GPUDatacenterReleased Jun 22, 2020

NVIDIA A100 PCIe 40GB

40 GB HBM2 · 5120-bit · 6,912 cores

The PCI Express add-in card version of NVIDIA's first Ampere data center accelerator, for mainstream servers that cannot take an SXM module. It offers the same third-generation Tensor Cores, TF32 support, structured sparsity and Multi-Instance GPU partitioning as the SXM part within a 250 W envelope, and two cards can be joined with an NVLink bridge.

General

Manufacturer: NVIDIA
Model: A100 PCIe 40GB
Segment: Datacenter
GPU chip: GA100
Architecture: Ampere
Release date: Jun 22, 2020
Price: Search on Amazon

Memory

Memory size: 40 GB
Memory type: HBM2
Bus width: 5120-bit
Bandwidth: 1,555 GB/s
Memory clock: 1,215 MHz

Clocks & silicon

GPU clock: 765 MHz
Boost clock: 1,410 MHz
Shader units: 6,912 CUDA Cores
Tensor / AI cores: 432
RT cores: —
Transistors: 54.2 billion
Technology (nm): 7 nm
TSMC N7
TDP / TBP: 250 W

Interface & APIs

Bus interface: PCIe 4.0 x16
SLI / multi-GPU: NVLink bridge (600 GB/s, 2 GPUs)
DirectX: N/A (compute-only)
OpenGL: N/A (compute-only)
Vulkan: N/A (compute-only)
Other APIs: CUDA (compute capability 8.0)

AI support

Precisions: FP8FP16BF16INT8INT4TF32FP64
AI accelerator: Third-generation Tensor Cores (432)
Peak AI TOPS: 1,248 TOPS
Notes: Third-generation Tensor Cores supporting FP64, TF32, BF16, FP16, INT8, INT4 and binary; FP8 arrived with Hopper. Peak throughput with structured sparsity: INT8 1,248 TOPS, FP16 and BFLOAT16 624 TFLOPS, TF32 312 TFLOPS; dense rates are half. FP64 is 9.7 TFLOPS, FP64 Tensor Core and FP32 19.5 TFLOPS each. Multi-Instance GPU partitions the card into up to seven instances.

All NVIDIA GPUs →

Datacenter gpus from NVIDIA announced around the same time as the NVIDIA A100 PCIe 40GB. Add any of them to your compare list to see the specs side by side.

gpu