Supermicro 1U-4U GPU SuperServers and 7U SuperBlade Maximize Compute Density and Performance per Watt with Support for New NVIDIA Tesla M40 GPU Accelerator

SAN JOSE, CA -- Super Micro Computer, Inc. delivers the industry's widest range of GPU-enabled SuperServers ready to support the new addition to the NVIDIA Tesla Accelerated Computing Platform, the NVIDIA Tesla M40 GPU Accelerator.

Available immediately, the Supermicro 1U 4x GPU (SYS-1028GQ-TR/-TRT), 2U 6x GPU (SYS-2028GR-TR/-TRH/-TRHT), 4U 8x GPU (SYS-4028GR-TR/-TRT), 4U/Tower 4x GPU (SYS-7048GR-TR) and 7U 20x GPU SuperBlade® (SBI-7128RG-X/-F/-F2) offer unrivaled configuration flexibility and industry leading GPU density. With Supermicro's GPU cooling optimized architecture in the 1U 4x GPU SYS-1028GQ-TR/-TRT, NVIDIA Tesla M40 accelerators can operate at a sustained 1000W delivering up to 28 Teraflops of single precision performance for deep learning training applications.

"Supermicro's 1U 4x GPU high performance computing SuperServer maximizes GPU density and performance per watt with a non-preheat GPU cooling architecture providing maximum system performance and reliability," said Charles Liang, President and CEO of Supermicro. "With an expanding range of solutions incorporating the NVIDIA Tesla M40 GPUs we deliver the industry's widest range of accelerated computing solutions optimized for next generation deep learning research."

"The NVIDIA Tesla M40 is purpose-built for deep learning training at scale, dramatically reducing the time required to train sophisticated neural networks," said Roy Kim, group product manager of Accelerated Computing at NVIDIA. "With support for the new Tesla M40 GPUs, Supermicro offers data scientists a range of high-performance, high-density accelerated platforms to advance their most challenging deep learning projects."

Product Specifications

•1U 4x GPU (SYS-1028GQ-TR/-TRT) -- supports 4x NVIDIA Tesla M40 GPUs, 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, 2x PCI-E 3.0 x8 (in x16) LP slot, dual port GbE LAN (-TR SKU), dual 10GBase-T (-TRT), 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, redundant 2000W Titanium Level (96%+) power supplies
•2U 6x GPU (SYS-2028GR-TR/-TRH/-TRHT) -- supports 6x NVIDIA Tesla M40 GPUs, dual Intel® Xeon® processor E5-2600 v3 family, 10x 2.5" Hot-swap SATA3 HDD Bays, 16x DIMM slots; up to 1TB DDR4 2133MHz reg. ECC memory, 4x PCI-E 3.0 x16 and 1x PCI-E 3.0 x8 slots, 2x GbE/10GBase-T (-TRT, -TRHT), 1x Video, 4x USB 3.0 (2 rear, 2 via header), 2x USB 2.0 (2 via header), Built-in Server management tool (IPMI 2.0, KVM/media over LAN) with dedicated LAN port, redundant 2000W Platinum Level (94%+) power supplies
•4U 8x GPU (SYS-4028GR-TR/-TRT) -- supports 8x NVIDIA Tesla M40 GPUs, 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/10GBase-T (-TRT), and four redundant 1600W Platinum Level (94%+) power supplies
•4U/Tower 4x GPU (SYS-7048GR-TR) -- supports 4x NVIDIA Tesla M40 GPUs, dual Intel® Xeon® processor E5-2600 v3 family, 8x 3.5" Hot-swap SATA HDD Bays, 3x 5.25" peripheral drive bays, 1x 3.5" fixed drive bay, 16x DIMM slots; up to 1TB DDR4 2133MHz reg. ECC memory, 4x PCI-E 3.0 x16 (4 GPU cards opt.), 2x PCI-E 3.0 x8 (1 in x16), and 1x PCI-E 2.0 x4 (in x8) slot, 2x GbE, 1x Video, 2x COM/Serial, 5x USB 3.0, 4x USB 2.0, Built-in Server management tool (IPMI 2.0, KVM/media over LAN) with dedicated LAN port, redundant 2000W Titanium Level (96%+) power supplies
•7U SuperBlade® (SBI-7128RG-X/-F/-F2) -- 20x NVIDIA Tesla M40 GPUs in 10 Blade Servers, each supports Dual Intel® Xeon® processor E5-2600 v3 family, up to 512GB DDR4 2133MT/s ECC RDIMM in 8 DIMM slots, 1x 2.5" SSD, 1 SATADOM, FDR 56Gb/s InfiniBand switches, 1 and 10Gb/s Ethernet switches, redundant chassis management module (CMM) and Titanium Level (96%+) 3200W and Platinum Level (95%) 3000W/2500W (N+N or N+1 redundant) power supplies with cooling fans.

Additional Information:
http://www.supermicro.com/GPU
http://www.supermicro.com