* Remove old CK Tile Stream-K implementation
The original CK Stream-K implementation was based on old CK's Stream-K
block to C tile map. However, this implementation did not align with the
original Stream-K paper. Thus, we implemented a new tile partitioner and
associated Stream-K kernel, which was placed in the reboot namespace.
Now that the new Stream-K implementation is ready, this change removes
all artifacts of the old implementation. Specifically, the following
changes were made:
- Removes old Stream-K tile partitioner from CK Tile
- Removes the reboot namespace such that the new implementation resides
in the ck_tile namespace only.
- Adds tests for bf8 and fp8 using the new implementation
- Removes tests for the old implementation
- Remove the v2 suffix from the new CK Tile Tile Partitioner
derived classes.
- Updates Stream-K Kernel ops file to use /** commenting style.
* Remove v2 from tile partitioner validation function names
1. Enable grouped_gemm_quant and gemm_streamk on gfx12
- test_ck_tile_streamk_smoke is kept on gfx9, since it looks someone is still working on it.
2. Update warp tile size in grouped_gemm_quant and gemm_streamk unit test
3. Reduce gemm tile size to pass the build on gfx12 in test_gemm_streamk_reboot_types.hpp
* Wrap ck host utitlies in CK namespace.
The CK and CK-Tile source code bases are incompatible because CK is not properly using namespaces everywhere. In particular, we need to put hip_check_error in the ck namespace.
Move all functions in include/ck_/host_utility that were in global namespace into the ck namespace.
There may be additional namespace problems like this, and it's possible we'll have namespace clashes. But it is good design to properly guard our to code bases (CK and CKTile) so that they can both coexist. Moreover, estabilishing this compatiblity is essential if we are going to allow the builder to instantiate kernels from either template library.
* Add using declarations to test code.
After moving some of the untils into the ck namespace, most examples and a few tests had to be updated to recognize the new namespace declarations. We add using declarations to individual compute units for functions that were previously in the global namespace.
* Add using declarations to client examples.
* Add missing copyright statements
* Use ck_tile::host_tensor_descriptor instead of a custom lambda
* Refactor use of check_data_type in test classes
* Use TEST_SUITE_NAME with TYPED_TEST_SUITE
* Remove an unused namespace
* Make dim3 const
* Add BF8 x BF8 tests for CompV3 in test_gemm_pipeline_kernel_types.hpp
* Add F8 x BF8 tests for CompV3 in test_gemm_pipeline_kernel_types.hpp
* Add BF16 x I4 tests for CompV3 in test_gemm_pipeline_kernel_types.hpp
* Add BF16 x BF16 tests for CompV3 in test_gemm_pipeline_kernel_types.hpp
* Add BF8 x I4 tests for CompV3 in test_gemm_pipeline_kernel_types.hpp
* Add F8 x I4 tests for CompV3 in test_gemm_pipeline_kernel_types.hpp
* Add F16 x I4 tests for CompV3 in test_gemm_pipeline_kernel_types.hpp
* Skip failing tests of F16 x I4 for CompV3 with K == 2 * K_Tile
* Add missing precision type combinations to CompV4 from CompV3
* Move the INT8 tests around for consistency with KernelTypesCompV3Wmma
* Add missing precision type combinations to CompV3Wmma from CompV3
* Remove the basic and universal tests and their dependencies
* On __gfx950__, avoid using transposed loading of A with datatype pk_int4_t of B
* Use ADataType and BDataType instead of ComputeDataType for WarpGemm
* Explicitly set some return types to void
* Use more general typenames in InterleavedPKTypeLoader
* Add load_interleaved_pk_type.hpp to common.hpp
* Use std::is_same_v in load_int4_tile
* Add handling of LoadTranspose to load_int4_tile
* Factor out common code in several places using load_int4_tile
* Add support for pk_int4_t using load_int4_tile
* Fix formatting
* Add gtests for compiler CI for faster testing
* Add changes to have a custom target
* Add a gtest suite for gemm kernel for running CI tests with compiler mode
* Fix Clang error (EOL)
* Removed compiler subfolder from CMake
* Add gtest suite for gemm kernel
* Disable failed tests
* Fix build errors
* Resolved PR comments
* Update shape for persistent gemm kernel test
* Seperated types by H/W archs
* Made changes to persistent types
* Fix persistent build failure issue
---------
Co-authored-by: Thomas Ning <Thomas.Ning@amd.com>
This change replaces pipeline macros like CK_TILE_PIPELINE_COMPUTE_V3,
CK_TILE_PIPELINE_MEMORY, etc in the CK Tile examples with a common enum
called GemmPipeline to reduce code duplication.
