Home NVIDIA CMP 70HX

NVIDIA CMP 70HX

This is a GPU manufactured with Samsung 8nm process, based on Nvidia Ampere architecture and released on 2021. It features 17.4 billion transistors, 6144 CUDA cores and 8GB GDDR6X memory, with 4MB L2 cache, theoretical performance of 17.14TFLOPS.

Graphics Card

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

Clock Speeds

[Report Issues]
Base Clock
1365MHz
Boost Clock
1395MHz
Memory Clock
1188MHz

Memory

[Report Issues]
Memory Size
8GB
Memory Type
GDDR6X
Memory Bus
256bit
Bandwidth
608.3 GB/s

Render Config

[Report Issues]
SM Count
48
Shading Units
6144
TMUs
192
ROPs
96
Tensor Cores
192
RT Cores
48
L1 Cache
128 KB (per SM)
L2 Cache
4MB

Theoretical Performance

[Report Issues]
Pixel Rate
133.9 GPixel/s
Texture Rate
267.8 GTexel/s
FP16 (half)
17.14 TFLOPS
FP32 (float)
17.14 TFLOPS
FP64 (double)
267.8 GFLOPS

Graphics Processor

[Report Issues]
GPU Name
GA104
GPU Variant
GA104-100-A1
Architecture
Ampere
Foundry
Samsung
Process Size
8 nm
Transistors
17,400 million
Die Size
392mm²

Board Design

[Report Issues]
TDP
Unknown
Suggested PSU
200W
Outputs
No outputs
Power Connectors
1x 12-pin

Graphics Features

[Report Issues]
DirectX
12 Ultimate (12_2)
OpenGL
4.6
OpenCL
3.0
Vulkan
1.3
CUDA
8.6
Shader Model
6.7

Rankings

[Report Issues]
FP32 (float)
17.27 TFLOPS
Intel Arc A750 8 GB GDDR6
17.2 TFLOPS
17.2 TFLOPS
NVIDIA CMP 70HX 8 GB GDDR6X
17.14 TFLOPS
16.79 TFLOPS
16.7 TFLOPS
16.7 TFLOPS

Related Comparisons

© 2024 - TopCPU.net   Contact Us Privacy Policy