Open source as a research method Many people still picture innovation as a line. The professor thinks and publishes. The engineer reads the paper and designs a product. The customer consumes it. It rarely works that way. The industrial revolution was not set off by professors writing papers. It was driven by demand for cheap and better clothing for the masses. Demand came first. Michael Stonebraker made a related point in “Where We Have Failed” (2018). He argued that the database research community has lost its customer: “there are no ‘real world’ clients to keep us focused.” Without a customer, research drifts. In 2019, JSON was everywhere, and parsing it was slow, at a few hundred megabytes per second. So we built simdjson. Today it parses JSON at gigabytes per second; I measured about 4.8 GB/s on twitter.json on a recent Intel Xeon. We did not write the paper first. We wrote the code, then a… https://lemire.me/blog/2026/11/04/open-source-as-a-research-method/

Beating the compiler at signed 32-bit division Dividing integers is slow on our processors. A 32-bit division costs: processor | latency | throughput ------------------------------ Emerald Rapids | about 12 cycles | one every 6 cycles ------------------------------ Zen 4 | 9 to 12 cycles | one every 6 cycles ------------------------------ Zen 5 | 10 to 13 cycles | one every 6 cycles ------------------------------ Arrow Lake performance core | 12 cycles | one every 6 cycles ------------------------------ Apple M4 performance core | 7 cycles | one every 2 cycles On Zen 4 and Zen 5, the latency depends on the inputs. The x86 rows are idiv (uops.info). The Apple row is sdiv (measurements). A multiplication has a latency of 3 cycles. Emerald Rapids can do one every cycle. Zen 5 and Arrow Lake do three 64-bit multiplications per cycle (uops.info). Thankfully, when the divisor is a… https://lemire.me/blog/2026/10/31/beating-the-compiler-at-signed-32-bit-division/

Billion-query-per-second lookup tables in C++ A lot of software spends its time mapping strings to values. A web server must identify the HTTP method (GET, POST, …). It must recognize header names. A URL parser must recognize the protocol (http, https, ftp, …). A compiler must recognize keywords. In C++, the default approach is to put the strings in a std::unordered_map. std::unordered_mapmethods={{:space:}{"GET",Method::GET},{"POST",Method::POST},{"PUT",Method::PUT},{:space:}{"DELETE",Method::DELETE},{"PATCH",Method::PATCH}};{:space:} It works. But notice something: the keys are known when you write the code. They never change. And yet we pay at runtime as if they could change at any time: we hash the whole string, we pick a bucket, we follow a pointer, we compare, maybe we walk a list. Perfect hashing A hash function maps keys to slots. When two keys land in the same slot, we have a collision, and we must… https://lemire.me/blog/2026/10/26/billion-query-per-second-lookup-tables-in-c/