NVIDIA A100 PCIe 80 GB vs NVIDIA PG506-232

Comparison of NVIDIA A100 PCIe 80 GB with 80 GB HBM2e and 6,912 cores vs NVIDIA PG506-232 with 24 GB HBM2 and 3,584 cores.

Loading...

Performance Rating

NVIDIA A100 PCIe 80 GB outperforms NVIDIA PG506-232 by 107.03% in the overall GPU ARK performance rating

A100 A100
H200 H200
MI325X MI325X

NVIDIA A100 PCIe 80 GB

25.6

NVIDIA A100 PCIe 80 GB

25.6
RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

NVIDIA PG506-232

12.4

NVIDIA PG506-232

12.4

Contents:

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

Memory

Memory Size

🔥 +233% 80 ГБ
24 ГБ

Memory Type

HBM2e HBM2

Memory Bandwidth

🔥 1.94 TB/s
933.1 GB/s

Memory Bus Width

5,120 бит 3,072 бит

ML Performance

FP16 (Half Precision)

🔥 +656% 77.97 TFLOPS
10.32 TFLOPS

BF16 (Brain Float)

🔥 311.84 TFLOPS
No

TF32 (TensorFloat)

🔥 155.92
No

Compute Power

FP32 (Single Precision)

🔥 +89% 19.49 TFLOPS
10.32 TFLOPS

FP64 (Double Precision)

🔥 +89% 9.746 TFLOPS
5.161 TFLOPS

CUDA Cores

🔥 +93% 6,912
3,584

RT Cores

No No

Architecture & Compatibility

GPU Architecture

Ampere Ampere

SM (Streaming Multiprocessor)

🔥 +93% 108
56

PCIe Version

PCIe 4.0 x16 PCIe 4.0 x16

ML Software Support

CUDA Version

8.0 8.0

Clocks & Performance

Base Clock

🔥 +15% 1,065
930

Boost Clock

1,410
🔥 +2% 1,440

Memory Clock

🔥 +24% 1,512
1,215

Power Consumption

TDP/TGP

300 W
🔥 -45% 165 W

Recommended PSU

700 W
🔥 -36% 450 W

Power Connector

8-pin EPS 8-pin EPS

Rendering

Texture Units (TMU)

🔥 +93% 432
224

ROP

No No

L2 Cache

🔥 +233% 80 MB
24 MB

Additional

Slots

Dual-slot Dual-slot

Release Date

June 28, 2021 April 12, 2021

Display Outputs

No outputs
No outputs

Renting is cheaper than buying