On Sat, Oct 15, 2011 at 03:52:55PM +1000, David Seikel wrote: > On Sat, 15 Oct 2011 16:13:07 +1100 Jochen Schröder > <cycoma...@gmail.com> wrote: > > > On 10/15/2011 01:37 PM, Carsten Haitzler (The Rasterman) wrote: > > > On Fri, 14 Oct 2011 16:16:44 -0700 Jim Kukunas > > > <james.t.kuku...@linux.intel.com> said: > > > > > >> On Sat, Oct 15, 2011 at 12:54:00AM +0200, Tom Hacohen wrote: > > >>> On 14/10/11 19:20, Jim Kukunas wrote: > > >>>> What is your compiler version and CFLAGS? > > >>>> > > >>>> The parameters to _mm_set_epi32 look reasonable. The only reason > > >>>> I could imagine this failing is if your compiler isn't aligning > > >>>> things properly. > > >>> > > >>> It's the sse3 issue all over again. As you can see, his CPU > > >>> doesn't support sse3 but sse3 code is called. > > >> > > >> His CPU does support SSE3, hence the ``pni'' in his /proc/cpuinfo. > > > > > > let's eliminate first shall we. > > > > > > tomas - can you either --disable-cpu-sse3 when configuring evas, OR > > > set EVAS_CPU_NO_SSE3=1 as an env var before running e to see if > > > this is sse3 stuff or not or a more generic problem. > > > > > I assume you mean me not Tomas, as I reported the segfault. This was > > on my PC at work so it will have to wait until Monday. This is a Core > > 2 Duo, which AFAIK does support SSE3 (wikipedia says SSE3 was > > introduced with Prescott). > > It did say "ssse3" in your flags, just not straight after "sse2", it's > two lines further down. > > > flags : fpu vme de pse tsc msr pae mce cx8 apic sep > > mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht > > tm pbe syscall nx lm constant_tsc arch_perfmon pebs bts rep_good nopl > > aperfmperf pni dtes64 monitor ds_cpl vmx smx est tm2 ssse3 cx16 xtpr > > pdcm lahf_lm dts tpr_shadow vnmi flexpriority > > Dunno about that extra 's' though.
ssse3 != sse3. ssse3 adds instructions like palignr and horizontal operations. > > For what it's worth, mine says "sse4a" later in the flags after "sse2", > but no "sse3". sse3 is represented by ``pni'' in /proc/cpuinfo. > > -- > A big old stinking pile of genius that no one wants > coz there are too many silver coated monkeys in the world. > ------------------------------------------------------------------------------ > All the data continuously generated in your IT infrastructure contains a > definitive record of customers, application performance, security > threats, fraudulent activity and more. Splunk takes this data and makes > sense of it. Business sense. IT sense. Common sense. > http://p.sf.net/sfu/splunk-d2d-oct > _______________________________________________ > enlightenment-devel mailing list > enlightenment-devel@lists.sourceforge.net > https://lists.sourceforge.net/lists/listinfo/enlightenment-devel -- Jim Kukunas Intel Open Source Technology Center ------------------------------------------------------------------------------ All the data continuously generated in your IT infrastructure contains a definitive record of customers, application performance, security threats, fraudulent activity and more. Splunk takes this data and makes sense of it. Business sense. IT sense. Common sense. http://p.sf.net/sfu/splunk-d2d-oct _______________________________________________ enlightenment-devel mailing list enlightenment-devel@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/enlightenment-devel
