Archive 1997–2024

The NVIDIA Titan V Deep Learning Deep Dive: It's All About The Tensor Cores

DeepBench Inference: RNN and Sparse GEMM

Rounding out the last of our DeepBench inference tests are RNN and Sparse GEMM, both available in single precision only. That being said, the FP16 parameter could be selected anyway. Given the low results all around, this is more of an artifact than anything else.

DL Inference: DeepBench - RNN (LSTM)

DL Inference: DeepBench - RNN (GRU)

DL Inference: DeepBench - Sparse GEMM

While RNNs might also be accelerated, DeepBench and NVIDIA only support single precision RNN inference at this time.

Originally published at https://www.anandtech.com/show/12673/titan-v-deep-learning-deep-dive (Wayback Machine).