NVIDIA A100 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. Available in 40GB and 80GB memory versions, A100 80GB debuts the world’s fastest memory bandwidth at over 2 terabytes per second (TB/s) to run the largest models and datasets.
A100 is part of the complete NVIDIA data center solution that incorporates building blocks across hardware, networking, software, libraries, and optimized AI models and applications from NGC™. Representing the most powerful end-to-end AI and HPC platform for data centers, it allows researchers to deliver real-world results and deploy solutions into production at scale. Specification NVIDIA A100 Product SKU P1001 SKU 200
NVPN: 699-21001-0200-xxx Total board power 250 W Thermal solution Passive Mechanical Form Factor Full-height, full-length (FHFL) 10.5 ”, dual-slot GPU SKU GA100-883AA-A1 PCI Device IDs Device ID: 0x20F1
Vendor ID: 0x10DE
Sub-Vendor ID: 0x10DE
Sub-System ID: 0x145F
GPU clocks Base: 765
MHz Boost: 1410
MHz VBIOS EEPROM size: 8
Mbit UEFI: Supported PCI Express interface PCI Express 4.0 ×16 Lane and polarity reversal supported Power connectors and headers One CPU 8-pin auxiliary power connector
Weight Board: 1240 Grams (excluding bracket and extenders)
Bracket with screws: 20
Grams Long offset extender: 64
Grams Straight extender: 39 Grams Memory clock 1215 MHz Memory type HBM2 Memory size 40 GB Memory bus width 5120 bits Peak memory bandwidth Up to 1555 GB/s SR-IOV support Supported -- 16 VF (virtual functions) BAR address (physical function) BAR 0: 16 MiB1 BAR 1: 64 GiB1 BAR 3: 32 MiB1 BAR address (virtual function) BAR 0: 512 MiB, (256 KiB p
