This post introduces NVIDIA TITAN X Pascal, GTX 1080, and the comparisons between them.
In order to use TensorFlow with GPU support you must have a NVIDIA graphic card with a minimum compute capability of 3.0.
A single NVIDIA TITAN X Pascal is apparently much more powerful than a GTX 1080 graphics card if we do not consider their cost. But two GTX 1080 GPU cards will outperform a single NVIDIA Ttian X Pascal and from the financial cost perspective, two GTX 1080 will save your some money as well comparing to purchasing a single NVIDIA TITAN X. See my post, choose proper GeForce GPU(s) according to your machine, for some detailed explanations.
References:
- Get Started with Deep Learning (NVIDIA) – this is the place to find deep learning related resources, including choosing NVIDIA GPUs etc.
- NVIDIA Titan X – The fastest accelerator for deep neural network training on a desktop PC based on the revolutionary NVIDIA Pascal™ architecture
- Pascal TITAN X vs. the GTX 1080 – First Benchmarks Revealed! (Posted on August 3, 2016 in Reviews, Video Cards) (pdf-p1, pdf-p2, pdf-p3, pdf-p4)
- UserBenchmark: Nvidia GTX 1080 vs Titan X Pascal (pdf)