AMD Radeon Instinct MI300X vs Intel UHD Graphics 48EU Mobile

Comparison AMD Radeon Instinct MI300X with 192 GB HBM3 and 19,456 cores vs Intel UHD Graphics 48EU Mobile and 384 cores.

Loading...

Performance Rating

A100 A100
H200 H200
MI325X MI325X

AMD Radeon Instinct MI300X

94.1

AMD Radeon Instinct MI300X

94.1
RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

Intel UHD Graphics 48EU Mobile

Intel UHD Graphics 48EU Mobile

Expert Comparison

AMD Radeon Instinct MI300X значительно превосходит Intel UHD Graphics 48EU Mobile по всем параметрам. MI300X имеет гораздо больше ядер, большую память и пропускную способность, а также более высокие показатели FP32. Он предназначен для вычислительных задач, машинного обучения и высокопроизводительных вычислений. В то время как Intel UHD Graphics 48EU Mobile более энергоэффективен и подходит для базовых задач графики и офисной работы.

Contents:

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

Memory

Memory Size

🔥 192 ГБ
No

Memory Type

HBM3 System Shared

Memory Bandwidth

🔥 10.3 TB/s
System Dependent

Memory Bus Width

8,192 бит No

ML Performance

FP16 (Half Precision)

🔥 +36,916% 653.7 TFLOPS
1.766 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

🔥 +9,153% 81.72 TFLOPS
0.8832 TFLOPS

FP64 (Double Precision)

🔥 +36,911% 81.72 TFLOPS
0.2208 TFLOPS

CUDA Cores

🔥 +4,967% 19,456
384

RT Cores

No No

Architecture & Compatibility

GPU Architecture

CDNA 3.0 Generation 12.2

SM (Streaming Multiprocessor)

No No

PCIe Version

PCIe 5.0 x16 Ring Bus

ML Software Support

CUDA Version

No No

CUDA Toolkit status

Supported Supported

Clocks & Performance

Base Clock

🔥 +233% 1,000
300

Boost Clock

🔥 +83% 2,100
1,150

Memory Clock

🔥 2,525
No

Power Consumption

Recommended PSU

1150 W No

Power Connector

None No

TDP/TGP

750 W
🔥 -94% 45 W

Rendering

Texture Units (TMU)

🔥 +4,967% 1,216
24

ROP

No No

L2 Cache

🔥 16 MB
1024 KB

Benchmarks

MLPerf, llama2-70b-99.9 (UNSET)

1 983 tokens/s

MLPerf, llama2-70b-99.9 (fp16)

1 740 tokens/s

MLPerf, llama2-70b-99.9 (fp8)

1 057 tokens/s

MLPerf, llama3.1-405b (UNSET)

30.4 tokens/s

MLPerf, llama3.1-405b (fp16)

34.8 tokens/s

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

232.9 tokens/s

MLPerf, mixtral-8x7b (fp8)

5 975 tokens/s

Additional

Slots

OAM Module IGP

Release Date

Dec. 6, 2023 Jan. 4, 2022

Display Outputs

No outputs
Portable Device Dependent

Renting is cheaper than buying