* initial commit
* remove extra files
* fixing errors
* updated ReadMe file for mapping of diff quants with diff configs
* addressing review comments
* addressing review comments
* Resolved merge conflicts
* [CK TILE GEMM] Replace get_preshuffle_or with is_quantpreshuffle_enabled
The get_preshuffle_or was not working as expected, which led to incorrect behavior
in the quantization preshuffle process. This change replaces it with the more reliable
is_quantpreshuffle_enabled function to properly determine when preshuffle should be applied.
* initial commit
* debugging
* working fp8 for init constant
* fp8 working with all inits
* updated block level code with comments
* changing the loop iter
* debugging
* debugging
* debugging
* code fix
* code clean up
* clang formatted
* Add comment
* code cleanup
* clang formatted
* merge conflicts fixes
* applying the latest int4 changes to the piepline
* fixing test code for updated traits
* Adding gtest
* review comments addressed
* addressing review comments
* remove c++20 code
* added flush cache changes
---------
Co-authored-by: Cong Ma <congma13@amd.com>
Co-authored-by: root <root@banff-cyxtera-s73-2.ctr.dcgpu>
[ROCm/composable_kernel commit: 81458a6681]
* Change the return type of run_gemm_combinations in the basic tests
* Change the return type of run_gemm_combinations in the universal tests
* Add universal GEMM tests for bf16 x pk_i4 and fp16 x pk_i4
* Add universal GEMM test for fp8 x pk_i4
* Add basic GEMM tests for bf16 x pk_i4, fp16 x pk_i4 and fp8 x pk_i4.
* Add missing GemmTypeConfig<ck_tile::fp8_t, ck_tile::pk_int4_t, ck_tile::half_t>
* Add missing GemmTypeConfig<ck_tile::bf16_t, ck_tile::pk_int4_t, ck_tile::bf16_t>
* No need for utility in test_ck_tile_elementwise_1d
* Fix conversion from pk_int4x4_t to bf16x8_t in PassThroughPack8
* Avoid union-based type punning in float_to_bf16_truc_raw to make it constexpr compliant
* For consistency also make float_to_bf16_truc_nan_raw constexpr compliant by removing the union
* Use a static_cast to bfloat16_t only when CK_TILE_USE_LLVM_BUILTIN_BF16 is enforced
* Convert from float to bf16 during compilation rather than using magic values
* Fix conversion from pk_int4x4_t to fp8x8_t in PassThroughPack8
* Comment out the basic test for fp16 x pk_i4 as it does not pass
* Add missing GemmTypeConfig<ck_tile::bf8_t, ck_tile::pk_int4_t, ck_tile::half_t>
* Fix conversion from pk_int4x4_t to bf8x8_t in PassThroughPack8
* Add basic and universal GEMM tests for bf8 x pk_i4
* Switch back to amd_assembly_i4_to_fp8x8 in PassThroughPack8 as it works now
* Switch back to amd_assembly_i4_to_bf8x8 in PassThroughPack8 as it works now
* Remove the inefficient fallbacks for fp8 and bf8 in elementwise/unary_element_wise_operation.hpp
* Use explicit macros for enabling and disabling the the constexpr lookup based converters
* Fix two failing tests
* Avoid union-based type punning in float_to_bf16_rtn_raw to make it constexpr compliant
* Use float_to_bf16_rtn_raw instead of float_to_bf16 to create the bf16 lookup table for use in conversions from pk_int4 to bf16
* On ROCm 7.0.1 we need an explicit cast to from uint16_t to bf16_t
[ROCm/composable_kernel commit: 0f10e6d921]
* Support 16x16 (MFMA, WMMA) and 32x32 (MFMA) tiles in fwd and bwd BlockDropout
Add comments with dropout implementation details
Fix performance regression of fwd+dropout
* Remove some usage of type punning (reinterpret_cast with ref or ptr) in Philox;
* "scalarize" seed and offset, they may come either from kernel args or from device memory
(presumably loaded with vector loads).
These changes help the compiler to procude more optimal code and reduce register spilling.
Use WarpGemmDispatcher instead of explicit WarpGemmMfma... to get CWarpDstrEncoding
Use code based on BlockDropout in BlockDropoutBwd
Refactor BlockDropout (fwd)
Implement BlockDropout (fwd) for WMMA
Originally BlockDropout only supported 32x32 tiles (IsWG32 = true),
this version supports 16x16 tiles.
If MPerBlock > MWarp * 16, it can generate numbers for two 16x16 tiles, similarly
to BlockDropoutBwd.
Implement BlockDropoutBwd for WMMA
Remove MakeRandValLds* functions unused in BlockDropoutBwd
Remove unused Run overload from BlockDropoutBwd
* Fix regression with philox seed and offset when they exceed 32-bit int
__builtin_amdgcn_readfirstlane works with 32-bit values, seed and offset
are 64-bit so they get truncated.
* Add F32 MFMA warp gemms
* Support f32 in fwd FMHA
* Implement transpose_vectors for 4-byte types (float)
* Fix unexpected implicit f32->uint32 cast in buffer_store<4>
__builtin_amdgcn_raw_buffer_store_b32 expects unsigned int but float was passed (implicitly casted to uint).
mbuf_t types in other buffer_store<> are changed for consistency.
* Support F32 in bwd FMHA
hdim = 256 is disabled for now because it uses too much memory on gfx90a
* Support Headdim = 48 (divisible by 16) in fwd
* Add fp32-specific receipts (800 and 801)
* Tune fwd tiles
* Tune bwd tiles
* Use small tiles only for small seqlen_q
* Fix after rebasing
* Fix selection of a fallback tile based on bm0
The assumption that the largest bm0 == 128 is not always true for
current fp32 tiles.
* Remove constraints and adjust filtering for fp32
Custom constraints are no longer needed because now the smallest tile
is selected automtically based on seqlen_q.