* initial commit for testing datatypes, layouts and traits
* correct warp tile size for small datatype config to make a validate instance for fp16, bf16, fp8
* add tile size coverage test
* Cover more tests, parallel instance generation, documentation
* update cmakelist to run more tests
* initial codes to support add test params in json file
* add congurable problem sizes for different tests
* modify README.md
* clean test_gemm_simple code
* correct padding coverage test
* Add comprehensive and quick tile size config files
* remove fp64 from datatypes
* update documents. manage selecting tile_size config (quick or Comprehensive)
* correct padding test problem sizes
* update comprehensive test and correct documents
* Skip GEMM tests with unsupported arguments instead of failing
* change gen_single instead of gen_indivisual because of an issue. add splitk tests to tile_size_quick_config
* clean CMakeList, remod py file
* Refactor test configs: Rename tile_size to coverage, remove separate traits config, clean cmakefile, readme
* update fp32, fp8 to test all layouts, clean documents and comments
* limit fp32 test layouts to rcr because of compilation error on some gpus
* remove fp32 because of the removing from gemm_instance_builder, make quick test smaller, updating comments
* Fix fp8/bf8 test failures on gfx950 by adding OCP FP8 format support
* Reduce quick_coverage test count from ~250 to ~144 for faster CI
* Refactor quant group size to be configurable for M/N/K, not just K
* add some asserts for configurations not implemented
* start setting of group size for N dimension
* enable 2d for reference quant gemm
* WIP: trying to figure out tile dstr and/or indexing for scale matrix
* WIP
* Fix handling of n dim blocks in tile windows etc
* remove commented code and enable all tests again
* fix formatting
* Add more specialized tile distributions
* Enable NWarps replication for bquant tile dstr
* fix formatting
* fix format
* Fix some issues from the merge
* fix formatting
* one more fix to tile dstr, and revert debug initialization
* Remove commented code
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* simplify conditions that are needed for tile distributions
* only enable the working group sizes in tests
* fix formatting
* Update tile distribution for 2D bquant
* add some documentation and 2d block scale example
* fix formatting
* Add in Changlog and restructure the quant 2d example
* fix CMake
* support the change for blockscale 2d
* fix the test file
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Cong Ma <congma13@amd.com>
Co-authored-by: ThomasNing <thomas.ning@amd.com>
* fix: fix bug in print tile window when printing bf8/fp8 tiles
* test(print_tile_window_range): add unit tests to maintain function integrity
* fix: fp8 numerical mismatch error on gfx950 by adding DCK_TILE_USE_OCP_FP8
* add tensorwise quant in grouped gemm
* fix example issue
* update test cases
* format codes
* clang format
* use GTEST_FAIL
* add bquant to grouped_gemm
* add tensorwise quant in grouped gemm
* fix example issue
* update test cases
* format codes
* clang format
* use GTEST_FAIL
* fix a bug in test_grouped_gemm_util
* skip test when use wmma on grouped_quant kernel
* change cmake
* fix a bug in test_grouped_gemm_util
* skip test when use wmma on grouped_quant kernel
* change cmake
* tests(quant_grouped_gemm): add unit tests to cover bquant in grouped_gemm
* Update test/ck_tile/grouped_gemm_quant/test_grouped_gemm_util_quant.hpp
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* Update example/ck_tile/17_grouped_gemm/quant_grouped_gemm.hpp
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* feat: add bf8 support
* chore: remove unnecessary decltype usage
* chore: add default quant_mode to function signature as fallback
* fix: pass correct runtime pipeline params in grouped_gemm bquant kernel
Calculate has_hot_loop, num_loop, and tail_number on device side for each
GEMM problem instead of using default values. This fixes incorrect results
when different problems in the group have different K dimensions.
