Commit 196a5397 authored by qjivy's avatar qjivy Committed by drpngx
Browse files

For the "m <= 4" GEMM that would call into (#9622) 

Gemlmowp/meta lib, change the single thread invoking to
multi-threads invoking.
Because for the FC layers, multi-thread would improve the
memory accessing of the relatively large weights matrix.
parent f7525de0
Show whitespace changes
Inline Side-by-side
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Please to comment