Filters related to qr_async_trload disabled valid fp32 tiles.
* Add fp32 tests
* Make splitkv and appendkv compile for fp32 only
There are no instances yet, but API still must compile when only fp32 is
requested.
* Remove unimportant f32 instances
* Add test_ck_tile_fmha_*_fp32 to REGRESSION_TESTS
* Replace magic numbers with a constant, improve comments for dropout
* Update changelog
* Fix condition that dq_acc must be set to zero when mask is used
The change was introduced in #2799
* Replace warp_uniform with recently added amd_wave_read_first_lane
* Add hdim = 96 and 192 to fwd
[ROCm/composable_kernel commit: 1edd250115]
* feat(grouped_gemm_multi_d): add new example that integrates grouped_gemm and multi_d_gemm feature
* feat: generalized grouped_gemm_kernel.hpp
* feat: generalized grouped_gemm_kernel.hpp even further by removing hardcoded 0
* refactor: grouped_gemm_multi_d relies on grouped_gemm_kernel
* tests(grouped_gemm): grouped_gemm test suite passes with minor adjustments
* fix: segfault fix by passing correct parameters for d tensors
* docs: add multi d info and trim down outdated content
* tests: add unit tests for grouped_gemm_multi_d and minor changes in grouped_gemm related test for compatibility
* style: clang format
* fix: incorrect validation method and Dtensor layout in test suite
[ROCm/composable_kernel commit: a44bea45b2]
* * [CK_TILE] Add sequence padding and variable length support in fmha (and v3)
- Group Mode Padding: Introduces the `-s_qpad` argument to support
physically padded layouts. Kernels now use padded start pointers
(`seqstart_padded_*_ptr`) for memory addressing.
- Batch Mode Variable Length: Adds `-q_eff_lens` and `-kv_eff_lens`
arguments for efficient processing of variable-length sequences by
passing cumulative effective lengths (`cu_seqlen_*_ptr`) to the kernel.
- FMHA examples: Support padding and variable length both in
group and batch mode. Dispatcher is updated as well (dispatch to
kPadSeqLenK enabled pipeline).
- New padding test cases: Add padding test cases to `smoke_test_fwd.sh` and
`test_fmha_fwd.inc`, and add benchmarks to `benchmark_fwd.sh` and
`benchmark_fwd_v3.sh` as well. These test cases and benchmarks that
specifically validate/benchmark the new padding and variable-length
functionalities in both group and batch modes.
* [CK_TILE] Fix build error in fmha unit tests
* [CK_TILE] add mqa, gqa to sequence padding unit tests
* [CI_TILE] Reduce the number of padding seqlen unit tests in FMHA to avoid timeouts in CI
* [CK_TILE] remove unnecessary MageKArgs overload in FmhaFwdV3Kernel and FmhaFwdKernel
[ROCm/composable_kernel commit: 518d24e662]
* Update grouped_gemm example and pipeline
* find the root cause error in did not enable the transpose in gfx950 correctly
* Fix v3 pipeline, row and col major
* Disable f8 datatype tests, it fails on gfx950
* fix the abd test by clear the runtime argument unsupported
---------
Co-authored-by: AviralGoelAMD <aviral.goel@amd.com>
Co-authored-by: Mateusz Ozga <mateusz.ozga@amd.com>
[ROCm/composable_kernel commit: b159841a06]
* rename gemm_group_quant to gemm_quant
* Add TensorWise quant mode
* Cshuffle epilogue tests with tensor scaling
* Add tensor quant to example
* Don't use readfirstlane for reading scales - doesn't work for some reason
* Add to changelog
* revert include - from a merge problem?
* revert common.hpp include
* revert host.hpp include
* remove unused utility function
* rename quant pipeline problem
* refactor quant tests
* remove aquant utils
* use TEST_F
* fix all tests by changing gemm config
* Use typed tests
* fix copyright
[ROCm/composable_kernel commit: 4363a82bd6]
* [CK_TILE] Add sequence padding and variable length support in fmha (and v3)
- Group Mode Padding: Introduces the `-s_qpad` argument to support
physically padded layouts. Kernels now use padded start pointers
(`seqstart_padded_*_ptr`) for memory addressing.
- Batch Mode Variable Length: Adds `-q_eff_lens` and `-kv_eff_lens`
arguments for efficient processing of variable-length sequences by
passing cumulative effective lengths (`cu_seqlen_*_ptr`) to the kernel.
- FMHA examples: Support padding and variable length both in
group and batch mode. Dispatcher is updated as well (dispatch to
kPadSeqLenK enabled pipeline).
- New padding test cases: Add padding test cases to `smoke_test_fwd.sh`,
and add benchmarks to `benchmark_fwd.sh` and `benchmark_fwd_v3.sh` as well.
These test cases and benchmarks that specifically validate/benchmark the
new padding and variable-length functionalities in both group and batch modes.
* [CK_TILE] Fix build error in fmha unit tests
---------
Co-authored-by: Po Yen Chen <PoYen.Chen@amd.com>
Co-authored-by: Yi DING <yi.ding@amd.com>
[ROCm/composable_kernel commit: 86dd59cd01]
* change host using fp16 to check
* fp8 to fp8 compare
* rewrite input parameters
* add not squant
* remove some output code
* for scale = 1
* format
* saturates only for fp8
* add fp8bf16 data type
* add fp8bf16 data type
* fix test fp8 code
* add run_fp8bf16_tests
* change fmha fwd example parameter(adding fp8bf16)
* Support fp8bf16 for Aiter
* Support aiter fp8bf16 in c++
* fix comment about fp8 in readme.md
* add fp8fp32
* add fp8fp32 test
* remove range_q etc.
