Home NVIDIA CMP 170HX

NVIDIA CMP 170HX

This is a GPU manufactured with TSMC 7nm process, based on Nvidia Ampere architecture and released on Sep 2021. It features 54.2 billion transistors, 4480 CUDA cores and 16GB HBM2e memory, with 8MB L2 cache, theoretical performance of 12.63TFLOPS, with total power consumption of 250W.

Graphics Card

[Report Issues]
Release Date
Sep 2021
Generation
Mining GPUs
Type
Desktop
Bus Interface
PCIe 4.0 x4

Clock Speeds

[Report Issues]
Base Clock
1140MHz
Boost Clock
1410MHz
Memory Clock
1458MHz

Memory

[Report Issues]
Memory Size
16GB
Memory Type
HBM2e
Memory Bus
4096bit
Bandwidth
1493 GB/s

Render Config

[Report Issues]
SM Count
70
Shading Units
4480
TMUs
280
ROPs
128
Tensor Cores
280
L1 Cache
192 KB (per SM)
L2 Cache
8MB

Theoretical Performance

[Report Issues]
Pixel Rate
180.5 GPixel/s
Texture Rate
394.8 GTexel/s
FP16 (half)
50.53 TFLOPS
FP32 (float)
12.63 TFLOPS
FP64 (double)
6.317 TFLOPS

Graphics Processor

[Report Issues]
GPU Name
GA100
GPU Variant
GA100-105F-A1
Architecture
Ampere
Foundry
TSMC
Process Size
7 nm
Transistors
54,200 million
Die Size
826mm²

Board Design

[Report Issues]
TDP
250W
Suggested PSU
600W
Outputs
No outputs
Power Connectors
2x 8-pin

Graphics Features

[Report Issues]
DirectX
N/A
OpenGL
N/A
OpenCL
3.0
Vulkan
N/A
CUDA
8.0
Shader Model
N/A

Rankings

[Report Issues]
FP32 (float)
12.66 TFLOPS
12.66 TFLOPS
NVIDIA CMP 170HX 16 GB HBM2e
12.63 TFLOPS
NVIDIA Quadro P6000 24 GB GDDR5X
12.63 TFLOPS
Intel Arc A580 8 GB GDDR6
12.29 TFLOPS
12.29 TFLOPS

Related Comparisons

© 2024 - TopCPU.net   Contact Us Privacy Policy