Matrox D1480 Quad DisplayPort vs NVIDIA CMP 170HX 8 GB

Comparison of Matrox D1480 Quad DisplayPort with 4 GB GDDR5 and 512 cores vs NVIDIA CMP 170HX 8 GB with 8 GB HBM2e and 4,480 cores.

Loading...

Performance Rating

H200 H200
MI325X MI325X
A100 A100

Matrox D1480 Quad DisplayPort

Matrox D1480 Quad DisplayPort

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

NVIDIA CMP 170HX 8 GB

NVIDIA CMP 170HX 8 GB

Contents:

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

Memory

Memory Size

4 GB 8 GB

Memory Type

GDDR5 HBM2e

Memory Bandwidth

96.13 GB/s 1.49 TB/s

Memory Bus Width

128 бит 4,096 бит

ML Performance

FP16 (Half Precision)

0.0223 TFLOPS 50.53 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

1.4254 TFLOPS 12.63 TFLOPS

FP64 (Double Precision)

0.0445 TFLOPS 6.317 TFLOPS

CUDA Cores

512 4,480

RT Cores

No No

Architecture & Compatibility

GPU Architecture

Pascal Ampere

SM (Streaming Multiprocessor)

4 70

PCIe Version

PCIe 3.0 x16 PCIe 1.0 x4

ML Software Support

CUDA Version

6.1
🔥 8.0

Clocks & Performance

Base Clock

1,354 1,140

Boost Clock

1,392 1,410

Memory Clock

1,502 1,458

Power Consumption

TDP/TGP

🔥 -81% 47 W
250 W

Recommended PSU

🔥 -67% 200 W
600 W

Power Connector

None 2x 8-pin

Rendering

Texture Units (TMU)

32 280

ROP

No No

L2 Cache

1024 KB 8 MB

Additional

Slots

Single-slot IGP

Release Date

May 21, 2020 Sept. 1, 2021

Display Outputs

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

Renting is cheaper than buying