* WIP: host level interwave pipeline compiles
* WIP: interwave implementation computes correct GEMM result when no aquant
* WIP: quantization works for subset of problem shapes
* WIP: quantization works for subset of problem shapes
* WIP: interwave memory pipeline passes local test
* feat: Add interwave pipeline implementation for memory pipline in aquant
* test: add unit test for aquant memory pipeline
* WIP: host level interwave pipeline compiles
* WIP: interwave implementation computes correct GEMM result when no aquant
* WIP: quantization works for subset of problem shapes
* WIP: quantization works for subset of problem shapes
* WIP: interwave memory pipeline passes local test
* feat: Add interwave pipeline implementation for memory pipline in aquant
* fix: compilation error on gfx950
* chore: remove debug statements from the code
* test: resolve merge conflict
* test: remove non rcr unit tests from test suite
* Fix alignment issue in Stream-K workspace buffer
In CK Tile Stream-K, the workspace buffer is used to hold flags and
partials, where the first i bytes holds the flags and the remaining
bytes hold partials. This change adds padding to the flags prefix of the
workspace buffer to ensure the number of bytes is 128B-aligned. Without
this alignment, since workgroups do not skip cache when reading from
partials, they may read stale partials data in cache, leading to
incorrect results. The added padding avoids the stale data reading.
This change also re-enables the test_ck_tile_streamk_reduction tests.
* Compute reference GEMM on GPU for test verification to decrease testing time
* add block scale parameters to kernel
* add block scale to kernel
* add smoke test
* format
* Revert "format"
This reverts commit 356c3c9706.
* only format my code
* format py
* fix auto not allowd in function prototype
* change instance tttt to ttff
* fix structured binding issue
* change s_acc elementwise op
* async pipeline add block scale
* add quantation P using shift exp2
* precompute (m - shift) once per row
* change blk scale seqstrt ptr name
* fix some name
* fix for deduction guide
* fix some comments
* add P scale to qr_ksvs_pipeline
* add comment to idx_identity
* change the method of calculating descale block index
* unify naming style: use block_scale_ as name prefix
* unify naming style
* update the CHANGELOG.md
* Add FP8 block scale quantization support for FMHA forward kernel
---------
Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
Co-authored-by: Po Yen Chen <PoYen.Chen@amd.com>
Add signal-based synchronization for persistent GEMM kernels where
input data becomes available incrementally. Uses modulo wraparound
(like PyTorch's AsyncMM) for chunk index calculation:
chunk_idx = ((tile_idx + tile_idx_pivot) / tiles_per_chunk) % num_chunks
Key components:
- PersistentAsyncInputScheduler struct with tiles_per_chunk_m,
chunk_signals, tile_idx_pivot_m, and num_chunks fields
- wait_eq_wave method using __builtin_amdgcn_s_sleep for power efficiency
- IsSupportedArgument validation for scheduler parameters
- Example demonstrating async input scheduling with simulated producer
- GTest unit tests covering all layout combinations
* Rename member variable to better reflect its actuall meaning.
* Add transfer checks for conv fwd xdl.
* Validate tensor layouts & vector size conv fwd v3.
* Add combined transfer concepts.
* Add transfer concepts for conv fwd factories.
* Fix clang format
* Add helper instruction to get max mem vector instruction width.
* Apply review comments.
* Rename thread cluster access(->arrange) order concept
* FIx merge artifacts.
* Add generic access order limits into block transfer concept.
* formatted
* formatted
* formatting
* formatting
* formatting
* [CK TILE GEMM] Refactor block_scale_gemm examples
- Split cpp file to reduce building time
- Support multiple GemmConfig
* [CK TILE GEMM] Refactor block_scale_gemm examples
- Update Readme
* enable prefill shapes
* [CK TILE GEMM] Refactor block_scale_gemm examples
- Add support for rowcol and tensor GEMM operations
* [CK TILE GEMM] Refactor block_scale_gemm examples
- Update README
* adding preshuffle quant as new parameter and its associated new files
* remove debugging statements
* adding test
* enable preshuffle quant with permuteN
* updating readme and correcponding gemmconfigs
* updating cmake file
* fixing CI failures for grouped quant gemm
* debugging permuteN
* debugging
* debugging PermuteN
* initial commit
* resolving merge conflicts
* adding test cases
* initial commit with prints
* debugging
* fine-grained working
* debugging medium grained
* fixing the tile window
* formatting
* enabling prefill shapes
* working prefill shapes
* formatted
* clean up
* code cleanup
* bug fix after merging with develop
* G128 working for both prefill and decode shapes for preshufflequant
* clean up after merging with develop
* fixing group 64 for decode shapes
* non preshufflequant working for group size 128
* enable preshuffleb and preshufflequant with variour group sizes
* reduce build time by splitting example into diff datatype files
* Adding tests for preshuffleQuant
* address review comment
* fix for gfx1201
* compile time fix for gfx1201
* clang formatted
---------
Co-authored-by: Cong Ma <congma13@amd.com>
Co-authored-by: Thomas Ning <Thomas.Ning@amd.com>
Co-authored-by: Agarwal <khuagarw@ctr2-alola-login-03.amd.com>
* solve compiler issue
* solve the gfx950 mfma shuffle regression
* refactor jenkinsfile to handle arch name better
* [CK TILE] set divisor to count of thread along k dimension
* fix the compiler error
* solve degradation
* Finish the multiplies fix
* fix the scales
* solve compilation error
* solve the composes
* solve the error of tile sweeper
* fix the test and example
* fix for gfx950
---------
Co-authored-by: Max Podkorytov <4273004+tenpercent@users.noreply.github.com>
Co-authored-by: illsilin_amdeng <Illia.Silin@amd.com>
Co-authored-by: Cong Ma <congma13@amd.com>
This commit addresses numerical stability issues in the BlockFmhaPipelineQRKSVS pipeline when bias has -inf masking values:
1. Explicitly handle the case where the accumulated exponential sum (l) is zero. In this case, the LSE is now correctly set to negative infinity, preventing log(0) errors.
