IMPORTANT: To view this page as Markdown, append `.md` to the URL (e.g. /get-started.md). For the complete documentation index, see llms.txt.
Skip to main content
For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /get-started.md).

Mojo function

tmem_copy_async

def tmem_copy_async(dst: TileTensor[Engine=TMemEngine, address_space=dst.address_space, linear_idx_type=dst.linear_idx_type], src: TileTensor[Engine=src.Engine, address_space=src.address_space, linear_idx_type=src.linear_idx_type])

Issues the stores that copy src into the TMEM row dst, without waiting.

The tile-level spelling of TMemEngine.copy_from_async. Pair it with TMemEngine.wait_store before src is modified or dst is read back.

Args:

def tmem_copy_async(dst: TileTensor[Engine=dst.Engine, address_space=dst.address_space, linear_idx_type=dst.linear_idx_type], src: TileTensor[Engine=TMemEngine, address_space=src.address_space, linear_idx_type=src.linear_idx_type])

Issues the loads that copy the TMEM row src into dst, without waiting.

The tile-level spelling of TMemEngine.copy_to_async. dst must be a register tile, and it holds valid data only after TMemEngine.wait_load.

Args:

Was this page helpful?