PNY

The NVIDIA Quadro 5000 Multi-GPU Compute Pack consists of four NVIDIA Quadro 5000 GPU boards. The NVIDIA Fermi-based Quadro 5000 GPU combines CUDA high performance computing, OpenGL hardware acceleration and advanced visualization capabilities.

Featuring ECC memory integrity and fully IEEE 764-2008 compliant 32- and 64-bit fast double-precision, each Quadro 5000 GPU is capable of delivering 718.08 Gigaflops (Single Precision) or 359.04 Gigaflops (Double Precision) to enable applications ranging from immersive visualization, interactive ray tracing and real-time video processing, to other personal supercomputing solutions ranging from computational fluid dynamics to bioinformatics.

Target Markets

Clustered GPU compute servers
Personal supercomputing systems
Remote rendering and video encoding
Clustered image processing systems
Large-scale visualization

GPU Memory Size		2.5 GB GDDR5
Memory Interface		320-bit
CUDA Cores		352
Performance	SPECViewperf (Geomean)	13x (faster)
Graphics	Open GL 4.1 Hardware Acceleration DirectX 11 Quad Buffered OpenGL Stereo	Yes 11 Yes
Compute	ECC Memory Fast Double Precision Dual Copy Engines	Yes Yes Yes
Software	ISV Workstation Certification ISV CUDA Certification	Yes Yes
Power	Max Power Consumption Energy Star Compliant	204W Yes
Remote Monitoring	Remote GPU Monitoring and Power Management	Yes

PNY provides unsurpassed service and commitment to its professional graphics customers offering: 3 year warranty, pre and post sales support, dedicated Quadro Field Application engineers and direct tech support hot lines. In addition, PNY delivers a complete solution including the appropriate adapters, cables, brackets, driver CD and documentation to ensure a quick and successful install.

SPECIFICATIONS PER GPU

Memory	2.5 GB GDDR5
Memory Interface	320-bit
Memory Bandwidth	120 GB/sec
Memory Clock Speed	1.5 GHz
CUDA Parallel Processing Cores	352
Frequency of CUDA Cores	1.15GHz
ECC (Error Correcting Code)	Yes
High Performance Double Precision	Yes
Double Precision floating point performance (peak)	369.04 Megaflops
Single Precision floating point performance (peak)	718.08 Megaflops
Maximum Power Consumption	152 W
Energy Star Compliant	Yes
Physical Dimensions	4.376" H x 9.50" L Dual Slot
Display Connectors	DVI-DL + DP + DP + ST
Number of Displays Supported	2
DP	Yes
DVI	Yes
VGA	Yes
Graphics Bus	PCI Express 2.0 x16
Thermal Solution	Active
3D Vision Pro	Support via 3-pin Mini-DIN
G-Sync	Version Available
HD SDI Capture/Output	Version Available
Maximum Digital Resolution	2560 x 1600 at 60Hz
Graphics APIs	DirectX 11, OpenGL 4.0 and Shader Model 5.0
Compute APIs	NVIDIA CUDA, DirectCompute and OpenCL
Software Development Tools	CUDA C/C++/Fortran, OpenCL, Direct Compute Toolkits, NVIDIA Parallel Nsignt™ for Visual Studio
Warranty	3 Year Warranty
PNY Part Number	VCGPU5K-PCK

TECHNICAL SPECIFICATIONS

Supported Platforms

Microsoft^® Windows^® 7 (64-bit and 32-bit)
Microsoft Windows Vista (64-bit and 32-bit)
Microsoft Windows XP (64-bit and 32-bit)
Linux^® - Full OpenGL implementation, complete with NVIDIA and ARB extensions (64-bit and 32-bit)
Solaris^®

3D Graphics Architecture

Scalable geometry architecture
Hardware tessellation engine
NVIDIA^® GigaThread™ engine with dual copy engines
OpenGL 4.1, DirectX 11.0 and Shader Model 5.0
Optimized compiler for Cg and Microsoft HLSL
Up to 16K x16K texture and render processing
Transparent multisampling and super sampling
16x angle independent anisotropic filtering
128-bit floating point performance
32-bit per-component floating point texture filtering and blending
64x full scene antialiasing (FSAA)
Decode acceleration for MPEG-2, MPEG-4 Part 2 Advanced Simple Profile, H.264, MVC, VC1, DivX (version 3.11 and later), and Flash (10.1 and later)
DivX (version 3.11 and later), and Flash (10.1 and later)
Blu-ray dual-stream hardware acceleration (supporting HD picture-in-picture playback)

NVIDIA CUDA Parallel Processing Architecture

API support includes CUDA C, CUDA C++, DirectCompute 5.0, OpenCL, Java, Python, and Fortran
NVIDIA^® Parallel DataCache™ hierarchy (configurable L1 and unified L2 caches)
ECC (Error Correction Code) memory
64 KB of RAM (configurable partitioning of shared memory and L1 cache)
Fully IEEE 754-2008 compliant fast 32- and 64-bit double precision floating point computation
Dual Warp Scheduler (schedules and dispatches simultaneously instructions from two independent warps)

