GIGABYTE AORUS RTX 5090 INFINITY vs NVIDIA DRIVE A100 PROD

Comparison of GIGABYTE AORUS RTX 5090 INFINITY with 32 GB GDDR7 and 21,760 cores vs NVIDIA DRIVE A100 PROD with 32 GB HBM2e and 6,912 cores.

Loading...

Performance Rating

GIGABYTE AORUS RTX 5090 INFINITY outperforms NVIDIA DRIVE A100 PROD by 122.28% in the overall GPU ARK performance rating

A100 A100
H200 H200
MI325X MI325X

GIGABYTE AORUS RTX 5090 INFINITY

47.2

GIGABYTE AORUS RTX 5090 INFINITY

47.2
RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

NVIDIA DRIVE A100 PROD

21.2

NVIDIA DRIVE A100 PROD

21.2

Contents:

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

Memory

Memory Size

32 GB 32 GB

Memory Type

GDDR7 HBM2e

Memory Bandwidth

🔥 1.79 TB/s
1.87 TB/s

Memory Bus Width

512 бит 6,144 бит

ML Performance

FP16 (Half Precision)

🔥 +71% 118.8 TFLOPS
69.67 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

🔥 +582% 118.8 TFLOPS
17.42 TFLOPS

FP64 (Double Precision)

1.856 TFLOPS
🔥 +369% 8.709 TFLOPS

CUDA Cores

🔥 +215% 21,760
6,912

RT Cores

🔥 170
No

Architecture & Compatibility

GPU Architecture

Blackwell 2.0 Ampere

SM (Streaming Multiprocessor)

🔥 +57% 170
108

PCIe Version

PCIe 5.0 x16 PCIe 4.0 x16

ML Software Support

CUDA Version

🔥 12.0
8.0

Clocks & Performance

Base Clock

🔥 +60% 2,017
1,260

Boost Clock

🔥 +117% 2,730
1,260

Memory Clock

🔥 +44% 1,750
1,215

Power Consumption

Recommended PSU

950 W
🔥 -16% 800 W

Power Connector

1x 16-pin None

TDP/TGP

575 W
🔥 -30% 400 W

Rendering

Texture Units (TMU)

🔥 +57% 680
432

ROP

🔥 170
No

L2 Cache

🔥 +200% 96 MB
32 MB

Additional

Slots

Triple-slot IGP

Release Date

Jan. 30, 2025 May 14, 2020

Display Outputs

1x HDMI 2.1b
3x DisplayPort 2.1b
No outputs

Renting is cheaper than buying