm-docs-core

* point requirements to source rocm-docs-core repo

* Add CMake Option "USE_OPT_NAVI3X" (#647)

* Add CMake Option "USE_OPT_NAVI3X"

* remove navi3x opt compile option from cmake script

* Conv + quantization + tanh  (#645)

* Rename file. Prepare to support another activation

* Add comment for quantization

* Extract out_elementop

* Add tanh example

* Add conv + bias + tanh quantization instance

* Add missing parameter

* Refine cmake

* Add external api and client example

* Extract variable in example

* Fix the comment

---------

Co-authored-by: zjing14 <zhangjing14@gmail.com>

* Add a denorm test fix (#603)

* Add type_convert implementations for bf16

* Add the fix for conv_fwd

* Add the fix for conv_bwd_data

* Add the fix for conv_bwd_weight

* Format

* Format

* Another format

* Add a macro to use workaround on MI200 only

* Format

---------

Co-authored-by: Rosty Geyyer <rosty.geyyer@amd.com>
Co-authored-by: zjing14 <zhangjing14@gmail.com>

* simplify karg in device/grid of split-k op (#644)

* simplify karg in device/grid split-k op

* fix mk_kn_mn instances

* add more instances

* use name from tensor layout

* fix 3rd dword of buffer source descriptor (#659)

* add fp64 instances (#658)

Co-authored-by: root <root@ctr-ubbsmc15.amd.com>

* Issue #666: Revert "simplify karg in device/grid of split-k op (#644)" (#665)

This reverts commit bb5530af91.

* Groupnorm + swish external api (#668)

* Rename to proper naming

* Add example of groupnorm + swish

* Extract duplicate code in example

* Add groupnorm + swish instances

* Ractor instance generation, split into multiple cpp file

* Add external api and client example

* Refine profiler message

* Use ck math version of exp

* Refine problem size in example

* Add host version of exp

* add a marco to turn on/off denorm fix (off by default) (#673)

* add a marco to turn off denorm fix by default

* expose the marco

---------

Co-authored-by: root <root@ctr-ubbsmc15.amd.com>

* fixed quant example (#672)

Co-authored-by: root <root@ctr-ubbsmc15.amd.com>

* Add dependabot config and pin rocm-docs-core (#663)

* [gtest] suppress unsafe buffer warn (#670)

ref: https://github.com/ROCmSoftwarePlatform/MIOpen/pull/1912

* Add memory index guard in wmma device ops (#667)

* Add more macros to turn on/off denorm fix (#678)

Co-authored-by: Rosty Geyyer <rosty.geyyer@amd.com>

* Fix a typo (#676)

* Add (#677)

* Allow using ROCm release candidate compilers. (#679)

* enable use of rocm5.5 release candidate 4

* upgrade to ROCM5.5 RC5

* try fix the PUB_KEY error, remove the cmake-data package

* upgrade to latest cmake version

* use private dockerhub repo for rocm5.5 rc5

* add missing bracket

* add vector load check

* solve conflicts

---------

Co-authored-by: Sam Wu <sjwu@ualberta.ca>
Co-authored-by: Sam Wu <sam.wu2@amd.com>
Co-authored-by: rocking5566 <ChunYu.Lai@amd.com>
Co-authored-by: zjing14 <zhangjing14@gmail.com>
Co-authored-by: Rostyslav Geyyer <46627076+geyyer@users.noreply.github.com>
Co-authored-by: Rosty Geyyer <rosty.geyyer@amd.com>
Co-authored-by: carlushuang <carlus.huang@amd.com>
Co-authored-by: root <root@ctr-ubbsmc15.amd.com>
Co-authored-by: Jun Liu <Liu.Jun@amd.com>
Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>

* Disable SkipLDS & Align AIT api (#3)

* fix layernorm, reduction Ops (#4)

* [Navi3x] Fix Gridwise_multiple_d operation (#649)

* Add CMake Option "USE_OPT_NAVI3X"

* fix bug

* standardize docs (#655)

* Separate bibtex requirement from rocm-docs-core (#656)

