Andriy Roshchenko
4a8a1befd5
Adding more instances of grouped convolution 3d forward for FP8 with ConvScale+Bias element-wise operation. ( #1412 )
...
* Add CMakePresets configurations.
* Add binary elementwise ConvScaleAdd and an example.
* Numerical verification of results.
Observed significant irregularities in F8 to F32 type conversions:
```log
ConvScaleAdd: float=145.000000 f8_t=160.000000 e=144.000000
ConvScaleAdd: float=97.000000 f8_t=96.000000 e=104.000000
ConvScaleAdd: float=65.000000 f8_t=64.000000 e=72.000000
```
* Implemented ConvScaleAdd + Example.
* Add ConvScale+Bias Instances
* Add Client Example for ConvScale+Bias
* Fix number of bytes in an example..
* Cleanup.
2024-07-24 15:49:55 -05:00
Haocong WANG
8c90f25be3
[GEMM] F8 GEMM, performance optimized. ( #1384 )
...
* add ab_scale init support
* enabled interwave
* add scale type; update isSupport
* adjust example
* clean
* enable f8 pure gemm rcr ckprofiler
* Add gemm_multiply_multiply instances
* clang format
* Optimize for ScaleBlockMNK=128
* enable abscale f8 gemm ck profiler
* Add pure f8 gemm test suite
* Reverting to the state of project at f60fd77jizhan@amd.com >
2024-07-19 22:06:52 +08:00
Qianfeng
ee768148f0
Replace the using of __expf by __ocml_exp_f32 to work-around the test_softmax_rank4 failure ( #1394 )
2024-07-17 09:15:05 -07:00
Andriy Roshchenko
802a8a1df1
Adding more instances of grouped convolution 3d forward for FP8 with ConvScale element-wise operation and ReLU activation. ( #1386 )
...
* Add CMakePresets configurations.
* Add ConvScale+ReLU Functor and an Example
* Account for ReLU FLOPs.
* Add instances of 3D convolutions with ConvscaleRelu operation.
* Implement Client Example
* Cleanup
2024-07-16 08:51:49 -07:00
ThruptiRajLakshmanaGowda
0162a5f6ba
Adding Missed Activation Functions for Grouped 2D/3D Convolutions ( #1348 )
...
* Initial Push
* First Push
* Fixed Clang format
* Resolve merge conflict
* Addressed review comments
* Addressed review comments
* Addressed review comments
2024-06-20 09:24:54 -05:00
Rostyslav Geyyer
ce66277a76
Add a convinvscale op, related instances and examples ( #1307 )
...
* Update the element op
* Add an example
* Add instances
* Add a client example
* make sure new instances only build on gfx9
* Update element op and its handling
* Format
* Update instances to take element op as an argument
* Update examples to use random scale values
* Format
* Update client example with random scales
* Format
---------
Co-authored-by: illsilin <Illia.Silin@amd.com >
2024-06-10 14:48:49 -05:00
Rostyslav Geyyer
cb0645bedc
Add a scale op, related instances and examples ( #1242 )
...
* Add a scale op
* Update the element op
* Add instances
* Add an example
* Add a client example
* Add a flag check
* Revert flag check addition
* Fix flag check
* Update d strides in example
* Update d strides in client example
* Apply suggestions from code review
Update copyright header
Co-authored-by: Bartłomiej Kocot <barkocot@amd.com >
* Move the example
* Move the client example
* Update element op
* Update example with the new element op
* Add scalar layout
* Update example
* Update kernel for scalar Ds
* Revert kernel changes
* Update element op
* Update example to use scales' pointers
* Format
* Update instances
* Update client example
* Move element op to unary elements
* Update element op to work with values instead of pointers
* Update instances to take element op as an argument
* Update examples to use random scale values
---------
Co-authored-by: Bartłomiej Kocot <barkocot@amd.com >
2024-06-04 19:28:15 -05:00
Rostyslav Geyyer
f044ff71fb
Add element op ( #1259 )
2024-04-26 12:55:45 -05:00
zjing14
0d0150db20
bf16A_Int8B with fastgelu/bias ( #1264 )
...
