AMD Stream Processor vs NVIDIA H200 SXM 141 GB

Comparison AMD Stream Processor with 1,024 GB GDDR3 vs NVIDIA H200 SXM 141 GB with 141 GB HBM3e and 16,896 cores.

Loading...

Performance Rating

A100 A100
H200 H200
MI325X MI325X

AMD Stream Processor

AMD Stream Processor

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

NVIDIA H200 SXM 141 GB

67.4

NVIDIA H200 SXM 141 GB

67.4

Expert Comparison

Видеокарта NVIDIA H200 SXM значительно превосходит AMD Stream Processor по многим параметрам. У нее больше памяти (141 ГБ против 1024 МБ), шина памяти шире (6144 бит против 256 бит), пропускная способность выше (4.89 ТБ/с против 41.47 ГБ/с) и большая мощность (700 Вт против 165 Вт). H200 SXM также имеет более современную архитектуру Hopper и высокую производительность в FP32 (66.91 ТФЛПС). AMD Stream Processor более старый и менее эффективный вариант для современных задач, таких как глубокое обучение и вычисления на GPU.

Contents:

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

Memory

Memory Size

1,024 MB
🔥 141 ГБ

Memory Type

GDDR3 HBM3e

Memory Bandwidth

41.47 GB/s
🔥 4.89 TB/s

Memory Bus Width

256 бит 6,144 бит

ML Performance

FP16 (Half Precision)

No
🔥 267.6 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

No
🔥 66.91 TFLOPS

FP64 (Double Precision)

No
🔥 33.45 TFLOPS

CUDA Cores

No
🔥 16,896

RT Cores

No No

Architecture & Compatibility

GPU Architecture

Ultra-Threaded SE Hopper

SM (Streaming Multiprocessor)

No
🔥 132

PCIe Version

PCIe 1.0 x16 PCIe 5.0 x16

ML Software Support

CUDA Version

No 9.0

CUDA Toolkit (first supported)

v12

CUDA Toolkit status

Supported Supported

Clocks & Performance

Base Clock

No
🔥 1,500

Boost Clock

No
🔥 1,980

Memory Clock

648
🔥 +146% 1,593

Power Consumption

Recommended PSU

🔥 -59% 450 W
1100 W

Power Connector

1x 6-pin 8-pin EPS

TDP/TGP

🔥 -76% 165 W
700 W

Rendering

Texture Units (TMU)

16
🔥 +3,200% 528

ROP

No No

L2 Cache

No
🔥 50 MB

Benchmarks

MLPerf, llama2-70b-99.9 (UNSET)

3 534 tokens/s

MLPerf, llama2-70b-99.9 (fp16)

3 553 tokens/s

MLPerf, llama2-70b-99.9 (fp8)

2 444 tokens/s

MLPerf, llama3.1-405b (fp16)

40.8 tokens/s

MLPerf, llama3.1-405b (fp8)

25.3 tokens/s

MLPerf, llama3.1-8b (fp8)

5 161 tokens/s

MLPerf, deepseek-r1 (fp8)

1 113 tokens/s

MLPerf, mixtral-8x7b (fp8)

7 132 tokens/s

Additional

Slots

Dual-slot
🔥 SXM Module

Release Date

March 12, 2006 Nov. 18, 2024

Display Outputs

2x DVI
1x S-Video
No outputs

Rent on Intelion Cloud

H200 (141GB)

Available for rent on Intelion Cloud

from 375.0 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