* separate bibtex requirement from rocm-docs-core

* point requirements to source rocm-docs-core repo

* Add CMake Option "USE_OPT_NAVI3X" (#647)

* Add CMake Option "USE_OPT_NAVI3X"

* remove navi3x opt compile option from cmake script

* Conv + quantization + tanh  (#645)

* Rename file. Prepare to support another activation

* Add comment for quantization

* Extract out_elementop

* Add tanh example

* Add conv + bias + tanh quantization instance

* Add missing parameter

* Refine cmake

* Add external api and client example

* Extract variable in example

* Fix the comment

---------

Co-authored-by: zjing14 <zhangjing14@gmail.com>

* Add a denorm test fix (#603)

* Add type_convert implementations for bf16

* Add the fix for conv_fwd

* Add the fix for conv_bwd_data

* Add the fix for conv_bwd_weight

* Format

* Format

* Another format

* Add a macro to use workaround on MI200 only

* Format

---------

Co-authored-by: Rosty Geyyer <rosty.geyyer@amd.com>
Co-authored-by: zjing14 <zhangjing14@gmail.com>

* simplify karg in device/grid of split-k op (#644)

* simplify karg in device/grid split-k op

* fix mk_kn_mn instances

* add more instances

* use name from tensor layout

* fix 3rd dword of buffer source descriptor (#659)

* add fp64 instances (#658)

Co-authored-by: root <root@ctr-ubbsmc15.amd.com>

* Issue #666: Revert "simplify karg in device/grid of split-k op (#644)" (#665)

This reverts commit bb5530af91.

* Groupnorm + swish external api (#668)

* Rename to proper naming

* Add example of groupnorm + swish

* Extract duplicate code in example

* Add groupnorm + swish instances

* Ractor instance generation, split into multiple cpp file

* Add external api and client example

* Refine profiler message

* Use ck math version of exp

* Refine problem size in example

* Add host version of exp

* add a marco to turn on/off denorm fix (off by default) (#673)

* add a marco to turn off denorm fix by default

* expose the marco

---------

Co-authored-by: root <root@ctr-ubbsmc15.amd.com>

* fixed quant example (#672)

Co-authored-by: root <root@ctr-ubbsmc15.amd.com>

* Add dependabot config and pin rocm-docs-core (#663)

* [gtest] suppress unsafe buffer warn (#670)

ref: https://github.com/ROCmSoftwarePlatform/MIOpen/pull/1912

* Add memory index guard in wmma device ops (#667)

* Add more macros to turn on/off denorm fix (#678)

Co-authored-by: Rosty Geyyer <rosty.geyyer@amd.com>

* Fix a typo (#676)

* Add (#677)

* Allow using ROCm release candidate compilers. (#679)

* enable use of rocm5.5 release candidate 4

* upgrade to ROCM5.5 RC5

* try fix the PUB_KEY error, remove the cmake-data package

* upgrade to latest cmake version

* use private dockerhub repo for rocm5.5 rc5

* add missing bracket

* Disable SkipLDS & Align AIT api

* Update dependabot config (#682)

Co-authored-by: samjwu <samjwu@users.noreply.github.com>

* update attn api

* solve type_convert bug + enable

---------

Co-authored-by: Sam Wu <sjwu@ualberta.ca>
Co-authored-by: Sam Wu <sam.wu2@amd.com>
Co-authored-by: rocking5566 <ChunYu.Lai@amd.com>
Co-authored-by: zjing14 <zhangjing14@gmail.com>
Co-authored-by: Rostyslav Geyyer <46627076+geyyer@users.noreply.github.com>
Co-authored-by: Rosty Geyyer <rosty.geyyer@amd.com>
Co-authored-by: carlushuang <carlus.huang@amd.com>
Co-authored-by: root <root@ctr-ubbsmc15.amd.com>
Co-authored-by: Jun Liu <Liu.Jun@amd.com>
Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
Co-authored-by: samjwu <samjwu@users.noreply.github.com>
Co-authored-by: haocwang <Haocong.WANG@amd.com>

