RES-NT2-1U GRID High-Performance Computer
The Themis RES-NT2-1U High-Performance Computer (HPC) combines an NVIDIA® GRID Maxwell M60 GPU accelerator, two E5-2600 v3/v4 Series Intel® Xeon® processors with up to eighteen cores per processor, and up to 1 TB ECC DDR4 memory in a ruggedized 1U form factor to meet the requirements for demanding environments where Size, Weight, and Power (SWAP) are severely limited.
The RES-NT2-1RU HPC is designed with superior resilience to environmental extremes that include shock, vibration, and temperature extremes. This expertise in thermal and kinetic management design keeps mission-critical applications available, improves life-cycle management, and reduces the total cost of ownership. The system’s aluminum chassis is typically half the weight of a standard steel chassis and operates reliably in hot or cold environments to save power.Download the RES-NT2-1U GRID High Performance Computer Data Sheet
|GPU, Processor, and Memory|
|GPUs||4 Maxwell GPUs|
|Processor||Two E5 2600 v3/v4 Series Intel Xeon with up to 18 cores per processor|
|Memory||Up to 1 TB ECC DDR4 2133MHz; 16x DIMM slots|
|NVIDIA CUDA cores||4,096|
|Total GPU Memory||16 GB GDDR5|
|Expansion slots||7||4 PCIe 3.0 x16, 2 PCIe 3.0 x8 (in x16 slot), 1 PCIe 2.0 x4 (in x8 slot)|
|Management and Operating System|
|OS||Supports popular virtualization technologies|
|Management Interface||IPMI v2.0 support|
|Front Panel Access I/O|
|Status LEDs||2||Front panel|
|Power switch||1 standard||Front panel|
|Gigabit Ethernet ports (RJ45)||2||Rear panel|
|USB 2.0 ports||2||Rear panel|
|IPMI 2.0 port||1||Rear panel|
|Power connector||1 or 2||Rear panel|
|Video||1 VGA Port||Rear panel|
|Power Supply Options||Single or redundant 1200W 110/220 VAC|
|Temperature Range||-40° C – 70° C||0°C – to 50°C|
|Humidity (non-condensing)||5% to 95%||8% to 95%|
|Shock||3 axis, 35g, 25ms||3 axis, 35g, 25ms|
|Vibration (10-2000Hz)||3.0 Grms, 8 Hz to 2000 Hz||3.0 Grms, 8 Hz to 2000 Hz|
* Themis designs all products to meet or exceed listed data sheet specifications. Some specifications are configuration dependant. Please contact Themis for information specific to your desired configuration requirements.
|Dimensions||Height: 1U or 1.75 inches (44.45 mm)
Width: 17.06 inches (433.3 mm)
Depth: 24 inches (610 mm)
|Weight||24 pounds (9.98 kg)|
|Coated aluminum for light weight and corrosion resistance|
|Stainless steel in selected areas to add strength and stiffness|
|Modular design for easy upgrade and service|
|Optional rack-mount slides|
|Airflow direction: front to rear|
|MIL-STD-810G||Shock and vibration|
With teraflops of single and double precision performance, NVIDIA® Kepler GPU Computing Accelerators are the world’s fastest and most efficient high performance computing (HPC) companion processors. Based on the Kepler compute architecture, Kepler GPU Computing Accelerators make hybrid computing dramatically easier, and applicable to a broader set of computing applications. Kepler’s break-through performance is made possible by three key features:
- SMX (streaming multiprocessor) delivers more processing performance and efficiency through this new, innovative streaming multiprocessor design that allows a greater percentage of space to be applied to processing cores versus control logic.
- IC Parallelism simplifies GPU programming by allowing programmers to easily accelerate all parallel nested loops – resulting in a GPU dynamically spawning new threads on its own without going back to the CPU.
- Hyper-Q slashes CPU idle time by allowing multiple CPU cores to simultaneously utilize a single Kepler GPU, dramatically advancing programmability and efficiency.
GRID K1 and K2 GPU Virtualization
GRID boards feature the NVIDIA® Kepler™ architecture that, for the first time, enables hardware virtualization of the GPU. Multiple users can share a single GPU, improving user density while providing true PC performance and compatibility. An optimized multi-GPU design helps to maximize user density.
Low-Latency Remote display
NVIDIA’s patented low-latency remote display technology greatly improves the user experience by reducing the lag that users feel when interacting with their virtual machine. With this technology, the virtual desktop screen is pushed directly to the remoting protocol.
The Kepler GPU includes a high performance H.264 engine capable of encoding simultaneous streams with superior quality. This provides a giant leap forward in cloud server efficiency by offloading the CPU from encoding functions and allowing these functions to scale with the number of GPUs in a server.
Maximum User Density
NVIDIA GRID boards have an optimized multi-GPU design that helps to maximize user density. GRID K1 boards, which include four Kepler-based GPUs and 16GB of memory, are designed to host the maximum number of concurrent users. GRID K2 boards, which include two higher end Kepler GPUs and 8GB of memory, deliver maximum density for users of graphics-intensive applications
GRID GPUs are designed to provide data center-class power efficiency, including the revolutionary new streaming multiprocessor, called “SMX”. The result is an innovative, proven solution that delivers revolutionary performance per-watt for the enterprise data center.
GRID boards are designed, built, and tested by NVIDIA for 24/7 operation. Working closely with leading server vendors ensures that GRID cards perform optimally and reliably for the life of the system.
Widest Range of Virtualization Solutions
GRID boards enable GPU-capable virtualization solutions allow the flexibility to choose from a wide range of proven solutions.