AMD Radeon Instinct MI250 vs Intel Arc A730M

Comparison AMD Radeon Instinct MI250 with 128 GB HBM2e and 13,312 cores vs Intel Arc A730M with 12 GB GDDR6 and 3,072 cores.

Loading...

Performance Rating

AMD Radeon Instinct MI250 outperforms Intel Arc A730M by 561.77% 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

Intel Arc A730M

7.7

Intel Arc A730M

7.7

Expert Comparison

AMD Radeon Instinct MI250 значительно превосходит Intel Arc A730M в производительности, особенно в вычислительной математике (FP32: 45.26 TFLOPS против 12.6 TFLOPS). MI250 также имеет гораздо больше памяти (128 ГБ HBM2e против 12 ГБ GDDR6) и большую пропускную способность (3.28 ТБ/с против 336 ГБ/с). Однако Arc A730M потребляет меньше энергии (80 Вт против 500 Вт) и более актуален для мобильных устройств благодаря своей низкой тепловыделительной мощности.

Contents:

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

Memory

Memory Size

🔥 +967% 128 ГБ
12 GB

Memory Type

HBM2e GDDR6

Memory Bandwidth

🔥 3.28 TB/s
336.0 GB/s

Memory Bus Width

8,192 бит 192 бит

ML Performance

FP16 (Half Precision)

🔥 +1,337% 362.1 TFLOPS
25.19 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

🔥 +259% 45.26 TFLOPS
12.6 TFLOPS

FP64 (Double Precision)

🔥 45.26 TFLOPS
No

CUDA Cores

🔥 +333% 13,312
3,072

RT Cores

No
🔥 24

Architecture & Compatibility

GPU Architecture

CDNA 2.0 Xe-HPG

SM (Streaming Multiprocessor)

No No

PCIe Version

PCIe 4.0 x16 PCIe 4.0 x16

ML Software Support

CUDA Version

No No

CUDA Toolkit status

Supported Supported

Clocks & Performance

Base Clock

1,000
🔥 +10% 1,100

Boost Clock

1,700
🔥 +21% 2,050

Memory Clock

1,600
🔥 +9% 1,750

Power Consumption

Recommended PSU

900 W No

Power Connector

2x 8-pin No

TDP/TGP

500 W
🔥 -84% 80 W

Rendering

Texture Units (TMU)

🔥 +333% 832
192

ROP

No
🔥 24

L2 Cache

🔥 +33% 16 MB
12 MB

Benchmarks

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

63.9 tokens/s

Additional

Slots

Dual-slot IGP

Release Date

Nov. 8, 2021 March 12, 2022

Display Outputs

No outputs
Portable Device Dependent

Renting is cheaper than buying