* fix typo

* Fix attention with causal mask

* multiple fix, try ait compile

* Add A/B not use LDS pipeline

* Clang format, Add gfx1101, gfx1102 support of FMHA example

* cancel change of format script

* 1. Enable 2-stage global Prefetch ( May cause VGPR spilling)
2. Enable FP16 accumulator blockwise_gemm

* clang-format

* 1. change blockwise gemm loopover direction from kmn to mnk ( ~1% improvement)
2. change kernel timing mode to 50 warmup + 50 timed repeat

* Update low level abstration of blockwise gemm wmma

* (2/5) bilinear gemm pass, perf bug: skip a lds has lower performance than skip b lds

* (3/5) batched gemm pass, perf bug: skip a lds has lower performance than skip b lds

* (4/5) grouped conv pass

* (5/5) attention pass, todo: debug lds perf bug

* AIT Attention API refactor (#8)

* sanity pass

* sanity pass 2

* confirm significant performance regression.

* turn on all instances

* turn off instance format

* Fix bug & tunning & format

* DML meta, self_attn+cross_attn

* sanity pass

* remove useless flag

* update tile and problem size used in AIT attention

* bug fix in grouped conv supporting check

* deprecate inline asm wmma

* Bug fix: double lds skip

* clang-format

* Fix errors in
1. example, fmha
2. gridwise pipeline
3. deviceop, fmha, change some containers from vector to array

* part2 of previous commit

* clang format

* API fix of gridwisegemmpipeline

* separate array base and vector base attention tensor transformation

* fix gemm

* clang format

* add gemm fp16 instances

* Temp save

* fpAintB kernel compile pass

* Sanity pass.

* Temp save

* debug code enabled

* Fp16AInt8B_GEMM sanity

* MQA implementation

* GQA-4 example

* tempsave

* Compile pass

* New implementation of fp16Aint8B Gemm, Acheieve similar math throughput with native fp16 Gemm

* format

* Todo: fix gemm_bilinear_wmma instances compilation bug

* Solve a bug when K1=16

* remove unnecessary changes

* Remove tensor layout limitation to LDS usage in tesnor contraction

* update self-attention and cross-attention

* fix a typo of name

* Add arch limiter for fp8 gemm

* enable fp8 gemm_xdl for all gfx9 targets

* temporarily disable gemm_xdl_fp16_fp8 on MI100/200

* fix the cmake logic for gemm_xdl_fp16_fp8

* re-enable the gemm_xdl_fp16_fp8 on MI100/200

---------

Co-authored-by: aska-0096 <haocwang@amd.com>
Co-authored-by: Sam Wu <sjwu@ualberta.ca>
Co-authored-by: Sam Wu <sam.wu2@amd.com>
Co-authored-by: rocking5566 <ChunYu.Lai@amd.com>
Co-authored-by: Rostyslav Geyyer <46627076+geyyer@users.noreply.github.com>
Co-authored-by: Rosty Geyyer <rosty.geyyer@amd.com>
Co-authored-by: carlushuang <carlus.huang@amd.com>
Co-authored-by: root <root@ctr-ubbsmc15.amd.com>
Co-authored-by: Jun Liu <Liu.Jun@amd.com>
Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
Co-authored-by: samjwu <samjwu@users.noreply.github.com>
Co-authored-by: haocwang <Haocong.WANG@amd.com>
Co-authored-by: illsilin <Illia.Silin@amd.com>
 2024-03-08 17:11:51 -08:00
Rostyslav Geyyer
363feb482d Refactor tolerances for correctness check in gemm op (#1188) 
* Refactor tolerances for correctness check

* Update tolerances

* Update host-side gemm

* Update reference gemm call
 2024-03-08 12:05:05 -08:00
Lisa
0e28de9766 Update link (#1186) 2024-03-07 10:09:17 -08:00
yhuiYH
adb3615d1a Update CODEOWNERS to use documentation group (#1190) 
Also had to remove a name
 2024-03-07 10:08:37 -08:00
dependabot[bot]
1ddc8a841a Bump rocm-docs-core from 0.35.0 to 0.35.1 in /docs/sphinx (#1187) 
Bumps [rocm-docs-core](https://github.com/RadeonOpenCompute/rocm-docs-core) from 0.35.0 to 0.35.1.
- [Release notes](https://github.com/RadeonOpenCompute/rocm-docs-core/releases)
- [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md)
- [Commits](https://github.com/RadeonOpenCompute/rocm-docs-core/compare/v0.35.0...v0.35.1)

