Home NVIDIA A10G

NVIDIA A10G

This is a GPU manufactured with Samsung 8nm process, based on Nvidia Ampere architecture and released on Apr 2021. It features 28.3 billion transistors, 9216 CUDA cores and 12GB GDDR6 memory, with 6MB L2 cache, theoretical performance of 31.52TFLOPS, with total power consumption of 150W.

Graphics Card

[Report Issues]
Release Date
Apr 2021
Generation
Tesla
Type
Professional
Bus Interface
PCIe 4.0 x16

Clock Speeds

[Report Issues]
Base Clock
1320MHz
Boost Clock
1710MHz
Memory Clock
1563MHz

Memory

[Report Issues]
Memory Size
12GB
Memory Type
GDDR6
Memory Bus
384bit
Bandwidth
600.2 GB/s

Render Config

[Report Issues]
SM Count
72
Shading Units
9216
TMUs
288
ROPs
96
Tensor Cores
288
RT Cores
72
L1 Cache
128 KB (per SM)
L2 Cache
6MB

Theoretical Performance

[Report Issues]
Pixel Rate
164.2 GPixel/s
Texture Rate
492.5 GTexel/s
FP16 (half)
31.52 TFLOPS
FP32 (float)
31.52 TFLOPS
FP64 (double)
985.0 GFLOPS

Graphics Processor

[Report Issues]
GPU Name
GA102
GPU Variant
GA102-890-A1
Architecture
Ampere
Foundry
Samsung
Process Size
8 nm
Transistors
28,300 million
Die Size
628mm²

Board Design

[Report Issues]
TDP
150W
Suggested PSU
450W
Outputs
No outputs
Power Connectors
8-pin EPS

Graphics Features

[Report Issues]
DirectX
12 Ultimate (12_2)
OpenGL
4.6
OpenCL
3.0
Vulkan
1.3
CUDA
8.6
Shader Model
6.6

Rankings

[Report Issues]
FP32 (float)
32.69 TFLOPS
AMD Radeon RX 7700 12 GB GDDR6
31.95 TFLOPS
31.95 TFLOPS
NVIDIA A10G 12 GB GDDR6
31.52 TFLOPS
NVIDIA A10 PCIe 24 GB GDDR6
31.24 TFLOPS
30.64 TFLOPS
NVIDIA L4 24 GB GDDR6
30.29 TFLOPS
Blender
NVIDIA A10G 12 GB GDDR6
3664
NVIDIA RTX A4000 16 GB GDDR6
3658
3619

Related Comparisons

© 2024 - TopCPU.net   Contact Us Privacy Policy