NVIDIA A100 PCIe 80 GB vs NVIDIA Switch GPU 20nm

Comparison of NVIDIA A100 PCIe 80 GB with 80 GB HBM2e and 6,912 cores vs NVIDIA Switch GPU 20nm with 4 GB DDR4 and 256 cores.

Loading...

Performance Rating

NVIDIA A100 PCIe 80 GB outperforms NVIDIA Switch GPU 20nm by 10.62% 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 Switch GPU 20nm

23.2

NVIDIA Switch GPU 20nm

23.2

Contents:

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

Memory

Memory Size

🔥 +1,900% 80 ГБ
4 ГБ

Memory Type

HBM2e DDR4

Memory Bandwidth

🔥 1.94 TB/s
25.60 GB/s

Memory Bus Width

5,120 бит 64 бит

ML Performance

FP16 (Half Precision)

🔥 77.97 TFLOPS
786.4 TFLOPS

BF16 (Brain Float)

🔥 311.84 TFLOPS
No

TF32 (TensorFloat)

🔥 155.92
No

Compute Power

FP32 (Single Precision)

🔥 19.49 TFLOPS
393.2 TFLOPS

FP64 (Double Precision)

🔥 +79,200% 9.746 TFLOPS
0.012289999999999999 TFLOPS

CUDA Cores

🔥 +2,600% 6,912
256

RT Cores

No No

Architecture & Compatibility

GPU Architecture

Ampere Maxwell 2.0

SM (Streaming Multiprocessor)

🔥 108
No

PCIe Version

PCIe 4.0 x16 No

ML Software Support

CUDA Version

🔥 8.0
5.3

Clocks & Performance

Base Clock

🔥 +177% 1,065
384

Boost Clock

🔥 +84% 1,410
768

Memory Clock

🔥 1,512
1,600

Power Consumption

TDP/TGP

300 W
🔥 -95% 15 W

Recommended PSU

700 W No

Power Connector

8-pin EPS No

Rendering

Texture Units (TMU)

🔥 +2,600% 432
16

ROP

No No

L2 Cache

🔥 80 MB
No

Additional

Slots

Dual-slot No

Release Date

June 28, 2021 March 17, 2017

Display Outputs

No outputs
1x USB Type-C

Renting is cheaper than buying