Memory Requirements

By default, algorithms in Intel® Extension for Scikit-learn* run in multi-thread mode, which uses all available threads. This may lead to optimized algorithms consuming more RAM than the corresponding stock scikit-learn algorithms.

Algorithm	Single-thread mode	Multi-thread mode
SVM	Both Scikit-learn and Intel® Extension for Scikit-learn* consume approximately the same amount of RAM.	In Intel® Extension for Scikit-learn*, an algorithm with N threads will consume N times more RAM.

Memory consumption on GPU

In all Intel® Extension for Scikit-learn* algorithms with GPU support, computations run on device memory. The device memory must be large enough to store a copy of the entire dataset. Additional device memory may also be required for internal arrays used in computation.