We investigate how memory consumption, dataset size and software performance correlate…
All posts tagged data cache
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…
Why do programs get slower with time?
We investigate why software gets slower as new features are added or data set grows and what can you do about it.
The quest for the fastest linked list
Linked lists are celebrity data structures of software development. They are celebrities because every engineer has had something to do with them in one part of their career. They are used in many places: from low-level memory management in operating systems up to data wrangling and data filtering in machine learning. They promise a lot:…
Memory Access Pattern and Performance: the Example of Matrix Multiplication
We use matrix multiplication example to investigate loop interchange and loop tiling as techniques to speed up your program that works with matrices.
The true price of virtual functions in C++
We talk about virtual functions, and how the performance of software with virtual functions depends on many factors: the cost of additional instructions, cache misses, branch prediction misses, instruction cache misses and compiler optimizations.
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
2-minute read: How is Big O notation relevant on modern systems?
Big O notation is commonly used to describe algorithm performance. But modern hardware makes performance analysis much harder than it used to be. In this short article we give three interesting examples to illustrate the limits of big O notation.
Crash course introduction to parallelism: the algorithms
When it comes to performance, there are two ways to go: one is to improve the usage of the existing hardware resources, the other is to use the new hardware resources. We already talked a lot about how to increase the performance of your program by better using the existing resources, for example, by decreasing…
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.