Supermicro Systems Optimized for NVIDIA v100 Volta GPUs
Supermicro has released a new series of products supporting and optimized for NVIDIA Tesla V100 PCI-E and V100 SXM2 GPUs.
The new GPU optimized systems are specifically engineered to deliver optimal parallel computing performance at maximum GPU density, NVLink support and achieve fastest time-to-results with maximum performance per watt, per square foot and per dollar.
Supermicro’s new 4U system with next-generation NVIDIA NVLink™ GPU-to-GPU interconnect is engineered to fully exploit the new Volta GPU architecture, with over five times the bandwidth of PCI-E 3.0. This system features an independent GPU and CPU thermal zones design, which ensures uncompromised performance and stability under the most demanding workloads.
For maximum acceleration of highly parallel applications like artificial intelligence (AI), deep learning, autonomous vehicle systems, energy and engineering/science, Supermicro’s new 4U system with next-generation NVIDIA NVLink is optimized for overall performance. The SuperServer 4028GR-TXRT supports eight NVIDIA Tesla V100 SXM2 GPU accelerators with maximum GPU-to-GPU bandwidth for important HPC clusters and hyper-scale workloads. Incorporating the latest NVIDIA NVLink GPU interconnect technology with over five times the bandwidth of PCI-E 3.0, this system features an independent GPU and CPU thermal zoning design, which ensures uncompromised performance and stability under the most demanding workloads.
Similarly, the performance optimized 4U SuperServer 4028GR-TRT2 system can support up to 10 PCI-E Tesla V100 accelerators with Supermicro’s innovative and GPU optimized single root complex PCI-E design, which dramatically improves GPU peer-to-peer communication performance. For even greater density, the SuperServer 1028GQ-TRT supports up to four PCI-E Tesla V100 GPU accelerators in only 1U of rack space. Ideal for media, entertainment, medical imaging, and rendering applications, the powerful 7049GP-TRT workstation supports up to four NVIDIA Tesla V100 GPU accelerators.
“Supermicro designs the most application-optimized GPU systems and offers the widest selection of GPU-optimized servers and workstations in the industry,” said Charles Liang, President and CEO of Supermicro. “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. With our latest innovations incorporating the new NVIDIA V100 PCI-E and V100 SXM2 GPUs in performance-optimized 1U and 4U systems with next-generation NVLink, our customers can accelerate their applications and innovations to help solve the world’s most complex and challenging problems.”
“Supermicro’s new high-density servers are optimized to fully leverage the new NVIDIA Tesla V100 data center GPUs to provide enterprise and HPC customers with an entirely new level of computing efficiency,” said Ian Buck, vice president and general manager of the Accelerated Computing Group at NVIDIA. “The new SuperServers deliver dramatically higher throughput for compute-intensive data analytics, deep learning and scientific applications while minimizing power consumption.”
With the convergence of Big Data Analytics, the latest NVIDIA GPU architectures, and improved Machine Learning algorithms, Deep Learning applications require the 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.