Advanced Display Features

30-bit color (10-bit per each red, green, blue channel)
Support for any combination of two connected displays
Dual DisplayPort resolution up to 2560 x 1600 at 60Hz or 1920 x 1200 at 120Hz
DisplayPort 1.1a with HDCP support
Single DVI-DL output up to 2560 x 1600 at 60Hz or 1920 x 1200 at 120Hz
DisplayPort to VGA adapter sold separately, PNY PN 91007808-T
DisplayPort to DVI-DL adapter sold separately, PNY PN 91008126
DisplayPort to HDMI adapters available from 3rd parties
Full OpenGL quad buffered stereo support
NVIDIA^® 3D Vision™ Pro support via dedicated 3-pin mini-DIN stereo bracket
Underscan/overscan compensation and hardware scaling
NVIDIA^® Mosaic™ multi-display technology
NVIDIA^® nView^® multi-display technology

DisplayPort and HDMI Digital Audio

Support for Dolby Digital (AC3), DTS 5.1, Multi-channel (7.1) LPCM, Dolby Digital Plus (DD+), and MPEG-2/MPEG-4 AAC
Data rates of 44.1 KHz, 48 KHz, 88.2 KHz, 96 KHz, 176 KHz, and 192 KHz
Word sizes of 16-bit, 20-bit, and 24-bit
HDMI digital audio requires the purchase of a 3rd party DisplayPort to HDMI adapter

Minimum System Requirements

Windows^® 7, Vista, XP SP3, Linux^®, or Solaris^®
PCIe x16 expansion slot
1GB or more of system memory, 2GB recommended
200MB of available disk space for full driver installation
Blu-ray, DVD-ROM or CD-ROM drive
DisplayPort, DVI or VGA compatible display(s)

GPU FEATURES

Next-Generation NVIDIA^® CUDA™ Architecture
Breakthrough NVIDIA CUDA parallel computing architecture, code named Fermi, tightly integrates advanced visualization and compute features at 1/10th the cost and 1/20th the power requirements of CPU-based systems utilizing the latest quad core processors.

352 CUDA Parallel Processing Cores
Delivers up to 369 Megaflops of double precision floating point peak performance per GPU and 718 Megaflops of single precision floating point peak performance per GPU, enabling a single workstation to deliver over 1.2 Teraflops of double precision, or 2.8 Teraflops of single precision compute power.

NVIDIA Parallel DataCache™
Supports a true cache hierarchy combined with on-chip shared memory. L1 and L2 caches drive exceptional throughput, accelerating features such as real-time ray tracing, physics, and life sciences applications, including bioinformatics

2.5 GB of GDDR5 Memory with Ultra-Fast Bandwidth
Large 2.5 GB GPU memory with fast bandwidth enables display of complex models and scenes, as well as computation of large datasets.

Fast 64-Bit Floating Point Precision
Industry's fastest double precision floating point performance enables accurate results on mission-critical applications ranging from physical simulations and finite element analysis to computational fluid dynamics.

Error Correcting Code (ECC) Memory
Meets strict requirements for mission critical applications with uncompromised computing accuracy and reliability for workstations. Offers protection of data in memory to enhance application data integrity.

NVIDIA GigaThread™ Engine
Provides up to 10x faster context switching compared to previous generation architectures, concurrent kernel execution, and improved thread block scheduling.

Asynchronous Transfer
Optimizes system performance by transferring data over the PCIe bus while the computing cores are crunching other data. Even applications with heavy data-transfer requirements, such as seismic processing, can maximize computing efficiency by transferring data to local memory before it is needed.

Dual Copy Engines
Provides the highest rates of parallel data processing and concurrent throughput between the GPU and host, further accelerating any computational task.

Unified Driver Architecture (UDA)
The NVIDIA UDA guarantees forward and backward compatibility with software drivers. Simplifies upgrading to a new solution because all Quadro products work with the same driver software.

IMAGE QUALITY

Full-Scene Antialiasing (FSAA)
Up to 128X FSAA dramatically reduces visual aliasing artifacts or "jaggies," resulting in unparalleled image quality and highly realistic scenes.

GPU Tessellation with Shader Model 5.0
Quadro Tessellation Engines automatically generate finely detailed geometry, for cinematic quality environments and scenes, without sacrificing performance.

16K Texture and Render Processing
The ability to texture from and render to 16K x 16K surfaces. Beneficial for applications that demand the highest resolution and quality image processing.

NVIDIA High Precision High Dynamic Range (HDR) Technology
Sets new standards for image clarity and quality through floating point capabilities in shading, filtering, texturing, and blending. Enables unprecedented rendered image quality for visual effects processing.

