Intel Arc A350M vs NVIDIA A100 PCIe 80 GB

Comparison Intel Arc A350M with 4 GB GDDR6 and 768 cores vs NVIDIA A100 PCIe 80 GB with 80 GB HBM2e and 6,912 cores.

Loading...

Performance Rating

NVIDIA A100 PCIe 80 GB outperforms Intel Arc A350M by 1,024.12% in the overall GPU ARK performance rating

A100 A100
H200 H200
MI325X MI325X

Intel Arc A350M

2.3

Intel Arc A350M

2.3
RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

NVIDIA A100 PCIe 80 GB

25.6

NVIDIA A100 PCIe 80 GB

25.6

Expert Comparison

Intel Arc A350M подходит для легких задач, таких как просмотр видео, обработка фотографий и базовые игры при небольшом энергопотреблении (25 Вт). NVIDIA A100 PCIe 80 GB предназначена для мощных вычислений, машинного обучения и высокопроизводительных задач с огромным объемом памяти (80 ГБ) и высокой пропускной способностью (1.94 ТБ/с), но потребляет гораздо больше энергии (300 Вт).

Contents:

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

Memory

Memory Size

4 GB
🔥 +1,900% 80 ГБ

Memory Type

GDDR6 HBM2e

Memory Bandwidth

112.0 GB/s
🔥 1.94 TB/s

Memory Bus Width

64 бит 5,120 бит

ML Performance

FP16 (Half Precision)

6.758 TFLOPS
🔥 +1,054% 77.97 TFLOPS

BF16 (Brain Float)

No
🔥 311.84 TFLOPS

TF32 (TensorFloat)

No
🔥 155.92

Compute Power

FP32 (Single Precision)

3.379 TFLOPS
🔥 +477% 19.49 TFLOPS

FP64 (Double Precision)

0.8448 TFLOPS
🔥 +1,054% 9.746 TFLOPS

CUDA Cores

768
🔥 +800% 6,912

RT Cores

🔥 6
No

Architecture & Compatibility

GPU Architecture

Xe-HPG Ampere

SM (Streaming Multiprocessor)

No
🔥 108

PCIe Version

PCIe 4.0 x8 PCIe 4.0 x16

ML Software Support

CUDA Version

No 8.0

CUDA Toolkit (first supported)

v11

CUDA Toolkit status

Supported Supported

Clocks & Performance

Base Clock

🔥 +8% 1,150
1,065

Boost Clock

🔥 +56% 2,200
1,410

Memory Clock

🔥 +16% 1,750
1,512

Power Consumption

Recommended PSU

No 700 W

Power Connector

No 8-pin EPS

TDP/TGP

🔥 -92% 25 W
300 W

Rendering

Texture Units (TMU)

48
🔥 +800% 432

ROP

🔥 6
No

L2 Cache

4 MB
🔥 +1,900% 80 MB

Additional

Slots

IGP Dual-slot

Release Date

March 30, 2022 June 28, 2021

Display Outputs

Portable Device Dependent
No outputs

Rent on Intelion Cloud

Tesla A100 (80GB)

Available for rent on Intelion Cloud

from 200.89 RUB/hour Rent
Pay-as-you-go, per-second billing
Prices include 22% VAT
EDI & closing documents
Server ready in 3 minutes
Russian-speaking support
Card, SBP or invoice