NVIDIA Tesla S870 Professional Computing Solution

4x Tesla C870

Product status: Official | Last Update: 2015-02-20 | Report Error
Overview
Manufacturer
NVIDIA
Original Series
Tesla 8
Release Date
May 2nd, 2007
Launch Price
$11,999 USD
Graphics Processing Unit
GPU Model
4× G80
Architecture
G80
Fabrication Process
90 nm
Die Size
4× 484 mm2
Transistors Count
4× 681M
Transistors Density
1.4M TRAN/mm2
Cores
4× 128 (512)
SM
4× 8 (32)
TPCs
4× 2 (8)
TMUs
4× 32 (128)
ROPs
4× 24 (96)
Clocks
Base Clock
600 MHz
Boost Clock
TBC MHz
Memory Clock
800 MHz
Effective Memory Clock
1600 Mbps
Memory Configuration
Memory Size
4× 1536 (6144) MB
Memory Type
GDDR3
Memory Bus Width
4× 384 (1536)-bit
Memory Bandwidth
4× 76.8 (307.2) GB/s
Physical
Interface
PCI-Express 1.0 x16
TDP/TBP
800 W
Recommended PSU
1100 W
API Support
DirectX
10.0
Vulkan
-
OpenGL
3.3
OpenCL
-

Performance
Pixel Fillrate
57.6 GPixels/s
Texture Fillrate
76.8 GTexel/s
Peak FP32
614.4 GFLOPS
FP32 Perf. per Watt
768 FLOPS/W
FP32 Perf. per mm2
317 FLOPS/mm2




 ModelCoresBoost ClockMemory ClockMemory Config.
Thumbnail
NVIDIA Tesla S870
 
512
-
 
1.6 Gbps
 
24 GB GD3 384b
Thumbnail
NVIDIA Tesla D870
 
256
-
 
1.6 Gbps
 
6 GB GD3 384b
Thumbnail
NVIDIA Tesla C870
 
128
-
 
1.6 Gbps
 
1.5 GB GD3 384b
 ModelCoresBoost ClockMemory ClockMemory Config.
Thumbnail
NVIDIA Tesla S870
 
512
-
 
1.6 GB/s
 
24 GB GD3 384b
Thumbnail
NVIDIA Quadro PLEX 2100 S4
 
512
-
 
1.6 GB/s
 
24 GB GD3 384b
Thumbnail
NVIDIA Tesla D870
 
256
-
 
1.6 GB/s
 
6 GB GD3 384b
Thumbnail
NVIDIA Quadro PLEX 1000 Model-IV
 
256
-
 
1.6 GB/s
 
6 GB GD3 384b
Thumbnail
NVIDIA Quadro FX 5600 SDI
 
128
-
 
1.6 GB/s
 
1.5 GB GD3 384b
Thumbnail
NVIDIA Quadro FX 5600
 
128
-
 
1.6 GB/s
 
1.5 GB GD3 384b
Thumbnail
NVIDIA Tesla C870
 
128
-
 
1.6 GB/s
 
1.5 GB GD3 384b
Thumbnail
NVIDIA GeForce 8800 Ultra
 
128
-
 
2.2 GB/s
 
768 MB GD3 384b
Thumbnail
NVIDIA GeForce 8800 GTX
 
128
-
 
1.8 GB/s
 
768 MB GD3 384b
Thumbnail
NVIDIA GeForce 8800 GTS 640 (122 Cores)
 
112
-
 
1.6 GB/s
 
640 MB GD3 320b
Thumbnail
NVIDIA Quadro FX 4600 SDI
 
96
-
 
1.4 GB/s
 
768 MB GD3 384b
Thumbnail
NVIDIA Quadro FX 4600
 
96
-
 
1.4 GB/s
 
768 MB GD3 384b
Thumbnail
NVIDIA GeForce 8800 GTS 640
 
96
-
 
1.6 GB/s
 
640 MB GD3 320b
Thumbnail
NVIDIA GeForce 8800 GTS 320
 
96
-
 
1.6 GB/s
 
320 MB GD3 320b

NVIDIA Unveils Tesla GPU Computing Processor

NVIDIA today announced Tesla, a new class of processors based on a revolutionary new graphics processing unit (GPU). Under the Tesla brand, NVIDIA will offer a family of GPU computing products that will place the power previously available only from supercomputers in the hands of every scientist and engineer. The Tesla family of GPU computing solutions span PCs to large scale server clusters.

The new family includes:

  • NVIDIA Tesla C870 GPU Computing Processor, a dedicated computing board that scales to multiple Tesla GPUs inside a single PC or workstation. The Tesla GPU features 128 parallel processors, and delivers up to 518 gigaflops of parallel computation. The GPU Computing processor can be used in existing systems partnered with high-performance CPUs.
  • NVIDIA Tesla S870 Deskside Supercomputer, a scalable computing system that includes two NVIDIA Tesla GPUs and attaches to a PC or workstation through an industry-standard PCI-Express connection. With multiple deskside systems, a standard PC or workstation is transformed into a personal supercomputer, delivering up to 8 teraflops of compute power to the desktop.
  • NVIDIA Tesla D870 GPU Computing Server, a 1U server housing up to eight NVIDIA Tesla GPUs, containing more than 1000 parallel processors that add teraflops of parallel processing to clusters. The Tesla GPU Server is the first server system of its kind to bring GPU computing to the datacenter.

Pricing and Availability
For more NVIDIA Tesla product information, including a list of officially certified host systems and authorized partners, please visit: nvidia.com/tesla.