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 | A100 SXM4 40 GB |
|---|---|
| Overview | |
| Product name | NVIDIA A100 SXM4 40 GB |
| Architecture | Ampere |
| Generation / family | NVIDIA A-Series |
| GPU codename | GA100 |
| Launch date | 2020-05-14 |
| Market segment | Data Center in NVIDIA A-Series |
| Board type / entry type | Data Center GPU |
| GPU | |
| Process node | TSMC 7 nm |
| Die size | 826 mm² |
| Transistor count | 54.2 billion |
| GPU chip | GA100 |
| SM / multiprocessor count | 108 |
| CUDA Cores | 6912 |
| Tensor Cores | 432 |
| ROPs | 160 |
| TMUs | 432 |
| Clocks | |
| Base / Core clock | 1,095 MHz |
| Boost clock | 1,410 MHz |
| Memory clock | 1,215 MHz |
| Memory | |
| Memory size | 40 GB |
| Memory type | HBM2e |
| Memory bus width | 5,120-bit |
| Memory bandwidth | 1,560 GB/s |
| Bus / Interface | |
| Bus interface | PCIe 4.0 x16 |
| AGP / PCI / PCIe distinction | PCIe |
| Power | |
| TDP / TBP / board power | 400 W |
| Recommended PSU | 800 W |
| Power connectors | None |
| Slot width | SXM Module |
| Features | |
| CUDA support | 8.0 |
| Performance / Benchmarks | |
| FP32 throughput | 19.49 TFLOPS |
| FP16 throughput | 77.97 TFLOPS |
Overview
Product name
A100 SXM4 40 GB
NVIDIA A100 SXM4 40 GB
Architecture
A100 SXM4 40 GB
Ampere
Generation / family
A100 SXM4 40 GB
NVIDIA A-Series
GPU codename
A100 SXM4 40 GB
GA100
Launch date
A100 SXM4 40 GB
2020-05-14
Market segment
A100 SXM4 40 GB
Data Center in NVIDIA A-Series
Board type / entry type
A100 SXM4 40 GB
Data Center GPU
GPU
Process node
A100 SXM4 40 GB
TSMC 7 nm
Die size
A100 SXM4 40 GB
826 mm²
Transistor count
A100 SXM4 40 GB
54.2 billion
GPU chip
A100 SXM4 40 GB
GA100
SM / multiprocessor count
A100 SXM4 40 GB
108
CUDA Cores
A100 SXM4 40 GB
6912
Tensor Cores
A100 SXM4 40 GB
432
ROPs
A100 SXM4 40 GB
160
TMUs
A100 SXM4 40 GB
432
Clocks
Base / Core clock
A100 SXM4 40 GB
1,095 MHz
Boost clock
A100 SXM4 40 GB
1,410 MHz
Memory clock
A100 SXM4 40 GB
1,215 MHz
Memory
Memory size
A100 SXM4 40 GB
40 GB
Memory type
A100 SXM4 40 GB
HBM2e
Memory bus width
A100 SXM4 40 GB
5,120-bit
Memory bandwidth
A100 SXM4 40 GB
1,560 GB/s
Bus / Interface
Bus interface
A100 SXM4 40 GB
PCIe 4.0 x16
AGP / PCI / PCIe distinction
A100 SXM4 40 GB
PCIe
Power
TDP / TBP / board power
A100 SXM4 40 GB
400 W
Recommended PSU
A100 SXM4 40 GB
800 W
Power connectors
A100 SXM4 40 GB
None
Slot width
A100 SXM4 40 GB
SXM Module
Display / Media
Features
CUDA support
A100 SXM4 40 GB
8.0
Performance / Benchmarks
FP32 throughput
A100 SXM4 40 GB
19.49 TFLOPS
FP16 throughput
A100 SXM4 40 GB
77.97 TFLOPS