Support GEMM on CPU & MetaX and Add Generic Dispatcher #1
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
- Add additional entries to the Device enum class to support new hardware targets. - Adapt GEMM mcblas implementation to use MetaX backend and add the test example. - Extract common BLAS interfaces into a new blas.h abstraction for GEMM implementations to share.
…GEMM implementation - Add `ConstexprMap` and compile-time traits in `common/` for efficient type-to-metadata mapping and relevant operations. - Implement a generic dispatcher to reduce boilerplate for dispatching, especially for data types and devices. - Add the CPU implementation for the GEMM - Update `DataType` definitions and type lists to support wide dispatching. Follow-up: support for fp16 and bf16 kernels is pending.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
TL;DR: This PR primarily extends the support of the GEMM (
gemm) operator to MetaX and adds a generic dispatcher.Key Changes
Multi-platform Support:
mcblasimplementation ofgemmon MetaX along with its example program.gemmand is tested on MetaX.BLAS Abstraction: Abstract a
blas.hwhich contains the common framework for calling the blas library across different platforms (currently CUDA-ish).Generic Dispatcher: Add the generic dispatcher in
src/dispatcher.h, which provides both the core dispatcher and some specialized interfaces/APIs.Codebase Refactoring:
DataType, specifically change it from aclassto aenum classand updates the relevant caller codes.common/directory which contains the common constructs that can be used internally (no expose to the outside), and later it is planned to have device-specific subdirectories.Add a bunch of constructs for compile-time usage, currently they are mainly used by the dispatcher and its caller code.
Known Issues & Future Work:
C++ Standard Compatibility: the dispatcher currently still uses a specific C++20 feature, which is explicit template parameter list for lambdas. For compatiability, a pure C++17 substitute is planned to be developed.
Type Mapping:
float16andbfloat16have NOT been mapped to primitive types yet.