Supermicro Showcases 1U 4x GPU SuperServer and 3U/6U MicroBlade at SIGGRAPH 2015

Additional Highlights include Hyper-Speed Ultra SuperServer and 7U 20/30 GPU SuperBlade, MicroBlade for High Performance and High Density Compute Infrastructure
11 August 2015    Source: http://www.supermicro.co.uk

Los Angeles, CA, August 11, 2015 - Super Micro Computer, Inc. (NASDAQ: SMCI), a global leader in high-performance, high-efficiency server, storage technology and green computing will showcase its new high-density 1U 4x GPU SuperServer (SYS-1028GQ-TR/-TRT) which maximizes performance and density through pioneering non-preheat GPU architecture and PCIe direct connect (no extension cables, re-drivers, or bridge chips) for lowest latency. Supermicro's new 6U MicroBlade (MBI-6118D-T2H/-T4H) will be shown in Intel booth #701, running a live Citrix virtual workstation demo highlighting Intel® Xeon® processor E3-1200 v4 with Intel® Iris™ Pro graphics P6300 for high definition video & graphics in remote workstation applications. Supermicro exhibits also highlight its 4U/Tower 4x GPU SuperWorkstation (SYS-7048GR-TR) featuring 4x next generation NVIDIA® Quadro® GPUs running a live Autodesk® Maya® demo, 2U Hyper-Speed Ultra demonstrating high-performance virtual workstations powered by NVIDIA® GRID™ vGPU™ technology, 1U 3x GPU SuperServer and 7U 20/30 GPU SuperBlade® solutions for High Performance and High Density Compute Infrastructures.

"Supermicro's 1U 4x GPU SuperServer with cooling optimized non-preheat GPU architecture and 3U/6U MicroBlade with Intel Xeon E3-1200 v4 deliver best performance for graphics, video and visualization applications," said Charles Liang, President and CEO of Supermicro. "Our enterprise-class server solutions are designed for the most demanding, mission critical application environments and with a wide range of solutions from Ultra servers to MicroBlade, SuperBlade, and SuperWorkstations, professionals in creative and scientific fields can deploy exactly the best accelerated computing solutions with full confidence in performance, scalability and reliability."

"Citrix continues to lead in harnessing innovative graphic acceleration technologies to deliver the best user experience on any end point device," said Jim Luna, Senior Director of Strategic Global Alliances, Citrix Systems. "Citrix offers unmatched customer flexibility as the only virtual app and desktop delivery offering that supports both NVIDIA discrete graphic cards and Intel integrated graphics solutions. As the only virtualization solution that supports Intel Xeon E3 with Iris Pro product offerings, including this unique and highly flexible form-factor solution now available from Supermicro, Citrix provides enterprise customers with the most cost-effective offering available, providing unmatched support for server density and flexibility."