* changed the copy function to v7r2
* adding multi_abd
* in-progress
* add post-load oob check
* debugging
* adjust instances
* add run_lds
* add elemntwise_op
* replace multi_abd_device with v3
* clean up
* clean
* clean
* Added LDSType
* profiling
* adjust oobcheck
* add missing file
* refactor
* clean
* add examples
2024-04-26 07:26:30 -05:00
zjing14
12865fbf28
Added Multi_ABD support into Gemm and GroupedGemmFixedNK ( #978 )
...
* added an example grouped_gemm_multi_abd
* fixed ci
* add setElementwiseOp
* changed API
* clean code: add multiA into example
* fixed v7r2 copy
* add transpose
* clean
* fixed vector_load check
* Update example/15_grouped_gemm/grouped_gemm_multi_abd_xdl_fixed_nk_bias_fp16.cpp
Co-authored-by: Bartłomiej Kocot <barkocot@amd.com >
* Update example/15_grouped_gemm/grouped_gemm_multi_abd_xdl_fixed_nk_bias_fp16.cpp
Co-authored-by: Bartłomiej Kocot <barkocot@amd.com >
* Update example/15_grouped_gemm/grouped_gemm_multi_abd_xdl_fixed_nk_bias_fp16.cpp
Co-authored-by: Bartłomiej Kocot <barkocot@amd.com >
* Update include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_abd_xdl_cshuffle.hpp
Co-authored-by: Bartłomiej Kocot <barkocot@amd.com >
* Update include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_abd_xdl_cshuffle.hpp
Co-authored-by: Bartłomiej Kocot <barkocot@amd.com >
* Update include/ck/tensor_operation/gpu/device/device_grouped_gemm_multi_abd.hpp
Co-authored-by: Bartłomiej Kocot <barkocot@amd.com >
* Update include/ck/tensor_operation/gpu/device/device_grouped_gemm_multi_abd.hpp
Co-authored-by: Bartłomiej Kocot <barkocot@amd.com >
* Update include/ck/tensor_operation/gpu/device/device_grouped_gemm_multi_abd.hpp
Co-authored-by: Bartłomiej Kocot <barkocot@amd.com >
* Update include/ck/tensor_operation/gpu/device/device_grouped_gemm_multi_abd.hpp
Co-authored-by: Bartłomiej Kocot <barkocot@amd.com >
* Update include/ck/tensor_operation/gpu/device/device_grouped_gemm_multi_abd.hpp
Co-authored-by: Bartłomiej Kocot <barkocot@amd.com >
* Update include/ck/tensor_operation/gpu/device/device_grouped_gemm_multi_abd.hpp
Co-authored-by: Bartłomiej Kocot <barkocot@amd.com >
* Update include/ck/tensor_operation/gpu/device/device_grouped_gemm_multi_abd_fixed_nk.hpp
Co-authored-by: Bartłomiej Kocot <barkocot@amd.com >
* Update include/ck/tensor_operation/gpu/device/device_grouped_gemm_multi_abd_fixed_nk.hpp
Co-authored-by: Bartłomiej Kocot <barkocot@amd.com >
* add reduce
* testing
* add example_b16_i8
* refactor example
* clean
* add mpading
* disable reduce for kbatch = 1
* seperate reduce device op
* add reduce op
* add guard for workspace_size
* add instances
* format
* fixed
* add client example
* add a colmajor
* add instances
* Update cmake-ck-dev.sh
* Update profile_gemm_splitk.cpp
* Update gridwise_gemm_xdlops_v2r4r2.hpp
* format
* Update profile_gemm_splitk.cpp
* fixed
* fixed
* adjust test
* adjust precision loss
* adjust test
* fixed
* add bf16_i8 scale bias
* fixed scale
* fixed scale elementwise_op
* revert contraction deviceop changes
* fixed
* Add AddFastGelu
* Revert "Merge branch 'jizhan/gemm_splitk_reduce' into grouped_gemm_multi_abd_fixed_nk_example"
This reverts commit 3b5d001efd943199a991barkocot@amd.com >
* Update device_reduce_threadwise.hpp
* clean
* Fixes
* Fix example
---------
Co-authored-by: Jing Zhang <jizha@amd.com >
Co-authored-by: Bartłomiej Kocot <barkocot@amd.com >
2024-04-15 21:09:45 -05:00
Haocong WANG
f83e9701e9
[GEMM] Gemm universal device operation ( #1154 )
...
