[mlir][spirv] Lower mapped TOSA custom ops to ExperimentalML.Call (#202581) Extend the TOSA to SPIR-V Graph conversion with an optional custom-op-domain-to-opcode mapping. TOSA custom ops whose domain appears in this mapping are lowered to spirv.ExperimentalML.Call using the mapped CALL opcode. Later mappings for the same domain override earlier ones, matching command-line option precedence. For this TOSA lowering, CALL operands start with a spirv.array<N x i8> carrying the operator_name byte blob. This is followed by another i8 array for implementation_attrs, then the original tensor inputs. Empty strings are encoded as a single NUL byte because SPIR-V array types require at least one element. Use existing SPIR-V array constants for the metadata operands so the target test stays on the SPIR-V binary round-trip path. Signed-off-by: Niklas Lithammer <niklas.lithammer@arm.com> Signed-off-by: Davide Grohmann <davide.grohmann@arm.com> Co-authored-by: Niklas Lithammer <niklas.lithammer@arm.com>
Welcome to the LLVM project!
This repository contains the source code for LLVM, a toolkit for the construction of highly optimized compilers, optimizers, and run-time environments.
The LLVM project has multiple components. The core of the project is itself called “LLVM”. This contains all of the tools, libraries, and header files needed to process intermediate representations and convert them into object files. Tools include an assembler, disassembler, bitcode analyzer, and bitcode optimizer.
C-like languages use the Clang frontend. This component compiles C, C++, Objective-C, and Objective-C++ code into LLVM bitcode -- and from there into object files, using LLVM.
Other components include: the libc++ C++ standard library, the LLD linker, and more.
Consult the Getting Started with LLVM page for information on building and running LLVM.
For information on how to contribute to the LLVM project, please take a look at the Contributing to LLVM guide.
Join the LLVM Discourse forums, Discord chat, LLVM Office Hours or Regular sync-ups.
The LLVM project has adopted a code of conduct for participants to all modes of communication within the project.