AMD Radeon Instinct MI250 vs Matrox D1480 Quad DisplayPort

Comparison of AMD Radeon Instinct MI250 with 128 GB HBM2e and 13,312 cores vs Matrox D1480 Quad DisplayPort with 4 GB GDDR5 and 512 cores.

Loading...

Performance Rating

Matrox D1480 Quad DisplayPort outperforms AMD Radeon Instinct MI250 by 29.12% in the overall GPU ARK performance rating

A100 A100
H200 H200
MI325X MI325X

AMD Radeon Instinct MI250

50.9

AMD Radeon Instinct MI250

50.9
RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

Matrox D1480 Quad DisplayPort

65.7

Matrox D1480 Quad DisplayPort

65.7

Expert Comparison

AMD Radeon Instinct MI250 лучше подходит для вычислений и машинного обучения благодаря большей пропускной способности памяти (3.28 TB/s) и более высокому количеству ядер (13312). Matrox D1480Quad DisplayPort более эффективен для графических задач с меньшими требованиями к вычислительной мощности, обладая более высокой пропускной способностью памяти (96.13 GB/s) и меньшим энергопотреблением (47 Вт).

Contents:

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

Memory

Memory Size

🔥 +3,100% 128 ГБ
4 ГБ

Memory Type

HBM2e GDDR5

Memory Bandwidth

🔥 3.28 TB/s
96.13 GB/s

Memory Bus Width

8,192 бит 128 бит

ML Performance

FP16 (Half Precision)

🔥 +1,526% 362.1 TFLOPS
22.27 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

45.26 TFLOPS
🔥 +3,048% 1,425.0 TFLOPS

FP64 (Double Precision)

🔥 +101,517% 45.26 TFLOPS
0.044539999999999996 TFLOPS

CUDA Cores

🔥 +2,500% 13,312
512

RT Cores

No No

Architecture & Compatibility

GPU Architecture

CDNA 2.0 Pascal

SM (Streaming Multiprocessor)

No
🔥 4

PCIe Version

PCIe 4.0 x16 PCIe 3.0 x16

ML Software Support

CUDA Version

No 6.1

Clocks & Performance

Base Clock

1,000
🔥 +35% 1,354

Boost Clock

🔥 +22% 1,700
1,392

Memory Clock

🔥 +7% 1,600
1,502

Power Consumption

TDP/TGP

500 W
🔥 -91% 47 W

Recommended PSU

900 W
🔥 -78% 200 W

Power Connector

2x 8-pin None

Rendering

Texture Units (TMU)

🔥 +2,500% 832
32

ROP

No No

L2 Cache

🔥 16 MB
1024 KB

Benchmarks

llama.cpp, llama-2-7b-Q4_0

63.9 tokens/s

Additional

Slots

Dual-slot Single-slot

Release Date

Nov. 8, 2021 May 21, 2020

Display Outputs

No outputs
4x mini-DisplayPort 1.4a
4x DisplayPort 1.4a

Renting is cheaper than buying