Commit a444f6a2 authored by Eugene Zhulenev's avatar Eugene Zhulenev Committed by TensorFlower Gardener
Browse files

Correctly compute loop bounds in pack_rhs_mem for convolutions. 

(1) Correctly compute maxCols/maxRows/maxPlanes for the fast path.
(2) Use fast divisors in a hot path.

~8-20% improvement for cuboid convolutions (Conv3D).
~1-5% improvement for spatial convolutions (Conv2D).

PiperOrigin-RevId: 214061787
parent e4e036fe
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