AMD Radeon E8950 vs AMD Radeon Instinct MI325X

Comparison AMD Radeon E8950 with 8 GB GDDR5 and 2,048 cores vs AMD Radeon Instinct MI325X with 288 GB HBM3e and 19,456 cores.

Loading...

Performance Rating

AMD Radeon Instinct MI325X outperforms AMD Radeon E8950 by 2,685.52% in the overall GPU ARK performance rating

A100 A100
H200 H200
MI325X MI325X

AMD Radeon E8950

3.6

AMD Radeon E8950

3.6
RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

AMD Radeon Instinct MI325X

100.0

AMD Radeon Instinct MI325X

100.0

Expert Comparison

AMD Radeon Instinct MI325X значительно превосходит AMD Radeon E8950 в большинстве параметров. MI325X имеет больше ядер, более высокую пропускную способность памяти и значительно большую производительность в FP32. Он предназначен для вычислительных задач и обработки больших объемов данных, тогда как E8950 больше подходит для игр и базовых задач.

Contents:

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

Memory

Memory Size

8 GB
🔥 +3,500% 288 ГБ

Memory Type

GDDR5 HBM3e

Memory Bandwidth

192.0 GB/s
🔥 10.3 TB/s

Memory Bus Width

256 бит 8,192 бит

ML Performance

FP16 (Half Precision)

4.096 TFLOPS
🔥 +15,859% 653.7 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

4.096 TFLOPS
🔥 +1,895% 81.72 TFLOPS

FP64 (Double Precision)

0.256 TFLOPS
🔥 +31,822% 81.72 TFLOPS

CUDA Cores

2,048
🔥 +850% 19,456

RT Cores

No No

Architecture & Compatibility

GPU Architecture

GCN 3.0 CDNA 3.0

SM (Streaming Multiprocessor)

No No

PCIe Version

MXM-B (3.0) PCIe 5.0 x16

ML Software Support

CUDA Version

No No

CUDA Toolkit status

Supported Supported

Clocks & Performance

Base Clock

735
🔥 +36% 1,000

Boost Clock

1,000
🔥 +110% 2,100

Memory Clock

1,500
🔥 +68% 2,525

Power Consumption

Recommended PSU

No 1400 W

Power Connector

None None

TDP/TGP

🔥 -90% 95 W
1000 W

Rendering

Texture Units (TMU)

128
🔥 +850% 1,216

ROP

No No

L2 Cache

512 KB
🔥 16 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

MXM Module OAM Module

Release Date

Sept. 29, 2015 Oct. 12, 2024

Display Outputs

Portable Device Dependent
No outputs

Renting is cheaper than buying