- [mlir][spirv] Update dependencies for #100138
- [mlir][spirv] Support vector.step in vector to spirv conversion
- Address comments
- Build dependencies
- CI jobs
- Add a one workgroup argmax benchmark
- Address comments
- [mlir][spirv] Add tests for scf.while and scf.for in convert-to-spirv pass
- Address comments
Angel Zhang angelz913
angelz913
/ convert-to-spirv-v0.md
Last active
June 18, 2024 15:11
This PR implements a MVP version of an MLIR lowering pipeline to SPIR-V. The goal is to have a better test coverage of SPIR-V compilation upstream and enable writing simple kernels by hand. The dialects supported in this version include arith, vector (only 1-D vectors with size 2,3,4,8 or 16), scf, ub, index, func and math.
Relevant links:
Future plans:
- Add conversion patterns for other dialects, e.g.
gpu,tensor, etc. - Include vector transformation to unroll vectors to 1-D, and handle those with illegal sizes.
- Implement multiple-return. SPIR-V does not support multiple return values since a
spirv.funccan only return zero or one values. It might be possible to wrap the return values in aspirv.struct.
angelz913
/ convert-to-spirv.md
Last active
June 11, 2024 20:28
- Created new pass
- Moved most of the parts from IREE's
ConvertToSPIRVPass
angelz913
/ commands.md
Last active
June 6, 2024 14:34
angelz913
/ vector-reshapes.md
Last active
June 3, 2024 14:58
Upstream unrolling patterns + canonicalization
- Vectorizing
tensor.pad- Apply vectorization to generate vectors of the original tensor shape for
tensor.padops. - https://github.com/iree-org/iree/blob/main/compiler/src/iree/compiler/Codegen/SPIRV/SPIRVInitialVectorLowering.cpp#L306
- Apply vectorization to generate vectors of the original tensor shape for
angelz913
/ mlir-to-spirv-ideas.md
Last active
June 6, 2024 14:36
- A generic pass to convert to LLVM, using the
ConvertToLLVMPatternInterfaceto delegate to dialects the injection of conversion patterns