Constraints

This section describes the constraints on the Kunpeng BoostKit machine learning algorithm library.

The machine learning algorithm library has no impact on the system.

Table 1 describes the usage restrictions.

**Table 1** Constraints
Item	Description
OSs	openEuler 22.03 LTS SP1
Components	The algorithm library is compatible with Spark 3.3.1 and supports DBSCAN, Word2Vec, DTB, and SVM algorithms. It can also be adapted to 3.X.
Hardware	Kunpeng servers
Hybrid deployment	A Spark cluster cannot have Kunpeng and another type of servers at the same time. The machine learning and graph analysis algorithms library cannot be used in a task with other open source algorithms.
Performance metrics	The machine learning algorithm library leverages optimized datasets and parameters to deliver 1.2 times higher computing performance on Kunpeng 920 5250 than native MLlib algorithms on x86 5318. Most of the algorithms in the graph analysis algorithm library have positive performance gains when CPU prefetch is enabled. Therefore, Huawei strongly recommends that CPU prefetch be enabled. For details, see Kunpeng BoostKit for Big Data Machine Learning Algorithm Library Acceptance Test Guide.

The machine learning algorithm library does not interact with other features.

Parent topic: Feature Description