Re: multimedia/MMX, Celeron CPU, and the kernel config
On 09/01/03 08:22 PM, Hendrik Hasenbein sat at the `puter and typed: > Louis LeBlanc wrote: > > Now, I realize no one will want to make 'supported' or 'guaranteed' > > recommendations, but I would certainly appreciate some pointers on > > taking the above information and determining the ideal CPU options to > > use in my kernel. I looked at the handbook, and can't find any such > > details or links. My main goal is to find out what CPU features are > > disabled through the kernel config, and enable them - particularly MMX > > support. > > You don't need to enable MMX in the kernel. Your mplayer had MMX on, the > mplayerxp not I remember. Perhaps there is a switch for mplayerxp. > > > Features=0x183f9ff > > > > Does this specify just detection or kernel config? > > I would call it detection. > > Hendrik Thank you. Glad I checked before just rebuilding. Lou -- Louis LeBlanc [EMAIL PROTECTED] Fully Funded Hobbyist, KeySlapper Extrordinaire :) http://www.keyslapper.org ԿԬ Optimization hinders evolution. ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to "[EMAIL PROTECTED]"
Re: multimedia/MMX, Celeron CPU, and the kernel config
Louis LeBlanc wrote: Now, I realize no one will want to make 'supported' or 'guaranteed' recommendations, but I would certainly appreciate some pointers on taking the above information and determining the ideal CPU options to use in my kernel. I looked at the handbook, and can't find any such details or links. My main goal is to find out what CPU features are disabled through the kernel config, and enable them - particularly MMX support. You don't need to enable MMX in the kernel. Your mplayer had MMX on, the mplayerxp not I remember. Perhaps there is a switch for mplayerxp. Features=0x183f9ff Does this specify just detection or kernel config? I would call it detection. Hendrik ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to "[EMAIL PROTECTED]"
Re: multimedia/MMX, Celeron CPU, and the kernel config
On 09/01/03 05:04 AM, Ricardo Mesquita sat at the `puter and typed: > Louis LeBlanc wrote: > > Hey all. I've just installed the mplayer and mplayerxp ports for > > video support. I've never quite had it right with aviplay and > > plaympeg, but I never quite understood why. > > > > Well, when I run mplayer, I get the following: > > > > CPU: Intel Celeron A Mendocino/Pentium II Dixon (Family: 6, Stepping: 0) > > Detected cache-line size is 32 bytes > > CPUflags: MMX: 1 MMX2: 0 3DNow: 0 3DNow2: 0 SSE: 0 SSE2: 0 > > Compiled with Runtime CPU Detection - WARNING - this is not optimal! > > To get best performance, recompile MPlayer with --disable-runtime-cpudetection > > > > And mplayerxp gives the following: > > CPU vendor name: GenuineIntel max cpuid level: 2 > > CPU: Intel Celeron A Mendocino/Pentium II Dixon (Type: 6, Stepping: 0) > > MMX supported but disabled > > CPUflags: Type: 6 MMX: 0 MMX2: 0 3DNow: 0 3DNow2: 0 SSE: 0 SSE2: 0 > > Compiled for x86 CPU with features: 3DNow 3DNowEx SSE > > > > So I'm confused as to whether I've got the best configuration for my > > custom kernel. Is there a way I can discover the exact model of my > > cpu without cracking the case? > > > > > Thanks! > > Lou > > Check x86info Thanks a lot! This gives quite a lot of info about the chip: Family: 6 Model: 6 Stepping: 0 Type: 0 Brand: 0 CPU Model: Celeron (Mendocino) Original OEM Feature flags: Onboard FPU Virtual Mode Extensions Debugging Extensions Page Size Extensions Time Stamp Counter Model-Specific Registers Physical Address Extensions Machine Check Architecture CMPXCHG8 instruction SYSENTER/SYSEXIT Memory Type Range Registers Page Global Enable Machine Check Architecture CMOV instruction Page Attribute Table 36-bit PSEs MMX support FXSAVE and FXRESTORE instructions Extended feature flags: Instruction TLB: 4KB pages, 4-way associative, 32 entries Instruction TLB: 4MB pages, fully associative, 2 entries Data TLB: 4KB pages, 4-way associative, 64 entries L2 unified cache: Size: 128KB 4-way associative. line size=32 bytes. L1 Instruction cache: Size: 16KB 4-way associative. line size=32 bytes. Data TLB: 4MB pages, 4-way associative, 8 entries L1 Data cache: Size: 16KB 4-way associative. line size=32 bytes. /dev/cpu/0/msr: No such file or directory Connector type: Socket 370 (370 Pin PGA) MTRR registers: MTRRcap (0xfe): MTRRphysBase0 (0x200): MTRRphysMask0 (0x201): MTRRphysBase1 (0x202): MTRRphysMask1 (0x203): MTRRphysBase2 (0x204): MTRRphysMask2 (0x205): MTRRphysBase3 (0x206): MTRRphysMask3 (0x207): MTRRphysBase4 (0x208): MTRRphysMask4 (0x209): MTRRphysBase5 (0x20a): MTRRphysMask5 (0x20b): MTRRphysBase6 (0x20c): MTRRphysMask6 (0x20d): MTRRphysBase7 (0x20e): MTRRphysMask7 (0x20f): MTRRfix64K_0 (0x250): MTRRfix16K_8 (0x258): MTRRfix16K_A (0x259): MTRRfix4K_C8000 (0x269): MTRRfix4K_D 0x26a: MTRRfix4K_D8000 0x26b: MTRRfix4K_E 0x26c: MTRRfix4K_E8000 0x26d: MTRRfix4K_F 0x26e: MTRRfix4K_F8000 0x26f: MTRRdefType (0x2ff): 400MHz processor (estimate). Now, I realize no one will want to make 'supported' or 'guaranteed' recommendations, but I would certainly appreciate some pointers on