Google Posts Patches So The Linux Kernel Can Be LTO-Optimized By Clang

[FPScholten]

Yes, but there is an actual and measurable performance and efficiency effect using the matching architecture for your processor. LTO might help even more but unfortunately does not build.

[CochainComplex]

No, I have a Haswell based system so I optimise my kernels for that.

I have seen LTO builds break more easily with march other then generic.

[freedonuts]

Execution speed is usually not really improving with lto, but size reduction is often measurable.

Wouldn't that size reduction possibly imply less cache misses and thus greater performance?

[FPScholten]

Yes LTO or even PGO with the Kernel is seriously not so easy. DId you use march=generic in config?

No, I have a Haswell based system so I optimise my kernels for that.

[Hans Bull]

Execution speed is usually not really improving with lto, but size reduction is often measurable.

Reducing kernel obesity would be more than welcome.

[Aryma]

i have a dream to see linux without GNU

[CochainComplex]

Yes LTO or even PGO with the Kernel is seriously not so easy. DId you use march=generic in config?

[FPScholten]

imagine a ltoed xanmod

Last time I tried this, building failed... (with GCC10)
This is the case with more software, for example ffmpeg also fails to build with lto enabled

[carewolf]

Gonna wait that out. Expect data losses.

[caligula]

Execution speed is usually not really improving with lto, but size reduction is often measurable.

IIRC, LTO also detects some type signature changes across modules.