Hi Lumin, thanks for your long explanation. While I have a divergent opinion in some points I do not feel competent enough to discuss this here. However, I stumbled upon one point which I consider a valuable topic to move to debian-de...@lists.debian.org.
On Wed, Feb 08, 2017 at 03:33:16PM +0000, lumin wrote: > * Debian's official binary packages have lost performance from SIMD > instruction sets. One of my research program runs several times > faster after recompiled OpenBLAS with -march=native and some > other tweaks. Building packages with generic flags, a result > of Debian's goal of being Universal, makes official binary packages > not quite suitable for both compute-bound and IO-bound task. > Compiling from source following the upstream guide is fine. So do you think we are doing a bad service to our users by striping -march=native? Could you please provide some numbers? I wonder whether we could invent some mechanism that is rebuilding a package in postinst and installs the result on the machine instead of a pre-build binary. Or we could provide some toolset which enables scientists to download a set of source packages and build these after re-activating -march=native and move the results in a local repository which just needs to be added to sources.list. Do you consider this as feasible ideas? Kind regards Andreas. -- http://fam-tille.de