AMD Radeon Pro Duo Polaris vs NVIDIA A100 PCIe 80 GB

Comparison of AMD Radeon Pro Duo Polaris with 16 GB GDDR5 and 2,304 cores vs NVIDIA A100 PCIe 80 GB with 80 GB HBM2e and 6,912 cores.

Loading...

Performance Rating

NVIDIA A100 PCIe 80 GB outperforms AMD Radeon Pro Duo Polaris by 418.83% in the overall GPU ARK performance rating

A100 A100
H200 H200
MI325X MI325X

AMD Radeon Pro Duo Polaris

4.9

AMD Radeon Pro Duo Polaris

4.9
RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

NVIDIA A100 PCIe 80 GB

25.6

NVIDIA A100 PCIe 80 GB

25.6

Contents:

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

Memory

Memory Size

16 ГБ ×2 (32 ГБ)
🔥 +400% 80 ГБ

Memory Type

GDDR5 HBM2e

Memory Bandwidth

224.0 GB/s ×2 (448 GB/s)
🔥 1.94 TB/s

Memory Bus Width

256 бит ×2 (512 бит) 5,120 бит

ML Performance

FP16 (Half Precision)

5.728 TFLOPS
🔥 +1,261% 77.97 TFLOPS

BF16 (Brain Float)

No
🔥 311.84 TFLOPS

TF32 (TensorFloat)

No
🔥 155.92

Compute Power

FP32 (Single Precision)

5.728 TFLOPS
🔥 +240% 19.49 TFLOPS

FP64 (Double Precision)

0.358 TFLOPS
🔥 +2,622% 9.746 TFLOPS

CUDA Cores

2,304 ×2 (4608)
🔥 +200% 6,912

RT Cores

No No

Architecture & Compatibility

GPU Architecture

GCN 4.0 Ampere

SM (Streaming Multiprocessor)

No
🔥 108

PCIe Version

PCIe 3.0 x16 PCIe 4.0 x16

ML Software Support

CUDA Version

No 8.0

Clocks & Performance

Base Clock

No
🔥 1,065

Boost Clock

No
🔥 1,410

Memory Clock

1,750
🔥 1,512

Power Consumption

TDP/TGP

🔥 -17% 250 W
300 W

Recommended PSU

🔥 -14% 600 W
700 W

Power Connector

1x 6-pin + 1x 8-pin 8-pin EPS

Rendering

Texture Units (TMU)

144 ×2 (288)
🔥 +200% 432

ROP

No No

L2 Cache

2 MB
🔥 +3,900% 80 MB

Additional

Slots

Dual-slot Dual-slot

Release Date

April 24, 2017 June 28, 2021

Display Outputs

1x HDMI 2.0b
3x DisplayPort 1.4a
No outputs

Renting is cheaper than buying