Profile Guided Optimizations (PGO) Likely Coming To Linux 5.14 For Clang

[r08z]

This is just another unwarranted accusations because Unfortunately, there are people who believe in conspiracy theories.
it's good that I don't care and I will continue to compile anything with any compiler that gives a performance improvement.

Well that's good for you.

[alex19EP]

This is just another marketing attempt at pushing Clang to become the default compiler for all distros instead of GCC because they hate GNU and what it stands for. I don't care and I'll compile Linux with GCC/anything else until it becomes impossible to do so.

This is just another unwarranted accusations because Unfortunately, there are people who believe in conspiracy theories.
it's good that I don't care and I will continue to compile anything with any compiler that gives a performance improvement.

[r08z]

This is just another marketing attempt at pushing Clang to become the default compiler for all distros instead of GCC because they hate GNU and what it stands for. I don't care and I'll compile Linux with GCC/anything else until it becomes impossible to do so.

[zerothruster]

Reading the thread on lkml, this is initially only for x86_64, but it was submitted without Cc'ing x86 maintainers. Looking at the comments from Peter Z, I think the chances of this getting into 5.14 are slim.

[caligula]

They've had a beta version of 64-bit native Raspberry Pi OS, for a couple of years now. You need to know where to find it, but it seems pretty stable. I have no idea when they're planning to mainstream it. Runs on the Pi v3 and newer.

Yes that's true. My point was, it took them quite a while to adopt these new technologies. Rpi 2 had ARMv7 in 2015 while Rpi OS appeared in 2020. The ARMv6 version was called Raspbian. Armbian is the more optimized distro.

[coder]

IIRC, Rpi used ARMv6 optimized binaries for ARMv7 and ARM64. Also 32-bit kernel on 64-bit hardware, no?

They've had a beta version of 64-bit native Raspberry Pi OS, for a couple of years now. You need to know where to find it, but it seems pretty stable. I have no idea when they're planning to mainstream it. Runs on the Pi v3 and newer.

[caligula]

By the same token, older and legacy hardware, such as the recent story of more compatibility for Motorola 68000 cpus could see some benefit for this. Also, VMs with lower resources, Raspberry Pis and other SoCs, not to mention controller projects that are generally special purpose applications,

i wonder is this implementation is added if the same data can be used by GCC PGO?

IIRC, Rpi used ARMv6 optimized binaries for ARMv7 and ARM64. Also 32-bit kernel on 64-bit hardware, no?

[dragorth]

Possibly the smaller distros meant for routers and access points will make use of LTO-PGO optimised kernels. I assume projects like OpenWRT, DD-WRT, Hyper-WRT, Tomato, AdvancedTomato, FreshTomato, ... all those that run inside network devices, they should see a nice gain from it especially since these run on lower spec hardware where the gains should be more noticeable. For these should an optimised kernel produce higher throughput and lower latency.

By the same token, older and legacy hardware, such as the recent story of more compatibility for Motorola 68000 cpus could see some benefit for this. Also, VMs with lower resources, Raspberry Pis and other SoCs, not to mention controller projects that are generally special purpose applications,

i wonder is this implementation is added if the same data can be used by GCC PGO?

[sdack]

I wonder if some (especially enterprise targeted) distros will start to offer kernel streams optimized for certain types of workloads. Variants such as "container optimized", or "LAMP optimized" might make sense.

Possibly the smaller distros meant for routers and access points will make use of LTO-PGO optimised kernels. I assume projects like OpenWRT, DD-WRT, Hyper-WRT, Tomato, AdvancedTomato, FreshTomato, ... all those that run inside network devices, they should see a nice gain from it especially since these run on lower spec hardware where the gains should be more noticeable. For these should an optimised kernel produce higher throughput and lower latency.

[Aryma]

when the code is a mess that only compiled with quirky compiler