---
updated-dependencies:
- dependency-name: rocm-docs-core
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2024-03-05 21:55:01 -08:00
Paul Fultz II
8eff4d62b6 Add host lib (#1134) 
* Format

* Format

* Format

* Remove const

* Use the right template

* Format

* Format

* add row/col instances

* Add missing file

* fixed

* Format

* Updates

* Format

* fixed rrr layout

* Format

* Update test and embed modules

* Restore older version

* Update year

* Set -fPIC

* Format

* Use double for isnan

* rename host folder to codegen + minor fix

* add codegen CI test

* add option to build components without building CK

* fix the groovy syntax

* fix typo

* use the correct function for the codegen stage

---------

Co-authored-by: Jing Zhang <jizha@amd.com>
Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
Co-authored-by: illsilin <Illia.Silin@amd.com>
 2024-03-05 17:08:43 -08:00
Illia Silin
cf86621170 [CI] Add CI build and test stage on MI300. (#1185) 2024-03-05 10:42:16 -08:00
Rostyslav Geyyer
9ce18b045d Fix example_gemm_xdl_fp8 (#1183) 2024-03-01 16:42:15 -08:00
Rostyslav Geyyer
acfb339238 Update clipping for fp8/bf8 conversion (#1182) 
* Update clipping for fp8 conversion

* Add clipping for bf8 conversion

* Format
 2024-03-01 10:30:38 -08:00
amoskvic
a776978cbe Style improvement: improving type alias usage consistency in gemm-related client examples. Also copyright year update for all client examples. (#1180) 
Co-authored-by: Arseny Moskvichev <amoskvic@amd.com>
 2024-02-28 16:39:03 -08:00
Illia Silin
d0c7b45150 Clip fp8 to +/-240 on all targets. (#1172) 
* clip fp8 to +/-240 on all targets

* if inputs to fp8 conversion are +/-inf, they remain unaltered

* increase tolerance for test_elementwise_layernorm to prevent false errors

* change the input values for gemm examples to floats

* reduce gemm example float input values to prevent errors

* increase the tolerance for gemm examples
 2024-02-27 14:31:05 -06:00
Bartłomiej Kocot
d909599729 Remove unnecessary comments (#1177) 2024-02-26 07:56:06 -06:00
dependabot[bot]
2eb74a9c0c Bump rocm-docs-core from 0.34.2 to 0.35.0 in /docs/sphinx (#1175) 
Bumps [rocm-docs-core](https://github.com/RadeonOpenCompute/rocm-docs-core) from 0.34.2 to 0.35.0.
- [Release notes](https://github.com/RadeonOpenCompute/rocm-docs-core/releases)
- [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md)
- [Commits](https://github.com/RadeonOpenCompute/rocm-docs-core/compare/v0.34.2...v0.35.0)

---
updated-dependencies:
- dependency-name: rocm-docs-core
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2024-02-22 21:39:16 -08:00
jakpiase
32d4be3d09 Add support for mixed precision bf16&int8 grouped gemm (#1166) 
* add support for mixed precision bf16&int8 grouped gemm

* fix gfx versions and add bf16 kbatch condition

* added reviewers comments
 2024-02-21 10:35:35 +01:00
Bartłomiej Kocot
66736edb95 Extend permute scale support up to 6D (#1168) 
* Extend permute scale support up to 6D