* Optimize GEMM on MI200/300:
1. Add new blockwise gemm pipeline
2. Add irregular splitk intances
* clang format + typo fix
* Fix a bug
* initial commit
* Add more instances to irregular splitk
* blkgemm pipeline v1~4 prototype
* Sanity Checked. Known issue:
1. Poor performance of splitk
2. Register spill on blkgemmpipeline v3
* Sanity and Performance fix:
1. fix a bug related to sanity in grouped b2c mapping
2. fix a bug related to sanity and performance in splitk offset
* Sanity and API update:
1. Remove prefetch stage
2. Fix valid check bug
3, Add first gemm_universal instance into ckProfiler
* Add NN instances for gemm universal
* 1. Add NT instances for gemm_universal
2. Fix a bug about Kpadding in gemm_universal
* Fix a bug regarding padding Odd K number
* remove kernel print
* Fix KPadding bug...
* Update safety check
* another try to fix kpadding..
* Sanity checked
* new instances..
* clang format+typo fix
* remove clang format script's change
* Add non-hotloop compile option
* 1. Add fp16xfp8 example
2. pull packed convert f8 from pr1150
* Some miscs.. opt and fix
* Add pipeline description docs
* Split universal gemm instance library to cut profiler compiling time
* uncomment cmakefile
* Fix a bug caused by blockwise_gemm_pipe_v2
* reduce default splitk to 1
* Add 224x256x64 tile size
* update, including:
1. Experiment pipeline 5~7
2. Optimization for pipeline 4
3. Organized instance library
* temp save
* temp save
* Permuted lds layout, sanity and function checked
* clang format
* Move OOB check from RunRead to RunWrite, for better software pipeline.
TODO: agpr spill when NN layout
* clangformat
* A/B splitpipe scheduler for v3
* Fix two bugs
* bug fix
* fix a bug in oob check
* Example for mixed fp16_fp8 gemm
* Clean experimental code blocks
* Add mixed precision gemm into profiler
* tempsave
* optimize m/n major lds layout
* Add RRR GEMM mixed precision instances
* Optimize f8 matrix transpose
* Add test_gemm_universal
* A/B spilt schedule for blkpip v5
* Take ds_read2 into iglp scheduling scheme
* format
* fixed cmake
* Add llvm-option into CI cmake flag
---------
Co-authored-by: Jing Zhang <jizhan@amd.com >
2024-04-13 21:03:18 -05:00
Bartłomiej Kocot
9a194837af
Introduce combined elementwise ops ( #1217 )
...
* Introduce combined elementwise ops
* Introduce refrence elementwise
2024-04-02 17:23:49 -05:00
Bartłomiej Kocot
285251768e
Add conv fwd/bwd data scale instances, extend bilinear instances ( #1178 )
...
* Add conv fwd/bwd data scale instances
* Fix cmake client example file
---------
Co-authored-by: Adam Osewski <19374865+aosewski@users.noreply.github.com >
2024-03-13 23:09:08 +01:00
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#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#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
Bartłomiej Kocot
bf98b47697
Add bilinear conv fwd and bwd data instances ( #1164 )
2024-02-13 11:49:05 +01:00
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
Lakhinder Walia
1f306024d0
fast_gelu: minor code reorg to enhance ref & gpu performance ( #1162 )
2024-02-07 19:24:51 -08:00
jakpiase
ba86eadce5
Add support for mixed-precision f16bf16_int8 gemm ( #1127 )
2024-02-07 15:54:13 +01:00
Artur Wojcik
fb5bd51b42
enable compilation of INSTANCES_ONLY for Windows ( #1082 )
...
* enable compilation of INSTANCES_ONLY for Windows
* suppress ROCMChecks warnings on GoogleTests
* suppress -Wfloat-equal warning on GoogleTests
---------
Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com >
2023-12-20 14:34:53 -08:00
Rostyslav Geyyer
6ef034f6ca
Switch default f8 conversion to stochastic rounding ( #1048 )
...
* Switch default f8 conversion to stochastic rounding
* Refactor f8-related type_converts
* Add an element-wise op
2023-11-27 20:06:17 -06:00
arai713
454cf7bd1f
Hip tensor permute ( #1002 )
...
