Mehdi Akiki

Posts tagged "benchmarking"

  • Published on
    mold 3.0 is the first Rust version of mold. I linked the same ripgrep object files with it, mold 2, GNU ld, gold, LLD and wild. With one thread, LLD, mold and wild were equal, the Rust mold was a bit slower with 16, and all outputs were the same program.
  • Published on
    An optimization comparison needs equivalent work. Hold inputs steady, separate implementation changes, and investigate interactions after establishing a trustworthy baseline.
  • Published on

    Investigation · Part 20 of 20 · When the benchmark lies

    A Benchmark Result Someone Else Can Check

    For the last part, I ran two earlier parts again with the same script. The assembly was identical, part 1 ran 10 to 14 percent faster, and the conclusions of both parts held. This is what a result must carry so that someone else can make the same check.
  • Published on

    Investigation · Part 19 of 20 · When the benchmark lies

    The Microbenchmark Won and the Program Got Slower

    Alone, a lookup table was four times faster than a division. In a loop that also used 1 to 8 MiB of its own counters, the same table made the whole loop 4 to 34 percent slower. The microbenchmark had the cache for itself, and the program had to share it.
  • Published on

    Investigation · Part 15 of 20 · When the benchmark lies

    Does Code Alignment Change the Speed of the Same Code?

    I placed the same 11-instruction loop at all 64 positions of a cache line, two copies each, and measured them in shuffled order. At one position the loop was 16 to 21 percent slower, in three runs out of three. The same bytes, a different address, a different speed.