* format
* fix test parameters about squant and fmha example input fp8bf16 fp8fp32 data type
* add fp8bf16 to data_type function
* change colmajor to rowmajor in test_ck_tile_fmha_fwd_fp8
* format
* reset atol for fp8
* fix bug for atol
---------
Co-authored-by: rocking <ChunYu.Lai@amd.com>
Co-authored-by: asleepzzz <hanwen.chang@amd.com>
[ROCm/composable_kernel commit: dd249f1cd6]
* Factor out the three separate copies of load_interleaved_pk_type into a common utility class
* Add preprocessing with optional cache flushing and clearing of output for k_batch > 1 to the weight preshuffle GEMM example
* Remove a duplicate function
* Add support for B tensor type pk_int4_t for the weight preshuffle GEMM, with tests included
* I4 support introduced more failing test cases that mirror the existing ones for F8
* Simplify the check for which tests to skip (they all have F8 as A tensor type)
* Add a changelog entry
* add the test for v2 wp pipeline, polish the code, add the support of int4 for v2 wp pipeline
* have a workable version for atomic add
* Revert "have a workable version for atomic add"
This reverts commit 792377a590c26cfff9c8f545d9a9e8484a7422eb.
---------
Co-authored-by: ThomasNing <thomas.ning@amd.com>
[ROCm/composable_kernel commit: 47cd0d5cff]
- profiler for gemm quantization for DL/XDL
- tests for gemm quantization for DL/XDL
- implementation for gemm quantization for WMMA
- profiler/tests for gemm qunatization for WMMA
Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
[ROCm/composable_kernel commit: f97b2a3f5d]
* test(grouped_gemm): add gtests for the example to maintain its integrity
* test(grouped_gemm_preshuffle): add prefill variant to testbed to cover wider range
* fix: removed residue code to make b_shuffle() work again
* test(grouped_gemm_preshuffle): limit the test suite to gfx942 arch as it fails on gfx90a
* build: add gfx950 as build target for gtests
* test(grouped_gemm_preshuffle): temporarily disable fp8 prec tests due to numerical errors
* fix(grouped_gemm_preshuffle): resolved fp8 tests failure on gfx950 by adding correct compiler flag
[ROCm/composable_kernel commit: 48e08c6429]
* Change splitk_batch_offset parameter to k_size in UniversalGemmKernel::MakeGemmTensorViews function
Prior to this change, the splitk_batch_offset parameter of
MakeGemmTensorViews had type SplitKBatchOffset. But, the only member
variable of the SplitKBatchOffset class used in the MakeGemmTensorViews
function was splitted_k (an int32_t). The splitted_k value was used as
part of defining the dimensions of the tensor view. That said, for
Stream K, we do not need to use the SplitKBatchOffset class since we are
not using Split K. Thus, this commit changes the splitk_batch_offset
parameter to a int32_t called k_size. This will avoid the constraint of
requiring a caller of MakeGemmTensorViews to use the SplitKBatchOffset
class while still providing the same functionality. Calls to
UniversalGemmKernel::MakeGemmTensorViews have been updated accordingly.
* StreamK Kernel RunGemm Implementation
Stream K cannot simply use UniversalGemmKernel's RunGemm for the
following reasons:
1. The UniversalGemmKernel::RunGemm function computes num_loop based on
a static function of the TilePartitioner. That said, for Stream K,
num_loop must be computed using a member function (namely
GetCurrentIterLength from PR #2708).
2. The UniversalGemmKernel::RunGemm function requires the use of a
SplitKBatchOffset object which is not used for Stream K since we are
not using Split K.
Thus, this change adds a RunGemm function in the StreamKKernel class.
* initial implementation for operator() for StreamKKernel: adding stream-k algorithm and calls to RunGemm
* Fix indexing and offset issues for StreamK
These changes do the following:
- Ensure offsets along the M and N dimensions are multiplied by
MPerblock or NPerBlock, respectively. This ensures tile window origins
are at the correct locations.
- Fix bug in the tile partitioner's GetTileIdxWithOffset. Now, we apply
divmod to the given references to ensure correct values are available
to the caller.
- Added documentation in the Stream-K operator()
* Initial gtests for Stream-K
These changes add an initial gtest suite for the CK Tile Stream-K
kernel. Currently, due to bugs in the StreamKTilePartitioner (which will
be handled in a future PR), there are validation issues for certain
cases which may differ on different architectures. Thus, we opted to run
cases that are only fully data-parallel (skipping others). A guard was
added to Stream-K's IsSupportedArgument method to ensure that callers
are aware of this constraint. Additionally, to ensure testing
reproducibility, options for setting the number of CUs and occupancy
were added to MakeKernelArgs.
* Use GemmPipeline operator() variant that takes hot loop and tail num
In Stream-K, the num_loop value varies per WG and per iteration of a
Stream-K loop. So instead, we use the version of the GemmPipeline's
operator() function that takes in has_hot_loop and tail_num. This is
similar to what is done in Grouped GEMM.
* changes from review: comments, move readfirstlane, remove ifndef
* Switch direction of C tensor traversal & add padding guard
Prior to this change, WGs travelled backwards through their assigned
macro tiles in the C tensor. For instance, if WG0 is responsible for C
tiles 0 and 1, it would first visit tile 1 then tile 0. This means that
the iter_end decrements in each iteration of the stream-K while loop.
Since we are working with unsigned integers, the subtraction operation
may not be safe. Thus, this change makes is such that WGs travel forward
so that their iter_start is incremented and their iter_end remains
fixed.
Additionally, we added a guard against WGs that are neither sk_blocks
nor dp_blocks to ensure such WGs do not participate in the GEMM.
Together, these changes make is such that the algorithm is correct when
sk_blocks is greater than zero.
* Disable StreamK_M256_N256_K256_SKBlocks12 test case
This instance involves >=3 WGs contributing to each macro tile in C. Due
to the use of atomics, this is resulting in precision errors. These
errors will not persist once the reduction strategy is implemented. We
will re-enable this test then.
