AMD Radeon Instinct MI300X vs NVIDIA GRID A100A

Comparison AMD Radeon Instinct MI300X with 192 GB HBM3 and 19,456 cores vs NVIDIA GRID A100A with 32 GB HBM2e and 6,912 cores.

Loading...

Performance Rating

AMD Radeon Instinct MI300X outperforms NVIDIA GRID A100A by 316.74% in the overall GPU ARK 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

NVIDIA GRID A100A

22.6

NVIDIA GRID A100A

22.6

Expert Comparison

AMD Radeon Instinct MI300X имеет более мощную архитектуру CDNA 3.0 и значительно больше памяти (192 ГБ HBM3 против 32 ГБ HBM2e), что делает его предпочтительным для вычислений и машинного обучения. Однако NVIDIA GRID A100A с архитектурой Ampere предлагает лучшую пропускную способность (1.87 TB/s против 10.3 TB/s) и более высокий индекс производительности (94.1 против 22.6), что делает его подходящим для графических задач и виртуализации.

Contents:

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

Memory

Memory Size

🔥 +500% 192 ГБ
32 GB

Memory Type

HBM3 HBM2e

Memory Bandwidth

🔥 +451% 10.3 TB/s
1.87 TB/s

Memory Bus Width

8,192 бит 6,144 бит

ML Performance

FP16 (Half Precision)

🔥 +738% 653.7 TFLOPS
77.97 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

🔥 +319% 81.72 TFLOPS
19.49 TFLOPS

FP64 (Double Precision)

🔥 +738% 81.72 TFLOPS
9.746 TFLOPS

CUDA Cores

🔥 +181% 19,456
6,912

RT Cores

No No

Architecture & Compatibility

GPU Architecture

CDNA 3.0 Ampere

SM (Streaming Multiprocessor)

No
🔥 108

PCIe Version

PCIe 5.0 x16 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

1,000
🔥 +10% 1,095

Boost Clock

🔥 +49% 2,100
1,410

Memory Clock

🔥 +108% 2,525
1,215

Power Consumption

Recommended PSU

1150 W
🔥 -30% 800 W

Power Connector

None None

TDP/TGP

750 W
🔥 -47% 400 W

Rendering

Texture Units (TMU)

🔥 +181% 1,216
432

ROP

No No

L2 Cache

16 MB
🔥 +100% 32 MB

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 May 14, 2020

Display Outputs

No outputs
No outputs

Renting is cheaper than buying