Re: Phase 0 devices just running @100MHz?
On 3/9/07, Siarhei Siamashka <[EMAIL PROTECTED]> wrote: On Friday 09 March 2007 11:07, pHilipp Zabel wrote: > On 3/8/07, Nils Faerber <[EMAIL PROTECTED]> wrote: > > Pierre Hébert schrieb: > > > It doesn't seem so bad : my [EMAIL PROTECTED] shows 199bogomips, so at > > > 200MHz 100bogomips seems correct (s3c2440 has the same cpu as s3c2410). > > > I don't know if the bogomips indication is a value in which we can > > > really trust, these little devices are really efficient even at > > > 100/200bogomips. > > > > The bogomips result is a little different depending on the core > > architecture. So for the Samsung CPU bogomips ~= 1/2 MHz. > > OK, good to know! > > A PXA270 I have on my desk has the ~ 1:1 bogomips to MHz mapping... > > I guess this depends on how many cycles the __delay(loops_per_jiffy) loop > > ENTRY(__delay) > subsr0, r0, 1 > bhi __delay > mov pc,lr > > takes on the given cpu. > On the S3C2440 subs takes 1S and bhi takes 2S+1N cycles. > Is information about the PXA27x instruction cycle times available > somewhere? If you are interested in estimating cpu clock frequency, you can try a simple test program I have written some time ago: http://ufo2000.xcomufo.com/maemo/testfreq.c Thanks, I'm just interested in understanding the bogomips issue for now. A few references related to arm cpu performance. Instruction timings and optimization guide for ARM9E: http://arm.com/pdfs/DDI0222B_9EJS_r1p2.pdf Instruction timings and optimization guide for ARM11 (used in OMAP2): http://arm.com/pdfs/DDI0360C_arm11mpcore_r0p3_trm.pdf Instruction timings and optimization guide for Intel XScale: http://download.intel.com/design/int...e/27347302.pdf This is exactly what I was looking for! On Xscale, b(hi) has a minimum issue latency of 1 cycle if there is no branch misprediction, same for sub(s) (with a result latency of another cycle). So the average __delay loop on Xscale takes 2 cycles opposed to 4 on the S3C2440, resulting in a factor of 1:2 in the BogoMips values. regards Philipp ___ OpenMoko community mailing list community@lists.openmoko.org http://lists.openmoko.org/mailman/listinfo/community
Re: Phase 0 devices just running @100MHz?
On Friday 09 March 2007 11:07, pHilipp Zabel wrote: > On 3/8/07, Nils Faerber <[EMAIL PROTECTED]> wrote: > > Pierre Hébert schrieb: > > > It doesn't seem so bad : my [EMAIL PROTECTED] shows 199bogomips, so at > > > 200MHz 100bogomips seems correct (s3c2440 has the same cpu as s3c2410). > > > I don't know if the bogomips indication is a value in which we can > > > really trust, these little devices are really efficient even at > > > 100/200bogomips. > > > > The bogomips result is a little different depending on the core > > architecture. So for the Samsung CPU bogomips ~= 1/2 MHz. > > OK, good to know! > > A PXA270 I have on my desk has the ~ 1:1 bogomips to MHz mapping... > > I guess this depends on how many cycles the __delay(loops_per_jiffy) loop > > ENTRY(__delay) > subsr0, r0, 1 > bhi __delay > mov pc,lr > > takes on the given cpu. > On the S3C2440 subs takes 1S and bhi takes 2S+1N cycles. > Is information about the PXA27x instruction cycle times available > somewhere? If you are interested in estimating cpu clock frequency, you can try a simple test program I have written some time ago: http://ufo2000.xcomufo.com/maemo/testfreq.c A few references related to arm cpu performance. Instruction timings and optimization guide for ARM9E: http://arm.com/pdfs/DDI0222B_9EJS_r1p2.pdf Instruction timings and optimization guide for ARM11 (used in OMAP2): http://arm.com/pdfs/DDI0360C_arm11mpcore_r0p3_trm.pdf Instruction timings and optimization guide for Intel XScale: http://download.intel.com/design/int...e/27347302.pdf Instruction timings and optimization guide for Cortex (used in OMAP3): http://arm.com/pdfs/DDI0337C_cortexm3_r1p0_trm.pdf Comparison of ARM7 and ARM9: http://arm.com/pdfs/comparison-arm7-arm9-v1.pdf Comparison of ARM9 and Cortex: http://arm.com/pdfs/13128.pdf ___ OpenMoko community mailing list community@lists.openmoko.org http://lists.openmoko.org/mailman/listinfo/community
Re: Phase 0 devices just running @100MHz?