* adding files for F32 example
* adding functioning implementation with scalar multiplication and unary operator support
* added fp 16 type check in unary square
* updating scalar multiplication as an operator
* functioning version with scalar operator
* changing strides for col major
* updated column major implementation
* working column major implementation
* cleaned up comments, rearranged/renamed files
2023-11-13 11:15:48 -06:00
Bartłomiej Kocot
49e52bb357
Support multi AB for grouped conv fwd xdl ( #1027 )
...
* Support multi AB for grouped conv fwd xdl
* Add instances
* Add client example
* Add example
* Add interface test
* Minor fixes
Minor fixes
Minor fixes
* Comment fixes
* Fixes
* Reference fix
* Test xdl fixes
* Improve multi_ab interface test
2023-11-10 15:54:44 +01:00
zjing14
98fd41f597
Add Gemm instances for performance improvement ( #1018 )
...
* improve kpad
* more tuning parameters
* f16_f8_fp16
* cut test time
* add f16_f8_fp16
* add f16_f8_f16
* testing instances for skinny cases
* format
* clean
* add fp16_f8_fp16
* clang-format
* add grouped gemm instalces
* fixed profile grouped_gemm
* clean
* clean
* clean
* clean
* clean
* add missing instance func
* fixed inferface
---------
Co-authored-by: Jing Zhang <jizha@amd.com >
Co-authored-by: root <root@sh5-1e707-rc06-38.mkm.dcgpu >
2023-11-07 09:09:58 -06:00
Bartlomiej Wroblewski
4ef704d8a6
Add support for mixed precision in contraction scale and bilinear ( #973 )
...
* Add support for mixed precision in contraction scale and bilinear (#936 )
* Extract common functionality to separate files
* Reference contraction: Remove incorrect consts from type_converts
* Reference contraction: Add missing type_convert for dst value
* Reference contraction: Fix incorrect order of B matrix dimensions
* Add support for mixed precision in contraction scale and bilinear
* Move using statements from instances to a common file
* Move using statements from examples to a common file
* Fix the order of B matrix dimensions across examples and profiler
* Fix the computation of error threshold
* Make ComputeDataType an optional argument
* Include possible DataType -> ComputeDataType casting error in the threshold
* Remove commented code
* Make the ComputeDataType an optional argument in instance
---------
Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com >
2023-11-02 14:26:33 -07:00
Bartłomiej Kocot
f27ea94ecb
Add ScaleAddScaleAddRelu post op for conv fwd ( #1006 )
...
* Add ScaleAddScaleAddRelu post op for conv fwd
* Fixes
* Fix instance file name
* Minor fix
2023-11-01 18:31:30 -05:00
Rostyslav Geyyer
1fd27d520f
Fix bf8 conversion issues ( #1003 )
...
* Fix the conversion
* Add bf8 functionality
* Enable example on MI200 as well
2023-10-20 08:00:45 -05:00
Bartłomiej Kocot
82f3a835d5
Extend available elementwise operations with conv examples ( #995 )
...
* Extend available elementwise operations with conv examples
* Fixes
* Remove not needed convert
* Update CMakeFile and dir name
2023-10-19 17:23:19 +02:00
zjing14
bf435140dc
Clean DTYPES conditions in CMake ( #974 )
...
* Add a condition to build fp8 instances
* simplified buffer_load/store
* add bfp8/fp8
* fixed
* remove all f8/bf8 condition include folder
* fixed cmake conditions
* fixed DTYPES=fp16/bfp16
* fix
* fixed buffer_load
* fixed buffer_store
* fix
* clean example cmake files
* fixed ci
* fixed cit
---------
Co-authored-by: Rostyslav Geyyer <rosty.geyyer@amd.com >
Co-authored-by: Jing Zhang <jizha@amd.com >
2023-10-18 11:14:14 -05:00
zjing14
ac9595a9f1
Fixed f8_gemm NaN ( #975 )
...
* workaround nan problem by changing output to fp16
* enable f8/bf8 gemm tests on MI200
* workaround f16 to f8 conversion
---------
Co-authored-by: Jing Zhang <jizha@amd.com >
2023-10-10 10:30:26 -05:00
Illia Silin
4daedf8ca5
Revert "Add support for mixed precision in contraction scale and bilinear" ( #967 )
...
* Revert "Add support for mixed precision in contraction scale and bilinear (#936 )"
This reverts commit f07485060e#957 and #960
2023-10-05 14:58:23 -07:00
Rostyslav Geyyer
42facfc6b7
Add conv bwd weight fp16 comp bf8 fp8 op, instances and example ( #945 )
...
