8 GB
GDDR5811 MHz
Boost Clock100 W
TDP28 nm
ProcessShare on Social Media
Share Tesla K8 specifications with othersTechnical Specifications
Core Specifications
Architecture:
Kepler
Process Size:
28 nm
Base Clock:
693 MHz
Boost Clock:
811 MHz
Shader Units:
1536
TMUs:
128
ROPs:
32
Memory & Performance
Memory Size:
8 GB
Memory Type:
GDDR5
Memory Bandwidth:
160.0 GB/s
Bus Interface:
PCIe 2.0 x16
TDP:
100 W
Suggested PSU:
300 W
Cache & Die Information
L1 Cache:
16 KB
L2 Cache:
0.5 MB
Die Size:
294 mm²
Transistors:
3.5 billion
Transistor Density:
12.0 million/mm²
Physical Specifications
Board Length:
241 mm
Power Connectors:
1x 6-pin
Quick Facts
Performance
Pixel Fill Rate
25.9 GPixel/s
Texture Fill Rate
103.8 GTexel/s
FP32 Performance
2.5 TFLOPS
CUDA Toolkit Compatibility
Cuda Compute
3.0
sm_30
Architecture
Kepler
Supported CUDA Toolkits
5.0
5.5
6.0
6.5
7.0
7.5
8.0
Note: Support dropped in CUDA 9.0
Kepler architecture (GK104) - Support dropped in CUDA 9.0