The Nvidia Tesla P100 - IBM Power Systems S822LC Technical Overview And Introduction

1.2 The NVIDIA Tesla P100

NVIDIA's new NVIDIA Tesla P100 accelerator (see Figure 1-3) takes GPU computing to the
next level. This section discusses the Tesla P100 accelerator.
Figure 1-3 NVIDIA Tesla P100 accelerator
With a 15.3 billion transistor GPU, a new high performance interconnect that greatly
accelerates GPU peer-to-peer and GPU-to-CPU communications, new technologies to
simplify GPU programming, and exceptional power efficiency, Tesla P100 is not only the most
powerful, but also the most architecturally complex GPU accelerator architecture ever built.
Key features of Tesla P100 include:
Extreme performance
Powering HPC, Deep Learning, and many more GPU Computing areas
NVLink
NVIDIA's new high speed, high bandwidth interconnect for maximum application
scalability
HBM2
Fast, high capacity, extremely efficient CoWoS (Chip-on-Wafer-on-Substrate) stacked
memory architecture
Unified Memory, Compute Preemption, and New AI Algorithms
Significantly improved programming model and advanced AI software optimized for the
Pascal architecture;
16nm FinFET
Enables more features, higher performance, and improved power efficiency
4
IBM Power Systems S822LC for High Performance Computing