* Fixes

* Fixes

* Update profiler/README.md

Co-authored-by: Lisa <lisajdelaney@gmail.com>

* Update profiler/README.md

Co-authored-by: Lisa <lisajdelaney@gmail.com>

* Update profiler/README.md

Co-authored-by: Lisa <lisajdelaney@gmail.com>

* Update profiler/README.md

Co-authored-by: Lisa <lisajdelaney@gmail.com>

* Update profiler/README.md

Co-authored-by: Lisa <lisajdelaney@gmail.com>

* Update profiler/README.md

Co-authored-by: Lisa <lisajdelaney@gmail.com>

* Update profiler/README.md

Co-authored-by: Lisa <lisajdelaney@gmail.com>

---------

Co-authored-by: Lisa <lisajdelaney@gmail.com>
 2024-02-20 09:56:54 -08:00
dependabot[bot]
abac8b07dd Bump rocm-docs-core from 0.34.0 to 0.34.2 in /docs/sphinx (#1170) 
Bumps [rocm-docs-core](https://github.com/RadeonOpenCompute/rocm-docs-core) from 0.34.0 to 0.34.2.
- [Release notes](https://github.com/RadeonOpenCompute/rocm-docs-core/releases)
- [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md)
- [Commits](https://github.com/RadeonOpenCompute/rocm-docs-core/compare/v0.34.0...v0.34.2)

---
updated-dependencies:
- dependency-name: rocm-docs-core
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2024-02-16 07:48:52 -08:00
Illia Silin
b9ab9f4b4f upgrade the ccache version and update links (#1169) 2024-02-15 15:46:01 -08:00
Bartłomiej Kocot
1e73adbc28 Add optimized blockwise gemm using ck wrapper (#1157) 
* Add optimized blockwise gemm using ck wrapper

* Add basic gemm example

* Update docs

* Add tutorial for gemm using ck wrapper

* Add perf note

* edits

* Fix cmake

* Fixes

---------

Co-authored-by: Lisa Delaney <lisa.delaney@amd.com>
 2024-02-13 17:04:36 +01:00
Bartłomiej Kocot
bf98b47697 Add bilinear conv fwd and bwd data instances (#1164) 2024-02-13 11:49:05 +01:00
Illia Silin
a78be3f69e add docker credentials before pushing image (#1165) 2024-02-12 16:11:32 -08:00
zjing14
602c4cc0d9 Optimizing fp8_fp16 mixedprec gemm (#1150) 
* add delayed cvt

* extend fp16 gemm_splitk instances for fp8_fp16 gemm

* add f8 example

* add 128 kperblk instances for fp8

* add kpb128 instance

* added more instances into kpb128

* clean code

* clean code

* fix

* fix

* fixed

* Update example/35_splitK_gemm/splitK_gemm_xdl_fp16_fp8.cpp

Co-authored-by: Bartłomiej Kocot <barkocot@amd.com>

* Update include/ck/tensor_operation/gpu/thread/threadwise_tensor_slice_transfer.hpp

Co-authored-by: Bartłomiej Kocot <barkocot@amd.com>

* Update library/src/tensor_operation_instance/gpu/gemm_splitk/device_gemm_xdl_splitk_f16_fp8_f16_mk_nk_mn_kpb128_instance.cpp

Co-authored-by: Bartłomiej Kocot <barkocot@amd.com>

---------

Co-authored-by: Jing Zhang <jizha@amd.com>
Co-authored-by: Bartłomiej Kocot <barkocot@amd.com>
 2024-02-12 09:45:42 -08:00
zjing14
94fbaac002 add generic instances for DeviceGemm_Xdl_CShuffle (#1161) 
* add generic instances

* clean code
 2024-02-09 10:20:53 -06:00
dependabot[bot]
4581b5d504 Bump rocm-docs-core from 0.33.2 to 0.34.0 in /docs/sphinx (#1163) 
Bumps [rocm-docs-core](https://github.com/RadeonOpenCompute/rocm-docs-core) from 0.33.2 to 0.34.0.
- [Release notes](https://github.com/RadeonOpenCompute/rocm-docs-core/releases)
- [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md)
- [Commits](https://github.com/RadeonOpenCompute/rocm-docs-core/compare/v0.33.2...v0.34.0)

---
updated-dependencies:
- dependency-name: rocm-docs-core
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2024-02-08 21:35:39 -08:00
Lakhinder Walia
1f306024d0 fast_gelu: minor code reorg to enhance ref & gpu performance (#1162) 2024-02-07 19:24:51 -08:00
Illia Silin
1b0fbaebbb Split-up instances to improve build times. (#1159) 
* split up splitk-gemm instances

