CMP 90HX

GPU Code: GA102

10 GB

GDDR6X

1710 MHz

Boost Clock

320 W

TDP

8 nm

Process
Share on Social Media
Share CMP 90HX specifications with others

Technical Specifications

Core Specifications
Architecture: Ampere
Process Size: 8 nm
Base Clock: 1500 MHz
Boost Clock: 1710 MHz
Shader Units: 6400
SMs: 50
Tensor Cores: 200
RT Cores: 50
TMUs: 200
ROPs: 80
Memory & Performance
Memory Size: 10 GB
Memory Type: GDDR6X
Memory Bandwidth: 760.3 GB/s
Bus Interface: PCIe 1.0 x4
TDP: 320 W
Suggested PSU: 700 W
Cache & Die Information
L1 Cache: 128 KB
L2 Cache: 5.0 MB
Die Size: 628 mm²
Transistors: 28.3 billion
Transistor Density: 45.1 million/mm²

API Support

DirectX
12.2
OpenGL
4.6
Vulkan
1.3
Cuda Compute
8.6 sm_86

Physical Specifications

Board Length: 285 mm
Board Width: 112 mm
Power Connectors: 2x 8-pin

Quick Facts

Release Date: 2021-07-28
Manufacturer: NVIDIA
Generation: Mining GPUs

Performance

Pixel Fill Rate 136.8 GPixel/s
Texture Fill Rate 342.0 GTexel/s
FP32 Performance 21.9 TFLOPS

CUDA Toolkit Compatibility

Cuda Compute
8.6 sm_86
Architecture

Ampere

Supported CUDA Toolkits
11.1 11.2 11.3 11.4 11.5 11.6 11.7 11.8 12.0 12.1 12.2 12.3 12.4 12.5 12.6 12.7 12.8

Ampere architecture with 2nd gen RT cores and hardware AV1 decode