, 1 min read
The computation capacity needed by artificial intelligence doubles every 3.4 months. In parallel, we are making fast progress in hardware and software: what took three hours a year and half ago can now take less than two minutes. In Luxembourg, a small European country, all public transportation…
, 1 min read
It is common in software system to map objects to unique identifiers. For example, you might map all web pages on the Internet to a unique identifier. Often, these identifiers are integers. For example, many people like to use 64-bit integers. If you assign two 64-bit integers at random to distinct…
, 2 min read
Most servers on the Internet run on x64 processors, mostly made by Intel. Meanwhile, most smartphones run ARM processors. From a business perspective, these are different technologies. The x64 processors are mostly designed by only two companies (Intel and AMD), with one very large dominant player…
, 1 min read
Amazon´s new ARM servers: Graviton 2
, 1 min read
Incredibly, there is a new simpler way to solve the quadratic formula. I used to rely on the completion of the square, but this is better! There is a video report on the finding. Surgeons are putting patients in suspended animation (biostasis) during surgery, replacing their blood with a cold…
, 1 min read
Intel makes some of the very best processors many can buy. For a long time, its main rival (AMD) failed to compete. However, its latest generation of processors (Zen 2) appear to roughly match Intel, at a lower price point. In several benchmarks that I care about, my good old Intel Skylake (2015)…
, 3 min read
The performance of a processor is determined by several factors. For example, processors with a higher frequency tend to do more work per unit of time. Physics makes it difficult to produce processors that have higher frequency. Modern processors can execute many instructions per cycle. Thus a…
, 5 min read
A recent magazine article presents a theoretical result: Harvey and van der Hoeven have shown that you can multiply two n-bit integers using O(n log n) complexity. Roughly speaking, this means that as n grows large, there is a mathematical model of how long the resulting algorithm might run that…
, 2 min read
When thinking about “parallelism”, most programmers think about having multiple processors. However, even a single core in a modern processor has plenty of parallelism. It can execute many instructions per cycle and, importantly, it can issue multiple memory requests concurrently. Our…
, 2 min read
Many businesses today run “in the cloud”. What this often means is that they have abstracted out the hardware entirely. Large corporations like Amazon, Google, Microsoft or IBM operate the servers. The business only needs to access the software, remotely. In theory, this means that you can…
, 1 min read
We have new technology to do genetic engineering on human beings (CRISPR). In a small clinical trial, the researchers tested it on live human subjects and found it to be safe. Girls and boys have a similar intelligence according to psychometric tests, but girls do much better in school, and this…
, 2 min read
Modern processors predict branches (e.g., if-then clauses), often many cycles a ahead of time. When predictions are incorrect, the processor has to start again, an expensive process. Adding a hard-to-predict branch can multiply your running time. Does it mean that you should only care about…
, 2 min read
Software is full of “branches”. They often take the form of if-then clauses in code. Modern processors try to predict the result of branches often long before evaluating them. Hard-to-predict branches are a challenge performance-wise because when a processor fails to predict correctly a branch,…
, 1 min read
When programming, we often want to convert strings (e.g., “1.0e2”) into numbers (e.g., 100). In C++, we have many options. In a previous post, I reported that it is an expensive process when using the standard approach (streams). Many people pointed out to me that there are faster alternatives.…
, 2 min read
In C++, there are multiple ways to convert strings into numbers. E.g., to convert the string “1.0e2” into the number 100. In software, we frequently have to parse numbers from strings. Numbers are typically represented in computers as 32-bit or 64-bit words whereas strings are variable-length…
, 2 min read
People who were the oldest in the classes in school tend to be more confident and to take more risks. At the University of Montreal, about 32% of the students are male and 68% are female. Did blind orchestra auditions really benefit women? Wealthy people are happier, but the effect is small. Among…
, 2 min read
A lot of software is an intricate of branches (if–then clauses). For performance reasons, modern processors predict the results of these branches. In my previous post, I showed how the bulk of your running time could be due to mispredicted branches. My benchmark consisted in writing 64 million…
, 3 min read
Modern processors are superscalar, meaning that they can execute many instructions at once. For example, some processors can retire four or six instructions per cycle. Furthermore, many of these processors can initiate instructions out-of-order: they can start working on instructions that appear…
, 2 min read
In many countries, like Canada, there is relatively little private (business) research. Meanwhile, other research indicates that private research is precisely the kind of research that leads directly to productivity growths. Private research seems concentrated in hubs like the Silicon Valley. To…
, 1 min read
Apple sells identical laptops worldwide. There might be small differences with respect to power adaptors and so forth, but the laptops are the same internally. Of course, there are differences in taxes but Apple quote prices with taxes included. So I went shopping for a basic MacBook Air, in…