* Add f8 bf8 gemm example
* Add element-wise ops
* Add intrinsics
* Update reference calculation
* Add an additional type option for xdlops gemm
* Fix build process
* Add bf8 to buffer addressing
* Update blockwise op, split typeA and typeB
* Update for compatibility
* Uppdate naming to f8->fp8
* Update naming
* Format
* Update naming (#937 )
* Add a client example
* Add computetypes to device and gridwise ops
* Add instances, update instance factory
* Format
* Fix a flag
* Add ckProfiler mode
* Fix typos
* Add an example
* Add bf8 generator
* add bf8 mfma; fixed type_convert for bf8
* move verfication ahead of timing
* Update reference calculation
* Fix reference
* Narrow down float init range
* Fix bf8 bf8 mfma
* Add bf8 @ fp8 mfma
* Update example
* Update instances
* Update profiler api
* Update for compatibility
* Format
* Remove extra example
* Clean up
* workaround convert
---------
Co-authored-by: Jing Zhang <jizha@amd.com >
2023-10-04 08:19:08 -05:00
Rostyslav Geyyer
bd09b5c538
Add fp8 @ bf8 gemm support and example ( #933 )
...
* Add f8 bf8 gemm example
* Add element-wise ops
* Add intrinsics
* Update reference calculation
* Add an additional type option for xdlops gemm
* Fix build process
* Add bf8 to buffer addressing
* Update blockwise op, split typeA and typeB
* Update for compatibility
* Uppdate naming to f8->fp8
* Update naming
* Format
2023-10-02 16:39:03 -05:00
Bartlomiej Wroblewski
f07485060e
Add support for mixed precision in contraction scale and bilinear ( #936 )
...
* Extract common functionality to separate files
* Reference contraction: Remove incorrect consts from type_converts
* Reference contraction: Add missing type_convert for dst value
* Reference contraction: Fix incorrect order of B matrix dimensions
* Add support for mixed precision in contraction scale and bilinear
* Move using statements from instances to a common file
* Move using statements from examples to a common file
* Fix the order of B matrix dimensions across examples and profiler
* Fix the computation of error threshold
* Make ComputeDataType an optional argument
* Include possible DataType -> ComputeDataType casting error in the threshold
* Remove commented code
2023-09-29 10:54:31 -05:00
zjing14
f9d0eddb90
Add fp16/fp8 support into Grouped gemm FixedNK ( #874 )
...
* move all arguments into device
* add b2c_tile_map
* add examples
* add SetDeviceKernelArgs
* dedicated fixed_nk solution
* init client api
* add grouped_gemm_bias example
* add a instance
* add instances
* formatting
* fixed cmake
* Update EnableCompilerWarnings.cmake
* Update cmake-ck-dev.sh
* clean; fixed comments
* fixed comment
* add instances for fp32 output
* add instances for fp32 output
* add fp32 out client example
* fixed CI
* init commit for kbatch
* add splitk gridwise
* format
* fixed
* clean deviceop
* clean code
* finish splitk
* fixed instances
* change m_loops to tile_loops
* add setkbatch
* clean code
* add splitK+bias
* add instances
* opt mk_nk instances
* clean examples
* fixed CI
* remove zero
* finished non-zero
* clean
* clean code
* optimized global_barrier
* fixed ci
* fixed CI
* instance and client
* removed AddBias
* format
* fixed CI
* fixed CI
* move 20_grouped_gemm to 21_grouped_gemm
* clean
* formatting
* clean
* clean
* fixed computeType
---------
Co-authored-by: Jing Zhang <jizha@amd.com >
2023-09-14 21:04:10 -05:00
zjing14
a66d14edf2
fixed fp8 issues ( #894 )
...
* fixed fp8 init; and reference gemm
* Update host_tensor_generator.hpp
* fixed convert
* fixed reference gemm
* fixed comments
* fixed comments
* fixed ci
* fixed computeType
---------
Co-authored-by: Jing Zhang <jizha@amd.com >
2023-09-12 22:17:56 -05:00
Rostyslav Geyyer
62d4af7449
Refactor f8_t, add bf8_t ( #792 )
...
