Inno3D P102-100 Twin X2 vs NVIDIA A100 PCIe 80 GB

Comparison of Inno3D P102-100 Twin X2 with 5 GB GDDR5X and 3,200 cores vs NVIDIA A100 PCIe 80 GB with 80 GB HBM2e and 6,912 cores.

Loading...

Performance Rating

NVIDIA A100 PCIe 80 GB outperforms Inno3D P102-100 Twin X2 by 273.07% in the overall GPU ARK performance rating

A100 A100
H200 H200
MI325X MI325X

Inno3D P102-100 Twin X2

6.9

Inno3D P102-100 Twin X2

6.9
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

5 ГБ
🔥 +1,500% 80 ГБ

Memory Type

GDDR5X HBM2e

Memory Bandwidth

440.3 GB/s
🔥 1.94 TB/s

Memory Bus Width

320 бит 5,120 бит

ML Performance

FP16 (Half Precision)

168.3 TFLOPS
🔥 77.97 TFLOPS

BF16 (Brain Float)

No
🔥 311.84 TFLOPS

TF32 (TensorFloat)

No
🔥 155.92

Compute Power

FP32 (Single Precision)

10.77 TFLOPS
🔥 +81% 19.49 TFLOPS

FP64 (Double Precision)

0.3366 TFLOPS
🔥 +2,795% 9.746 TFLOPS

CUDA Cores

3,200
🔥 +116% 6,912

RT Cores

No No

Architecture & Compatibility

GPU Architecture

Pascal Ampere

SM (Streaming Multiprocessor)

25
🔥 +332% 108

PCIe Version

PCIe 1.0 x4 PCIe 4.0 x16

ML Software Support

CUDA Version

6.1
🔥 8.0

Clocks & Performance

Base Clock

1,582
🔥 1,065

Boost Clock

1,683
🔥 1,410

Memory Clock

1,376
🔥 +10% 1,512

Power Consumption

TDP/TGP

🔥 -17% 250 W
300 W

Recommended PSU

🔥 -14% 600 W
700 W

Power Connector

2x 8-pin 8-pin EPS

Rendering

Texture Units (TMU)

200
🔥 +116% 432

ROP

No No

L2 Cache

2.5 MB
🔥 +3,100% 80 MB

Additional

Slots

Dual-slot Dual-slot

Release Date

Feb. 12, 2018 June 28, 2021

Display Outputs

No outputs
No outputs

Renting is cheaper than buying