---------
Co-authored-by: Astha Rai <astha.rai713@gmail.com>
[ROCm/composable_kernel commit: dee185d80c]
* [CK_TILE][REGRESSION] Correct blockSize in Generic2dBlockShape (5b17f135b7 )
WarpPerBlock_M * WarpPerBlock_N are not equal with ThreadPerBlock_M * ThreadPerBlock_N /warpSize. we should calculate BlockSize from WarpPerBlock_M * WarpPerBlock_N
To compatible with wave32, function GetBlockSize is added to calculate correct size in host side.
* fix blocksize for all kernel related with generic2dblockshap
* remove constexpr for blocks
[ROCm/composable_kernel commit: b7a806f244]
* Use lse = false for PagedKV tests
There are no instances with lse = true so splitkv is actually launched
as a fallback.
* Reduce build time by disabling instances that are not tested
[ROCm/composable_kernel commit: 847834a408]
* Improve random number generation
* use different seed for each input (Q, K, V...);
* use deterministic generation of:
* seqstart_q/k (for group mode);
* block_table (for paged-kvcahe);
* cache_batch_idx (for kvcache);
* Extract arg_parser-related code from run functions to use them as tests
* Split examples into main programs and fmha runners, build instances separately
* Add dummy tests that use instances and runners
* Fix a missed corner case of f32->f8 conversion
When value if < min f8 denormal but > min f8 denormal / 2, it must be
rounded to min f8 denormal (i.e. 0b1), not to 0.
* Fix incorrect fp8 scales for P and O in validation code
DataTypeConfig was incorrectly compared with fp8_t.
* Add host generation of dropout random values and use it for validation
Previously host validation (reference_batched_dropout) used random
numbers generated by BlockDropout of the kernel, meaning that incorrect
generation on device (bad distribution, repeated numbers, too many zeros,
etc.) would not trigger any validation errors.
* Implement tests from smoke_test_bwd.sh
* Return result as enum to distinguish failure and missing instance
* Add tests for bwd features: bias, alibi, dropout
* Implement tests from smoke_test_fwd.sh
* Pass seqlen_q/k as vectors to fwd and bwd runners
* Add tests for fwd features: bias, alibi, dropout
* Add tests for pagedkv and splitkv
* Fix conditions when to use splitkv and pagedkv kernels
splitkv was executed only when use_kvcache which == (need_append_kvcache || use_cache_batch_idx || 0 < page_block_size).
In the SplitKV tests: the regular fwd kernel was executed if use_cache_batch_idx was not requested even when num_splitkv > 1.
In the AppendKV tests: the pagedkv kernel was executed but it often failed to find an instance.
* Add tests for appendkv
* Use is_v_rowmajor = true because there are no instances with column layout anymore
* Split public and private compile options for instances
Tests and examples need to know only about CK_TILE_FMHA_FWD_*_API.
* Improve parsing validation in bias and mask
* Pass bias as string for consistency with mask
* Catch parsing and other exceptions
* Add bwd test for deterministic flag
* Initialize fp8 tensors (-init=ufq) similarly to uf
* Fix splitkv/pagedkv invocation: use padded sk when seqlen_k_ptr is not null
seqlen_k cannot be used to determine padding when seqlen_k_ptr is
provided. The actual seqlen_k is taken from seqlen_k_ptr[b].
Even seqlen_k values (% bn0 == 0) use padded seqlen_k while seqlen_k_ptr
may contain arbitrary values.
In the example or tests this produces incorrect results with appendkv
(for example, -d=32 -s=1 -s_k=64 -s_knew=7 -vlayout=c -b=8).
* Fix use_pagedkv value when kvcache = true but page_block_size = 0
In this case block_table_ptr is nullptr which is accessed in the kernel.
* Clean up bwd tests
* Unify fwd tests for f16/bf16 and fp8
* Use better explicit instantiation declaration for fmha_bwd<2>
* Use the same seed for all tests, allow to override it with env variable
* Undo clang-format of one irrelevant file
For some reason my local clang-format-18 and the one in CI work differently.
* Do not build instances and tests on unsupported archs
* Build instance libraries as OBJECT library
* CI: Enable sccache for HIP
There are source files with LANGUAGE HIP, they need
-DCMAKE_HIP_COMPILER_LAUNCHER=sccache
* Add tests to REGRESSION_TESTS
* Fix OOB accesses in deterministic bwd due to incorrectly assumed kN0
The runner assumes kN0 = (hdim_q <= 128) ? 128 : 64 but there are
smaller tiles (for tr_load or fp32). This can create too small dq_acc_buf.
* Pass CK_TILE_FMHA_FWD_*_API as INTERFACE compile options
The instances don't actually depend on them, only examples and tests do.
Passing these definitions as INTERFACE allows to change FMHA_FWD_ENABLE_APIS
without recompiling instances that are already in ccache.
* Fix formatting and names
[ROCm/composable_kernel commit: ec006bb8e0]
BlockWarps, WarpTile in Generic2dBlockShape are wave size dependent, it causes mangled name mismatch between host and device side.
