NVIDIA Tesla C2070 Professional Graphics Card

Product status: Official | Last Update: 2015-02-26 | Report Error
Overview
Manufacturer
NVIDIA
Original Series
Tesla 20
Release Date
July 25th, 2011
Launch Price
$3999
P/N Code
900-21030-0220
Model
NVIDIA P1030 SKU 220
Graphics Processing Unit
GPU Model
T20 (GF100)
Architecture
Fermi
Fabrication Process
40 nm
Die Size
529 mm2
Transistors Count
3.2B
Transistors Density
6M TRAN/mm2
CUDAs
448
SMXs
14
GPCs
4
TMUs
56
ROPs
48
Clocks
Base Clock
575 MHz
Memory Clock
750 MHz
Effective Memory Clock
3000 Mbps
Memory Configuration
Memory Size
6144 MB
Memory Type
GDDR5
Memory Bus Width
384-bit
Memory Bandwidth
144.0 GB/s

Physical
Interface
PCI-Express 2.0 x16
Height
2-slot
Power Connectors
1× 8-pin, 1× 6-pin
TDP/TBP
238 W
Recommended PSU
600 W
Display Outputs
DVI-I DualLink
1 ×
API Support
DirectX
12.0
Vulkan
-
OpenGL
4.5
OpenCL
1.1

Performance
Pixel Fillrate
27.6 GPixels/s
Texture Fillrate
32.2 GTexel/s
Peak FP32
515.2 GFLOPS
FP32 Perf. per Watt
2.2 GFLOPS/W
FP32 Perf. per mm2
974 FLOPS/mm2




