"Second of all, a C+ASM approach will always win eventually, given enough time invested. That is because a C+ASM programmer has at his/her disposal literally every possible optimization technique that is implementable on that CPU, with no language-imposed overhead. What this means is that a higher-level language being "faster than C" is just a local maximum; the global maximum is that C is faster."

Exactly

The C program presented is very naive. getc? ungetc? malloc inside a loop?

For example, I can create a table to convert 4 characters at once instead of only one. Just as a start. Doable in haskell sure, but it would most likely not use the resources of modern processors (SSE2, AVX, etc)