NVIDIA Tesla V100
The NVIDIA Tesla V100 is a data center graphics card based on the Volta architecture. Released on 2017-05-10 with a launch price of $10,000.00, it features 5120 CUDA cores and 32 GB of HBM2 memory.
General info about Tesla V100
| Architecture |
Volta (GV100) |
| Market Segment |
Data Center |
| Release Date |
2017-05-10 |
| Launch Price |
$10,000.00 |
| Manufacturing Process |
12nm |
Technical specs of Tesla V100
| CUDA Cores |
5120 |
| Base Clock Speed |
1245 MHz |
| Boost Clock Speed |
1455 MHz |
| Transistor Count |
21.1B |
| VRAM Capacity |
32 GB HBM2 |
| Memory Bus Width |
4096 bits |
| Memory Bandwidth |
900.0 GB/s |
| TDP |
300 W |
Key technical parameters of the NVIDIA Tesla V100 include its 5120 CUDA cores, 1245 MHz base clock, and 1455 MHz boost clock, delivering high performance for data center applications.
Benchmark performance of Tesla V100
| FP32 (float) |
14 TFLOPS |
| FP16 (half) |
112 TFLOPS |
The NVIDIA Tesla V100 achieves 14 TFLOPS in FP32 performance, making it a top contender in data center workloads.
Gaming performance of Tesla V100
The NVIDIA Tesla V100 is not designed for gaming.
Features and connectivity of Tesla V100
| Tensor_cores |
Gen 1 |
| Mixed_precision |
True |
| Ports |
NVLink 2, PCIe Gen3 |
Physical dimensions of Tesla V100
| Length |
10.5in |
| Width |
4.4in |
| Height |
2-slot |
Rankings and efficiency of Tesla V100
| Ranking Position |
#10 |
| Popularity Ranking |
#15 |
| Cost Effectiveness |
1.0/5 |
| Power Efficiency |
1.1/5 |