Supermicro® Introduces NVIDIA® Pascal™ GPU-Enabled Server Solutions Featuring NVIDIA Tesla® P100 GPUs
New 4U SuperServer supporting up to 10 Tesla P100 PCI-E cards, 1U with 4 Tesla P100s, and 2U with up to 6 Tesla P100 cards, featuring Supermicro’s single-root complex design optimized for Machine Learning
SAN JOSE, CA, September 8, 2016 – Super Micro Computer, Inc. (NASDAQ: SMCI), a global leader in compute, storage, networking technologies and green computing today announced the general availability of its SuperServer solutions optimized for NVIDIA® Tesla® P100 accelerators with the new Pascal™ GPU architecture.
Supermicro’s density optimized 4U SuperServer 4028GR-TR(T)2 supports up to 10 PCI-E Tesla P100 accelerators for up to 210 TFLOPS FP16 peak performance with GPU Direct RDMA support. Supermicro’s innovative and GPU optimized single root complex PCI-E design is proven to dramatically improve GPU peer-to-peer communication efficiency over QPI and PCI-E links, with up to 21% higher QPI throughput and 60% lower latency compared to previous generation products. These 4U SuperServers support dual Intel® Xeon® processor E5-2600 v4/v3 product families, up to 3TB DDR4-2400MHz memory, optional dual onboard 10GBase-T ports, and redundant Titanium Level (96%) digital power supplies.
“Our high-performance computing solutions enable deep learning, engineering, and scientific fields to scale out their compute clusters to accelerate their most demanding workloads and achieve fastest time-to-results with maximum performance-per-watt, per-square-foot, and per-dollar,” said Charles Liang, President and CEO of Supermicro. “With our latest innovations incorporating the new NVIDIA P100 GPUs, our customers can accelerate their applications and innovations to solve the most complex real world problems.”
“Supermicro’s new high-density servers are optimized to fully leverage the new NVIDIA Tesla P100 accelerators to provide enterprise and HPC customers with an entirely new level of computing horsepower,” said Ian Buck, General Manager of the Accelerated Computing Group at NVIDIA. “The new SuperServers deliver superior energy-efficient performance for compute-intensive data analytics, deep learning and scientific applications while minimizing power consumption.”
With the convergence of Big Data Analytics, the latest GPU architectures, and improved Machine Learning algorithms, Deep Learning applications require processing power of multiple GPUs that must communicate efficiently and effectively to expand the GPU network. Supermicro’s single-root GPU system allows multiple GPUs to communicate efficiently to minimize latency and maximize throughput as measured by the NCCL P2PBandwidthTest.
In addition to the 4U supporting up to 10 Tesla P100s, Supermicro also offer the following SuperServers optimized for these new Pascal GPUs:
- 1U 4 Pascal GPU Optimized SuperServer solution – SuperServer 1028GQ-TR generates massively parallel processing power for Machine Learning applications.
- 2U 6 Pascal GPU Optimized SuperServer solution – SuperServer 2028GR-TRHT delivers the highest density massively parallel processing power for Machine Learning applications in 2U.
- 1U Ultra SuperServers – Designed to deliver unrivaled performance, flexibility, scalability, and serviceability, Supermicro’s 1028U servers support the new Pascal GPU. Ideal for demanding Enterprise workloads, these server support Intel® Xeon® processor E5-2600 v4 and v3 product families (160W/up to 22 Cores), up to 1.5TB of memory in 24 DIMMs, SATA3 with optional SAS3 and NVMe support for increased storage bandwidth, Ultra Riser options available which includes built-in 1G, 10GBase-T, 10G SFP+, 40G, and InfiniBand options, and Redundant Titanium Level (96%+) power supplies.
- 2U Ultra SuperServers – Designed to deliver unrivaled performance, flexibility, scalability, and serviceability, Supermicro’s 2028U SuperServers support up to 4 Pascal GPUs. Ideal for demanding Enterprise workloads, these server support Intel® Xeon® processor E5-2600 v4 and v3 product families (160W/up to 22 Cores), up to 1.5TB of memory in 24 DIMMs, SATA3 with optional SAS3 and NVMe support for increased storage bandwidth, Ultra Riser options available which includes built-in 1G, 10GBase-T, 10G SFP+, 40G, and InfiniBand options, and Redundant Titanium Level (96%+) power supplies.
Supermicro also offers the latest cost-effective Top-of-Rack switching technologies, whether traditional fully-featured models incorporating both hardware and software in a complete solution, or bare metal hardware capable of running third-party software configurable to specific customer needs in an Open Network Environment. Supermicro’s new SSH-C48Q is a 1U top-of-rack switch with 48 100Gbps QSFP+ ports. Meanwhile, Supermicro’s Server Management Softwareprovides a multifunctional suite of tools that can perform health monitoring, power management and firmware maintenance to help customers deploy and maintain servers in data centers.