I implemented many different algorithms for searching and splitting strings using SMID methods as well: https://github.com/naver/tamgu/blob/06aedf2f14895925d7b5a8e2... I used a different algorithm than the ones presented here.

Could you summarize your algorithm? Like a high-level description?

Like algorithm 1 (from the article) checks N possible positions at a time by matching the first and last character; algorithm 2 instead tests the 4 leading characters.

We know that the libc strstr performs horrible, but musl is fast and state of the art.

Now we just need a name, and we can add it to the smart shootout. Wonder how it compares to the best SIMD algos

Would be good to have more SIMD algorithms in smart. Maybe I'll have a play with it if I get time.

missing (2018) ?

What is the string sizes thresold for efficiency?

Because the SIMD (aligned, size computations, etc) setup code is usually more expensive that byte-oriented basic search for "small" strings.

Yes, it depends heavily on the hardware architecture.

Here, it's often the opposite.

These algorithms are basically brute force with very little setup, and can become quadratic for large, periodic needles.

String search algorithms that avoid quadratic behaviour (and may even be sublinear) have an higher cost setup that explores needle structure

What? It all depends on the sizes of the strings. Hardware benchmarks, for each significant hardware µarchitectures, must be done on combinations of string sizes in order to know "when" the SIMD setup code is worth it.

Often the setup code is not worth it, even the SIMD complexity is not bringing enough performance in many use cases (basically, kept for niche applications, little lib statically linked for those).

Did you look at the algorithm 1? The setup code is a pair of splats. There's no consideration for alignment, it works with unaligned data just fine. So what do you mean? What threshold would you expect for it to be worth it (assuming it's useful at all)?

Dude, I cannot be more explicit than that.

That said, when you work on such code, use assembly, C code is for reference (have a look at dav1d av1 decoder).

What? You don't have to do that. Hell, the SIMD code that ripgrep uses is written in Rust.

The swar algorithm has UB because it casts the 1 byte aligned data to 8 byte aligned. Perhaps it suffers some performance issues from unaligned loads?

I always took these as "idealized" algorithms or pseudo-code. In addition to not doing correct unaligned loads (using `memcpy`), the boundary checks are wrong. The code assumes the length of the haystack is a multiple of 8. Additionally, if the needle is empty, you'll get unsigned integer overflow leading to an out-of-bounds access on the needle. That's three different ways to get UB.

This is pretty common in my experience when demonstrating SIMD code. Often only the relevant bits are shown, and not a lot of effort is given to getting the boundary cases correct. It's rarely acknowledged explicitly, but I would assume it's because the boundary conditions are somewhat less interesting than the "meat" of how to use vectors in an interesting way.

The "AVX2 (generic)" approach is roughly what ripgrep uses (via Rust's `regex` crate) to accelerate most searches. Even something like `\w+\s+Sherlock\s+\w+` will benefit since ripgrep will pluck `Sherlock` out of the regex and search that.

The actual implementation is here: https://github.com/BurntSushi/memchr?tab=readme-ov-file#algo...

The main difference with the algorithm presented here is that instead of always using the first and last bytes of the needle, a heuristic is used to try to pick two bytes that occur less frequently according to a background frequency distribution.

It ends up being quite a bit faster than just plain Two-Way or even GNU libc's implementation of `memmem`. From the root of the `memchr` repository:

    $ rebar rank benchmarks/record/x86_64/2023-12-29.csv -e '^rust/memchr/memmem/(oneshot|prebuilt|twoway)' -e '^libc/memmem/oneshot'
    Engine                       Version  Geometric mean of speed ratios  Benchmark count
    ------                       -------  ------------------------------  ---------------
    rust/memchr/memmem/prebuilt  2.7.1    1.07                            57
    rust/memchr/memmem/oneshot   2.7.1    1.39                            54
    libc/memmem/oneshot          unknown  3.15                            54
    rust/memchr/memmem/twoway    2.7.1    5.26                            54

The "prebuilt" benchmarks also demonstrate the API deficiencies of routines like `memmem`. Because of their API, they need to rebuild the state necessary to execute a search for the needle given. But it is often the case that the needle is invariant across repeated calls with different haystacks. So you end up doing that repeated work for no gain.

Interesting. How do you know the background distribution of bytes? Won't a scan of the haystack to get the distribution take up a significant amount of time?

Now if I can just use SIMD directly from Python without calling out to another language.

why would you want to? if you are performance bound with Python code, you can pick up a 20-50x performance improvement by switching language.

Right, but if there's only a small portion of my code that does string search and it's a hot path, it would still be much much much more convenient to access SIMD-based string search code direct from Python rather than writing the code (LLM or not) in another language and then construct bindings (LLM or not).