News for hackers. Stuff that matters.

A comment on The Nvidia DGX-1 Deep Learning Supercomputer in a Box. Parent comment

Re:The Nvidia DGX-1 Deep Learning Supercomputer in a Box by maaku on Tuesday April 05, 2016 @06:40PM (#11435162)
Uh, using what hardware? The 980 Ti is about 11 TFLOP in half-precision (apples to apples). So 16x 980 Ti cards would take up twice as much rack space for $11k. Your estimate (and NVIDIA's pricing) is off by more than an order of magnitude...
[ Parent | on HN ]
Re:The Nvidia DGX-1 Deep Learning Supercomputer in a Box by mon_insider on Tuesday April 05, 2016 @08:39PM (#11435770)
A 980 Ti doesn't have FP16 hardware. The only Maxwell based component with such support is their Tegra part.
[ Parent | on HN ]
Re:The Nvidia DGX-1 Deep Learning Supercomputer in a Box by wmf on Tuesday April 05, 2016 @07:36PM (#11435461)
Isn't the ECC tax around 10x?
[ Parent | on HN ]
Re:The Nvidia DGX-1 Deep Learning Supercomputer in a Box by marshray on Tuesday April 05, 2016 @08:57PM (#11435849)
So, just do the computation twice and compare the results?

OK, so there's twice the power to pay for but it seems like at $129k acquisition cost per 3.2KW consumption you could run for tens of years before break-even.

[ Parent | on HN ]