This is a follow-up of #117246.
I thought then it would be easy to edit a DictionaryAttr but it turns
out that these attributes are immutable and need to be passed during the
construction of the gpu.binary Op.
The first commit was using the NVVMTargetAttr to pass the information.
After feedback from @fabianmcg, this PR now passes the information
through a new option of the gpu-module-to-binary pass.
Please add reviewers, as you see fit.
Here is the [merged
MR](https://github.com/llvm/llvm-project/pull/116007) which caused a
failure and [was
reverted](https://github.com/llvm/llvm-project/pull/116811).
Thanks to @joker-eph for the help, I fix it (miss constructing
`ModuleObject` with callback functions in
`mlir/lib/Target/LLVM/NVVM/Target.cpp`) and split unit tests from origin
test which don't need `ptxas` to make the test runs more widely.
Fix docs modified by #94910 by adding information about the `module`
argument in `gpu::TargetAttrInterface::createObject`.
---------
Co-authored-by: Mehdi Amini <joker.eph@gmail.com>
This patch adds the `#gpu.kernel_metadata` and `#gpu.kernel_table`
attributes. The `#gpu.kernel_metadata` attribute allows storing metadata
related to a compiled kernel, for example, the number of scalar
registers used by the kernel. The attribute only has 2 required
parameters, the name and function type. It also has 2 optional
parameters, the arguments attributes and generic dictionary for storing
all other metadata.
The `#gpu.kernel_table` stores a table of `#gpu.kernel_metadata`,
mapping the name of the kernel to the metadata.
Finally, the function `ROCDL::getAMDHSAKernelsELFMetadata` was added to
collect ELF metadata from a binary, and to test the class methods in
both attributes.
Example:
```mlir
gpu.binary @binary [#gpu.object<#rocdl.target<chip = "gfx900">, kernels = #gpu.kernel_table<[
#gpu.kernel_metadata<"kernel0", (i32) -> (), metadata = {sgpr_count = 255}>,
#gpu.kernel_metadata<"kernel1", (i32, f32) -> (), arg_attrs = [{llvm.read_only}, {}]>
]> , bin = "BLOB">]
```
The motivation behind these attributes is to provide useful information
for things like tunning.
---------
Co-authored-by: Mehdi Amini <joker.eph@gmail.com>
This patch adds an argument to `gpu::TargetAttrInterface::createObject`
to pass the GPU module. This is useful as `gpu::ObjectAttr` contains a
property dict for metadata, hence the module can be used for extracting
things like the symbol table and adding it to the property dict.
---------
Co-authored-by: Oleksandr "Alex" Zinenko <ftynse@gmail.com>
The test is meant to execute on the native target and only initializes
the native target. However, it then gets the default target triple
instead of the process (host) triple. This fails in cases where the
native target and the default target are not the same.
The test was added here: https://reviews.llvm.org/D154100
**For an explanation of these patches see D154153.**
Commit message:
This patch adds the utility base class `ModuleToObject`. This class provides an
interface for compiling module operations into binary strings, by default this
class serialize modules to LLVM bitcode.
Reviewed By: mehdi_amini
Differential Revision: https://reviews.llvm.org/D154100
**For an explanation of these patches see D154153.**
Commit message:
This patch adds the utility base class `ModuleToObject`. This class provides an
interface for compiling module operations into binary strings, by default this
class serialize modules to LLVM bitcode.
Reviewed By: mehdi_amini
Differential Revision: https://reviews.llvm.org/D154100