DISPLAY FEATURES

High-Quality Display Connectors
Attaches to ultra-high-resolution digital panels producing phenomenal photorealistic image quality from a range of display connectors. The Quadro 6000 GPU simultaneously supports two active display channels including DVI-I dual link and DisplayPort at resolutions up to 2560 x 1600 at 60Hz. The included DVI to VGA adapter supports resolutions up to 2048 x 1536 at 85Hz. HDMI 1.3a compliant displays can be driven with a 3rd party adapter (must be purchased separately) at resolutions up to 1920 x 1080 at 60Hz.

30-Bit Color Fidelity
30-bit color fidelity (10-bits per color) enables billions rather than millions of color variations for rich, vivid image quality with the broadest dynamic range.

NVIDIA 3D Vision Pro™ Stereoscopic Solution
Advanced active shutter glasses deliver crystal-clear stereoscopic 3D visualization for the most immersive experience. RF technology enables a range of environments ranging from collaborative work spaces to theaters. 3D Vision Pro solution sold separately.

OpenGL Quad Buffered Stereo Support
OpenGL Quad Buffered Stereo offers professional applications the capability of smooth and immersive 3D Stereo experience.

Professional 3D Stereo Synchronization
Enables robust control of stereo effect through a dedicated 3-pin mini-din connection between the graphics card and 3D stereo hardware.

SOFTWARE SUPPORT

Programming the CUDA Parallel Computing Architecture
General purpose GPU computing using standard programming languages like C/C++ and Fortran, and emerging APIs such as OpenCL and Direct Compute. This broad adoption of CUDA is accelerating techniques like ray tracing, video and image processing, and computation fluid dynamics.

Cg Programming
Programmable GPU leverages Cg high-level, open-standard shading language to enable the creation and integration of real-time photorealistic effects into 3D models, scenes and designs.

Microsoft^® Windows^® 7 Support
Take advantage of all the new and compelling features included with Windows 7, delivering unprecedented application performance, advanced visual realism, and premium reliability with superior application compatibility on mobile and desktop workstations.

Shader Model 5.0 Programmability
Infinite length vertex programs and dynamic flow control remove the previous limits on OpenGL and DirectX shader programs, delivering sophisticated effects never before imagined.

NVIDIA Graphics API Extensions
NVIDIA provides a set of extensions to standard graphics APIs for Linux and Windows, enabling applications to take maximum advantage of state-of-the-art GPU capabilities.

NVIDIA Application Acceleration Engines Support
Supercharge application performance and capabilities with highly optimized software modules, including SceniX™, OptiX™, and CompleX™, for advanced creative and investigative possibilities.

NVIDIA Mosaic Mode Technology
NVIDIA Mosaic Mode enables transparent scaling of any application across up to 8 display channels, while delivering full performance.

NVIDIA NVIEW™ Multi-Display Technology
NVIEW advanced display software delivers maximum flexibility for single-large display or multi-display options, providing unprecedented end-user control of the desktop experience for increased productivity.

Package Contains

Four NVIDIA Quadro 5000 by PNY CUDA, OpenCL, and DirectCompute enabled processor boards
Four 6-pin auxiliary power cables
DisplayPort to DVI-D SL adapter
DVI to VGA adapter

NVIDIA Scalable Visualization and Mosaic Solutions
PNY offers a range of Quadro-fueled solutions ranging from multi-monitor workstation configurations to CAVE environments powered by Quadro Plex 7000 visual computing systems – in 2D or 3D stereo. Learn how Quadro visualization solutions can take virtual or augmented reality applications to the next level of capabilities and performance.

NVIDIA Quadro by PNY Grayscale Solutions
Studies show that diagnostic speed and accuracy are both improved by 10- or 12-bit capable imaging solutions; this presentation recommends specific Quadro products capable of delivering 10- or 12-bit grayscale images for medical and diagnostic imaging applications.

NVIDIA Quadro by PNY Graphics for Design Professionals
The entire design workflow is going digital – and the assets generated by this transition are now usable by marketing and sales to bring a product to market with a full array of traditional and web-based media assets. Learn how Quadro can take any Intel Core i3, i5, i7, or Xeon-based workstation to new levels of performance, interactivity, and productivity.

NVIDIA Quadro by PNY (including Multi-GPU) for 3ds Max and iray
Learn how NVIDIA Quadro by PNY graphics solutions combined with 3ds max and iray are raising the bar for 3ds Max users with features such as photorealistic iray-enabled interactive raytracing. Quadro DirectX and CUDA acceleration, in many instances augmented by multiple GPUs are defining the new edge of the 3D design or DCC workstation performance envelope. Recommended configurations for the most demanding 3ds Max user are also listed.

NVIDIA Quadro by PNY for SolidWorks 2012
Learn how NVIDIA Quadro by PNY professional graphics boards can accelerate any SolidWorks-based workflow. From inspiration to initial customer delivery Quadro delivers all of the latest SolidWorks features, such as RealView, enabling unprecedented design interactivity and productivity.