AVX Programming – Packed Floating-Point
The source code examples of the previous chapter elucidated the fundamentals of AVX programming using scalar floating-point arithmetic. In this chapter, you’ll learn how to use the AVX instruction set to perform operations using packed floating-point operands. The chapter begins with three source code examples that demonstrate common packed floating-point operations, including basic arithmetic, data comparisons, and data conversions. The next set of source code examples illustrate how to carry out SIMD computations using floating-point arrays. The final two source code examples explain how to use the AVX instruction set to accelerate matrix transposition and multiplication.