Tuning Tips for A64FX Processors

• 1. Introduction
  • 1.1. What is This Document
  • 1.2. Structure of This Document
  • 1.3. Environment for Performance Measurement
• 2. Promoting Vectorization
  • 2.1. Interchange of Innermost Loop with Data Dependency
  • 2.2. Interchange of Innermost Loop with Small Iteration Count
  • 2.3. Fission of Imperfectly Nested Loops
• 3. Reduction of Waiting Time for Calculation
  • 3.1. Fission of Loop with Large Loop Body
  • 3.2. Striping of Innermost Loop with Small Iteration Count
• 4. Reduction of Waiting Time for Cache Access
  • 4.1. Full-Unrolling of Innermost Loop with Non-Contiguous Data Access
  • 4.2. Interchange of Array Dimension for AoS Layout
  • 4.3. Specifying CONTIGUOUS Attribute to Array Pointer
• 5. Summary