Solution: Replace them with ThreadPerBlock and move BlockWarps, WarpTile calculation into Generic2dBlockShape
[ROCm/composable_kernel commit: c254f3d7b4]
- Add support for tensor A/B in both fp16+pk_int4_t and fp8+pk_int4_t formats
- Implement A(bf8) B(i4) support in universal GEMM
- Use new implementation for i4 to fp8 conversion in Block Scale
[ROCm/composable_kernel commit: 82890192dd]
* Fixed cmake errors related to gemm_bilinear. Previously, if the above flags are set, cmake build fails: GPU_TARGETS="gfx1100;gfx1201" -D DTYPES="fp16;bf16;fp8"
* Fixed cmake build errors related to test_fp8
* Updates to support mixed precision
(cherry picked from commit e65d71180393e7b66169c56565a6bac740427de6)
Co-authored-by: Anca Hamuraru <anca@streamhpc.com>
* Adding support for RRR, F8xF16xF16 gemm_universal_wmma - wip
(cherry picked from commit f8c06322df0abcbd5945a56cdf5bffe56480f9f0)
Co-authored-by: Anca Hamuraru <anca@streamhpc.com>
* Added support for F8xF16xF16 to gemm_wmma_universal
(cherry picked from commit 15c851de6daa513a12c2e3af299bab0176175fb5)
Co-authored-by: Anca Hamuraru <anca@streamhpc.com>
* Added support for F16xF8xF16 to gemm_wmma_universal
* Added support for BF16xI4xBF16 to gemm_wmma_universal
(cherry picked from commit c6a4a69d2d43d59bae8bdabfae80d648646f217e)
Co-authored-by: Anca Hamuraru <anca@streamhpc.com>
* Added support for F16xI4xF16 to gemm_wmma_universal
* Fixed IsSupportedArgument to check ComputeTypeA, ComputeTypeB instead of ADataType, BDataType
* Added missing test class for FP16_KM_NK
* Pre-commit hooks fixes
* Added padding instances for f16xf16xf16
* Fixed cmake errors related to gemm_bilinear. Previously, if the above flags are set, cmake build fails: GPU_TARGETS="gfx1100;gfx1201" -D DTYPES="fp16;bf16;fp8"
(cherry picked from commit 5bdc993dbf)
Co-authored-by: Anca Hamuraru <anca@streamhpc.com>
* Fixed cmake build errors related to test_fp8
(cherry picked from commit 12176616b6)
Co-authored-by: Anca Hamuraru <anca@streamhpc.com>
* Ammending changes for adding support for padding instances for f16xf16xf16
* Fixes for padding instances for f16xf16xf16
* Added padding instances for bf16xbf16, f8xf8
* Added packed instances for bf16xi4xbf16
* Added padding instances for f8xf16xf16
* Added padding instances for f16xf8xf16, f16xi4xf16
* Fixed typos for bf16xbf16xbf16 padding instances
* Fixed typos for padded instances
* Added tests for fp16, KM_KN and KM_NK
* Padding not supported for when BDataType is pk_i4_t. Added fix for correct check and removed padding instances.
* Fixed typos
* Updated the set of tests for FP16
* Updated the set of tests for FP16
* Fix typo
* Moved f16xi4 test under the correct data layout group
* example for gemm_universal_bf16
* Adding examples for gemm_wmma instances
* Added the missing parameters
* Fixed review comments and added executable to cmakeLists
* Fixing clang format
* Fixing build erros
* Fixed compilation failure.
* Modified some code as per gemm_universal_examples
* Fixed the gemm specialization error
* Fixed the build errors.
* Fix strides of a/b_thread_desc
The descriptors are larger than needed (even though the compiler don't alloc registers for unused values).
* Load in M/NRepeat dims with thread copy's slice instead of a loop
* Clone BlockwiseGemmXdlops_pipeline_v1 for WMMA implementation
* Implement Intrawave and Interwave variants of pipeline v1
* Add instances for Interwave and Intrawave v1
* Add instances with ABlockLdsExtraM and BBlockLdsExtraN = 0
* Remove instances that are too slow (mostly because of register spilling)
* Add a workaround for fp8/bf8->f32 packed conversion issue
* Add instances for Interwave and Intrawave v1
* Enable profiling of mixed precision with f8 and int4 on WMMA
* Fix segfault in profiler when B is pk_i4_t
b_device_buf's size in bytes is larger than b_k_n_permute so b_device_buf.ToDevice reads out-of-bounds.
* Remove instances that are too slow (mostly because of register spilling)
* Add missing add_device_gemm_wmma_universal_f8_f8_bf16 declarations
* Add test case for bf16_i4
* Add missing Regular tests
* Add test_gemm_universal_xdl/wmma_fp16 to REGRESSION_TESTS
They take more than 30 seconds
* Fix a bug that fp16_i4 validation passes only with PermuteB
A permutation required by conversion from pk_i4_t to half_t does not
depend on PermuteB, they can be used independently.
* Use PermuteB with f16_i4 in most instances (as xdl)
Some instances use PermuteB = false for checking correctness.
See also the previous commit.
* Fix cache flushing for pk_i4
* Add mixed precision examples
* Disable all tests and instances with f8 on gfx11
Even though f8_f16 and f16_f8 don't require f8 WMMA instructions,
gfx11 still lacks hardware instructions for fast f8->f32 conversion.
* Add FP16 KM_NK and KM_KN test suites for XDL
These tests were added to common .inc for better testing of WMMA instances
* Support multiple D in GridwiseGemm_wmma_cshuffle_v3
DeviceGemm_Wmma_CShuffleV3 is changed for new template parameters.
* Use ThreadGroupTensorSliceTransfer_v7r3
* Clone for device_gemm_wmma_cshuffle_v3.hpp for future Multiple D support
* Clone example/65_gemm_multiply_multiply/gemm_add_add_xdl_fp16.cpp for wmma
* Implement DeviceGemmMultipleD_Wmma_CShuffleV3
* Make gemm_add_add_wmma to work with DeviceGemmMultipleD_Wmma_CShuffleV3
* Prepare gemma_add tests for adding wmma
* Add gemm_add_fastgelu instances and test
* Add a special wrapper to use DeviceGemmMultipleD_Wmma_CShuffleV3 with old API
ckProfiler uses DeviceGemmMultipleD (tests also call its functions), the wrapper allows to use
DeviceGemmMultipleDSplitK instances there.
