Matrox D1480 Quad DisplayPort vs NVIDIA H100 PCIe 96 GB

Comparison of Matrox D1480 Quad DisplayPort with 4 GB GDDR5 and 512 cores vs NVIDIA H100 PCIe 96 GB with 96 GB HBM3 and 16,896 cores.

Loading...

Performance Rating

Matrox D1480 Quad DisplayPort outperforms NVIDIA H100 PCIe 96 GB by 18.18% in the overall GPU ARK performance rating

A100 A100
H200 H200
MI325X MI325X

Matrox D1480 Quad DisplayPort

65.7

Matrox D1480 Quad DisplayPort

65.7
RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

NVIDIA H100 PCIe 96 GB

55.6

NVIDIA H100 PCIe 96 GB

55.6

Contents:

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

Memory

Memory Size

4 ГБ
🔥 +2,300% 96 ГБ

Memory Type

GDDR5 HBM3

Memory Bandwidth

96.13 GB/s
🔥 3.36 TB/s

Memory Bus Width

128 бит 5,120 бит

ML Performance

FP16 (Half Precision)

22.27 TFLOPS
🔥 +1,015% 248.3 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

🔥 +2,195% 1,425.0 TFLOPS
62.08 TFLOPS

FP64 (Double Precision)

0.044539999999999996 TFLOPS
🔥 +69,590% 31.04 TFLOPS

CUDA Cores

512
🔥 +3,200% 16,896

RT Cores

No No

Architecture & Compatibility

GPU Architecture

Pascal Hopper

SM (Streaming Multiprocessor)

4
🔥 +3,200% 132

PCIe Version

PCIe 3.0 x16 PCIe 5.0 x16

ML Software Support

CUDA Version

6.1
🔥 9.0

Clocks & Performance

Base Clock

1,354
🔥 +23% 1,665

Boost Clock

1,392
🔥 +32% 1,837

Memory Clock

🔥 +14% 1,502
1,313

Power Consumption

TDP/TGP

🔥 -93% 47 W
700 W

Recommended PSU

🔥 -82% 200 W
1100 W

Power Connector

None 8-pin EPS

Rendering

Texture Units (TMU)

32
🔥 +1,550% 528

ROP

No No

L2 Cache

1024 KB
🔥 50 MB

Additional

Slots

Single-slot Dual-slot

Release Date

May 21, 2020 March 21, 2023

Display Outputs

4x mini-DisplayPort 1.4a
4x DisplayPort 1.4a
No outputs

Renting is cheaper than buying