Home
NVIDIA Tesla S870
NVIDIA Tesla K10
NVIDIA Tesla K40m
NVIDIA Tesla K20m
NVIDIA Tesla K20c
NVIDIA Tesla C2050
NVIDIA A100 PCIe
NVIDIA Tesla S870
This is a GPU manufactured with TSMC 90nm process, based on Nvidia Tesla architecture and released on May 2007. It features 0.681 billion transistors, 128 CUDA cores and 1536MB GDDR3 memory, with 96KB L2 cache, theoretical performance of 345.6GFLOPS, with total power consumption of 800W.
Graphics Card
[Report Issues]
Release Date
May 2007
Generation
Tesla
Type
Professional
Bus Interface
PCIe 1.0 x16
Clock Speeds
[Report Issues]
Memory Clock
800 MHz
Memory
[Report Issues]
Memory Size
1536MB
Memory Type
GDDR3
Memory Bus
384bit
Bandwidth
76.80GB/s
Render Config
[Report Issues]
SM Count
16
Shading Units
128
TMUs
32
ROPs
24
L2 Cache
96 KB
Theoretical Performance
[Report Issues]
Pixel Rate
14.40 GPixel/s
Texture Rate
38.40 GTexel/s
FP32 (float)
345.6 GFLOPS
Graphics Processor
[Report Issues]
GPU Name
G80
Architecture
Tesla
Foundry
TSMC
Process Size
90 nm
Transistors
0.681 billion
Die Size
484 mm²
Board Design
[Report Issues]
TDP
800W
Suggested PSU
1200 W
Outputs
No outputs
Graphics Features
[Report Issues]
DirectX
11.1 (10_0)
OpenGL
3.3
OpenCL
1.1 (1.0)
Vulkan
N/A
CUDA
1.0
Shader Model
4.0
Rankings
[Report Issues]
FP32 (float)
