Finish Avx512 specific lightup for Vector128/256/512<T>

[tannergooding]

With #80814, we achieved functional parity of Vector512<T> with Vector128<T> and Vector256<T>. However, there are some new instructions available in Avx512 capable hardware that will allow additional hardware acceleration opportunities for all three types.

This includes:

• ConvertToDouble() - vcvtqq2pd & vcvtuqq2pd
• ConvertToInt64() - vcvtpd2qq
• ConvertToUInt32() - vcvtps2udq
• ConvertToUInt64() - vcvtpd2uqq
• ConditionalSelect() - vpternlog
• Shuffle() - vpermi2*, vpermt2*, etc

We should also ensure that all APIs are accelerated as intrinsic, where applicable, in particular the following are still managed fallbacks (but accelerated):

• Vector512.Dot()
• Vector512.Sum()

There may be others as well, so a general audit to validate would be good.

[ghost]

Tagging subscribers to this area: @JulieLeeMSFT, @jakobbotsch
See info in area-owners.md if you want to be subscribed.

Issue Details

---

With #80814, we achieved functional parity of Vector512<T> with Vector128<T> and Vector256<T>. However, there are some new instructions available in Avx512 capable hardware that will allow additional hardware acceleration opportunities for all three types.

This includes:

• ConvertToDouble() - vcvtqq2pd & vcvtuqq2pd
• ConvertToInt64() - vcvtpd2qq
• ConvertToUInt32() - vcvtps2udq
• ConvertToUInt64() - vcvtpd2uqq
• ConditionalSelect() - vpternlog
• Shuffle() - vpermi2*, vpermt2*, etc

We should also ensure that all APIs are accelerated as intrinsic, where applicable, in particular the following are still managed fallbacks (but accelerated):

• Vector512.Dot()
• Vector512.Sum()

There may be others as well, so a general audit to validate would be good.

Author:	tannergooding
Assignees:	-
Labels:	area-CodeGen-coreclr, arch-avx512
Milestone:	8.0.0

[DeepakRajendrakumaran]

@tannergooding Sum is a weird one. I don't believe any single avx512 instruction exists for it

Documentation:
https://www.intel.com/content/www/us/en/docs/cpp-compiler/developer-guide-reference/2021-8/intrinsics-for-integer-reduction-operations.html

Clang implementation:
https://godbolt.org/z/hW1Thxhe3

[JulieLeeMSFT]

Most of this is being handled in #100993.

[tannergooding]

Vector512.Dot is the only one left here and can be done in .NET 10, the current implementation is functionality correct and generating the expected codegen it just isn't handled directly as an intrinsic in the JIT.