* 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>
* CK Tile Stream-K Tree Reduction
This change adds the first implementation of the Stream-K tree reduction
strategy into CK Tile. The tree reduction reduces the the number of
steps for accumulating results for a tile from O(N) to O(logN) where N
is the number of workgroups contributing to a C tile.
Additionally, in the original non-atomic reduction strategy, atomics
were used to set the flags buffer and to read from the flags buffer.
Howeover, through investigation with the tree reduciton, atomics with
default (relaxed) semantics were not enough to guarantee workgroups
would not read stale data, leading to incorrect results. Stronger
acquire/release memory orderings are too expensive. So, this change
also eliminates the use of atomics for setting the flags. Instead, we
leverage cache modifiers (e.g., GLC) to avoid writing to cache, thereby
avoiding the use of atomics.
Prelimiary tests were also added for the normal reduction and tree
reduction. More will be added in a future PR via tile engine.
* Move Stream-K kernel files to a subdirectory
* Cleanup Code Style & Handle Unsupported Reductions
This change makes the following small changes:
- Add an explicit else block for unimplemented reduction strategies
- Clarify type of sk_flags_ptr via auto*
- Add description for extra_iters_before_me variable
* Run new copyright script on new files
