Key Architecture Highlights
- FP64 Compute performance: FP64: 9.7 TFLOPS; FP64 Tensor Core: 19.5 TFLOPS
- FP32 Compute performance: 19.5 TFLOPS
- Tensor Compute performance: The BFLOAT16 Tensor Core: common:312 TFLOPS; sparse:624 TFLOPS FP16 Tensor Core: common:312 TFLOPS; sparse:624 TFLOPS
Applications
- AI training and inference
- High-performance computing
- Data center
Engineering Parameters
| FP64 Compute performance | FP64: 9.7 TFLOPS FP64 Tensor Core: 19.5 TFLOPS |
|---|---|
| FP32 Compute performance | 19.5 TFLOPS |
| Tensor Compute performance | The BFLOAT16 Tensor Core: common:312 TFLOPS; sparse:624 TFLOPS FP16 Tensor Core: common:312 TFLOPS; sparse:624 TFLOPS |
| Integer Compute performance | Normal: 624 TOPS; Sparse: 1248 TOPS |
| GPU memory ／ Memory | 80GB HBM2e |
| GPU memory bandwidth | 2,039 GB/s |
| Power consumption | 400W * |
| MIG Division | Up to 7 MIGs @ 10GB |
| Form factor and installation | SXM |
| Interconnect Interface | NVLink: 600 GB/s PCIe Gen4: 64 GB/s |
Warranty
Public manufacturer information does not specify the warranty term applicable to our supply channel. The supply region, channel and actual warranty service are confirmed in the supply contract.
Manufacturer information
Manufacturer informationVerified Documentation & Datasheets
Manufacturer product information
Download Document