cpuinfo does not show mmxext or sse3, but the python script does. Host is a virtual machine: # cat /proc/cpuinfo processor : 0 vendor_id : GenuineIntel cpu family : 6 model : 2 model name : QEMU Virtual CPU version 0.9.1 stepping : 3 cpu MHz : 0.000 cache size : 512 KB fpu : yes fpu_exception : yes cpuid level : 2 wp : yes flags : fpu de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 syscall nx lm nopl pni hypervisor bogomips : 4530.17 TLB size : 1024 4K pages clflush size : 64 cache_alignment : 64 address sizes : 40 bits physical, 48 bits virtual power management: # cpuinfo2cpuflags-x86 CPU_FLAGS_X86="mmx mmxext sse sse2 sse3"
Well, the corresponding flag for sse3 is pni, and that is present in your cpuinfo. About mmxext, it is *almost* a subset of sse but I'm not sure it can be assumed when sse is exposed. /usr/portage/profiles/desc/cpu_flags_x86.desc claims that it is safe to assume mmxext whenever sse is present, so if that is wrong that is the place to fix.
I see mmxext where that isn't reported in /proc/cpuinfo, but mmxext is supposed to be a subset of sse, so it should be supported where sse is. $ cpuinfo2cpuflags-x86 CPU_FLAGS_X86="mmx mmxext sse sse2 sse3 sse4_1 ssse3" $ grep ^flags /proc/cpuinfo | head -n1 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 sse4_1 xsave lahf_lm dtherm tpr_shadow vnmi flexpriority
Sorry for missing this bug earlier. mmxext is a subset of sse, so it's supported everywhere sse is supported (see AMD developer's manual, there's no mnemonic that's purely mmxext, all are mmxext||sse). sse3 is called 'pni' in cpuinfo, for no good reason.