4
IBM Power Systems S822LC for High Performance Computing
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
Summary of Contents for S822LC
Page 2: ......
Page 10: ...THIS PAGE INTENTIONALLY LEFT BLANK...
Page 14: ...xii IBM Power Systems S822LC for High Performance Computing...
Page 74: ...60 IBM Power Systems S822LC for High Performance Computing...
Page 78: ...64 IBM Power Systems S822LC for High Performance Computing...
Page 79: ......
Page 80: ...ibm com redbooks Printed in U S A Back cover ISBN REDP 5405 00...