You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Current backend defines all hooks as function pointer. Some hooks are accessed at fast-path or accessed multiple times in a single ipack/iunpack call. Compiler cannot optimize much for function pointers. We want to make these "fast" hooks inline.
The text was updated successfully, but these errors were encountered:
@minsii The DMA access latencies for most GPUs are in microseconds. In comparison, a function pointer dereference is ~25 cycles. So perhaps an expected gain comparison is useful before doing this?
Current backend defines all hooks as function pointer. Some hooks are accessed at fast-path or accessed multiple times in a single ipack/iunpack call. Compiler cannot optimize much for function pointers. We want to make these "fast" hooks inline.
The text was updated successfully, but these errors were encountered: