Date: Fri, 05 Jun 2026 19:52:31 +0000 From: bugzilla-noreply@freebsd.org To: python@FreeBSD.org Subject: [Bug 295633] math/py-numpy: 2.4 illegal instruction on certain Intel amd64 v2 hardware Message-ID: <bug-295633-21822-L1LSlKWWq4@https.bugs.freebsd.org/bugzilla/> In-Reply-To: <bug-295633-21822@https.bugs.freebsd.org/bugzilla/>
index | next in thread | previous in thread | raw e-mail
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=295633 --- Comment #10 from Cy Schubert <cy@FreeBSD.org> --- I see the difference between v2 and my v1 processors (+ features). My AMD processors have all v2 features except SSE4.1 and SSE4.2. They have SSE4a, introduced by AMD before Intel released its SSE4.1 and 4.2 standards. I've said this before (in other places) and will say it again here: the versioning used by Intel paints processors with broad strokes of the brush where in fact features are more finely grained than that. One can see one's processor "version" by cloning https://github.com/HenrikBengtsson/x86-64-level.git and altering it a little to run under FreeBSD. I simply loaded the linux kld and altered the script to read /usr/compat/linux/proc/cpuinfo. -- You are receiving this mail because: You are the assignee for the bug.home | help
Want to link to this message? Use this
URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?bug-295633-21822-L1LSlKWWq4>