SIGGRAPH 2015 Exhibit Highlights

  • 1U 4x GPU SuperServer® (SYS-1028GQ-TR/-TRT) Whitepaper - Dual Intel® Xeon® processor E5-2600 v3, up to 1TB ECC, up to DDR4 2133MHz; in 16x DIMMs, 4x PCI-E 3.0 x16 slots (4x NVIDIA Tesla®, NVIDIA® GRID™, Intel® Xeon Phi™ coprocessor cards optional), 2x PCI-E 3.0 x8 (in x16) LP slot, dual port GbE LAN (-TR SKU), dual 10GBase-T (-TRT SKU), 2x 2.5" hot-swap drive bays, 2x 2.5" internal drive bays, efficient airflow heavy duty counter-rotating fans with air shroud & optimal fan speed control, 2000W Redundant Platinum Level (94%+) Power Supplies
  • 4U 8x GPU SuperServer® (SYS-4028GR-TR) - supports 8 GPU accelerators, dual Intel® Xeon® processor E5-2600 v3 (up to 160W), up to 1.5TB ECC DDR4, 2133MHz in 24 DIMM slots, 24 2.5" hot-swap SAS2/SATA3 drive bays, 8 PCI-E 3.0 x16 slots (double-width), 2 PCI-E 3.0 x8 (in x16) slots, 1 PCI-E 2.0 x4 (in x16) slot, dual 1GbE ports, and redundant 1600W Platinum Level (94%+) digital power supplies.
  • 1U 3x GPU SuperServer® (SYS-1028GR-TR/-TRT) World Record STAC-A2™ Benchmark - Dual Intel® Xeon® processor E5-2600 v3, up to 1TB ECC, up to DDR4 2133MHz in 16x DIMMs, 4x PCI-E 3.0 x16 slots (3x NVIDIA Tesla®, NVIDIA® GRID™, Intel® Xeon Phi™ coprocessor cards optional), 1x PCI-E 3.0 x8 LP slot, dual port GbE LAN (-TR SKU), dual 10GBase-T (-TRT SKU), 4x hot-swap 2.5" SATA3 drive bays, 1600W Redundant Platinum Level (94%+) Power Supplies, 10x Counter rotating fans w/ optimal fan speed control, Smart server management tools
  • 2U Hyper-Speed Ultra SuperServer® (SYS- 6028UX-TR4) - Dual Intel® Xeon® processor E5-2600 v3, up to 1TB ECC, up to DDR4 2133MHz in16x DIMMs, 3x PCI-E 3.0 x16 slot (FH, 10.5" L), 3x PCI-E 3.0 x8 slots (1 in x16 FH 10.5" L, 1 LP, 1 Internal LP), 4x GbE ports, 12x hot-swap 3.5" drive bays: SATA3 default, 12x SAS3 opt., 4x NVMe opt. via AOC, 4x heavy duty fans w/ optimal fan speed control, 1000W Redundant Titanium Level (96%) high-efficiency power supplies
  • 4U/Tower 4x GPU SuperWorkstation (SYS-7048GR-TR) -Dual socket Intel® Xeon® processor E5-2600 v3, up to 1TB ECC DDR4 2133MHz in16x DIMMs, 4x PCI-E 3.0 x16 slots, 2x PCI-E 3.0 x8 (1 in x16) slots, supports Thunderbolt 2.0 AOC1x PCI-E 2.0 x4 (in x8) slot, up to 4x GPU (supports 4-way NVIDIA® Geforce® SLI™), I/O ports: 1 VGA, 2 COM, 2 GbE, 10 USB 2.0, & 1 IPMI Dedicated LAN 8x 3.5" hot-swap, 3x fixed 5.25", and fixed 3.5" drive bays, 4x heavy duty fans, 2x exhaust fans, and 2x active heatsink with optimal fan speed control, 2000W Redundant Titanium Level High Efficiency (96%) power supplies, GPU Kit for passive GPU/Xeon Phi™ support (MCP-320-74701-0N-KIT)
  • 3U/6U MicroBlade - (MBI-6128R-T2/-T2X) performance oriented solution with highest density up to 196 Intel® Xeon® DP nodes (5488) cores) per 42U rack with 95% cable reduction - supports dual Intel® Xeon® Processor E5-2600 v3 (up to 14 cores) up to 28x DP servers with 1GbE and 10GbE options. (MBI-6118D-T2H/-T4H) supports Intel® Xeon® processor E3-1200 v4, features include power efficiency with 14nm technology, improved performance, coherency and balance of CPU and GPU Graphics via package interconnect shared L3 Cache and 128MB Graphic embedded cache. A simpler CPU subset and Intel® Iris™ Pro graphics P6300 in an interconnect package enable key technologies for the best server performance per watt per flop with great graphics emphasis.
  • 7U SuperBlade - advantages include maximum density, affordability, reduced management costs, lower power consumption, optimal ROI, and high scalability. Modules support latest Intel® Xeon® Processor E5-2600 v3 and are available in 20/30 GPU/Xeon Phi Blade; 2x NVIDIA® Tesla®, NVIDIA® GRID™ or Intel® Xeon Phi™ coprocessor cards per blade server (SBI-7128RG-X/-F/-F2), 3x NVIDIA Tesla® GPU per blade server (SBI-7127RG3), Data Center Blade (SBI-7428R-C3N, SBI-7428R-T3N), TwinBlade® (SBI-7228R-T2F/-T2F2/-T2X), Storage Blade with NVMe support (SBI-7128R-C6N), PCI-E Blade (SBI-7127R-SH, SBI-7427R-SH/-S2L, SBI-7126T-SH, SBI-7426T-SH) and 4-Way Blade (Intel® Xeon® Processor E5-2600 v2 SBI-7147R-S4X/-S4F) solutions. Chassis feature industry's only hot-swap NVMe solutions, hot-plug switch modules supporting Infiniband FDR/QDR, FC/FCoE, Layer 2/3 1/10 GbE, chassis management module (CMM) and redundant 3000W/2500W/1620W (3+1), hot-swap Platinum Level digital power supplies

Visit Supermicro at SIGGRAPH at the Los Angeles Convention Center August 9-13, Booth #550.

View the Supermicro range

Get in touch to discuss our range of solutions

+44 (0) 1727 876 100

Find your solution

Test out any of our solutions at Boston Labs

To help our clients make informed decisions about new technologies, we have opened up our research & development facilities and actively encourage customers to try the latest platforms using their own tools and if necessary together with their existing hardware. Remote access is also available

Contact us

Boston Training Academy Presents: NVIDIA - Deep Learning Fundamentals

Latest Event

Boston Training Academy Presents: NVIDIA - Deep Learning Fundamentals | 7th - 7th June 2018, Boston Headquarters, Frogmore, St Albans

NVIDIA Deep Learning Institute (DLI) workshops, hosted by Boston, offer hands-on training for developers, data scientists, and researchers looking to solve challenging problems with deep learning.

more info