* removed unnecessary ck parts from compilation
* initial gemm_add_multiply instance implementations
* fixed profiler help message for gemm_add_multiply
* improved multiply_add profiler layout help
* fixed template arguments for test instances
* added test for gemm_add_multiply
* Support multiple D in GridwiseGemm_wmma_cshuffle_v3
DeviceGemm_Wmma_CShuffleV3 is changed for new template parameters.
* Use ThreadGroupTensorSliceTransfer_v7r3
* Clone for device_gemm_wmma_cshuffle_v3.hpp for future Multiple D support
* Clone example/65_gemm_multiply_multiply/gemm_add_add_xdl_fp16.cpp for wmma
* Implement DeviceGemmMultipleD_Wmma_CShuffleV3
* Make gemm_add_add_wmma to work with DeviceGemmMultipleD_Wmma_CShuffleV3
* Prepare gemma_add tests for adding wmma
* Add gemm_add_fastgelu instances and test
* Add a special wrapper to use DeviceGemmMultipleD_Wmma_CShuffleV3 with old API
ckProfiler uses DeviceGemmMultipleD (tests also call its functions), the wrapper allows to use
DeviceGemmMultipleDSplitK instances there.
* switched to splitK interface
* log print added to splitk benchmarks
* revert main cmake comments
* newline change reverted
* added add_fastgelu instances
* revert unintended change in xdl add_fastgelu
* created gemm_add_add_fastgelu instances
* created fastegelu instances
* added tests for all splitk fastgelus
* Added tests.
* multiply_add instances created
* updates to add_multiply splitk instances
* splitk xdl test fixes
* added wmma multiply_multiply instances
* fixed ONLY_XDL_AND_WMMA_KERNELS tag
* Added gemm_add examples for wmma v1 and v3
* fixed / workarounded i8 instances
* Modified the v3 code to added one fp16 bxdl instance.
* added bf16 xdl instance.
* adding gemm_add wmma_cshuffle and other support
(cherry picked from commit ec447e7f564095ea969eddc39ec77b843aa52976)
Co-authored-by: Cenxuan <cenxuan@streamhpc.com>
* add instances into camkelists
(cherry picked from commit 23bf2d2771c939ea3ca7f493433c55255bffd08e)
Co-authored-by: Cenxuan <cenxuan@streamhpc.com>
* This is work in progress, edited the template parameters in order to build
(cherry picked from commit b4fde8a3314cb44659c4bbda35f1a0133c63dc41)
Co-authored-by: Cenxuan <cenxuan@streamhpc.com>
* temp work saved, changed the BDataType to f16 or bf16 since wmma currently not support non-equal A and B datatype
(cherry picked from commit 22fbd68f1db458ab50780a394ee2544c7a1484d1)
Co-authored-by: Cenxuan <cenxuan@streamhpc.com>
* added datatype and use clang-format-12
(cherry picked from commit ae4e853682ef1bb27784b2f965b4a66b3751ceec)
Co-authored-by: Cenxuan <cenxuan@streamhpc.com>
* Fixing build errors
* Added instances for v3
* Adding instances and executables
* Code update of template parameters modified.
* Renamed file.
* Added tests.
* resolved error tests.
* Fixing build errors
* Updated comments
* removed the changes as per the MR review comment.
* Updated tests.
* fp8 instances - not tested
* Restored the Cmake file that was reverted by mistake during rebase.
* fixed wmma_op test
* Updated comments.
* Updated the template parameter description
* fixed rdna4 instances
* fixed back compatibility on gfx11
* cleanups
* fix ckProfiler
* one more cmake fix
* added fp8 instances
* Updated tests to ad BF16 instances as per review comment
* Added include file and cleaned up(as per review comment)
* Updated and optimized the example code for all types.
* Fixed clang format
* Resolve "Implement `device_gemm_bilinear` for RDNA4"
* test generalization to handle FP16 shuffle better
* added missing changes
* Added bf16 wmma instance for add_relu
* Added f16 wmma instance and corrected bf16 instance errors.
* Added instances to Cmake
* Modified the template parameters to make the instances work.
* Fixed typo in profiler
* Added v3 instances for gemm_add_relu
* addressed core review comments
* Added test for gemm_add_relu wmma instance
* Cleaned up the code.
* Added examples for gemm_add_relu
* Fixing typo to resolve build errors.
* Fixes applied to fix the precision loss.
* fix billinear test after merge
* Removed the old wmma instances.
* Added wrapper and renamed the wmma_v3 instances
* Updated copyrights and added wrappers.
* Fixes applied according to review comments
* Apply 1 suggestion(s) to 1 file(s)
Co-authored-by: Robin Voetter <robin@streamhpc.com>
* Removed the old wmma instances.
* Updated wrapper for the v3 instances
* removed the old wmma examples
* Renamed the v3 instances
* Deleted the gtest file added by mistake.
* Updated thge profiler with wrapper
* Fixed test errors.
* Fixed the review comments
* Fixed the if condition MACROS.
* REVERTED THE PROFILER CHANGES
* Revert "REVERTED THE PROFILER CHANGES"
This reverts commit 21cb98546c.
* Revert "Fixed test errors."
This reverts commit 13efcc6fe1.
* Revert "Updated thge profiler with wrapper"
This reverts commit 536f86661d.
* Added missing wrapper instances
* Updated copyrights.
* Fixed typo.
* Fixed copyrights.
* Updated copyrights.
* updated copyrights.