* chore: set default quant mode in function signature
* test: add additional test cases to cover edge case of no hotloop
* change code based on comments
* WIP: bquant preshuffle b compiles but gives numerical error
* feat(grouped_gemm_quant): bquant with preshuffleB support added to grouped_gemm example & kernel
* refactor: refactor code after merge commit
* chore: remove print statements
* test(grouped_gemm): split test cases by quant mode to reduce compilation time and add bquant-preshuffleB mode test cases
---------
Co-authored-by: kyle-256 <Kyle.Zhao@amd.com>
Co-authored-by: ThomasNing <thomas.ning@amd.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* Summary:
- Refactor epilogue (with CShuffle) to support fused operations:
- EpilogueCShuffleBase holds common parts
- EpilogueCShuffle: runs CShuffle and write out
- EpilogueWelfordCShuffle: holds Welford specific arguments, runs CShuffle, write out, Welford first part and Welford write out
- Extend thread transfer v7r3:
- Support for intermediate data type different from src and dst type
- New functionality to write to dst buffer and keep data (to be able to use them for additional operations)
* Adress review comments
* HasHotLoop is a constexpr
* Remove an unused function
* Remove some unused include statements
* Add implementation and tests for fp8 x bf8 weight preshuffle GEMM
* Add implementation and tests for fp8 x bf8 in CK Tile basic and universal GEMMs
* Remove two barrier calls that HotLoopScheduler already calls
* No need to suppress a variable that hasn't been declared
* Replace six arg_parser arguments with constexpr literals
* Simplify run_gemm_test_prec_type
* The strides don't need to be passed via arg_parser as we use their default values
* The layouts don't need to be passed as arguments twice
* Pass M N and K as regular arguments, not using the argument parser
* We can now remove the argument parser
* Add a common file for precision types to be used in testing
* Convert basic and universal GEMM tests to use gtest
* Make GemmConfig a test parameter, and form test cases as the cartesian product GemmConfigs x PrecTypes
* Add GemmConfigComputeV4 to the GEMM configs to run the universal tests on
* Added a changelog entry
* Add missing copyright statements
* ifndef-define-endif is not needed with pragma once
* Fix a comment
* Add F8 x BF8 tests for CompV4 in test_gemm_pipeline_kernel_types.hpp
* Disable the unreliable test MoeSortingCase4
---------
Co-authored-by: Adam Osewski <19374865+aosewski@users.noreply.github.com>
* Pass hdim to tile_example_fmha_fwd in fp8 tests
* Add WMMA support to fwd FMHA pipelines
* Tune tile sizes a bit for less spilling
fp16 256 is still quite slow
* Fix Q grad tile distribution for warp size = 32 and hdim >= 256
With AccDataType = float and warp size = 32, K0 becomes 0, K repeat is required to correcty distribute the tile.
* Use code based on BlockDropout in BlockDropoutBwd
* Fix split KV combine kernel for gfx12 (warp size 32) and make it more universal
* Fix LSE LDS tensor descriptors: kMaxSplits and kM0 were swapped, it worked on gfx9
because they both equal to 8 while on gfx12 they are 8 and 4;
* Fix Oacc LDS tensor descriptor: it was transposed even though its shape=[4 * kM0, kN1],
it worked on gfx9 because 4 * kM == kN1 == 32;
* Removing these hidden dependecies allows to support:
* any number of warps (power-of-2), not only 4;
* kN1 = 16, not only 32;
* any number of splits;
* Rename ids like o_acc_4 and Oacc4 to eliminate confusion: kNumWarps doesn't have to be 4 now
* Replace hard-coded kN1 in dispatch code with the requested tile size
* Add gfx12-specific tile sizes for split KV
* Pass GPU architecture to kernel generation scripts
This is still a temporary solution.
* Build and run FMHA CI tests for gfx12
* Fix issue after merging
* Fix bwd tile sizes
The current pipelines always read only one tile K and V tile, this
requires bk0 == bhdq and bk2 == bhdv (kK0 == kQKHeaddim and
kK2 == kVHeaddim).
