NVIDIA A100 80GB Tensor Core GPU

NVIDIA A100 80GB Tensor Core GPU delivers unprecedented acceleration at every scale to power the world’s highest-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 shifting demands. The A100 80GB debuts the world’s fastest memory bandwidth at over 2 terabytes per second (TB/s) to run the largest models and datasets.

Features:

1. Unmatched Acceleration: Delivers exceptional performance for AI, data analytics, and HPC.
2. NVIDIA Ampere Architecture: The foundation for the world’s highest-performing data centers.
3. Up to 20X Performance Boost: Provides significant improvements over the previous generation.
4. Dynamic GPU Partitioning: Can be split into seven GPU instances to adapt to varying workloads.
5. World’s Fastest Memory Bandwidth: 80GB version offers over 2 TB/s for running large models
6. FP64 Performance: 9.7 TFLOPS
7. FP64 Tensor Core Performance: 19.5 TFLOPS
8. FP32 Performance: 19.5 TFLOPS
9. Tensor Float 32 (TF32): ,Standard: 156 TFLOPS , With Sparsity*: 312 TFLOPS
10. BFLOAT16 Tensor Core Performance: Standard: 312 TFLOPS,  With Sparsity*: 624 TFLOPS
11. FP16 Tensor Core Performance: Standard: 312 TFLOPS,  With Sparsity*: 624 TFLOPS
12. INT8 Tensor Core Performance: Standard: 624 TOPS,  With Sparsity*: 1248 TOPS

Package Includes:

1 x NVIDIA A100 80GB Tensor Core GPU