NVIDIA A100 PCIe 80 GB vs NVIDIA H100 CNX

Comparison of NVIDIA A100 PCIe 80 GB with 80 GB HBM2e and 6,912 cores vs NVIDIA H100 CNX with 80 GB HBM2e and 14,592 cores.

Loading...

Performance Rating

NVIDIA H100 CNX outperforms NVIDIA A100 PCIe 80 GB by 76.63% 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 H100 CNX

45.3

NVIDIA H100 CNX

45.3

Contents:

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

Memory

Memory Size

80 ГБ 80 ГБ

Memory Type

HBM2e HBM2e

Memory Bandwidth

1.94 TB/s
🔥 +5% 2.04 TB/s

Memory Bus Width

5,120 бит 5,120 бит

ML Performance

FP16 (Half Precision)

77.97 TFLOPS
🔥 +176% 215.4 TFLOPS

BF16 (Brain Float)

🔥 311.84 TFLOPS
No

TF32 (TensorFloat)

🔥 155.92
No

Compute Power

FP32 (Single Precision)

19.49 TFLOPS
🔥 +176% 53.84 TFLOPS

FP64 (Double Precision)

9.746 TFLOPS
🔥 +176% 26.92 TFLOPS

CUDA Cores

6,912
🔥 +111% 14,592

RT Cores

No No

Architecture & Compatibility

GPU Architecture

Ampere Hopper

SM (Streaming Multiprocessor)

108
🔥 +6% 114

PCIe Version

PCIe 4.0 x16 PCIe 5.0 x16

ML Software Support

CUDA Version

8.0
🔥 9.0

Clocks & Performance

Base Clock

🔥 +54% 1,065
690

Boost Clock

1,410
🔥 +31% 1,845

Memory Clock

1,512
🔥 +5% 1,593

Power Consumption

TDP/TGP

🔥 -14% 300 W
350 W

Recommended PSU

🔥 -7% 700 W
750 W

Power Connector

8-pin EPS 8-pin EPS

Rendering

Texture Units (TMU)

432
🔥 +6% 456

ROP

No No

L2 Cache

🔥 +60% 80 MB
50 MB

Additional

Slots

Dual-slot Dual-slot

Release Date

June 28, 2021 March 21, 2023

Display Outputs

No outputs
No outputs

Renting is cheaper than buying