PNY TCSC2070-PB NVIDIA Tesla C2070 6GB graphics card
Contents
1. 144 GB sec Power Consumpt ion gt gt 247W TDP SYSTEM INTERFACE gt gt PCle x16 Gen2 THERMAL SOLUTION gt gt Active Fansink SOFTWARE DEVELOPMENT TOOLS gt gt CUDA C C Fortran OpenCL DirectCompute Toolkits NVIDIA Parallel Nsight for Visual Studio FNY PNY Technologies Europe 9 rue Joseph Cugnot 33700 M rignac France tel 33 0 5 56 13 75 75 fax 33 O 5 56 13 75 76 For more information www pny eu tesla ONY TESLA C2050 C20 0 Data Sheet 1985 2010 FEATURES AND BENEFITS GPUS POWERED BY THE FERMI Delivers cluster performance at 1 10th the cost and 1 2Oth the power of GENERATION OF THE CUDA CPU only systems based on the latest quad core CPUs ARCHITECTURE 448 CUDA CORES Delivers up to 515 Gigaflops of double precision peak performance in each GPU enabling a single workstation to deliver a Teraflop or more of performance single precision peak performance is over a Teraflop per GPU ECC MEMORY Meets a critical requirement for computing accuracy and reliability for workstations Offers protection of data in memory to enhance data integrity and reliability for applications Register files L1 L2 caches shared memory and DRAM all are ECC protected DESKTOP CLUSTER Performance Solves large scale problems faster than a small server cluster on a single workstation with multiple GPUs UP TO 6GB OF GDDRS MEMORY PER Maximizes performance and reduces data transfers by keeping larger da2. gt NY CELEBRATING 25 YEARS 1985 2010 TESLA C2070 Data Sheet NVIDIA TESLA C2070 GPU COMPUTING PROCESS OR SUPERCOMPUTING AT 1 10TH THE COST The NVIDIA Tesla C2070 Computing Processors fuel the transition to parallel computing and bring the performance of a small cluster to the desktop Based on the next generation CUDA architecture codenamed Fermi the 20 series family of Tesla GPUs support many must have features for technical and enterprise computing including C support ECC memory for uncompromised accuracy and scalability and a 7X increase in double precision performance compared Tesla 10 series GPUs The Tesla C2050 and C2070 GPUs are designed to redefine high performance computing and make supercomputing available to everyone Compared to the latest quad core CPUs Tesla C2070 Computing Processors deliver equivalent supercomputing performance at 1 10th the cost and 1 20th the power consumption PRODUCT SPECIFICATIONS FORM FACTOR gt gt 9 75 PCle x16 form factor OF TESLA GPUS gt gt 1 OF CUDA CORES gt gt 448 FREQUENCY OF CUDA CORE gt gt 1 15 GHz DOU BLE PRECISION FLOATING PO INT PERFORMANCE PEAK gt gt 515 Gflops SINGLE PRECISION FLOATING PO INT PERFORMANCE PEAK gt gt 1 03 Tflops TOTAL DEDICATED MEMORY gt gt Tesla C2070 6GB GDDR5 MEMORY SPEED gt gt 1 5 GHz MEMORY INTERFACE gt gt 384 bit MEMORY BANDWIDTH gt gt
3. oads Support gt gt Tesla C2050 C2070 is supported gt gt Hardware Support under For RMA requests replacements and warranty issues regarding your NVIDIA Linux 32 bit and 64 bit based product please contact the reseller that you purchased it from Windows XP Windows Vista Windows gt gt Knowledgebase 7 Our knowledgebase is available online 24x 7x365 and contains answers to the 32 bit and 64 bit most common questions and issues gt gt Vertical Solutions and Software page www nvidia custhelp com cg bin nvidia cfg php enduser std_alp php www nvidia com object vertical_solution gt gt User Forums s html Discuss Tesla products talk about CUDA development and share interesting gt gt Software for Tesla C2050 C2070 issues tips and solutions with your fellow NVIDIA Tesla users on the CUDA Download latest driver at discussion forums www nvidia com Download index aspx www forums nvidia com ang en us gt gt Pre Purchasing Support Software development tools is available Pre purchasing support is available to at assist you in deciding which Tesla unit to purchase for www nvidia com object your application PNY tesla_software html www nvidia com object tesla_assistance html PNY Technologies Europe 9 rue Joseph Cugnot 33700 M rignac France tel 33 0 5 56 13 75 75 fax 33 O 5 56 13 75 76 For more information www pny eu tesla
4. ta GPU sets in local memory that is attached directly to the GPU Accelerates algorithms such as physics solvers ray tracing and sparse matrix NVIDIA PARALLEL DATA CACHE multiplication where data addresses are not known beforehand This includes a configurable L1 cache per Streaming Multiprocessor block and a unified L2 cache for all of the processor cores NVIDIA GIGA THREAD ENGINE Maximizes the throughput by faster context switching that is 10X faster than previous architecture concurrent kernel execution and improved thread block scheduling ASYNCHRONOUS TRANSFER Turbocharges system performance by transferring data over the PCle bus while the computing cores are crunching other data Even applications with heavy data transfer requirements such as seismic processing can maximize the computing efficiency by transferring data to local memory before it is needed CUDA PROGRAMMING ENVIRONMENT Choose C C OpenCL DirectCompute or Fortran to express application WITH BROAD SUPPORT OF parallelism and take advantage of the Fermi GPU s innovative architecture PROGRAMMING NVIDIA Parallel Nsight tool is available for Microsoft Visual Studio developers LANGUAGES AND APIS HIGH SPEED PCIE GEN 2 0 DATA Maximizes bandwidth between the host system and the Tesla processors TRANSFER Enables Tesla systems to work with virtually any PCle compliant host system with an open PCle x16 slot TECHNICAL SPECIFICATIONS Drivers and downl
Download Pdf Manuals
Related Search