* Refactor f8_t to add bf8_t
* Add check_err impl for f8_t
* Update fp8 test
* Format
* Revert the fix
* Update vector_type implementation
* Add bf8 test
* Add bf8, use BitInt types
* Add bf8 conversion methods
* Update type_convert for fp8/bf8
* Add check_err fp8/bf8 support
* Add subnorm fp8 tests
* Add subnorm bf8 tests
* Fix conversion
* Add bf8 cmake bindings
* Add macros to enable build with disabled fp8/bf8
* Remove is_native method
* Update flag combination for mixed precision instances
* Add more flag checks
* Add another flag to a client example
* Add type traits, decouple f8/bf8 casting
* Clean up
* Decouple fp8 and bf8 flags
* Remove more redundant flags
* Remove leftover comments
2023-09-12 17:04:27 -05:00
Haocong WANG
562b4cec48
[Navi3x] Add fp16/int8 wmma conv forward instances ( #746 )
...
* fix wmma gemm int8; add grouped conv int8 example
* Add int8 gemm-bilinear instances
* compile sanity check unknown
* Sanity pass + clang-format
* add int8 conv profiler instances
* solve merge conflict
---------
Co-authored-by: zjing14 <zhangjing14@gmail.com >
Co-authored-by: Chao Liu <chao.liu2@amd.com >
2023-09-07 21:59:26 -05:00
zjing14
f5ec04f091
Grouped Gemm with Fixed K and N with SplitK ( #818 )
...
* move all arguments into device
* add b2c_tile_map
* add examples
* add SetDeviceKernelArgs
* dedicated fixed_nk solution
* init client api
* add grouped_gemm_bias example
* add a instance
* add instances
* formatting
* fixed cmake
* Update EnableCompilerWarnings.cmake
* Update cmake-ck-dev.sh
* clean; fixed comments
* fixed comment
* add instances for fp32 output
* add instances for fp32 output
* add fp32 out client example
* fixed CI
* init commit for kbatch
* add splitk gridwise
* format
* fixed
* clean deviceop
* clean code
* finish splitk
* fixed instances
* change m_loops to tile_loops
* add setkbatch
* clean code
* add splitK+bias
* add instances
* opt mk_nk instances
* clean examples
* fixed CI
* remove zero
* finished non-zero
* clean
* clean code
* optimized global_barrier
* fixed ci
* fixed CI
* removed AddBias
* format
* fixed CI
* fixed CI
* move 20_grouped_gemm to 21_grouped_gemm
---------
Co-authored-by: Jing Zhang <jizha@amd.com >
2023-08-31 09:22:12 -05:00
zjing14
38ada109ea
add an example of customized type convert - bfp16_rtn ( #869 )
...
* add an example of customized bfp16_rtn
* fixed threadwise_copy
---------
Co-authored-by: Jing Zhang <jizha@amd.com >
2023-08-29 12:31:24 -05:00
zjing14
31ea132aa2
Fp16/fp8 mixed-precision Gemm with multiply+add fusion ( #865 )
...
* add compute_type
* add multiply_add ckProfiler
* add f8_fp16 support
* clean
* clean
* fixed lds size calc
* format
---------
Co-authored-by: Jing Zhang <jizha@amd.com >
2023-08-28 16:27:32 -05:00
Rostyslav Geyyer
f0c620c42e
FP8 enablement - add a pseudorandom number generator, add conversion methods ( #708 )
...
* Add basic fp8 definitions and prn-generator
* Format
* Add fp8<->fp32 type_convert
* Format
* Split type_convert and cast_to/from_f8
* Format
* Minor fix
* Minor fix
* Move fp8 utils to a separate header
* Add elementwise ops
* Add fp8_convert_sr
* Format
* Add element op
* Eliminate magic numbers
* Split f8_convert_sr in host and device
* Format
* Add some constexpr
* Add a datatype test
* Format
* Another format
* Add fp8<->fp16 tests
* Update type_converts
* Format
* Add fp16 casting functions
* Format
* Use seed as a runtime arg
* Use element location for PRNG
* Format
* Add fp8<->fp16 to PassThrough element op
* Clean up
* Merge host and device implementations
* Add comments on rounding modes
* Remove leftover code
* Put type_converts into a separate header
* Put random number gen to a separate header
* Rearrange f8_utils' namespaces
* Refactor type_convert.hpp
* Move f8_t definition
2023-06-19 11:20:35 -05:00
Illia Silin
b94fd0b227
update copyright headers ( #726 )
2023-05-31 18:46:57 -05:00
Rostyslav Geyyer
b076a02ad2
Optimize bf16 conversion ( #664 )
...
