Deep Learning GPU Benchmarks: GTX 1080 vs. Titan X Pascal

Re:Deep Learning GPU Benchmarks: GTX 1080 vs. Titan X Pascal by bhouston on Wednesday October 12, 2016 @12:22PM (#12694225)

They are using different CPUs for these tests. It seems that the CPU used for Pascal has a higher GHz speed. I hope that isn't confounding on the results.

[ Parent | on HN ]

Re:Deep Learning GPU Benchmarks: GTX 1080 vs. Titan X Pascal by web007 on Wednesday October 12, 2016 @01:15PM (#12694735)

They're using different CPUs[0], different amounts of RAM, different base OSes, different drivers and even one different product version (Tensorflow RC). As far as benchmarks go this is pretty awful. It does show some useful top-level comparisons, but it's about as un-rigorous as you can get.

[0] http://ark.intel.com/compare/82930,94188,77780

[ Parent | on HN ]

Re:Deep Learning GPU Benchmarks: GTX 1080 vs. Titan X Pascal by Nursie on Wednesday October 12, 2016 @12:47PM (#12694436)

The test setup for the 1080 also had half the RAM of the others, and used an older ubuntu.

Not a great test of GPUs in isolation.

[ Parent | on HN ]

Re:Deep Learning GPU Benchmarks: GTX 1080 vs. Titan X Pascal by eveningcoffee on Wednesday October 12, 2016 @05:40PM (#12696619)

I guess that sometimes you have to work with what you have and I prefer these results to no results.

[ Parent | on HN ]

Re:Deep Learning GPU Benchmarks: GTX 1080 vs. Titan X Pascal by eveningcoffee on Wednesday October 12, 2016 @12:34PM (#12694327)

I would assume that it definitely affects the result if the procedure involves moving data between GPU and main memory, but I do not know the size of the effect.

I am still pretty confident that the difference in performance comes mostly from differences between different GPU architectures.

[ Parent | on HN ]