GeekRadar / The comparison desk

COMPARE.

GPU

NVIDIA

NVIDIA RTX A500 Embedded

Graphics processor

Video memory: 4 GB^*
Memory bus: 64 bit^*
Rated memory bandwidth: 96 GB/s^*

No matched benchmark results are available for this entry yet.

Processing & platform

Architecture: Ampere^*
Process node: 8 nm^*
GPU cores: 2,048^*
Graphics interface: PCIe 4.0 x8^*
Reported chip die area: 200 mm²^*
Transistors: 8,700 million^*
GPU L2 cache: 2 MB^*
Graphics processor: GA107S^*
Texture mapping units: 64^*
Raster output units: 32^*
Streaming multiprocessors: 16^*
Tensor cores: 64^*
Ray tracing cores: 16^*
Chip foundry: Samsung^*
Card or module format: MXM Module^*
Declared GPU TDP: 20 W^*
External power connectors: None^*
DirectX / feature level: 12 Ultimate (12_2)^*
OpenGL: 4.6^*
OpenCL: 3.0^*
Vulkan: 1.4^*
CUDA compute capability: 8.6^*
Shader model: 6.9^*

Memory & storage

Memory options: 4^*
Video memory: 4 GB^*
Video memory type: GDDR6^*
Memory bus: 64 bit^*
Rated memory bandwidth: 96 GB/s^*

Power specifications

Thermal design power: 20 W^*

System configuration

Detailed specifications

Specifications 1 · 29 fields

proc transistors: 8,700 million^*
proc die size: 200^* mm²
cores: 2,048^*
tensor cores: 64^*
rt cores: 16^*
sm count: 16^*
base clock: 435^*
boost clock: 1,335^*
memory clock: 1,500^*
ram: 4^*
name: NVIDIA RTX A500 Embedded^*
ram type: GDDR6^*
bus width: 64^*
bus interface: PCIe 4.0 x8^*
ram bandwidth: 96^* GB/s
fp16 performance: 5.468^*
fp32 performance: 5.468^*
fp64 performance: 0.0854^*
tdp: 20^* W
slot width: MXM Module^*
api cuda: 8.6^*
is retail board: No^*
gpi value: 2.87^*
vendor: nvd^*
manufacturer: NVIDIA^*
arch name: Ampere^*
card release date: 2022-03-30^*
proc foundry: Samsung^*
proc process size: 8^* nm

Specifications 2 · 39 fields

CUDA compute capability

8.6^*

DirectX / feature level

12 Ultimate (12_2)^*

OpenCL

3.0^*

OpenGL

4.6^*

Shader model

6.9^*

Vulkan

1.4^*

Architecture

Ampere^*

Graphics interface

PCIe 4.0 x8^*

Memory bus

64^* bit

Reported shader processors

2,048^*

Reported theoretical FP16 peak

5.468^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Reported theoretical FP32 peak

5.468^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Reported theoretical FP64 peak

0.0854^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Declared L1 cache configuration

128 KB (per SM)^*

Declared GPU L2 cache

2 MB^*

Reported display outputs

Portable Device Dependent^*

Theoretical pixel fill rate

42.72 GPixel/s^*

External power connectors

None^*

Reported chip die area

200 mm²^*

Chip foundry

Samsung^*

Process node declaration

8 nm^*

Transistors

8,700 million^*

Graphics processor

GA107S^*

Reported video memory

4^* GB

Rated memory bandwidth

96.00 GB/s^*

Video memory type

GDDR6^*

Raster output units

32^*

Ray tracing cores

16^*

Reported shading units

2,048^*

Card or module format

MXM Module^*

Streaming multiprocessors

16^*

2:4 tensor sparsity

Yes^*

Declared GPU TDP

20 W^*

Tensor cores

64^*

Theoretical texture fill rate

85.44 GTexel/s^*

Texture mapping units

64^*

GPU cores

2,048^*

Video memory

4^* GB

Video memory type

GDDR6^*

* Provisional data