We investigate how memory consumption, dataset size and software performance correlate…
All posts in Low Level Performance
Vectorization, dependencies and outer loop vectorization: if you can’t beat them, join them
As I already mentioned in earlier posts, vectorization is the holy grail of software optimizations: if your hot loop is efficiently vectorized, it is pretty much running at fastest possible speed. So, it is definitely a goal worth pursuing, under two assumptions: (1) that your code has a hardware-friendly memory access pattern1 and (2) that…
Why is quicksort faster than heapsort? And how to make them faster?
We try to answer the question of why is quicksort faster than heapsort and then we dig deeper into these algorithms’ hardware efficiency. The goal: making them faster.
When vectorization hits the memory wall: investigating the AVX2 memory gather instruction
For all the engineers who like to tinker with software performance, vectorization is the holy grail: if it vectorizes, this means that it runs faster. Unfortunately, many times this is not the case, and the results of forcing vectorization by any means can mean lower performance. This happens when vectorization hits the memory wall: although…
2-minute read: Class Size, Member Layout and Speed
We are exploring how class size and layout of its data members affect your program’s speed
Crash course introduction to parallelism: SIMD Parallelism
This is the first article about hardware support for parallelization. We talk about SIMD, an extension almost every processor nowadays has that lets you speed up your program.
Making your program run faster in a multithreaded environment
We investigate the performance impact of multithreading.
Use explicit data prefetching to faster process your data structure
When processing (searching, inserting etc) your data structure, if you are accessing it in random-access fashion, the performance will suffer due to many data cache misses. Read on how to use the explicit data prefetching to speed up access to your data structure.
Make your programs run faster: avoid expensive instructions
We will talk about expensive instructions in modern CPUs and how to avoid them to speed up your program.
The price of dynamic memory: Memory Access
If your program uses dynamic memory, its speed will depend on allocation time but also on memory access time. Here we investigate how memory access time depends on the memory layout of your data structure. We also investigate ways to speed up your program by laying out your data structure optimally.