* Add TypeConvert class and start refactoring
* Refactor TypeConvert as a struct
* Get back to template functions type_convert
* Add a type_convert_bf16_rtn, set rtz as default
* Clean up
* Add UnaryConvertPrecision struct for high-precision workloads
* Format
* Update type_convert to UnaryConvert on threadwise level
* Update UnaryConvertPrecision
* Format
* Fix chmod
* Add a flag to pick converion method
* Format
* Remove the added flag
* Merge elementwise op with type conversion
* Move type_convert to elemwise op, update the op
* Update type_convert_precision -> bf16_convert_rtn
* Clean up
* Update comments
* Update the CK_WORKAROUND_DENORM_FIX flag handling
* Update the unneeded op to work but warn user
* Remove the message
* Use a PassThrough instead of ConvertBF16RTN to calcaulate reference
* Format
* Add missing include
2023-05-04 10:25:47 -05:00
rocking5566
ed3a2e5226
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
2023-04-10 08:02:17 -05:00
rocking5566
389e84a83b
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 >
2023-03-29 14:50:23 -05:00
rocking5566
16dc18e0f9
gemm/Conv xdlops + dlops quantization ( #625 )
...
* Add conv perlayer quantization
* Add gemm_dlops quantization
* Support int8 for innerproduct
* Refine gemm dlops int8 kernel parameter
* Support gfx908(MI100) and gfx90a(MI200)
* clang-format
* Rename example number
* Support different layout for d tensor
* Add conv dlops perchannel quantization example
* Move to example 40
* Extract the common code for different platform (dlops and xdlops)
* Move ot subfolder. Prepare to add other op of quantization
* Refine the quantization instance library
* Add conv dl instances and client example
* Remove unnecessary type
* Add gemm quantization instance
* Add external api and client example
* Refine num_bytes
* Separete different layout to different cpp
* Add more xdl instances
* Revert "Remove unnecessary type"
This reverts commit 820869182fzhangjing14@gmail.com >
2023-03-15 15:29:40 -05:00
Chao Liu
8f455615a8
Fast GeLU using built-in function ( #587 )
...
* clean up
* fast gelu using builtin function
* clean
* clean
* clean
* clean:
* clean
* fix compilation
* clean
* clean
---------
Co-authored-by: zjing14 <zhangjing14@gmail.com >
2023-02-26 23:19:11 -06:00
zjing14
24c9ee1d22
Add contraction_fp64 example ( #570 )
...
* add contraction_bilinear
* add contraction_scale_xdl_fp64
* reduce tile size to avoid register spill
---------
Co-authored-by: root <root@ctr-ubbsmc16.amd.com >
2023-02-15 12:00:58 -06:00
ltqin
332ccc3367
Add GemmAddSoftmaxGemm support for MSFT ORT (instances and client API) ( #576 )
...
* add instance for gemm bias softmax gemm
* add client example
* change CGridDesc_G_M_N to CGridDesc_G_M_O
* add gridwise
* change c grid name
* device add d0s data
* fix 08 client_example
* add example 47_fused_attention
* example output correct
* add d0 to example
* add d0 element op
* rechange instance code
* change Acc0ElementwiseOperation to C0DEElementwiseOperation
* change example name
* update instance for cdeelementwiseop
* add bhalf_t ScaleAdd
* add test
* not surport geem1 bias
* remove some ignore
* fix test bug
2023-02-08 14:34:45 -06:00
Qianfeng
a1b2441f8d
Batchnorm inference instances, external API, client examples and gtests ( #531 )
...
* File renaming and class renaming for device element-wise operation
* Add batchnorm-infer instances, external API and client example
* Add batchnorm-infer profiler module and gtests
* Remove file device_elementwise_extension.hpp and move NormalizeInInfer operation to element_wise_operation.hpp
* Remove the using of class aliasing for DeviceElementwiseForBatchNormInfer
* Rename class and file due to conflict from device_elementwise_2d.hpp
* Fix namespace in batcnnorm_infer_nhwc client example
2023-01-25 17:09:04 -06:00
