This commit is a further incremental step toward moving the whole
mlir-vulkan-runner MLIR pass pipeline into mlir-opt (see #73457). The
previous step was b225b3adf7b78387c9fcb97a3ff0e0a1e26eafe2, which moved
all device passes prior to SPIR-V serialization into a new mlir-opt test
pass, `-test-vulkan-runner-pipeline`.
This commit changes how SPIR-V serialization is accomplished for Vulkan
runner tests. Until now, this was done by the Vulkan-specific
ConvertGpuLaunchFuncToVulkanLaunchFunc pass. With this commit, this
responsibility is removed from that pass, and is instead done with the
existing generic GpuModuleToBinaryPass. In addition, the SPIR-V
serialization step is no longer done inside mlir-vulkan-runner, but
rather inside mlir-opt (in the `-test-vulkan-runner-pipeline` pass).
Both of these changes represent a greater alignment between
mlir-vulkan-runner and the other GPU integration tests. Notably, the IR
shapes produced by the mlir-opt pipelines for the Vulkan and SYCL
runners are now much more similar, with both using a gpu.binary op for
the serialized SPIR-V kernel.
In order to enable this, this commit includes these supporting changes:
- ConvertToSPIRVPass is enhanced to support producing the IR shape where
a spirv.module is nested inside a gpu.module, since this is what
GpuModuleToBinaryPass expects.
- ConvertGPULaunchFuncToVulkanLaunchFunc is changed to remove its SPIR-V
serialization functionality, and instead now extracts the SPIR-V from a
gpu.binary operation (as produced by ConvertToSPIRVPass).
- `-test-vulkan-runner-pipeline` now attaches SPIR-V target information
required by GpuModuleToBinaryPass.
- The WebGPU pass option, which had been removed from mlir-vulkan-runner
in the previous commit in this series, is restored as an option to
`-test-vulkan-runner-pipeline` instead, so that the WebGPU pass
continues being inserted into the pipeline just before SPIR-V
serialization.
This commit marks the type converter in `populate...` functions as
`const`. This is useful for debugging.
Patterns already take a `const` type converter. However, some
`populate...` functions do not only add new patterns, but also add
additional type conversion rules. That makes it difficult to find the
place where a type conversion was added in the code base. With this
change, all `populate...` functions that only populate pattern now have
a `const` type converter. Programmers can then conclude from the
function signature that these functions do not register any new type
conversion rules.
Also some minor cleanups around the 1:N dialect conversion
infrastructure, which did not always pass the type converter as a
`const` object internally.
**Description**
This PR adds a new option for `convert-to-spirv` pass to clone and
convert only GPU kernel modules for integration testing. The reason for
using pass options instead of two separate passes is that they both
consist of `memref` types conversion and individual dialect patterns,
except they run on different scopes. The PR also replaces the
`gpu-to-spirv` pass with the `convert-to-spirv` pass (with the new
option) in `mlir-vulkan-runner`.
**Future Plan**
Use nesting pass pipelines in `mlir-vulkan-runner` instead of adding
this option.
---------
Co-authored-by: Jakub Kuderski <kubakuderski@gmail.com>
This PR adds conversion patterns for GPU to the `convert-to-spirv` pass,
introduced in #95942. Now the pass is able to convert each `gpu.module`
and its ops within a `builtin.module` into a `spirv.module`.
**Future Plans**
- Use `gpu.launch_func` to invoke kernel from host functions
- Potentially integrate into the `mlir-vulkan-runner` for e2e testing
This PR adds conversion patterns for MemRef to the `convert-to-spirv`
pass, introduced in #95942. Conversions from MemRef memory space to
SPIR-V storage class were also included, and would run before the final
dialect conversion phase.
**Future Plans**
- Add tests for ops other than `memref.load` and `memref.store`
---------
Co-authored-by: Jakub Kuderski <kubakuderski@gmail.com>
### Description
This PR builds on #99872. It implements a minimal version of function
body vector unrolling to convert vector types into 1D and with a size
supported by SPIR-V (2, 3 or 4 depending on the original dimension). The
ops that are currently supported include those with elementwise traits
(e.g. `arith.addi`), `vector.reduction` and `vector.transpose`. This PR
also includes new LIT tests that only check for vector unrolling.
### Future Plans
- Support more ops
---------
Co-authored-by: Jakub Kuderski <kubakuderski@gmail.com>
### Description
This PR implements a minimal version of function signature conversion to
unroll vectors into 1D and with a size supported by SPIR-V (2, 3 or 4
depending on the original dimension). This PR also includes new unit
tests that only check for function signature conversion.
### Future Plans
- Check for capabilities that support vectors of size 8 or 16.
- Set up `OneToNTypeConversion` and `DialectConversion` to replace the
current implementation that uses `GreedyPatternRewriteDriver`.
- Introduce other vector unrolling patterns to cancel out the
`vector.insert_strided_slice` and `vector.extract_strided_slice` ops and
fully legalize the vector types in the function body.
- Handle `func::CallOp` and declarations.
- Restructure the code in `SPIRVConversion.cpp`.
- Create test passes for testing sets of patterns in isolation.
- Optimize the way original shape is splitted into target shapes, e.g.
`vector<5xi32>` can be splitted into `vector<4xi32>` and
`vector<1xi32>`.
---------
Co-authored-by: Jakub Kuderski <kubakuderski@gmail.com>
This PR relands #95942, which was reverted in #96332 due to link
failures. It fixes the issue by updating CMake dependencies. The bazel
support, originally introduced in #96334, is also included in this PR.
---------
Co-authored-by: Keith Smiley <keithbsmiley@gmail.com>
This PR implements a MVP version of an MLIR lowering pipeline to SPIR-V.
The goal of adding this pipeline 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`. New test cases for the pass are also included in this PR.
**Relevant links**
- [Open MLIR Meeting - YouTube
Video](https://www.youtube.com/watch?v=csWPOQfgLMo)
- [Discussion on LLVM
Forum](https://discourse.llvm.org/t/open-mlir-meeting-12-14-2023-discussion-on-improving-handling-of-unit-dimensions-in-the-vector-dialect/75683)
**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 unsupported sizes.
- Implement multiple-return. SPIR-V does not support multiple return
values since a `spirv.func` can only return zero or one values. It might
be possible to wrap the return values in a `spirv.struct`.
- Add a conversion for `scf.parallel`.
