NVIDIA CMP 70HX vs Pradeon RX 580 4 GB

Comparison of NVIDIA CMP 70HX with 8 GB GDDR6X and 3,840 cores vs Pradeon RX 580 4 GB with 4 GB GDDR5 and 2,304 cores.

Loading...

Performance Rating

H200 H200
MI325X MI325X
A100 A100

NVIDIA CMP 70HX

NVIDIA CMP 70HX

MI250 MI250
Instinct MI300X Instinct MI300X
RX 7900 XTX RX 7900 XTX

Pradeon RX 580 4 GB

Pradeon RX 580 4 GB

Contents:

Memory ML Performance Compute Power Architecture & Compatibility ML Software Support Clocks & Performance Power Consumption Rendering Additional

Memory

Memory Size

8 GB 4 GB

Memory Type

GDDR6X GDDR5

Memory Bandwidth

608.3 GB/s 256.0 GB/s

Memory Bus Width

256 бит 256 бит

ML Performance

FP16 (Half Precision)

10.71 TFLOPS 6.175 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

10.71 TFLOPS 6.175 TFLOPS

FP64 (Double Precision)

0.1674 TFLOPS 0.3859 TFLOPS

CUDA Cores

3,840 2,304

RT Cores

30 No

Architecture & Compatibility

GPU Architecture

Ampere GCN 4.0

SM (Streaming Multiprocessor)

30 No

PCIe Version

PCIe 1.0 x4 PCIe 3.0 x16

ML Software Support

CUDA Version

8.6 No

Clocks & Performance

Base Clock

1,365 1,257

Boost Clock

1,395 1,340

Memory Clock

1,188 2,000

Power Consumption

TDP/TGP

unknown 185 W

Recommended PSU

🔥 -56% 200 W
450 W

Power Connector

1x 12-pin 1x 8-pin

Rendering

Texture Units (TMU)

120 144

ROP

30 No

L2 Cache

4 MB 2 MB

Additional

Slots

Dual-slot Dual-slot

Release Date

March 11, 2021 April 18, 2017

Display Outputs

No outputs
1x HDMI 2.0b
3x DisplayPort 1.4a

1x DVI
1x HDMI 2.0b
3x DisplayPort 1.4a

Renting is cheaper than buying