* Use hardware f32->f8 on gfx12, remove v_perm
__builtin_amdgcn_perm is not needed because
__builtin_amdgcn_cvt_pk_fp8_f32 allows to specify which word (16 bit of
32-bit dword) is used to store results (two f8 values).
* Update changelog
* Add WMMA support to pagedkv
* Fix scripts after rebasing
* 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.
* Fix names after cherry-picking
* Fix selection of a fallback tile based on bm0
The assumption that the largest bm0 == 128 is not always true for
current fp32 tiles.
* Do not use filters related to qr_async_trload
They disable tiles/pipelines which are valid for gfx12.
* Use different dstr encoding when C is transposed
* Do not call GetQKBlockGemm (and hence WarpGemmDispatcher) in host code
Some WarpGemmDispatcher instantiations are defined only
for specific archs and undefined on host.
Calculations related to sched barriers are moved from Pipeline's public
fields into pipeline's operator().
* Fix incorrect name WarpGemmMfmaFp8Fp8F32M32N32K16SwizzleBTransposedCDistribution
Correct name is WarpGemmMfmaFp8Fp8F32M32N32K32SwizzleBTransposedCDistribution
because it's 32x32x16 with IterateK = 2 so K = 32, also all tiles used
in codegen scripts are 32, 32, 32.
* Generalize usages of WarpGemmDispatcher for MFMA and WMMA
WarpGemmMfmaFp8Fp8F32M32N32K32SwizzleBTransposedCDistribution is still
used explicitly becaus of swizzle factor = 4.
* Mark has_load_tr as maybe_unused
There are no transpose loading for RDNA.
* Remove CK_TILE_USE_MFMA/WMMA from fmha-related code
* Detect BlockSize on host based on warp size of the current device
If kBlockSize == kNumWarps * get_warp_size(), the kernel is launched with
kBlockSize / 2 because on host get_warp_size() == 64 always.
* Fix calculation of grid size for combine kernel with warp size = 32
* Add missing includes and header
* Support multiple archs in one binary for fwd
* Support multiple archs in one binary for fwd_splitkv, fwd_appendkv, pagedkv_prefill
* Support multiple archs in one binary for bwd
* trload kernels are compiled only for gfx950;
* instances with padding are checked after instances without padding so
they can be used as fallbacks (similarly to fwd);
* Extract common code from register_traits
* Revert "Fix regression with philox seed and offset when they exceed 32-bit int"
To simplify merging , the proper fix is in develop already.
* Support new numerical d paddings in trait ordering checks
* Build fp32 tests only on gfx9
* Do not use hardcoded M0 = 64 for dot bwd kernel
* Use textwrap.indent from standard library
* Make fp8 pipelines on gfx12 consistent with gfx9
* Update tests for current pipelines
* Make ninja check more responsive in CI
ninja buffers output so this job looks hanging.
* Support fp8fp32 by limiting O vector size
The fp32 output type requires storing 8 * sizeof(float) = 32 bytes,
which is not implemented (here 8 is the number of C values per lane for
v_wmma_f32_16x16x16...).
* Remove unused cmake options
* Unify including amd_buffer_addressing.hpp/_builtins.hpp
* Temporarily use amd_buffer_addressing.hpp on >=gfx10
amd_buffer_addressing_builtins.hpp uses inline asm for loads/stores
which is not compatible with >=gfx10:
* 1 scalar for exec masks instead of 2,
* gfx12 uses different instruction names etc.
* Update asm in bf16 conversions to work with warp 32
* Do not generate splitkv/appendkv with vlayout=col for consistency with fwd
* Add arch tags to kernels/host funcs, compile for each arch separately
* Add kM0 to fmha_bwd_dot_do_o kernel name to match filename
* Add workaround for miscompilation of bwd with padded hdim
SWDEV-559729: v_wmma instructions can be incorrectly placed in divergent
branches used to store padded tensors (when some lanes are inactive due
to padding). Inline asm with dummy dependencies on VGPRs of the tensors
prevents the compiler doing this.
* Fix add_gtest_executable for absolute paths
Some tests (like gemm_tile_engine) pass absolute paths to source files.
In CI the branch name is a part of the root dir, and if the branch name
contains "wmma", "xdl" etc., files can be incorrectly excluded.
