Calling taichi's zero_field function with default trace size causes Vulkan kernel error

[deehrlic]

Doing testing on the 3D notebooks with a Vulkan/AMD GPU

When using the 3D notebooks and attempting to run a block calling zero_field from taichi with MAX_TRACE_RESOLUTION of 512, taichi spits out this error:

RuntimeError Traceback (most recent call last)
Cell In[24], line 1
----> 1 zero_field(deposit_field)
2 zero_field(trace_field)
3 zero_field(vis_field)

File D:\Anaconda\envs\polyphy\lib\site-packages\taichi\lang\kernel_impl.py:1023, in _kernel_impl..wrapped(*args, **kwargs)
1020 @functools.wraps(_func)
1021 def wrapped(*args, **kwargs):
1022 try:
-> 1023 return primal(*args, **kwargs)
1024 except (TaichiCompilationError, TaichiRuntimeError) as e:
1025 raise type(e)('\n' + str(e)) from None

File D:\Anaconda\envs\polyphy\lib\site-packages\taichi\lang\shell.py:27, in _shell_pop_print..new_call(*args, **kwargs)
25 @functools.wraps(old_call)
26 def new_call(*args, **kwargs):
---> 27 ret = old_call(*args, **kwargs)
28 # print's in kernel won't take effect until ti.sync(), discussion:
29 # taichi-dev/taichi#1303 (comment)
30 print(_ti_core.pop_python_print_buffer(), end='')

File D:\Anaconda\envs\polyphy\lib\site-packages\taichi\lang\kernel_impl.py:950, in Kernel.call(self, *args, **kwargs)
948 impl.current_cfg().opt_level = 1
949 key = self.ensure_compiled(*args)
--> 950 return self.runtime.compiled_functionskey

File D:\Anaconda\envs\polyphy\lib\site-packages\taichi\lang\kernel_impl.py:853, in Kernel.get_function_body..func__(*args)
851 except Exception as e:
852 e = handle_exception_from_cpp(e)
--> 853 raise e from None
855 ret = None
856 ret_dt = self.return_type

File D:\Anaconda\envs\polyphy\lib\site-packages\taichi\lang\kernel_impl.py:850, in Kernel.get_function_body..func__(*args)
845 raise TaichiRuntimeError(
846 f"The number of elements in kernel arguments is too big! Do not exceed 64 on {_ti_core.arch_name(impl.current_cfg().arch)} backend."
847 )
849 try:
--> 850 t_kernel(launch_ctx)
851 except Exception as e:
852 e = handle_exception_from_cpp(e)

RuntimeError: [runtime.cpp:taichi::lang::gfx::GfxRuntime::launch_kernel@576] Dispatch error : RhiResult(-3)

---

Setting the max trace value to 256 fixes this, but is not a long term fix

taichi-dev/taichi#7674 might be related

[OskarElek]

Needs re-testing. Taichi has made significant progress on the backend interoperability since so this might already be a non-issue.

[deehrlic]

I'm not using a Vulkan GPU anymore, so I'm not in a position to test this myself anymore without Frankensteining my pc :(