DATASHEET Tesla TESLA C1060 COMPUTING PROCESSORS ARE THE CORE OF THE TESLA PERSONAL SUPERCOMPUTER To learn more about NVIDIA Tesla Personal Supercomputer please visit wwwnvidiacompersonalsupercom ID: 439994
Download Pdf The PPT/PDF document "TESLA PERSONAL SUPERCOMPUTER | DATASHEET..." is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.
TESLA PERSONAL SUPERCOMPUTER | DATASHEET | MAR09 | FINAL DATASHEET Tesla TESLA C1060 COMPUTING PROCESSORS ARE THE CORE OF THE TESLA PERSONAL SUPERCOMPUTER To learn more about NVIDIA Tesla Personal Supercomputer, please visit www.nvidia.com/personal_supercomputing© 2009 NVIDIA Corporation. All rights reserved. NVIDIA, the NVIDIA logo, NVIDIA Tesla, NVIDIA Quadro, and CUDA, are trademarks and/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 speci cations are all subject to change without notice.SUPPORTED PLATFORMS Microsoft Windows XP (64-bit recommended)Red Hat Enterprise Linux 4 and 5ESLA ARCHITECTUREMassively-parallel many-core architecture 240 scalar processor cores per GPUInteger, single-precision and double-precision oating point operationsHardware Thread Execution Manager enables thousands of concurrent threads per GPUParallel shared memory enables processor cores to collaborate on shared information at local cache performanceUltra-fast GPU memory access with 102 IEEE 754 single-precision and double-precision oating pointEach Tesla C1060 GPU delivers 933 GFlops Single Precision and 78 GFlops Double Precision performanceOFTAREEVELOPMENTOOLSC language compiler, debugger, pro ler, and emulation mode for debuggingStandard numerical libraries for FFT (Fast Fourier Transform), BLAS (Basic Linear Algebra Subroutines), and CuDPP (CUDA Data Parallel Primitives)RODUCTETAILS3 or 4 Tesla C1060 Computing Processors with 4 GB of dedicated 2.33 GHz+ Quad-core AMD Phenom or Opteron -OR- Quad-core Intel Core 2, Core i7 or Xeon. Minimum system memory: 12 GB for 3 Tesla C1060s and 16 GB for 4 Tesla C1060s (at least 4 GB per Tesla C1060)Acoustics 1200-1350 watt power supplyFEATURES AND OUROWNUPERCOMPUTERDedicated computing resource for every computational researcher and technical professional. LUSTERERFORMANCEONYOURESTOPThe performance of a cluster in a desktop system. Four Tesla computing processors deliver nearly 4 tera ops of performance. FOR O UPlugs into a standard of ce power socket and quiet enough for use at your desk.ASSIVELYARALLELANYOREGPU ARCHITECTURE240 parallel processor cores per GPU that can execute thousands of concurrent threads. OLVEARGESCALEROBLEMSUSINGULTIPLE GPUScale your application to multiple GPUs and harness the performance of thousands of processor cores to solve large-scale problems.IDELYACCEPTEDEASYTOLEARN CUDA ROGRAMMINGNVIRONMENTEasily express application parallelism to take advantage of the GPU’s many-core architecture using the NVIDIA CUDA C programming environment. 4 GB HIGH SPEEDEMORYPER GPUDedicated compute memory enables larger datasets to be stored locally for each processor minimizing data movement around the system.IEEE 754 FLOATINGOINTRECISIONSINGLEPRECISIONANDDOUBLEPRECISIONProvides results that are consistent across platforms and meet industry standards.64 BIT ALUFOROUBLE PRECISIONATHMeets the precision requirements of your most demanding applications with 64-bit ALUs.TECHNICAL SPECIFICATIONS