| |
| Product | NVIDIA® A100 GPU Computing Accelerator - 80GB HBM2 - PCIe 4.0 x16 - Passive Cooling |
| Action | Select |
| Main Specifications |
| Product Series |
Nvidia A100 |
| Core Type |
NVIDIA TENSOR |
| Host Interface |
PCI Express 4.0 x16 |
| GPU Architecture |
Ampere |
| Detailed Specifications |
| PCIe x16 Interconnect Bandwidth |
PCIe Gen4 64 GB/s |
| Max Memory Size |
80 GB |
| Max Memory Bandwidth |
1,935 GB/s |
| Peak FP64 |
9.7 TFLOPS |
| Peak FP64 Tensor Core |
19.5 TFLOPS |
| INT8 Tensor Core |
624 TOPS |
| TF32 Tensor Core |
156 TFLOPS |
| FP32 |
19.5 TFLOPS |
| Peak BFLOAT16 Tensor Core |
312 TFLOPS |
| Peak FP16 Tensor Core |
312 TFLOPS |
| Total NVLink Bandwidth |
600 GB/s (via NVLink Bridge for up to 2-GPUs) |
| Multi-Instance GPUs |
7 MIGs at 10GB |
| Cooling |
Passive |
| Dual Slot |
Yes |
| Supplementary Power Connectors |
1x 8-pin CPU (EPS12V) |
| Max Graphics Card Power (W) |
300W |
| Action | Select |