GeekRadar / The comparison desk

COMPARE.

GPU

NVIDIA

NVIDIA DRIVE A100 PROD

Graphics processor

Video memory: 32 GB^*
Memory bus: 6,144 bit^*
Rated memory bandwidth: 1,870 GB/s^*

No matched benchmark results are available for this entry yet.

Processing & platform

Architecture: Ampere^*
Process node: 7 nm^*
GPU cores: 6,912^*
Graphics interface: PCIe 4.0 x16^*
Reported chip die area: 826 mm²^*
Transistors: 54,200 million^*
GPU L2 cache: 32 MB^*
Graphics processor: GA100^*
Texture mapping units: 432^*
Raster output units: 192^*
Streaming multiprocessors: 108^*
Tensor cores: 432^*
Chip foundry: TSMC^*
Card or module format: IGP^*
Declared GPU TDP: 400 W^*
Suggested system PSU: 800 W^*
External power connectors: None^*
OpenCL: 3.0^*
CUDA compute capability: 8.0^*

Memory & storage

Memory options: 32^*
Video memory: 32 GB^*
Video memory type: HBM2e^*
Memory bus: 6,144 bit^*
Rated memory bandwidth: 1,870 GB/s^*

Power specifications

Thermal design power: 400 W^*

System configuration

Detailed specifications

Specifications 1 · 29 fields

proc transistors: 54,200 million^*
proc die size: 826^* mm²
cores: 6,912^*
tensor cores: 432^*
sm count: 108^*
base clock: 1,260^*
boost clock: 1,260^*
memory clock: 1,215^*
ram: 32^*
name: NVIDIA DRIVE A100 PROD^*
ram type: HBM2e^*
bus width: 6,144^*
bus interface: PCIe 4.0 x16^*
ram bandwidth: 1.87 TB/s^*
fp16 performance: 69.67^*
fp32 performance: 17.42^*
fp64 performance: 8.709^*
tdp: 400^* W
suggested psu: 800^* W
slot width: IGP^*
api cuda: 8^*
is retail board: No^*
gpi value: 21.23^*
vendor: nvd^*
manufacturer: NVIDIA^*
arch name: Ampere^*
card release date: 2020-05-14^*
proc foundry: TSMC^*
proc process size: 7^* nm

Specifications 2 · 35 fields

CUDA compute capability

8.0^*

OpenCL

3.0^*

Architecture

Ampere^*

Graphics interface

PCIe 4.0 x16^*

Memory bus

6,144^* bit

Reported shader processors

6,912^*

Reported theoretical FP16 peak

69.67^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Reported theoretical FP32 peak

17.42^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Reported theoretical FP64 peak

8.709^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Declared L1 cache configuration

192 KB (per SM)^*

Declared GPU L2 cache

32 MB^*

Reported display outputs

No outputs^*

Theoretical pixel fill rate

241.9 GPixel/s^*

External power connectors

None^*

Reported chip die area

826 mm²^*

Chip foundry

TSMC^*

Process node declaration

7 nm^*

Transistors

54,200 million^*

Graphics processor

GA100^*

Reported video memory

32^* GB

Rated memory bandwidth

1.87 TB/s^*

Video memory type

HBM2e^*

Raster output units

192^*

Reported shading units

6,912^*

Card or module format

IGP^*

Streaming multiprocessors

108^*

Suggested system PSU

800 W^*

2:4 tensor sparsity

Yes^*

Declared GPU TDP

400 W^*

Tensor cores

432^*

Theoretical texture fill rate

544.3 GTexel/s^*

Texture mapping units

432^*

GPU cores

6,912^*

Video memory

32^* GB

Video memory type

HBM2e^*

* Provisional data