It seems like you are not the only one confused, as described in a Rust issue. It seems to follow the same pattern as Clang: Os For optimising the size when compiling. Oz For even more size optimisation.
One limitation of the current Rust compiler is that it if you’re not using LTO (Link-Time Optimization), it will never inline a function not marked #[inline] across crates. Rust uses a separate compilation model similar to C++ because LLVM’s LTO implementation doesn’t scale well to large projects. Therefore, small functions exposed to other crates need … Read more
Summary: below 240, LLVM fully unrolls the inner loop and that lets it notice it can optimize away the repeat loop, breaking your benchmark. You found a magic threshold above which LLVM stops performing certain optimizations. The threshold is 8 bytes * 240 = 1920 bytes (your array is an array of usizes, therefore the … Read more
Rust originally did enable LLVM’s noalias attribute, but this caused miscompiled code. When all supported LLVM versions no longer miscompile the code, it will be re-enabled. If you add -Zmutable-noalias=yes to the compiler options, you get the expected assembly: adds: mov eax, dword ptr [rsi] add eax, eax add dword ptr [rdi], eax ret Simply … Read more
Yes, ISO C++ allows (but doesn’t require) implementations to make this choice. But also note that ISO C++ allows a compiler to emit code that crashes on purpose (e.g. with an illegal instruction) if the program encounters UB, e.g. as a way to help you find errors. (Or because it’s a DeathStation 9000. Being strictly … Read more