In our experiments with the memory access pattern, we have seen that good data locality is a key to good software performance. Accessing memory sequentially and splitting the data set into small-sized pieces which are processed individually improves data locality and software speed. In this post, we will present a few techniques to improve the…
![What is faster: vec.emplace_back(x) or vec[x] ?](https://johnnysswlab.com/wp-content/uploads/1_X_4r58mARIdCdTRz14Eraw.jpeg)
When we need to fill std::vector with values and the size of vector is known in advance, there are two possibilities: using emplace_back() or using operator[]. For the emplace_back() we should reserve the necessary amount of space with reserve() before emplacing into vector. This will avoid unnecessary vector regrow and benefit performance. Alternatively, if we…
This post has a second part, the same problem is solved differently. Read more. In this post we investigate long dependency chains: when an instruction depends on the previous instruction depends on the previous instruction… We want to see how long dependency chains lower CPU performance, and we want to measure the effect of interleaving…
We continue the investigation from the previous post, trying to measure how the memory subsystem affects software performance. We write small programs (kernels) to quantify the effects of cache line, memory latency, TLB cache, cache conflicts, vectorization and branch prediction.
In this post we investigate the memory subsystem of a desktop, server and embedded system from the software viewpoint. We use small kernels to illustrate various aspects of the memory subsystem and how it effects performance and runtime.
We talk about instruction level parallelism: what instruction-level parallelism is, why is it important for your code’s performance and how you can add instruction-level parallelism to improve the performance of your memory-bound program.
We investigate how memory consumption, dataset size and software performance correlate…
In this post we introduce the essentials of programming for systems with several CPU cores. We start with an explanation of software threads and synchronization, two fundamental building blocks of multithreaded programming. We explain how these are implemented in hardware, and finally, we present several multithreading APIs you can use for parallel programming.
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…
In this post we present key concepts of software performance engineering.