* comments on the atomics workaround
* fixed cmake comment
* Fix bug from merge
* clang-format-18
* Fix compilation error
* Fix linking error
* Fix bug in add and add_relu examples
* Fix error including file (typo)
* Quick fix to compile examples for different targets
* Fix for multi target
* implemented f16 and bf16 instances for gemm_silu
* addressed review comments
* addressed review comments
* Fix clang format
* Fix clang format
---------
Co-authored-by: Anca Hamuraru <anca@streamhpc.com>
Co-authored-by: apoorva <apoorva@streamhpc.com>
Co-authored-by: Anton Gorenko <anton@streamhpc.com>
Co-authored-by: Zoltan Lakatos <zoltan.lakatos@streamhpc.com>
Co-authored-by: Cenxuan <cenxuan@streamhpc.com>
Co-authored-by: Robin Voetter <robin@streamhpc.com>
Co-authored-by: Kiefer van Teutem <kiefer.van.teutem@streamhpc.com>
Co-authored-by: Kevin Abraham <kevin.abraham@streamhpc.com>
Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
[ROCm/composable_kernel commit: b740380906]
* Add cshuffle epilogue test
* add the poc implementation to the epilogue and tests
* refactor cshuffle epilogue
* WIP: adding tensor/tile usage to scale_tile
* fix usage of tile_elementwise_inout
* add gemm_quant_kernel for generalizing gemm quant kernel
* Add problem specific to different quants, add QuantType to Traits
* Add quant_type to quant_kernel template parameters
* Create aq/bq_block_windows and views depending on QuantType
* Use tile windows as inputs in cshuffle epilogue
* Fix some issues in epilogue
* initial new example code for new general gemm quant kernel test
* Fix issues in kernel
* Add verification check for rowcol Quantmode
* use AccDataType instead of AQ in pipeline
* fix aquant preshuffle
* fix formatting
* some cleanup
* remove gemm_aquant_basic.cpp
* remove gemm_aquant_kernel.hpp
* fix tests for the renamed quant kernel
* fix formatting
* clean example files
* fix some merge conflicts
* fix preshufflequant rename issue
* fix some templates after merging with develop
* fix test preshuffle parameter
* fix formatting
* Unify bquant kernel to the common quant kernel
* remove bquant kernel also from common header
* fix formatting
* clean up commented code
* fix formatting config hpp
* fix merge mistake
* Non-const for movable windows
* fix formatting
* Fix grammar in README
Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com>
* Remove #include<bit> and clean up example
* fix strides
* Add some descriptions for move_windows
---------
Co-authored-by: Mohsen Saffari <mohsen.saffari@amd.com>
Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com>
[ROCm/composable_kernel commit: c6010f2953]
* Create new copies of existing device struct and gridwise struct for batched_gemm_softmax_gemm and disable the softmax part. Still based on old wmma pipelines. Also copy the example and remove the softmax part from the reference calculation. Works and results match reference except for tiny float errors in problem 2.
* Turn DeviceBatchedGemmGemm_Wmma_CShuffleV3 into a proper DeviceBatchedGemmGemm derived class, with the right argument and invoker functions. Update example to use new definitions.
* Remove unused cross-attention and self-attention kernels, arguments, and invokers. Also remove other unused Argument types.
* Remove masking related code, test unusual sizes in example.
* Remove remaining softmax related code from GridwiseBatchedGemmGemm_wmma_cshuffle_v3 and example.
* Remove code related to numDims, bias, and TensorSpec from Device struct and example.
* Add layout template parameters to device struct
* Move (NPerBlock, LTilePerBlock) device struct template arguments up by two places to match XDL template argument ordering.
* Merge accumulation data types into one type to match XDL device struct.
* Remove NPerWmma template parameter from device struct and just set it equal to LPerWmma. Now device struct template params exactly match those for XDL batched gemm gemm.
* Add support for RCCR layout and test this in example
* Add batched_gemm_gemm_wmma to instance library + profiler, and add gtest just like for xdl.
* Add RCCR instance and additional RCRR instance to library.
* Remove unused permute and alpha related code. Time all tests. Fix B1 strides in argument verification.
* Remove references to G0, G1 in favor of batch, reduce dimensionality of length and stride arrays.
* Managed to replace old wmma gridwise pipeline and blockwise struct with new wmma blockwise pipeline. Some cleanup required but all tests pass.
* Make TransposeC a proper template parameter that gets passed all the way from BlockGemmPipeline_Selector to WmmaGemm so we can use the correct settings for bacthed gemm gemm as well as regular gemm. Gemm universal tests now pass again.
* Replace old LoopSched and PipelineVer params with BlockwiseGemm pipeline equivalents, and use these in instance factory. The v3 pipeline does not work yet, but v1 works for intrawave and interwave.
* Adapt the A wave descriptor to deal with RDNA4 wmma. This fixes batched gemm gemm functionality on RDNA4.
* Fixed two aspects of the v3 pipeline that were incorrect: First of all the blockwise copy operator was invoked once too many in all cases (RunRead and move window), which broke batched gemm gemm when the blockwise pipeline was used multiple times. Furthermore we should be using the mainloop (hotloop) for num_k_loop >=2 instead of num_k_loop >=3. Now we can use support any K dimension.
* Remove num prefetch parameter from gridwise struct since we don't use it and it doesn't do anything,
* Remove unused non-lds paths.
* Test and update the IsSupportedArgument() and CheckValidity() functions for all layouts + padding modes and various problem sizes.
* Add a lot of instances to the profiler with various blocksizes and pipelines, all verified.
* Add support for BF16: instance library, tests, and examples.
* Add examples for int8 and fp8, had to add type_convert_sp template specializations for the latter.
* Template the library instance lists and add default padding instances.
* Move memory calculations from the kernel to the Argument contructor. Also actually parse and use the user-provided batch strides.
* Actually parse and use user-provided regular strides.
* More refactor: remove references to multiple dims per dims, and g0 / g1. Also move xdl specific test utils out of generic test util header.
* Small post-rebase-on-develop fix due to bscale-related pipeline changes. All tests rerun + tested bscale and regular gemm.
* Introduce the correct GetCThreadDescriptor function in the blockwise gemm pipelines for the TransposeC=true case. It turns out to be identical for our batched gemm gemm (gemm0) usecases, but could theoretically be different for wmma_gemm instances with smaller-than-4-byte output data size.