2. Extend the zero-check protection in the normalization step to cover the ELEMENTWISE_BIAS case, preventing potential division by zero.
- Enable page_size=1 support in batch prefill codegen (linear layout only).
- Implement per-token page lookup in `kv_offset_array_transform` for page_size=1 to handle 3D input tensors correctly.
- Relax `kPageBlockSize` alignment assertion for the page_size=1 case.
* refactor: remove Default scheduler implementation as it not used anymore
* refactor: remove dead code from gemm universal kernel
* chore: add descriptive comments about amd intrinsic hardware sync instructions
* fix: label existing memory pipeline for aquant as intrawave
* WIP
* Add Unit tests for the Multi Reduction Kernel
* clang format
* Rename multiblock to threadwise
* Multiblock WIP
* Fix multi reduce multi block unit tests
* Multi Reduce Tile Engine: WIP
* refactoring + try addressing precision error
* Fix multiops examples
* Cleanup
* Clean up tile engine's reduce op
* Update changelog
* Fix remod/clang
* Fix dates
* Fix documentation & missing file
* Fix comments
* Use the update_tile api in the multi-block kernel
* Unify threadwise/multiblock into a single kernel + default multiblock output to float in tests
* Add TileParitioner
* Cleanup
* Add warning when no data to process, in the example
* Refactoring Reduce kernel Tile Partioner + cleanup
* Move the tile partioner to its own file
* Add missing includes
* Fix copyright header with update_amd_copyright_headers.py
* Fix change of interface in Reduce2dProblem
---------
Co-authored-by: Damien Lejeune <damien.lejeune@amd.com>
Co-authored-by: Adam Osewski <19374865+aosewski@users.noreply.github.com>
Refactor function amd_buffer_load_invalid_element_return_zero to avoid
the inefficient ASM code generated by compiler.
Compiler generates suboptimal assembly for ternary operator, causing excessive VGPR usage
Tested compilers:
- Rocm 7.0.1
- Rocm 7.1.1
Co-authored-by: Thomas Ning <Thomas.Ning@amd.com>
* update grouped_gemm blockwise kernel
* update config
* update kernel
* update examples
* remove test code for now
* sync test files with origin/develop
* update example
* fix code lint
* fix code-lint
* update test code
* run clang format
* run pre-commit
* update api
* [CK_TILE] unify double and single lds implementation (#108)
Unify LDS buffer management API for single and double buffering modes
This change consolidates the Local Data Store (LDS) buffer management by:
Merging single and double LDS buffer APIs into a unified interface
Implementing ping-pong address calculation in pipeline when double LDS is enabled
Computing pong buffer addresses dynamically using base address offsets
---------
Co-authored-by: joye <joye@amd.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* update wp_pipeline
* fix a c++17 issue
* update for ci errors
* fix ci issues
* include a header to fix ci errors
* fix some rebase issues
* update with rebase
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* add page_block_size parameter
* add is_sglang_layout to parameters
* add kv_offset_array_transform to batch async for page size 16
* add kv_last_page_lens to kernel
* change kv layout to [num_total_pages, page_block_size, hdim]
* format
* - enable codegen of batch_prefill kernels
- create new problem struct BlockFmhaBatchPrefillPipelineProblem for
batch prefill kernels
- generate different page sizes of batch prefill kernels (1, 16)
* 1. fix wrong calculation of page id in kv_offset_array_transform in gfx950
2. support page size 1024
* fix python format
* change kv cache layout to [num_blocks, num_kv_heads, head_size/x,
block_size, x] and [num_blocks, num_kv_heads, block_size/X, head_size, X]
* 1. Introduced `kVectorSize` in BlockFmhaBatchPrefillPipelineProblem instead of using hardcode values
2. Makes batch prefill kernel traits structures inherent from fmha fwd
traits
3. Add some static check for Page size, vector size, hdim, ..., etc.
* [Refactor] Replace is_sglang_layout with Enums for KV cache configuration
Refactored `fmha_batch_prefill` to use `BlockAttentionKVCacheMemoryLayoutEnum` (VECTORIZED/LINEAR) and `BlockAttentionKVCacheLookupTableEnum` (SGLANG_1D/VLLM_2D) instead of a single
boolean.
