Product Summary
The NVIDIA A100 40GB PCIe GPU (Part Number: 699-21001-0200-400) is a high-performance data center accelerator designed for artificial intelligence, machine learning, deep learning, high-performance computing (HPC), and enterprise data analytics. Built on NVIDIA's Ampere architecture, the A100 features 40GB of high-bandwidth HBM2 memory, third-generation Tensor Cores, and Multi-Instance GPU (MIG) technology, allowing a single GPU to be partitioned into up to seven independent GPU instances. Its PCIe 4.0 interface enables integration into compatible enterprise servers, while NVIDIA NVLink provides high-speed GPU-to-GPU communication in supported configurations. The A100 is engineered for demanding computational workloads requiring exceptional parallel processing performance, memory bandwidth, and scalability.
Technical Specifications
|
Specification |
Details |
|---|---|
|
Manufacturer |
NVIDIA |
|
Model |
A100 40GB PCIe |
|
Part Number |
699-21001-0200-400 |
|
Product Family |
NVIDIA A100 Tensor Core |
|
GPU Architecture |
NVIDIA Ampere |
|
GPU Processor |
GA100-883AA-A1 |
|
CUDA Cores |
6,912 |
|
Tensor Cores |
432 (3rd Generation) |
|
GPU Memory |
40GB HBM2 |
|
Memory Interface |
5,120-bit |
|
Memory Bandwidth |
1,555 GB/s |
|
Memory Clock |
1,215 MHz |
|
Base GPU Clock |
765 MHz |
|
Boost GPU Clock |
1,410 MHz |
|
FP32 Performance |
19.5 TFLOPS |
|
FP64 Performance |
9.7 TFLOPS |
|
FP64 Tensor Core |
19.5 TFLOPS |
|
TF32 Tensor Performance |
156 TFLOPS |
|
FP16/BF16 Tensor Performance |
312 TFLOPS |
|
INT8 Tensor Performance |
624 TOPS |
|
Interface |
PCI Express 4.0 x16 |
|
NVLink Support |
3rd Generation, up to 600 GB/s (two GPUs) |
|
Multi-Instance GPU (MIG) |
Up to 7 independent instances |
|
Error Correction |
ECC Memory Support |
|
Maximum Power Consumption |
250W |
|
Power Connector |
1 × 8-pin CPU/EPS auxiliary power |
|
Cooling |
Passive Heatsink (requires server airflow) |
|
Form Factor |
Full Height, Full Length, Dual Slot |
|
Card Length |
10.5 inches (266.7 mm) |
|
Operating System Support |
Linux and Windows (driver-dependent) |
|
Primary Applications |
AI, Deep Learning, HPC, Data Analytics, GPU Computing |