taking the above information and determining the ideal CPU options to use in my kernel. I looked at the handbook, and can't find any such details or links. My main goal is to find out what CPU features are disabled through the kernel config, and enable them - particularly MMX support. Finally, I noticed my message log from bootup has the following: Features=0x183f9ff Does this specify just detection or kernel config? It appears to match the features detected by x86info. Thanks for all the help! Lou -- Louis LeBlanc [EMAIL PROTECTED] Fully Funded Hobbyist, KeySlapper Extrordinaire :) http://www.keyslapper.org ԿԬ aphorism, n.: A concise, clever statement. afterism, n.: A concise, clever statement you don't think of until too late. -- James Alexander Thom ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to "[EMAIL PROTECTED]"
Re: multimedia/MMX, Celeron CPU, and the kernel config
Louis LeBlanc wrote: Hey all. I've just installed the mplayer and mplayerxp ports for video support. I've never quite had it right with aviplay and plaympeg, but I never quite understood why. Well, when I run mplayer, I get the following: CPU: Intel Celeron A Mendocino/Pentium II Dixon (Family: 6, Stepping: 0) Detected cache-line size is 32 bytes CPUflags: MMX: 1 MMX2: 0 3DNow: 0 3DNow2: 0 SSE: 0 SSE2: 0 Compiled with Runtime CPU Detection - WARNING - this is not optimal! To get best performance, recompile MPlayer with --disable-runtime-cpudetection And mplayerxp gives the following: CPU vendor name: GenuineIntel max cpuid level: 2 CPU: Intel Celeron A Mendocino/Pentium II Dixon (Type: 6, Stepping: 0) MMX supported but disabled CPUflags: Type: 6 MMX: 0 MMX2: 0 3DNow: 0 3DNow2: 0 SSE: 0 SSE2: 0 Compiled for x86 CPU with features: 3DNow 3DNowEx SSE So I'm confused as to whether I've got the best configuration for my custom kernel. Is there a way I can discover the exact model of my cpu without cracking the case? Thanks! Lou Check x86info regards, ricardo mesquita ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to "[EMAIL PROTECTED]"
multimedia/MMX, Celeron CPU, and the kernel config
Hey all. I've just installed the mplayer and mplayerxp ports for video support. I've never quite had it right with aviplay and plaympeg, but I never quite understood why. Well, when I run mplayer, I get the following: CPU: Intel Celeron A Mendocino/Pentium II Dixon (Family: 6, Stepping: 0) Detected cache-line size is 32 bytes CPUflags: MMX: 1 MMX2: 0 3DNow: 0 3DNow2: 0 SSE: 0 SSE2: 0 Compiled with Runtime CPU Detection - WARNING - this is not optimal! To get best performance, recompile MPlayer with --disable-runtime-cpudetection And mplayerxp gives the following: CPU vendor name: GenuineIntel max cpuid level: 2 CPU: Intel Celeron A Mendocino/Pentium II Dixon (Type: 6, Stepping: 0) MMX supported but disabled CPUflags: Type: 6 MMX: 0 MMX2: 0 3DNow: 0 3DNow2: 0 SSE: 0 SSE2: 0 Compiled for x86 CPU with features: 3DNow 3DNowEx SSE So I'm confused as to whether I've got the best configuration for my custom kernel. Is there a way I can discover the exact model of my cpu without cracking the case? I'm running: 4.8-RELEASE #0: built Sat Apr 12, 2003. The boot process logs the following: CPU: Pentium II/Pentium II Xeon/Celeron (399.12-MHz 686-class CPU) The machine is a Dell Optiplex G1, that was built several years ago, and given to me by my employer in a surplus lottery almost 2 years ago. I've put a new hard drive and video card in it, but that's about it. AFAIK, the machine had been unmodified before I got it. BTW, I have the following enabled in my kernel config: ### machine i386 cpu I686_CPU ident KEYSLAPPER maxusers0 options INET options INET6 options FFS options FFS_ROOT options SOFTUPDATES options MFS options MD_ROOT options NFS options NFS_ROOT options MSDOSFS options CD9660 options CD9660_ROOT options PROCFS options COMPAT_43 options SCSI_DELAY=15000 options UCONSOLE options USERCONFIG options VISUAL_USERCONFIG options KTRACE options SYSVSHM options SYSVMSG options SYSVSEM options P1003_1B options _KPOSIX_PRIORITY_SCHEDULING options ICMP_BANDLIM options KBD_INSTALL_CDEV options NSWAPDEV=1 options USER_LDT options ATA_STATIC_ID options IPFIREWALL options IPFIREWALL_VERBOSE options IPFIREWALL_VERBOSE_LIMIT=200 options IPDIVERT Plus of course, the various devices. There is no SCSI card in the machine at the time, so I don't know if the SCSI_DELAY option makes any difference. I have found a few other options I'm not sure about, the CPU_PPRO2CELERON, CPU_L2_LATENCY, and CPU_ENABLE_SSE options. I'm just not sure if they apply in my specific case. I'm thinking the CPU_ENABLE_SSE option does, but before I go to the bother of changing my kernel config and rebuilding, I'd like to know if it is going to make even a little difference. Can anyone give me a pointer? Anything will be welcome, whether a URL, or a direct indication. Thanks! Lou -- Louis LeBlanc [EMAIL PROTECTED] Fully Funded Hobbyist, KeySlapper Extrordinaire :) http://www.keyslapper.org ԿԬ We can defeat gravity. The problem is the paperwork involved. ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to "[EMAIL PROTECTED]"