NVIDIA Volta Only 2x Faster on LSTM

NVIDIA Volta reported being only 2x faster on LSTM training vs P100 in training, 1.7x in inference. This is due to LSTM largely not running matrix multiplications, which Volta accelerates in FP16.

Incidentally, NVIDIA DGX Station with 4 Volta GPUs runs on this ASUS X99-E-10G-WS motherboard.

Leave a Reply

Your email address will not be published. Required fields are marked *