AMD Radeon Instinct MI325X vs Intel Arc A380M

Comparison AMD Radeon Instinct MI325X with 288 GB HBM3e and 19,456 cores vs Intel Arc A380M with 6 GB GDDR6 and 1,024 cores.

Loading...

Performance Rating

AMD Radeon Instinct MI325X outperforms Intel Arc A380M by 3,125.81% in the overall GPU ARK performance rating

A100 A100
H200 H200
MI325X MI325X

AMD Radeon Instinct MI325X

100.0

AMD Radeon Instinct MI325X

100.0
RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

Intel Arc A380M

3.1

Intel Arc A380M

3.1

Expert Comparison

AMD Radeon Instinct MI325X значительно превосходит Intel Arc A380M по всем параметрам. MI325X имеет гораздо больше ядер, больше памяти и пропускную способность, а также более высокую производительность в FP32. MI325X подходит для вычислений высокой сложности и больших данных, тогда как Arc A380M лучше подходит для легких задач, таких как графика и базовые вычисления.

Contents:

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

Memory

Memory Size

🔥 +4,700% 288 ГБ
6 GB

Memory Type

HBM3e GDDR6

Memory Bandwidth

🔥 10.3 TB/s
186.0 GB/s

Memory Bus Width

8,192 бит 96 бит

ML Performance

FP16 (Half Precision)

🔥 +7,880% 653.7 TFLOPS
8.192 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

🔥 +1,895% 81.72 TFLOPS
4.096 TFLOPS

FP64 (Double Precision)

🔥 +7,880% 81.72 TFLOPS
1.024 TFLOPS

CUDA Cores

🔥 +1,800% 19,456
1,024

RT Cores

No
🔥 8

Architecture & Compatibility

GPU Architecture

CDNA 3.0 Xe-HPG

SM (Streaming Multiprocessor)

No No

PCIe Version

PCIe 5.0 x16 MXM-A (3.1)

ML Software Support

CUDA Version

No No

CUDA Toolkit status

Supported Supported

Clocks & Performance

Base Clock

1,000
🔥 +55% 1,550

Boost Clock

🔥 +5% 2,100
2,000

Memory Clock

🔥 +30% 2,525
1,937

Power Consumption

Recommended PSU

1400 W No

Power Connector

None No

TDP/TGP

1000 W
🔥 -96% 35 W

Rendering

Texture Units (TMU)

🔥 +1,800% 1,216
64

ROP

No
🔥 8

L2 Cache

16 MB
🔥 4 MB

Benchmarks

MLPerf, llama2-70b-99.9 (Dummy)

3 596 tokens/s

MLPerf, llama2-70b-99.9 (fp8)

1 946 tokens/s

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

22.4 tokens/s

MLPerf, mixtral-8x7b (fp8)

6 975 tokens/s

Additional

Slots

OAM Module MXM Module

Release Date

Oct. 12, 2024 Jan. 24, 2023

Display Outputs

No outputs
Portable Device Dependent

Renting is cheaper than buying