[jeffbee]

The compiler will only choose to use AVX-512 if you give it the right `-m` flags. Most people who are running generic distros that target the basic k8 instructions benefit from AVX-512 only when some library has runtime dispatch that detects the presence of the feature and enables optimized routines. This is common in, for example, cryptography libraries.

[mattst88]

Right. Since I'm using Gentoo and compiling my whole system with `-march=tigerlake`, the compiler is free to use AVX-512.

My question is just... does it? (And does it use AVX-512 profitably?)

[nwallin]

It will not use AVX-512 if you have CFLAGS="-march=tigerlake -O2". You will, at the very least, need CFLAGS="-march=tigerlake -O3" to get it to actually use AVX2, and tigerlake's AVX512 implementation is so poor (clock throttling etc) that gcc will not use AVX-512 on tigerlake. AVX-512 is used if you have -march=znver4 though, so the support for autovectorizing to AVX-512 is clearly there.

https://godbolt.org/z/1a39Mf3bv

[aseipp]

Is it actually that bad on Tiger Lake? Or just for really high-width vectors? On my old Ice Lake laptop, single-core AVX-512 workloads do not decrease frequency at all even with wider registers, and multi-core workloads will result in clock speed degradation of a small amount, maybe 100Mhz or so.

Depends on a couple factors (i.e. Ice Lake client only has 1 FMA unit) but I'd be surprised if Tiger Lake was a major regression relative to Ice Lake. It seems like they had it in an OK spot by then.

[secondcoming]

In my experience it depends on the compiler. clang seems far more willing to autovectorise than gcc. Also, when writing the code you have to write it in a way that strongly hints to the compiler that it can be autovectorised. So lots of handholding.

[jeffbee]

I guess a better question is why you rebuild the system without a rational basis to expect benefits.

[mattst88]

Are you familiar with source-based distributions?

I'm not rebuilding specifically for this one potential optimization.

[oconnor663]

Why not use -march=native?

[inopinatus]

Surprisingly, -march=native doesn’t always expand to the locally optimal build flags we might expect, particularly with gcc on non-Linux platforms.

[oconnor663]

Oh interesting. Is this one of those things where backwards compatibility eventually got in the way of the intended purpose?

[mattst88]

I actually do. I just said -march=tigerlake to make it clear what CPU family the compiler was targeting.

[aew4ytasghe5]

Why not use -march=snark?