pystencils.codegen.gpu_indexing.GpuIndexing

pystencils.codegen.gpu_indexing.GpuIndexing#

class pystencils.codegen.gpu_indexing.GpuIndexing(ctx, target, scheme, warp_size, manual_launch_grid=False, assume_warp_aligned_block_size=False)#

Factory for GPU indexing objects required during code generation.

This class acts as a helper class for the code generation driver. It provides the factories for the launch configuration required later by the runtime system.

Parameters:

  • ctx (KernelCreationContext) – The kernel creation context

  • scheme (GpuIndexingScheme) – The desired GPU indexing scheme

  • block_size – A user-defined default block size, required only if the indexing scheme permits modification of the block size

  • manual_launch_grid (bool) – If True, always emit a ManualLaunchConfiguration to force the runtime system to set the launch configuration explicitly

  • target (Target)

  • warp_size (int | None)

  • assume_warp_aligned_block_size (bool)

get_launch_config_factory()#

Retrieve a factory for the launch configuration for later consumption by the runtime system

Return type:

Callable[[], GpuLaunchConfiguration]

Contents