**Changes:**
* Added Enum definitions in `block_attention_kvcache_layout_enum.hpp`.
* Updated Kernel, Pipeline, and Traits to template on these Enums.
* Implemented `kv_offset_array_transform` logic based on `kKVMemoryLayout`.
* Refactored `PageBlockTableKargs` to adapt to `kKVLookupTable`.
* Updated CodeGen scripts to support new parameters.
This decouples memory layout from the paging mechanism, enabling flexible KV cache configurations.
* 1. remove batch prefill pipeline with sk_pad=false
2. correct some comments
3. add static assert to make sure v offsets is in same page within a tile.
* fix vgpr spill count
* remove unnecessary t2s functions
* add fp8 support for receipt 200 and 600 in fmha_bath_prefill.py
* support linear kv cache layout
* Remove block_table_ptr from fwd_batch_prefill_args. Instead, reuse
kv_page_indices as a pointer of the lookup table.
* 1. merge multiple transforms into single transform.
2. add static check to make sure vlayout is row-major.
* move FmhaFwdCommonKargs::seqlen_k_ptr to VllmPageTableKargs.
* update changelog
---------
Co-authored-by: ltqin <letaoqin@amd.com>
Co-authored-by: PoYen, Chen <PoYen.Chen@amd.com>
* initial poc
* factor out common parts in operator()
* cv4
* rest of the universal gemm pipelines
* fix test
* remove boilerplate from tile engine
* fix example
* fix example
* format
* fix tests build for gemm
* remove base pipeline codegen from gemm instance builder
* unify v3 logic with the rest of universal gemm pipelines
* fix build for multi abd test
* fix test gemm multi d
* fix build for weight preshuffle
* fix grouped gemm test
* fix grouped gemm multi d test
* fix grouped gemm preshuffle
* fix grouped gemm example except for quant
* fix gemm preshuffle
* fix splitk 2 stage example
* fix batched gemm example
* fix multid example
* fix multiabd example
* fix batched gemm test
* fixup
* fix examples build
* fix grouped gemm test build
* fix smoke builder
* hacky poc
* fix tile engine
* kill the lambda
* maybe fix test build
* more fixes
* clang-format
* save temp
* clang-format
* mostly fix examples
* clang-format
* remove dead code
* more cleanup
* fix fmha bwd build (default epilogue set/add appears to be broken)
* fix default epilogue tests but not correctness
* clang-format
* fix bquant
* clang-format
* cleanup dead code
* rearrange make windows for readability
* restore changes to IsSupportedArgument
* fix smoke-builder
* clang-format
* fixup rename class
* build fixes
* clang-format
* fix builder
* fixup
* remove set from builder tests
* fix test
* clang-format
* re-refactor the kernels
* clang-format
* fix header license
* remove memory operation from conv bwd test
* clang-format
* clang-format example,include
* clang-format test
* build fixes
* clang-format
* solve compilation error
* fix the CI
* solve compilation error
* clang format
* solve merge conflict
* solve merge conflict
* solve the gfx11 error
* solve test error
* moar build fixes
* remove AtomicAddRequiresKBatchGreaterThanOne test since the property is removed from the kernel scope
---------
Co-authored-by: Thomas Ning <Thomas.Ning@amd.com>
Previously, the code used unsigned long for literals and format specifiers to represent 64-bit unsigned values. While this worked on Linux, it caused compatibility issues on Windows.
The C++ standard does not guarantee that long is 64 bits. On LP64 systems (e.g., Linux), long maps to 64-bit values, but on LLP64 systems (e.g., Windows), long maps to 32-bit values. This discrepancy led to incorrect behavior when assuming unsigned long was always 64-bit.
This commit updates all relevant literals and format specifiers to explicitly use 64-bit unsigned types, ensuring consistent behavior across platforms.
* feat: add RRR, CRR, CCR layouts for a/b quant grouped gemm tests and examples. Refactor example setup to improve compile time
* chore: split out bquant preshuffle test, and reduce tile size to 128 to temporarily solve slow compile times
* chore: set m/n warp tile to 16 as configurations with 32 seem to have some support problems
* fix: missing check for transposed load in bquant pipeline
* chore: lower unit test tensors dimensions a bit for faster tests
* chore: set grouped gemm example M/N warp tile to 16
---------
Co-authored-by: Thomas Ning <Thomas.Ning@amd.com>
* fix for splitk if splitk < grid
* add different splitk implementation
* minor bugfix for streamk gemm
* Add test
---------
Co-authored-by: Bartlomiej Kocot <barkocot@amd.com>
