Tuesday April 05, 2016

NVIDIA Unveils The Tesla P100, Its Fastest GPU Ever

For those of you that haven't been following along with the keynote speech from this year's GPU Technology Conference, NVIDIA has made a number of product announcements today, including the Tesla P100. According to NVIDIA's CEO Jen-Hsun Huang, the Tesla P100 is based on the new NVIDIA Pascal GP100, at 600mmآ² is the largest FinFET GPU ever made. Huang even joked on stage that it was so big that you could easily see it from the back of the room. In addition to features like HBM2, NVLink, Unified memory and 16nm FinFET, NVIDIA says the GP100 is "composed of an array of Graphics Processing Clusters (GPCs), Streaming Multiprocessors (SMs), and memory controllers. GP100 achieves its colossal throughput by providing six GPCs, up to 60 SMs, and eight 512-bit memory controllers (4096 bits total). The Pascal architecture’s computational prowess is more than just brute force: it increases performance not only by adding more SMs than previous GPUs, but by making each SM more efficient. Each SM has 64 CUDA cores and four texture units, for a total of 3840 CUDA cores and 240 texture units."

News Image

The charts below offer a comparison of Tesla P100 specifications compared to previous-generation Tesla GPU accelerators.

News Image News Image

Continue watching GTC 2016 here.

Ongoing Discussion