domingo, 17 de dezembro de 2017

NVIDIA TESLA P100 for AI Research (Q2 2016) tech specifications | Data Center Graphics Card



P100 for PCIe-Based 

Double-Precision Performance : 4.7 TeraFLOPS
Single-Precision Performance : 9.3 TeraFLOPS
Half-Precision Performance : 18.7 TeraFLOPS
PCIe x16 Interconnect Bandwidth : 32 GB/s
CoWoS HBM2 Stacked Memory Capacity : 16 GB or 12 GB
CoWoS HBM2 Stacked Memory Bandwidth : 732 GB/s or 549 GB/s
Enhanced Programmability with Page Migration Engine : Yes
ECC Protection for Reliability : Yes
Server-Optimized for Data Center Deployment : Yes


Servers : P100 for NVLink-Optimized Servers

Double-Precision Performance : 5.3 TeraFLOPS
Single-Precision Performance : 10.6 TeraFLOPS
Half-Precision Performance : 21.2 TeraFLOPS
NVIDIA NVLink™ Interconnect Bandwidth : 160 GB/s
PCIe x16 Interconnect Bandwidth : 32 GB/s
CoWoS HBM2 Stacked Memory Capacity : 16 GB
CoWoS HBM2 Stacked Memory Bandwidth : 732 GB/s
Enhanced Programmability with Page Migration Engine : Yes
ECC Protection for Reliability : Yes
Server-Optimized for Data Center Deployment : Yes

Sem comentários:

Enviar um comentário