Fundamental GPU Support

This MR introduces the fundamentals of GPU support to the new backend

General

• Introduce GenericGpu platform and threads range export: GPU platforms communicate the kernel's required thread grid size to the outside via a GpuThreadsRange object separate from the AST
• Add configuration options relating to GPUs

CUDA Platform

• Introduce CUDA platform
• Add materialization + guards for full and sparse iteration spaces
• Add materialization of math functions

SYCL Platform

• Introduce SYCL platform
• Add materialization + guards for full and sparse iteration spaces
• Add materialization of math functions

CUDA Just-In-Time Compiler

• Migrate implementation of cupy-based JIT to new backend as an object-oriented structure

Deviations and Missing Features

In the new implementation, block size selection is entirely up to the JIT / the runtime system and no longer affects the backend. Adaptive block sizes, register restrictions, etc. are not yet implemented by this MR.

tests/nbackend/kernelcreation/platform/test_gpu_platforms.py

-#%%
 import pytest
 
 from pystencils.field import Field
@@ -8,9 +7,7 @@ from pystencils.backend.kernelcreation import (
     FullIterationSpace
 )
 
-from pystencils.backend.ast.structural import PsBlock, PsLoop, PsComment
-from pystencils.backend.ast.expressions import PsExpression
-from pystencils.backend.ast import dfs_preorder
+from pystencils.backend.ast.structural import PsBlock, PsComment
 
 from pystencils.backend.platforms import CudaPlatform, SyclPlatform
 
@@ -37,9 +34,5 @@ def test_thread_range(platform_class, layout):
         coordinate = loop_order[i]
         dimension = ispace.dimensions[coordinate]
         witems = threads_range.num_work_items[i]
-        desired = (dimension.stop - dimension.start) / dimension.step
+        desired = dimension.stop - dimension.start
         assert witems.structurally_equal(desired)
-
-
-#%%
-test_thread_range(CudaPlatform, "fzyx")