SoylentNews

takyon [soylentnews.org] writes:

During a keynote at GTC 2016 [gputechconf.com], Nvidia announced the Tesla P100 [tomshardware.com], a 16nm FinFET Pascal graphics processing unit with 15.3 billion transistors intended for high performance and cloud computing customers. The GPU includes 16 GB of High Bandwidth Memory 2.0 with 720 GB/s of memory bandwidth and a unified memory architecture. It also uses the proprietary NVLink [nvidia.com], an interconnect with 160 GB/s of bandwidth, rather than the slower PCI-Express.

Nvidia claims the Tesla P100 will reach 5.3 teraflops of FP64 (double precision) performance, along with 10.6 teraflops of FP32 and 21.2 teraflops of FP16. 3584 of a maximum possible 3840 stream processors are enabled on this version of the GP100 die [anandtech.com].

At the keynote [anandtech.com], Nvidia also announced a 170 teraflops (FP16) "deep learning supercomputer" or "datacenter in a box" called DGX-1 [nvidia.com]. It contains eight Tesla P100s and will cost $129,000. The first units will be going to research institutions such as the Massachusetts General Hospital [massgeneral.org].

Original Submission