HW optimized CRC32 implementation

[pbadari]

Describe the feature

Looking through the code (for Intel architecture), I see that aws_checksums_crc32() is only SW implementation. There is no hardware accelerated implementation (SSE4.2 or AVX512). However aws_checksums_crc32c() has HW accelerated implementation.

Is there a reason why CRC32 implementation is not hardware accelerated? There are no users for it?
Please let me know if there is interest.

Use Case

HW optimized CRC32 implementation for Intel architecture using AVX512.

Proposed Solution

I am working on AVX512 optimized CRC32c implementation (in AVX512 branch), I can easily modify it to support both CRC32 and CRC32c.

Other Information

No response

Acknowledgements

• I may be able to implement this feature request
• This feature might incur a breaking change

[jmklix]

Yes, please make a PR if this is something that would be easy for you to add. We will make sure to review it.