AMD Radeon Pro VII vs NVIDIA A800 SXM4 80 GB

Comparison of AMD Radeon Pro VII with 16 GB HBM2 and 3,840 cores vs NVIDIA A800 SXM4 80 GB with 80 GB HBM2e and 6,912 cores.

Loading...

Performance Rating

NVIDIA A800 SXM4 80 GB outperforms AMD Radeon Pro VII by 86.39% in the overall GPU ARK performance rating

A100 A100
H200 H200
MI325X MI325X

AMD Radeon Pro VII

13.9

AMD Radeon Pro VII

13.9
RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

NVIDIA A800 SXM4 80 GB

25.9

NVIDIA A800 SXM4 80 GB

25.9

Contents:

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

Memory

Memory Size

16 ГБ
🔥 +400% 80 ГБ

Memory Type

HBM2 HBM2e

Memory Bandwidth

1.02 TB/s
🔥 +100% 2.04 TB/s

Memory Bus Width

4,096 бит 5,120 бит

ML Performance

FP16 (Half Precision)

26.11 TFLOPS
🔥 +199% 77.97 TFLOPS

BF16 (Brain Float)

No
🔥 311.84 TFLOPS

TF32 (TensorFloat)

No
🔥 155.92

Compute Power

FP32 (Single Precision)

13.06 TFLOPS
🔥 +49% 19.49 TFLOPS

FP64 (Double Precision)

6.528 TFLOPS
🔥 +49% 9.746 TFLOPS

CUDA Cores

3,840
🔥 +80% 6,912

RT Cores

No No

Architecture & Compatibility

GPU Architecture

GCN 5.1 Ampere

SM (Streaming Multiprocessor)

No
🔥 108

PCIe Version

PCIe 4.0 x16 PCIe 4.0 x16

ML Software Support

CUDA Version

No 8.0

Clocks & Performance

Base Clock

🔥 +21% 1,400
1,155

Boost Clock

🔥 +21% 1,700
1,410

Memory Clock

1,000
🔥 +59% 1,593

Power Consumption

TDP/TGP

🔥 -38% 250 W
400 W

Recommended PSU

🔥 -25% 600 W
800 W

Power Connector

1x 6-pin + 1x 8-pin None

Rendering

Texture Units (TMU)

240
🔥 +80% 432

ROP

No No

L2 Cache

4 MB
🔥 +900% 40 MB

Additional

Slots

Dual-slot
🔥 SXM Module

Release Date

May 13, 2020 Aug. 11, 2022

Display Outputs

6x mini-DisplayPort 1.4a
No outputs

Renting is cheaper than buying