Memory

Introduction

hipecta.memory Python module that creates Numpy ndarray with data alignment, a method to force the compiler to create data objects in memory on specific byte boundaries.

Data alignment enables execution engines to take advantage of the latest SIMD operations included in modern processors. Data Alignment is optimized for better performance on modern hardware like CPUs see(https://software.intel.com/en-us/articles/data-alignment-to-assist-vectorization)

Reference/API

hipecta._memory Module

Functions

empty(shape[, dtype])	Return a new array, memory aligned, of given shape and type, without initializing entries.
get_alignment	empty(shape, dtype=float64)
is_data_align	empty(shape, dtype=float64)

hipecta.memory Package

Functions

copyto(dst, src)	Copies values from one array to another.
empty(shape[, dtype])	Return a new array, memory aligned, of given shape and type, without initializing entries.
get_alignment	empty(shape, dtype=float64)
is_data_align	empty(shape, dtype=float64)
ones(shape[, dtype])	Return a new array, memory aligned, of given shape and type, filled with ones.
zeros(shape[, dtype])	Return a new array, memory aligned, of given shape and type, filled with zeros.