Why Core-to-Core Latency Matters
Last year we had a global shortage of microchips; today, I feel there is a worldwide shortage of software developers. Like many other software companies, Chronicle Software is rapidly expanding and interviewing candidates. We usually ask candidates to demonstrate a good knowledge of core Java, then we cover slightly more advanced concepts, such as the use of volatile memory, memory barriers and fences. While it is important to have a high-level understanding of these concepts when writing concurrent code, it’s surprising how few Java developers with 10+ years of experience have a deep knowledge of the underlying hardware. An initial goal of Java was to “write once, run anywhere”, but does that mean we should not be sympathetic to the hardware?
Java has done an excellent job at shielding developers from their platform; it is not unreasonable that most developers would rather solve their business problem than become overly burdened with the internal workings of their silicon. However, some sectors, such as FinTech, benefit from fast software with predictable latencies, where every last microsecond can make a massive difference to their bottom line. For these sectors, it can be beneficial to have a reasonable grasp of the underlying hardware and basic knowledge of the areas described in the following sections.
