warp.get_mempool_used_mem_high#
- warp.get_mempool_used_mem_high(device=None)[source]#
Get the application’s memory usage high-water mark from the device’s CUDA memory pool.
- Parameters:
device (Device | str | None) – The
Deviceor device identifier for which the query is to be performed. IfNone, the default device will be used.- Returns:
The high-water mark of memory used from the memory pool in bytes.
- Raises:
ValueError – If
deviceis not a CUDA device.RuntimeError – If
deviceis a CUDA device, but does not support memory pools.
- Return type: