[zlib][x86] Implement AVX-512 based CRC-32 checksum

This patch will add an AVX-512 based implementation of CRC-32, allowing to
achieve higher speeds than the SSE4.2 implementation on newer Intel processors.

It enables multiple folding operations providing a boost of ~3.5x faster
checksums, thus yielding an average gain of ~3.7% in data decompression.

Bug: 1381000

Change-Id: I4f6bb813d1a889f451eb7433581f5d98b6644490
Reviewed-on: https://chromium-review.googlesource.com/c/chromium/src/+/4374529


Reviewed-by: Adenilson Cavalcanti <cavalcantii@chromium.org>
Commit-Queue: Adenilson Cavalcanti <cavalcantii@chromium.org>
Cr-Commit-Position: refs/heads/main@{#1125794}
NOKEYCHECK=True
GitOrigin-RevId: 71774699ed1905a70f5f98375613b012781c880c