* Remove unused NumPrefetch template parameter, we don't need to match the XDL template params one-to-one.
* Implement proper TailNum and HasMainLoop template parameters for the v3 pipeline. Now the Run() function knows at compile time whether there are 1, 2, or more loops in total, and adds or removes sections accordingly. It still uses the blockwise copy operators the correct amount of times.
* Add print lambda with env check and file and func to device and gridwise level compatibility error messages. Also respect compatibility in example script.
* RDNA3 does not support fp8
[ROCm/composable_kernel commit: 7330ec37ee]
* Code drop for gtest to test atomic_add for a tensor
* Adding additional test cases
* Fix clang errors in CI pipeline
* Updated test cases
* Fix the Navi card atomic add problem
* solved the define problem
* add more print out traces
* Fix the float4 missing case
* solved the gfx9 errors
* Address the comment
---------
Co-authored-by: Khushbu <khuagarw@amd.com>
Co-authored-by: Thomas Ning <Thomas.Ning@amd.com>
[ROCm/composable_kernel commit: 80ce6a573b]
The performance of Aquant has increased after enabling transposed C.
Do not need to exchange AQ elements among lanes after enabling
transposed C as one thread only holds data from one row.
[ROCm/composable_kernel commit: 428090f749]
* add gemm unit tests for int4, int8 datatypes
* minor changes based on reviews
---------
Co-authored-by: msaffari-amd <msaffari@banff-cyxtera-s78-2.ctr.dcgpu>
[ROCm/composable_kernel commit: b951416cdb]
In #2443, a helper function was added test new print functionality, but it used auto for the function parameter types.
We need to support c++17 for downstream libraries, so we cannot use auto there. This PR replaces it witht the equivalent function template implementation.
[ROCm/composable_kernel commit: 9751583f95]
* [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>
[ROCm/composable_kernel commit: 245467f359]
* Add CSV-driven convolution test pipeline
- Add test_grouped_convnd_fwd_dataset_xdl.cpp with CSV reader functionality
- Add complete dataset generation toolchain in test_data/
- Add Jenkins integration with RUN_CONV_COMPREHENSIVE_DATASET parameter
- Ready for comprehensive convolution testing with scalable datasets
* Update convolution test dataset generation pipeline
* add 2d, 3d dataset csv files
* Remove CSV test dataset files from repository
* Update generate_test_dataset.sh
* Fix channel division for MIOpen to CK conversion
* Remove unnecessary test files
* Fix clang-format-18 formatting issues
* TEST: Enable comprehensive dataset tests by default
* Fix test_data path in Jenkins - build runs from build directory
* Add Python dependencies and debug output for CSV generation
* Remove Python package installation - not needed
* Add better debugging for generate_test_dataset.sh execution
* Fix Jenkinsfile syntax error - escape dollar signs
* Add PyTorch to Docker image for convolution test dataset generation
- Install PyTorch CPU version for lightweight model execution
- Fixes Jenkins CI failures where CSV files were empty due to missing PyTorch
- Model generation scripts require PyTorch to extract convolution parameters
* Add debugging to understand Jenkins directory structure and CSV file status
- Print current working directory
- List CSV files in test_data directory
- Show line counts of CSV files
- Will help diagnose why tests fail in Jenkins
* Fix clang-format-18 formatting issues
- Applied clang-format-18 to test file
- Fixed brace placement and whitespace issues
* Add detailed debugging for CSV dataset investigation
- Check generated_datasets directory contents
- List all CSV files with line counts
- Show first 5 lines of main CSV file
- Applied clang-format-18 formatting
- This will help identify why CSV files are empty in Jenkins
* keep testing add pytorch installation in shell script
* Use virtual environment for PyTorch installation
- Jenkins user doesn't have permission to write to /.local
- Create virtual environment in current directory (./pytorch_venv)
- Install PyTorch in virtual environment to avoid permission issues
- Use PYTHON_CMD variable to run all Python scripts with correct interpreter
- Virtual environment will be reused if it already exists
* Remove debug code and reduce verbose logging in Jenkins
- Remove bash -x and debug commands from Jenkinsfile execute_args
- Remove all debug system() calls and getcwd from C++ test file
- Remove unistd.h include that was only needed for getcwd
- Remove debug print in CSV parser
- Add set +x to generate_test_dataset.sh to disable command echo
- Redirect Python script stdout to /dev/null for cleaner output
This makes Jenkins logs much cleaner while still showing progress messages.
* install gpu torch
* Clean up and optimize comprehensive dataset test pipeline
- Reorder Jenkinsfile execution: build -> generate data -> run test
- Remove commented-out debug code from generate_test_dataset.sh
- Ensure all files end with proper newline character (POSIX compliance)
- Keep useful status messages while removing development debug prints
- Set MAX_ITERATIONS=0 for unlimited test generation in production
* Add configuration modes to reduce test execution time
- Add --mode option (half/full) to generate_model_configs.py
- half mode (default): ~278 configs (224 2D + 54 3D) -> ~1,058 total tests
- full mode: ~807 configs (672 2D + 135 3D) -> ~3,093 total tests
- Update generate_test_dataset.sh to use CONFIG_MODE environment variable
- Keeps all model types but reduces parameter combinations intelligently
- Fixes Jenkins timeout issue (was running 3,669 tests taking 17+ hours)
- Default half mode should complete in ~4-5 hours instead of 17+ hours
* Add small mode for quick testing of comprehensive dataset
* jenkins pipeline test done
* jenkins test done
* Trigger CI build
* remove test comment and update data generation option as half
---------
Co-authored-by: Bartłomiej Kocot <barkocot@amd.com>
[ROCm/composable_kernel commit: 19d5327c45]