* clean up some unused variables

* split the mk_kn_mn interwave splitk-gemm instances

* split up f16_f16_f16 mk_nk_mn splitk gemm instances

* fix clang format

* fix function names

* fix typo

* split up the 2 largest fp16*fp8 splitk gemm instances

* get rid of unused variables

* split up the largest splitk-gemm fp8*fp16 instance file

* split up the instances for xdl fp8 gemms

* split the headers for f16 and i8 for wmmma convolution instances
 2024-02-07 12:47:12 -08:00
jakpiase
ba86eadce5 Add support for mixed-precision f16bf16_int8 gemm (#1127) 2024-02-07 15:54:13 +01:00
dependabot[bot]
753cef783f Bump rocm-docs-core from 0.33.1 to 0.33.2 in /docs/sphinx (#1160) 
Bumps [rocm-docs-core](https://github.com/RadeonOpenCompute/rocm-docs-core) from 0.33.1 to 0.33.2.
- [Release notes](https://github.com/RadeonOpenCompute/rocm-docs-core/releases)
- [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md)
- [Commits](https://github.com/RadeonOpenCompute/rocm-docs-core/compare/v0.33.1...v0.33.2)

---
updated-dependencies:
- dependency-name: rocm-docs-core
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2024-02-06 21:24:32 -08:00
Bartlomiej Wroblewski
6951858221 Implement direct loads split-K GEMM kernel (#1137) 
* WIP: Implement direct loads split-K GEMM kernel

* Clean the review

---------

Co-authored-by: Adam Osewski <19374865+aosewski@users.noreply.github.com>
Co-authored-by: Bartłomiej Kocot <barkocot@amd.com>
 2024-02-07 01:08:34 +01:00
dependabot[bot]
6299621107 Bump rocm-docs-core from 0.33.0 to 0.33.1 in /docs/sphinx (#1158) 
Bumps [rocm-docs-core](https://github.com/RadeonOpenCompute/rocm-docs-core) from 0.33.0 to 0.33.1.
- [Release notes](https://github.com/RadeonOpenCompute/rocm-docs-core/releases)
- [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md)
- [Commits](https://github.com/RadeonOpenCompute/rocm-docs-core/compare/v0.33.0...v0.33.1)

---
updated-dependencies:
- dependency-name: rocm-docs-core
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2024-02-06 09:24:34 -08:00
Illia Silin
f0dd1da088 Delete any dangling images after building a new one. (#1155) 
* delete dangling docker images

* fix groovy syntax

* fix groovy syntax again

* try a different way to delete dangling images
 2024-02-05 10:34:47 -08:00
Illia Silin
180f16f9ac Add support for more Navi2x and Navi3x models. (#1152) 
* add support for navi2x and navi3x models

* fix syntax

* use common macro for different mi300 architectures
 2024-02-02 11:35:26 -08:00
Bartłomiej Kocot
171ca260b5 Extend gemm traits number for ck wrapper (#1153) 2024-02-02 11:25:54 -08:00
Illia Silin
112b691bb7 add new performance tests for mixed fp16/fp8 gemms (#1151) 2024-01-31 13:27:17 -08:00
Bartłomiej Kocot
f3b6c23ac5 Add blockwise gemm to ck wrapper (#1139) 
* Add blockwise gemm to ck wrapper

* Add blockwise gemm traits

* Disable test_gemm for non xdl devices

* Fixes

* Add c layout descritpions
 2024-01-31 21:24:40 +01:00
Illia Silin
6651a124cc update the name of the compiler staging branch (#1148) 2024-01-30 13:55:31 -08:00
Illia Silin
e7495e6bb7 turn off performance tests in CI by default until the infrastructure is fixed (#1147) 2024-01-30 13:14:58 -08:00
dependabot[bot]
84832fc42d Bump rocm-docs-core from 0.31.0 to 0.33.0 in /docs/sphinx (#1144) 
Bumps [rocm-docs-core](https://github.com/RadeonOpenCompute/rocm-docs-core) from 0.31.0 to 0.33.0.
- [Release notes](https://github.com/RadeonOpenCompute/rocm-docs-core/releases)
- [Changelog](https://github.com/ROCm/rocm-docs-core/blob/develop/CHANGELOG.md)
- [Commits](https://github.com/RadeonOpenCompute/rocm-docs-core/compare/v0.31.0...v0.33.0)