 ModelCoresBoost ClockMemory ClockMemory Config.
Thumbnail
NVIDIA Tesla S2070
 
1792
-
 
3.1 Gbps
 
96 GB GD5 384b
Thumbnail
NVIDIA Tesla S2050
 
1792
-
 
3.1 Gbps
 
48 GB GD5 384b
Thumbnail
NVIDIA Tesla C2090
 
512
-
 
3.7 Gbps
 
6 GB GD5 384b
Thumbnail
NVIDIA Tesla M2090
 
512
-
 
3.7 Gbps
 
6 GB GD5 384b
Thumbnail
NVIDIA Tesla M2070Q
 
448
-
 
3 Gbps
 
6 GB GD5 384b
Thumbnail
NVIDIA Tesla C2070
 
448
-
 
3 Gbps
 
6 GB GD5 384b
Thumbnail
NVIDIA Tesla M2070
 
448
-
 
3 Gbps
 
6 GB GD5 384b
Thumbnail
NVIDIA Tesla M2075
 
448
-
 
3.1 Gbps
 
6 GB GD5 384b
Thumbnail
NVIDIA Tesla C2075
 
448
-
 
3 Gbps
 
6 GB GD5 384b
Thumbnail
NVIDIA Tesla M2050
 
448
-
 
3 Gbps
 
3 GB GD5 384b
Thumbnail
NVIDIA Tesla C2050
 
448
-
 
3 Gbps
 
3 GB GD5 384b
 ModelCoresBoost ClockMemory ClockMemory Config.
Thumbnail
NVIDIA Tesla S2070
 
1792
-
 
3.1 GB/s
 
96 GB GD5 384b
Thumbnail
NVIDIA Tesla S2050
 
1792
-
 
3.1 GB/s
 
48 GB GD5 384b
Thumbnail
NVIDIA Quadro PLEX 7000
 
896
-
 
3 GB/s
 
23.9 GB GD5 384b
Thumbnail
NVIDIA GeForce GTX 480
 
480
-
 
3.7 GB/s
 
1.5 GB GD5 384b
Thumbnail
NVIDIA Tesla C2070
 
448
-
 
3 GB/s
 
6 GB GD5 384b
Thumbnail
NVIDIA Tesla M2070
 
448
-
 
3 GB/s
 
6 GB GD5 384b
Thumbnail
NVIDIA Tesla M2070Q
 
448
-
 
3 GB/s
 
6 GB GD5 384b
Thumbnail
NVIDIA Quadro 6000
 
448
-
 
3 GB/s
 
6 GB GD5 384b
Thumbnail
NVIDIA Quadro 6000 SDI
 
448
-
 
3 GB/s
 
6 GB GD5 384b
Thumbnail
NVIDIA Quadro 6000 SDI I/O
 
448
-
 
3 GB/s
 
6 GB GD5 384b
Thumbnail
NVIDIA Tesla C2050
 
448
-
 
3 GB/s
 
3 GB GD5 384b
Thumbnail
NVIDIA Tesla M2050
 
448
-
 
3 GB/s
 
3 GB GD5 384b
Thumbnail
NVIDIA GeForce GTX 470
 
448
-
 
3.3 GB/s
 
1.3 GB GD5 320b
Thumbnail
NVIDIA Quadro 5000
 
352
-
 
3 GB/s
 
2.5 GB GD5 320b
Thumbnail
NVIDIA Quadro 5000 SDI
 
352
-
 
3 GB/s
 
2.5 GB GD5 320b
Thumbnail
NVIDIA Quadro 5000 SDI I/O
 
352
-
 
3 GB/s
 
2.5 GB GD5 320b
Thumbnail
NVIDIA Quadro 5000 SDI I/O Trebek
 
352
-
 
3 GB/s
 
2.5 GB GD5 320b
Thumbnail
NVIDIA Quadro 5000 SDI Trebek
 
352
-
 
3 GB/s
 
2.5 GB GD5 320b
Thumbnail
NVIDIA Quadro 5000 Trebek
 
352
-
 
3 GB/s
 
2.5 GB GD5 320b
Thumbnail
NVIDIA Quadro 5000G
 
352
-
 
3 GB/s
 
2.5 GB GD5 320b
Thumbnail
NVIDIA Quadro 5000G Trebek
 
352
-
 
3 GB/s
 
2.5 GB GD5 320b
Thumbnail
NVIDIA GeForce GTX 480M
 
352
-
 
2.4 GB/s
 
2 GB GD5 256b
Thumbnail
NVIDIA GeForce GTX 465
 
352
-
 
3.2 GB/s
 
1 GB GD5 256b
Thumbnail
NVIDIA Quadro 4000
 
256
-
 
2.8 GB/s
 
2 GB GD5 256b
Thumbnail
NVIDIA Quadro 4000 Mac Edition
 
256
-
 
2.8 GB/s
 
2 GB GD5 256b
Thumbnail
NVIDIA Quadro 4000 SDI
 
256
-
 
2.8 GB/s
 
2 GB GD5 256b
Thumbnail
NVIDIA Quadro 4000 SDI I/O
 
256
-
 
2.8 GB/s
 
2 GB GD5 256b
Thumbnail
NVIDIA Quadro 4000 SDI I/O Trebek
 
256
-
 
2.8 GB/s
 
2 GB GD5 256b
Thumbnail
NVIDIA Quadro 4000 SDI Trebek
 
256
-
 
2.8 GB/s
 
2 GB GD5 256b
Thumbnail
NVIDIA Quadro 4000 Trebek
 
256
-
 
2.8 GB/s
 
2 GB GD5 256b

New NVIDIA Tesla GPUs Reduce Cost Of Supercomputing By A Factor Of 10

New Fermi-based Tesla products deliver the performance of a CPU-based cluster at one-tenth the cost and one-twentieth the power.

Designed from the ground-up for parallel computing, the NVIDIA® Tesla™ 20-series GPUs slash the cost of computing by delivering the same performance of a traditional CPU-based cluster at one-tenth the cost and one-twentieth the power.PORTLAND, Ore.— SC09—Nov. 16, 2009NVIDIA Corporation (Nasdaq: NVDA) today unveiled the Tesla 20-series of parallel processors for the high performance computing (HPC) market, based on its new generation CUDA™ processor architecture, codenamed “Fermi”.

The Tesla 20-series introduces features that enable many new applications to perform dramatically faster using GPU Computing. These include ray tracing, 3D cloud computing, video encoding, database search, data analytics, computer-aided engineering and virus scanning.

“NVIDIA has deployed a highly attractive architecture in Fermi, with a feature set that opens the technology up to the entire computing industry,” said Jack Dongarra, director of the Innovative Computing Laboratory at the University of Tennessee and co-author of LINPACK and LAPACK.

The Tesla 20-series GPUs combine parallel computing features that have never been offered on a single device before. These include:

  • Support for the next generation IEEE 754-2008 double precision floating point standard
  • ECC (error correcting codes) for uncompromised reliability and accuracy
  • Multi-level cache hierarchy with L1 and L2 caches
  • Support for the C++ programming language
  • Up to 1 terabyte of memory, concurrent kernel execution, fast context switching, 10x faster atomic instructions, 64-bit virtual address space, system calls and recursive functions

At their core, Tesla GPUs are based on the massively parallel CUDA computing architecture that offers developers a parallel computing model that is easier to understand and program than any of the alternatives developed over the last 50 years.

“There can be no doubt that the future of computing is parallel processing, and it is vital that computer science students get a solid grounding in how to program new parallel architectures,” said Dr. Wen-mei Hwu, Professor in Electrical and Computer Engineering of the University of Illinois at Urbana-Champaign. “GPUs and the CUDA programming model enable students to quickly understand parallel programming concepts and immediately get transformative speed increases.”

The family of Tesla 20-series GPUs includes:

  • Tesla C2050 & C2070 GPU Computing Processors
    • Single GPU PCI-Express Gen-2 cards for workstation configurations
    • Up to 3GB and 6GB (respectively) on-board GDDR5 memoryi
    • Double precision performance in the range of 520GFlops – 630 GFlops
  • Tesla S2050 & S2070 GPU Computing Systems
    • Four Tesla GPUs in a 1U system product for cluster and datacenter deployments
    • Up to 12 GB and 24 GB (respectively) total system memory on board GDDR5 memoryii
    • Double precision performance in the range of 2.1 TFlops – 2.5 TFlops

The Tesla C2050 and C2070 products will retail for $2,499 and $3,999 and the Tesla S2050 and S2070 will retail for $12,995 and $18,995. Products will be available in Q2 2010. For more information about the new Tesla 20-series products, visit the Tesla product pages.

Editors’ note: As previously announced, the first Fermi-based consumer (GeForce®) products are expected to be available first quarter 2010.