* Run only hdim 128 smoke tests for fp8fp32
There are no instances for hdim 64 and 256.
* Format py with ruff to simplify merging develop
* Fix incorrect var name
* Codegen for gfx9,gfx950 when --targets is not specified
Aiter and Pytorch require changes for passing their targets to the codegen scripts.
With this temporary solution the files are generated but not all of them
have to be really built (depending on the used --offload-arch=).
* Combine arch-related values into ArchTrait
This more centralized approach removes duplication of various formatting templates.
* Try a workaround for Jenkins error "groovyjarjarasm.asm.MethodTooLargeException: Method too large"
Some code is extracted into a function.
* Add indexing support to pooling operator
- Add IndexDataType template parameter to pooling problem and kernel
definitions
- Enable pooling kernel to output indices of selected elements during
max/absmax pooling
- Add overloaded operators for Max and AbsMax that track when values
change using bool changed parameter
- Support optional index buffer allocation and management in device
memory
- Modify BlockReduce2d classes to handle index tensors alongside value
tensors
- Add separate shared memory allocation for index data in cross-warp
reductions
- Create validate_pool_indices function to verify index correctness
- Modify pool3d.cpp example to demonstrate index output functionality
- Add tests for index output
* fixes
* Refactor BlockReduce2D functions to get rid auxiliary private types.
* comment resolutions and some changes to block_reduce2d
- index reference implementation improved
- reduce_operator.hpp cleanedup
- updated the block_reduce2d.hpp to have index calculation for
BlockReduce2dLinearCrossWarpSync as well
* conditionally used variable declaration improvement
- the conditionally used vairbales are used only when indexing is
enabled. To inform the compiler that they may be unused and declare them
with least size possible. This may allow it to be optimized compared to
the previous declarations
* comment resolutions
* lexical ordering of the indicies
- introduced accumulate methods that handle the intermediate steps if
needed to order the indexes
* add reduce_operator_accumulate.hpp to core.hpp
---------
Co-authored-by: Adam Osewski <Adam.Osewski@amd.com>
* [CK_TILE] fmha: Add query padding support to backward pass
Introduces support for query sequence padding (q_padding) in the FMHA backward pass kernels.
- Passing `seqlen_q_ptr` to the backward kernels to distinguish logical from physical sequence lengths.
- Updating `OGradDotO`, `ConvertQGrad`, and `DQDKDV` kernels to respect logical lengths and handle zero-length sequences.
- Aligning LSE indexing in the forward kernel with the padded layout for consistency.
- Adding a new GTest suite (`test_fmha_bwd_kernel_padding.cpp`) with comprehensive tests for various padding scenarios, including zero-length
sequences and deterministic mode.
* fix clang format
* Adapt fmha_bwd_runner.cpp to new q, kv sequence padding
Add backward q/kv sequence padding unit tests.
* [CK_TILE] fmha: Unify sequence length and padding handling
Refactor the handling of sequence lengths and padding in the
FMHA forward and backward kernels to provide a more unified and flexible
interface.
- Replaced `seqstart_padded_*_ptr` with a more robust system that uses
`seqstart_*_ptr` for physical sequence lengths and introduces
`seqlen_*_ptr` and `cu_seqlen_*_ptr` for logical (unpadded) lengths.
- Established a clear order of precedence for determining sequence
length: cumulative lengths (`cu_seqlen_*_ptr`) take priority,
followed by per-sequence lengths (`seqlen_*_ptr`), and finally
physical lengths derived from `seqstart_*_ptr`.
- Clarified the distinction between "group mode" and "batch mode" and
how sequence lengths are handled in each case.
- Renamed `cu_seqlen_kv_ptr` to `cu_seqlen_k_ptr` for consistency.
- Updated comments and documentation to reflect the new argument
structure and usage.
