Home NVIDIA CMP 90HX

NVIDIA CMP 90HX

This is a GPU manufactured with Samsung 8nm process, based on Nvidia Ampere architecture and released on Jul 2021. It features 28.3 billion transistors, 6400 CUDA cores and 10GB GDDR6X memory, with 5MB L2 cache, theoretical performance of 21.89TFLOPS, with total power consumption of 320W.

Graphics Card

[Report Issues]
Release Date
Jul 2021
Generation
Mining GPUs
Type
Desktop
Bus Interface
PCIe 4.0 x16

Clock Speeds

[Report Issues]
Base Clock
1500MHz
Boost Clock
1710MHz
Memory Clock
1188MHz

Memory

[Report Issues]
Memory Size
10GB
Memory Type
GDDR6X
Memory Bus
320bit
Bandwidth
760.3 GB/s

Render Config

[Report Issues]
SM Count
50
Shading Units
6400
TMUs
200
ROPs
80
Tensor Cores
200
RT Cores
50
L1 Cache
128 KB (per SM)
L2 Cache
5MB

Theoretical Performance

[Report Issues]
Pixel Rate
136.8 GPixel/s
Texture Rate
342.0 GTexel/s
FP16 (half)
21.89 TFLOPS
FP32 (float)
21.89 TFLOPS
FP64 (double)
342.0 GFLOPS

Graphics Processor

[Report Issues]
GPU Name
GA102
GPU Variant
GA102-100-A1
Architecture
Ampere
Foundry
Samsung
Process Size
8 nm
Transistors
28,300 million
Die Size
628mm²

Board Design

[Report Issues]
TDP
320W
Suggested PSU
700W
Outputs
No outputs
Power Connectors
2x 8-pin

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)
22.02 TFLOPS
NVIDIA CMP 90HX 10 GB GDDR6X
21.89 TFLOPS
21.75 TFLOPS
21.75 TFLOPS
21.75 TFLOPS
21.75 TFLOPS
21.75 TFLOPS

Related Comparisons

© 2024 - TopCPU.net   Contact Us Privacy Policy