Nvidia TESLA C2075 Quick Manual

NVIDIA® TESLA
COMPANION PROCESSOR

CALCULATE RESULTS
EXPONENTIALLY FASTER

Tesla companion processors bring the power of high performance
computing to the workstation.

With 448 application-acceleration cores
per board, Tesla processors offload
parallel computations from the CPU to
dramatically accelerate the floating point
calculation performance. By adding a
Tesla processor, engineers, designers,
and content creation professionals
accelerate some of the most complex
tools exponentially faster than by adding
a second CPU. It’s an unbeatable solution
for getting more done in less time.

Take advantage of the newest analysis,
simulation, and rendering tools within
industry-leading applications and see
results in as little as half the time. Tesla
C2075 companion processors deliver
parallel processing power right at the
desk, capable of streamlining the way
users work every day. This means you
can now explore, discover and deliver
higher-quality projects faster than you
ever thought possible.

BIOSCIENCE

FINANCE

MEDICAL

™

C2075

TECHNICAL SPECIFICATIONS

FORM FACTOR

> 9.75” PCIe x16 form factor

# OF CUDA CORE S

> 448

FREQUENC Y OF CUDA CORES

> 1.15 GHz

DOUBLE PRECISION FLOATING POINT
PERFORMANCE PEAK

> 515 Gflops

SINGLE PRECISION FLOATING POINT
PERFORMANCE PEAK

> 1.03 Tflops

TOTAL DEDICATED MEMORY

> 6GB GDDR5*

MEMORY SPEED

> 1.5 GHz

MEMORY INTERFACE

> 384-bit

MEMORY BANDWIDTH

> 144 GB/sec

POWER CONSUMPTION

> 225W TDP

SYSTEM INTERFACE

> PCIe x16 Gen2

THERMAL SOLUTION

> Active Fansink

DISPLAY SUPPORT

> Dual-Link DVI-I: 1
> Maximum Display Resolution

1600x1200

*Note: With ECC on, a portion of the dedicated memory is used for ECC bits, so the available user memory is reduced by 12.5%.

(e.g. 6.144 GB total memory yields 5.376 GB of user available memory.)

NVIDIA TESLA | DATASHEET | SEPT 11

FEATURES AND BENEFITS

448 CUDA CORES

ECC MEMORY

UP TO 6GB OF GDDR5 MEMORY PER GPU

NVIDIA PARALLEL DATACACHE

NVIDIA GIGA THREAD™ ENGINE

DUAL COPY ENGINE ENABLES TRUE
ASYNCHRONOUS DATA TRANSFER

™

Tesla C2075 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.

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.

Maximizes performance and reduces data transfers by keeping larger data sets in
local memory that is attached directly to the GPU.

Accelerates algorithms such as physics solvers, ray-tracing, and sparse matrix
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.

Maximizes the throughput by faster context switching that is 10X faster than
previous architecture, concurrent kernel execution, and improved thread block
scheduling.

Turbocharges 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 the
computing efficiency by transferring data to local memory before it is needed

CUDA PROGRAMMING ENVIRONMENT
WITH BROAD SUPPORT OF PROGRAMMING
LANGUAGES AND APIs

HIGH SPEED, PCIe GEN 2.0
DATA TRANSFER

DRIVERS AND DOWNLOADS

> Tesla C2075 is supported under

- Linux 32-bit and 64-bit

- Windows XP, Windows Vista, Windows 7
(32-bit and 64-bit)

> Vertical Solutions and Software page:

www.nvidia.com/object/vertical_solutions.html

> Software for Tesla C2075

- Download latest driver at
www.nvidia.com/Download/index.aspx?lang=en-us

- Software development tools is available at
www.nvidia.com/object/tesla_software.html

Choose C, C++, OpenCL, DirectCompute, or Fortran to express application
parallelism and take advantage of the “Fermi” GPU’s innovative architecture.
NVIDIA Parallel Nsight GPU debugging tool is available for Microsoft Visual
Studio developers.

Maximizes bandwidth between the host system and the Tesla processors. En­ables Tesla products to work with virtually any PCIe-compliant host system with
an open PCIe x16 slot.

SUPPORT

> HARDWARE SUPPORT

For RMA requests, replacements and warranty issues regarding your NVIDIA based product,
please contact the OEM or the reseller that you purchased it from.

> KNOWLEDGEBASE

Our knowledgebase is available online 24x7x365 and contains answers to the most common
questions and issues: http://nvidia.custhelp.com/app/answers/list

> USER FORUMS

Discuss Tesla products, talk about CUDA development, and share interesting issues, tips
and solutions with your fellow NVIDIA Tesla users on the CUDA discussion forums:

http://forums.nvidia.com/

> PREPURCHASING SUPPORT

Pre-purchasing support is available to assist you in deciding which Tesla unit to purchase for
your application: www.nvidia.com/object/tesla_assistance.html

To learn more about NVIDIA workstation solutions, go to www.nvidia.com/workstation

©2011 NVIDIA Corporation. All rights reserved. NVIDIA, the NVIDIA logo, NVIDIA Tesla, CUDA, GigaThread, Parallel DataCache and Parallel NSight are
trademarksand/or registered trademarks of NVIDIA Corporation. All company and product names are trademarks or registered trademarks of the respective owners
with which they are associated. Features, pricing, availability, and specifications are all subject to change without notice.