why is data structure alignment important for performance?

by

Alignment helps the CPU fetch data from memory in an efficient manner: less cache miss/flush, less bus transactions etc.

Some memory types (e.g. RDRAM, DRAM etc.) need to be accessed in a structured manner (aligned “words” and in “burst transactions” i.e. many words at one time) in order to yield efficient results. This is due to many things amongst which:

  1. setup time: time it takes for the memory devices to access the memory locations
  2. bus arbitration overhead i.e. many devices might want access to the memory device

“Padding” is used to correct the alignment of data structures in order to optimize transfer efficiency.

In other words, accessing a “mis-aligned” structure will yield lower overall performance. A good example of such pitfall: suppose a data structure is mis-aligned and requires the CPU/Memory Controller to perform 2 bus transactions (instead of 1) in order to fetch the said structure, the performance is thus consequently lower.

More Related Contents:

  1. What’s the actual effect of successful unaligned accesses on x86?
  2. What is the best way to set a register to zero in x86 assembly: xor, mov or and?
  3. Why are loops always compiled into “do…while” style (tail jump)?
  4. Enhanced REP MOVSB for memcpy
  5. Why is Skylake so much better than Broadwell-E for single-threaded memory throughput?
  6. Understanding the impact of lfence on a loop with two long dependency chains, for increasing lengths
  7. How to speed up A* algorithm at large spatial scales?
  8. Comparing BSXFUN and REPMAT
  9. Branch alignment for loops involving micro-coded instructions on Intel SnB-family CPUs
  10. Why is XCHG reg, reg a 3 micro-op instruction on modern Intel architectures?
  11. What methods can be used to efficiently extend instruction length on modern x86?
  12. Should I use multiplication or division?
  13. Spark: Inconsistent performance number in scaling number of cores
  14. Lost Cycles on Intel? An inconsistency between rdtsc and CPU_CLK_UNHALTED.REF_TSC
  15. postgresql COUNT(DISTINCT …) very slow
  16. Why does the Mac ABI require 16-byte stack alignment for x86-32?
  17. Why should recursion be preferred over iteration?
  18. LCP time between LightHouse and Performance – Google Chrome
  19. simplest tool to measure C program cache hit/miss and cpu time in linux?
  20. Why is division more expensive than multiplication?
  21. Mapping 2 vectors – help to vectorize
  22. Should a developer aim for readability or performance first? [closed]
  23. MongoDB ranged pagination
  24. Return address prediction stack buffer vs stack-stored return address?
  25. When should we use prefetch?
  26. Relative performance of x86 inc vs. add instruction
  27. Efficient sse shuffle mask generation for left-packing byte elements
  28. preallocate list in R
  29. How to analyze golang memory?
  30. How to avoid Query Plan re-compilation when using IEnumerable.Contains in Entity Framework LINQ queries?

Leave a Comment