---------
Co-authored-by: illsilin_amdeng <Illia.Silin@amd.com>
* update test cases
* format codes
* use GTEST_FAIL
* add bquant to grouped_gemm
* fix a bug in test_grouped_gemm_util
* skip test when use wmma on grouped_quant kernel
* add tensorwise quant in grouped gemm
* fix example issue
* update test cases
* format codes
* fix a bug in test_grouped_gemm_util
* tests(quant_grouped_gemm): add unit tests to cover bquant in grouped_gemm
* Update test/ck_tile/grouped_gemm_quant/test_grouped_gemm_util_quant.hpp
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* Update example/ck_tile/17_grouped_gemm/quant_grouped_gemm.hpp
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* feat: add bf8 support
* chore: remove unnecessary decltype usage
* chore: add default quant_mode to function signature as fallback
* fix: pass correct runtime pipeline params in grouped_gemm bquant kernel
Calculate has_hot_loop, num_loop, and tail_number on device side for each
GEMM problem instead of using default values. This fixes incorrect results
when different problems in the group have different K dimensions.
* chore: set default quant mode in function signature
* test: add additional test cases to cover edge case of no hotloop
* chore: clang formatting
---------
Co-authored-by: kyle-256 <Kyle.Zhao@amd.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* Addition of streamk fp8 example for CK Tile
* Adding in bf8 streamk example in CK Tile
* Refactoring fp8/bf8 unit tests
Refactored the unit tests for fp8/bf8 to utilize the test harness.
Implemented smoke tests with layouts: CCR, CRR, RCR, RRR for fp8/bf8.
The tests are using 128x128x32 for the tile configuration, as other
configurations revealed implementation gaps that are currently being
documented.
* Implement argument passing to element-wise functions for fwd convolution
* Add files for fwd + bias + clamp example
* Implement Bias
* Implement Clamp
* Elementwise function composition
* Composition unit test
* Implement fwd + bias + clamp example
* Simplify argument passing and composition
* elfunc -> bias_and_clamp
* Rename function to specify example
* Move element-wise function instantiation to kernel
* Make bias a runtime tensor
* No ugly namespace aliasing
* Initialize element-wise function on host
* Remove function initialization helper, simplify Compose initialization
* Remove unintended LSP compatibility patch
* Clean up includes and unused code
* Switch names in cshuffle epilogue
* Move CDElementwise to conv traits
* Re-add required include
* Initialize bias in same way as other tensors
* Better type specification for ds pointer
* Disable 1D convolution
* Add warning for non-group-constant bias
* Persistent Stream-K Kernel Implementation
This change implements an operator() function in the
reboot::StreamKKernel class that is enabled when the Persistent flag is
set to true. In this case, the data-parallel portion and the Stream-K
portion of the kernel are fully persistent.
The changes were made in the reboot namespace. A future PR will remove
the old Stream-K kernel class and remove the reboot namespace.
* Unit Tests for Persistent Stream-K Kernel
This change contains the inital test suite for the Persitent Stream-K
Kernel. The files contain "reboot" in the name; a future PR will remove
tests for the old Stream-K Kernel and remove the "reboot" naming.
A future commit will add tests for the non-persistent kernel.
Also added estimate_num_wgs_per_tile to the StreamKTilePartitionerBase
class. This allows us to estimate the number of accumulations done per
macro tile in C to use during validation when computing relative and
absolute tolerance.
* Adding implementation for the Non-Persistent Stream-K kernel
This code is adding the operator() function for the Non-Persistent Stream-K
kernel. Persistency of the kernel is determined through a template argument.
The Non-Persistent kernel will allocate additional workgroups for the data
parallel section, leading to a different structure for processing the data
parallel and Stream-K sections.
There has been an addition to the TilePartitioner to get access to the whether
Persistent has been set to true or false in the StreamKKernel.
* Adding in the tests for the Non-Persistent Stream-K kernel
* Refactor Stream-K Reboot Unit Tests
This commit makes the following changes:
- Update test cases to determine M, N, and K based on the number of CUs.
This ensures that each test case is one of Edge Case, SK Only, DP
Only, or DP + 2 Tile SK regardless of the architecture.
- Since the DP + 2 Tile SK test case takes long to run, this change
moves this case into a separate .inc file and labels it as an extended
test.
- Since the extended test takes > 30 seconds to run, this test is added
to the list of regression tests.