---
updated-dependencies:
- dependency-name: rocm-docs-core
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2024-01-29 09:02:52 -08:00
Illia Silin
4a8297c28a fix CK path for hipTensor (#1143) 2024-01-25 17:05:43 -08:00
rocking
28f68a5a99 layernorm & groupnorm bwd gamma beta (#1133) 
* Add layernorm bwd gamma beta external api

* Add groupnorm external api

* Add layernorm bwd gamma beta profiler

* Add groupnorm bwd gamma beta ckProfiler

* Add layernorm & groupnorm bwd gamma beta test

* Fix groupnorm bwd gamma beta profiler bug

* Layernorm bwd weight client example

* Groupnorm bwd weight client example

* clang format

* Remove useless header

* Let inv_std be positive

* Rename to num_bytes and move this calculation outside the loop
 2024-01-25 19:53:15 +08:00
Illia Silin
180e572076 Fixing most of the cppcheck errors. (#1142) 
* fix cppcheck errors, first pass

* fix format

* fix returned value in examples

* add macro definitions for cppcheck

* fix the profile_gemm logic

* update the gemm profiler logic

* add more difinitions to cppcheck, fix couple more errors

* replace runtime error with message in device function

* fix a couple of int4 issues

* no return for fill function

* fix errors in data_types.hpp

* fix format

* fix few remaining errors

* fix errors in data_types.hpp

* fix last couple of errors in datat_types.hpp
 2024-01-24 13:47:48 -08:00
Bartłomiej Kocot
6169fbbdb3 Fix possible linting errors in changelog (#1141) 
* Fix possible linting errors in changelog

* Update CHANGELOG.md

* Update CHANGELOG.md

* Update CHANGELOG.md
 2024-01-24 17:19:02 +01:00
zjing14
1be4706366 fixed return (#1138) 2024-01-22 08:42:26 -08:00
Haocong WANG
bb63b9732c [GEMM] Optimization for MI200/300. (#1135) 
* Optimize GEMM on MI200/300:
1. Add new blockwise gemm pipeline
2. Add irregular splitk intances

* clang format + typo fix

* Fix a bug
 2024-01-19 07:02:22 -06:00
Bartłomiej Kocot
7e4eb4b800 Add optimized copy to ck wrapper (#1126) 
* Add optimized copy to ck wrapper

* Example optimizations

* Fixes

* Move img2col test to client example

* Refactor example

* Fix docs

* Fixes

* Fix

* Fixes

* Fixes

* Fixes

* Fixes

* Fixes

---------

Co-authored-by: zjing14 <zhangjing14@gmail.com>
 2024-01-19 11:29:00 +01:00
Illia Silin
38882d8ab5 add Adam to code owners (#1136) 2024-01-18 19:20:40 -06:00
randyh62
402a930a4a Randyh docfix (#1130) 
* Update LICENSE

update to 2024

* Update index.rst

change license.md to license.html

* fix syntax

---------

Co-authored-by: illsilin <Illia.Silin@amd.com>
 2024-01-16 09:00:37 -08:00
Illia Silin
c1b5b58192 add code owners (#1132) 2024-01-16 07:55:18 -08:00
Illia Silin
e6d099c830 Add cppcheck to CK CI. (#1125) 
* add cppcheck to the CK CI

* fix the path to CK source for cppcheck

* fix the path to CK source for cppcheck one more time

* fix the path to CK source for cppcheck third time

* change the path to ck_cppcheck.log

* install latest cppcheck from source

* fix bug in ck.hpp and use 20 threads for cppcheck

* create a switch to turn cppckeck on and off in CI
 2024-01-15 09:11:45 -08:00