simias has most of it but note also that that file appears to have last been compiled in the early 2000s. Compilers of that era were far less advanced, especially since many large companies were pretty conservative about the optimizations enabled (fixing a bug meant mailing CDs for many customers).
The general trend is that it's been getting harder and harder to do that easily, which means people want to be more focused — something like OpenSSL can still justify hand-tuned assembly for various processor families because it's a widespread hotspot but as compilers continue to improve the number of places where it's worth the maintenance cost is going to keep shrinking.
In the early 2000s, the scientific HPC programmers I worked with were careful to maintain a portable C implementation which they could use as a check both for correctness and for an optimization baseline — it wasn't uncommon for a new compiler and/or processor to substantially close the gap relative to a lot of hard manual work.
The general trend is that it's been getting harder and harder to do that easily, which means people want to be more focused — something like OpenSSL can still justify hand-tuned assembly for various processor families because it's a widespread hotspot but as compilers continue to improve the number of places where it's worth the maintenance cost is going to keep shrinking.
In the early 2000s, the scientific HPC programmers I worked with were careful to maintain a portable C implementation which they could use as a check both for correctness and for an optimization baseline — it wasn't uncommon for a new compiler and/or processor to substantially close the gap relative to a lot of hard manual work.