Barco MXRT-8700 vs NVIDIA CMP 70HX

Comparison of Barco MXRT-8700 with 16 GB GDDR5 and 2,304 cores vs NVIDIA CMP 70HX with 8 GB GDDR6X and 3,840 cores.

Loading...

Performance Rating

H200 H200
MI325X MI325X
A100 A100

Barco MXRT-8700

Barco MXRT-8700

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

NVIDIA CMP 70HX

NVIDIA CMP 70HX

Contents:

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

Memory

Memory Size

16 GB 8 GB

Memory Type

GDDR5 GDDR6X

Memory Bandwidth

224.0 GB/s 608.3 GB/s

Memory Bus Width

256 бит 256 бит

ML Performance

FP16 (Half Precision)

5.728 TFLOPS 10.71 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

5.728 TFLOPS 10.71 TFLOPS

FP64 (Double Precision)

0.358 TFLOPS 0.1674 TFLOPS

CUDA Cores

2,304 3,840

RT Cores

No 30

Architecture & Compatibility

GPU Architecture

GCN 4.0 Ampere

SM (Streaming Multiprocessor)

No 30

PCIe Version

PCIe 3.0 x16 PCIe 1.0 x4

ML Software Support

CUDA Version

No 8.6

Clocks & Performance

Base Clock

1,188 1,365

Boost Clock

1,243 1,395

Memory Clock

1,750 1,188

Power Consumption

TDP/TGP

130 W unknown

Recommended PSU

300 W
🔥 -33% 200 W

Power Connector

1x 6-pin 1x 12-pin

Rendering

Texture Units (TMU)

144 120

ROP

No 30

L2 Cache

2 MB 4 MB

Additional

Slots

Single-slot Dual-slot

Release Date

Nov. 10, 2016 March 11, 2021

Display Outputs

4x DisplayPort 1.4a
6x mini-DisplayPort 1.4a
No outputs

Renting is cheaper than buying