GPU Wiki
Compare NVIDIA GPUs
Select up to four GPU Wiki entries to compare matching specifications row by row. The comparison uses the site database and keeps generation-specific specs visibly separate.
Row order:
Muted cells indicate unavailable, not applicable, or not directly comparable specifications.
| Spec | Tesla V100 SXM2 16 GB |
|---|---|
| Overview | |
| Product name | NVIDIA Tesla V100 SXM2 16 GB |
| Architecture | Volta |
| Generation / family | Tesla V Series |
| GPU codename | GV100 |
| Launch date | 2019-11-26 |
| Market segment | Data Center in Tesla V Series |
| Board type / entry type | Data Center GPU |
| GPU | |
| Process node | TSMC 12 nm |
| Die size | 815 mm² |
| Transistor count | 21.1 billion |
| GPU chip | GV100 |
| SM / multiprocessor count | 80 |
| CUDA Cores | 5120 |
| Tensor Cores | 640 |
| ROPs | 128 |
| TMUs | 320 |
| Clocks | |
| Base / Core clock | 1,245 MHz |
| Boost clock | 1,597 MHz |
| Memory clock | 1,106 MHz |
| Memory | |
| Memory size | 16 GB |
| Memory type | HBM2 |
| Memory bus width | 4,096-bit |
| Memory bandwidth | 1,130 GB/s |
| Bus / Interface | |
| Bus interface | PCIe 3.0 x16 |
| AGP / PCI / PCIe distinction | PCIe |
| Power | |
| TDP / TBP / board power | 250 W |
| Recommended PSU | 600 W |
| Power connectors | None |
| Slot width | SXM Module |
| Features | |
| DirectX support | DirectX 12.1 |
| OpenGL support | OpenGL 4.6 |
| Vulkan support | Vulkan 1.4 |
| CUDA support | 7.0 |
| Shader Model | 6.8 |
| Performance / Benchmarks | |
| FP32 throughput | 16.35 TFLOPS |
| FP16 throughput | 32.71 TFLOPS |
Overview
Product name
Tesla V100 SXM2 16 GB
NVIDIA Tesla V100 SXM2 16 GB
Architecture
Tesla V100 SXM2 16 GB
Volta
Generation / family
Tesla V100 SXM2 16 GB
Tesla V Series
GPU codename
Tesla V100 SXM2 16 GB
GV100
Launch date
Tesla V100 SXM2 16 GB
2019-11-26
Market segment
Tesla V100 SXM2 16 GB
Data Center in Tesla V Series
Board type / entry type
Tesla V100 SXM2 16 GB
Data Center GPU
GPU
Process node
Tesla V100 SXM2 16 GB
TSMC 12 nm
Die size
Tesla V100 SXM2 16 GB
815 mm²
Transistor count
Tesla V100 SXM2 16 GB
21.1 billion
GPU chip
Tesla V100 SXM2 16 GB
GV100
SM / multiprocessor count
Tesla V100 SXM2 16 GB
80
CUDA Cores
Tesla V100 SXM2 16 GB
5120
Tensor Cores
Tesla V100 SXM2 16 GB
640
ROPs
Tesla V100 SXM2 16 GB
128
TMUs
Tesla V100 SXM2 16 GB
320
Clocks
Base / Core clock
Tesla V100 SXM2 16 GB
1,245 MHz
Boost clock
Tesla V100 SXM2 16 GB
1,597 MHz
Memory clock
Tesla V100 SXM2 16 GB
1,106 MHz
Memory
Memory size
Tesla V100 SXM2 16 GB
16 GB
Memory type
Tesla V100 SXM2 16 GB
HBM2
Memory bus width
Tesla V100 SXM2 16 GB
4,096-bit
Memory bandwidth
Tesla V100 SXM2 16 GB
1,130 GB/s
Bus / Interface
Bus interface
Tesla V100 SXM2 16 GB
PCIe 3.0 x16
AGP / PCI / PCIe distinction
Tesla V100 SXM2 16 GB
PCIe
Power
TDP / TBP / board power
Tesla V100 SXM2 16 GB
250 W
Recommended PSU
Tesla V100 SXM2 16 GB
600 W
Power connectors
Tesla V100 SXM2 16 GB
None
Slot width
Tesla V100 SXM2 16 GB
SXM Module
Display / Media
Features
DirectX support
Tesla V100 SXM2 16 GB
DirectX 12.1
OpenGL support
Tesla V100 SXM2 16 GB
OpenGL 4.6
Vulkan support
Tesla V100 SXM2 16 GB
Vulkan 1.4
CUDA support
Tesla V100 SXM2 16 GB
7.0
Shader Model
Tesla V100 SXM2 16 GB
6.8
Performance / Benchmarks
FP32 throughput
Tesla V100 SXM2 16 GB
16.35 TFLOPS
FP16 throughput
Tesla V100 SXM2 16 GB
32.71 TFLOPS