* Fix spelling errors in comments for test cases
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* Changes based on review
Removed const volatile for typenames
Set up alias for is_tuple_t
Naming changes for clarity: GemmCommon -> BaseGemm
Moved std::enable_if_t out of template parameters and changed to a return type for operator()
Added constructor for StreamKKernelArgs to clarify UniversalGemm inheritance
---------
Co-authored-by: Emily Martins <emily.martins@amd.com>
Co-authored-by: Christopher Millette <63608002+cgmillette@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* add tensorwise quant in grouped gemm
* fix example issue
* update test cases
* format codes
* clang format
* use GTEST_FAIL
* fix a bug in test_grouped_gemm_util
* skip test when use wmma on grouped_quant kernel
* change cmake
* change code based on comments
---------
Co-authored-by: ThomasNing <thomas.ning@amd.com>
fix transpose_vectors logic for 2x2 8-bit tiles
add a test which goes through this code path.
factor out constexpr'd cases into smaller functions.
add inline docs about the data movement
impact: gemms with 8-bit non-rcr inputs on gfx942
* Reading gpuname from target for gemm in ck tile engine
* Reading gpuname from target for gemm preshuffle in ck tile engine
* Reading gpuname from target for gemm preshuffle in ck tile engine
* Get GPU changes for GEMM Muti D in TILE ENGINE
* Addressing errors for gpu name in cktileengine
Prior to this change, the number of accumulations passed into
calculate_rtol_atol was 1. That said, in most cases, this is not correct
when there are multiple workgroups contributing to the same macro tile
in C.
This change ensures uses the function estimate_num_wgs_per_tile, which
was extracted into a common file and generalized, to estimate the number
of workgroups per macro tile. This estimate is passed into
calculate_rtol_atol to ensure we get a better relative and absolute
tolerance.
* rebased on top of develop
* fixed missing shuffeling and wrong indexing
* added tests for batched_b_scale
* added missing files
* fixed wrong stride computation and removed k batching (for now) due to precision issues
* reinstated k-batching with PRNG constrained to -1..1
* added specialization of GeneratorTensor_3 for int4 and fixed internal overflow
* added k-batching to reference and increased tolerances for test
* changed gemm_b_scale and gemm_universal tests to use correct parameters
* adressed review commentsd
* ported fixes back to non-batched version of b_scale
* adressed review comments
* run clang-format on older commits
* add type-conversion to AccDataType and then to CDataType to exactly mimic GPU's behavior
* added newline at end of file
* reflected changes from muitl-abd branch in batched b_scale
* fixed gfx11 issue
* changed range for pki4 to -1...1 (-0.5...0.5 never really made sense for i4 anyway and always should have caused compiler errors, but since there was no int4 specialization of GeneratorTensor3 until now, this passed
* run clang format
* set range of i4 generation to 0...1 for upstream tests to pass. This replicated previous behavior, which however means that it is NOT properly tested.
* reduced range for pk_i4 even further to 0..0
* removed failing xld instances. Failure now uncovered now that tests were fixed
* removed generation of int4 values entierly
* divide B buffer by BPackedSize
---------
Co-authored-by: Kevin Abraham <kevin.abraham@streamhpc.com>
The following changes were made
- Renamed iter to iter_start
- Renamed tile_iter to tile_iter_start
- Moved documentation from member variables to getters
- Removed double underscore from extra_iters_before_me variable
- Defined parent header in impl file
- Removed unused inlcudes
There are 2 derived structs based on whether Stream-K is persistent or not.
If it's persistent that means that both the data parallel and Stream-K sections
are data parallel. If it's non-persistent that means that only the
Stream-K section is persistent, while the data parallel section will have
separate workgroups allocated for it. Both structs will have a template
argument for Persistent.
The 2 derived classes will inherit common variables and functions from the
Stream-K TilePartitioner base class. There are additional variables for the
differing data parallel sections that will be added to each derived class,
that are in charge of the indexing/bookkeeping for the data parallel sections.
The only additional function that will differ between the 2 structs is GridSize(),
as the non-persistent will allocate extra workgroups for data parallel.
Unit tests for the derived structs are included.
To better align with the original Stream-K paper, this change implements
a new Stream-K tile partitioner base class. This class will handle the
Stream-K setup that is common to both a persistent and non-persistent DP
section. A later change will implement derived classes to handle the
differences between persistent and non-persistent DP.
This change also includes unit tests for the base tile partitioner.
