I added some SSE assisted hashes and fast intel/arm CRC32-C and AES HW variants, but not the fastest crcutil yet. See our crcutil results. See also the old https://code.google.com/p/smhasher/w/list.

So the fastest hash functions on x86_64 without quality problems are:

• falkhash (macho64 and elf64 nasm only, with HW AES extension)
• FarmHash (not portable, too machine specific: 64 vs 32bit, old gcc, ...)
• Metro (but not 64crc yet, WIP)
• Spooky32
• xxHash64
• fasthash
• City (deprecated)

Hash functions for symbol tables or hash tables typically use 32 bit hashes, for databases, file systems and file checksums typically 64 or 128bit, for crypto now starting with 256 bit.

Typical median key size in perl5 is 20, the most common 4. See github.com/rurban/perl-hash-stats

When used in a hash table the instruction cache will usually beat the CPU and throughput measured here. In my tests the smallest FNV1A beats the fastest crc32_hw1 with Perl 5 hash tables. Even if those worse hash functions will lead to more collisions, the overall speed advantage beats the worse quality.

• http://www.strchr.com/hash_functions lists other benchmarks and quality of most simple and fast hash functions.
• http://bench.cr.yp.to/primitives-hash.html lists the benchmarks of all currently tested secure hashes.
• The Hash Function Lounge overviews the known weaknesses and attacks.

Some popular SSE-improved FNV1 (sanmayce) variants, fletcher (ZFS), ... and slower cryptographic hashes or more secure hashes are still missing. BLAKE2, SHA-2, SHA-3 (Keccak), Grøstl, JH, Skein, ...

The hash table attacks described in SipHash against City, Murmur or Perl JenkinsOAAT or at Hash Function Lounge are not included here.

Such an attack avoidance cannot not be the problem of the hash function, but the hash table collision resolution scheme. You can attack every single hash function, even the best, if you detect the seed, e.g. from the sort-order, so you need to protect your collision handling scheme from the worst-case O(n), i.e. separate chaining with linked lists. Linked lists chaining is also very cache-unfriendly.

The '\0' vulnerability attack with binary keys is tested in the 2nd Sanity test.