NVIDIA - GPU computing processor
NVIDIA A100 Tensor Core GPU delivers unprecedented acceleration at every scale to power the high-performing elastic data centers for AI, data analytics, and HPC. Powered by the NVIDIA Ampere Architecture, A100 is the engine of the NVIDIA data center platform. A100 provides up to 20x higher performance over the prior generation and can be partitioned into seven GPU instances to dynamically adjust to JTFfting demands.
| General Information | |
|---|---|
| Category | Graphic accelerator cards |
| Description | NVIDIA - GPU computing processor - A100 Tensor Core - 40 GB HBM2 - PCIe 4.0 x16 - fanless - for ThinkAgile HX7530 Appliance; MX3530-H Hybrid Appliance; MX3531-H Hybrid Certified Node |
| Manufacturer | Lenovo |
| MSRP | $35,939.00 |
| UNSPSC | 43201401 |
| Main Specifications | |
| A/V Interface Type | PCI Express 4.0 x16 |
| Header / Brand | NVIDIA |
| Packaged Quantity | 1 |
| Video Memory / Technology | HBM2 |
| Video Output / Graphics Processor | NVIDIA A100 Tensor Core |
| Video Output / Graphics Processor Manufacturer | NVIDIA |
| Compatibility Information | |
| Designed For |
|
| General | |
| API Supported | OpenCL, DirectCompute, OpenACC |
| Bus Type | PCI Express 4.0 x16 |
| CUDA Cores | 6912 |
| Device Type | GPU computing processor - fanless |
| Features | NVIDIA Tensor Core, Multi-Instance GPU (MIG) technology, NVIDIA Ampere GPU technology, Error Correcting Codes (ECC) Memory, 9.7 Tflops peak double-precision floating point performance, 19.5 Tflops peak single-precision floating point performance, 312 Tflops peak half-precision floating point performance, 432 third-generation Tensor Cores per GPU, dual slot width, Nvidia CUDA technology, full-height full-length (FHFL) |
| Graphics Engine | NVIDIA A100 Tensor Core |
| Memory | |
| Size | 40 GB |
| Technology | HBM2 |
| Miscellaneous | |
| Power Consumption Operational | 250 Watt |
Write Your Own Review