On 3/8/07, Nils Faerber <[EMAIL PROTECTED]> wrote: Pierre Hébert schrieb: > It doesn't seem so bad : my [EMAIL PROTECTED] shows 199bogomips, so at > 200MHz 100bogomips seems correct (s3c2440 has the same cpu as s3c2410). > I don't know if the bogomips indication is a value in which we can really > trust, these little devices are really efficient even at > 100/200bogomips. The bogomips result is a little different depending on the core architecture. So for the Samsung CPU bogomips ~= 1/2 MHz. OK, good to know! A PXA270 I have on my desk has the ~ 1:1 bogomips to MHz mapping... I guess this depends on how many cycles the __delay(loops_per_jiffy) loop ENTRY(__delay) subsr0, r0, 1 bhi __delay mov pc,lr takes on the given cpu. On the S3C2440 subs takes 1S and bhi takes 2S+1N cycles. Is information about the PXA27x instruction cycle times available somewhere? regards Philipp ___ OpenMoko community mailing list community@lists.openmoko.org http://lists.openmoko.org/mailman/listinfo/community
Re: Phase 0 devices just running @100MHz?
http://en.wikipedia.org/wiki/BogoMips 2007/3/8, Nils Faerber <[EMAIL PROTECTED]>: Pierre Hébert schrieb: > It doesn't seem so bad : my [EMAIL PROTECTED] shows 199bogomips, so at > 200MHz 100bogomips seems correct (s3c2440 has the same cpu as s3c2410). > I don't know if the bogomips indication is a value in which we can really > trust, these little devices are really efficient even at > 100/200bogomips. The bogomips result is a little different depending on the core architecture. So for the Samsung CPU bogomips ~= 1/2 MHz. OK, good to know! A PXA270 I have on my desk has the ~ 1:1 bogomips to MHz mapping... Thanks! > cheers, > Pierre. Cheers nils faerber -- kernel concepts GbRTel: +49-271-771091-12 Sieghuetter Hauptweg 48Fax: +49-271-771091-19 D-57072 Siegen Mob: +49-176-21024535 -- ___ OpenMoko community mailing list community@lists.openmoko.org http://lists.openmoko.org/mailman/listinfo/community -- Denis Kot denis?jabber.org.by ICQ: 13680126 Mobil: +375 29 6-1234-78 ___ OpenMoko community mailing list community@lists.openmoko.org http://lists.openmoko.org/mailman/listinfo/community
Re: Phase 0 devices just running @100MHz?
Pierre Hébert schrieb: > It doesn't seem so bad : my [EMAIL PROTECTED] shows 199bogomips, so at > 200MHz 100bogomips seems correct (s3c2440 has the same cpu as s3c2410). > I don't know if the bogomips indication is a value in which we can really > trust, these little devices are really efficient even at > 100/200bogomips. The bogomips result is a little different depending on the core architecture. So for the Samsung CPU bogomips ~= 1/2 MHz. OK, good to know! A PXA270 I have on my desk has the ~ 1:1 bogomips to MHz mapping... Thanks! > cheers, > Pierre. Cheers nils faerber -- kernel concepts GbRTel: +49-271-771091-12 Sieghuetter Hauptweg 48Fax: +49-271-771091-19 D-57072 Siegen Mob: +49-176-21024535 -- ___ OpenMoko community mailing list community@lists.openmoko.org http://lists.openmoko.org/mailman/listinfo/community
Re: Phase 0 devices just running @100MHz?
It doesn't seem so bad : my [EMAIL PROTECTED] shows 199bogomips, so at 200MHz 100bogomips seems correct (s3c2440 has the same cpu as s3c2410). I don't know if the bogomips indication is a value in which we can really trust, these little devices are really efficient even at 100/200bogomips. cheers, Pierre. On Thursday 08 March 2007, Nils Faerber wrote: > Hi! > I just had a first quick run on a phase-0 Neo and found that > /proc/cpuinfo only shows ~100 bogomips. On other ARM based platforms > using 2.6.xx kernels I know the bogomips are usually about the same as > the CPU core clock MHz... > Well this might be different here so I just wanted to make sure that > experienced slowness is not simply caused by an underclocked CPU ;) > > Cheers > nils faerber ___ OpenMoko community mailing list community@lists.openmoko.org http://lists.openmoko.org/mailman/listinfo/community
Phase 0 devices just running @100MHz?
Hi! I just had a first quick run on a phase-0 Neo and found that /proc/cpuinfo only shows ~100 bogomips. On other ARM based platforms using 2.6.xx kernels I know the bogomips are usually about the same as the CPU core clock MHz... Well this might be different here so I just wanted to make sure that experienced slowness is not simply caused by an underclocked CPU ;) Cheers nils faerber -- kernel concepts GbRTel: +49-271-771091-12 Sieghuetter Hauptweg 48Fax: +49-271-771091-19 D-57072 Siegen Mob: +49-176-21024535 -- ___ OpenMoko community mailing list community@lists.openmoko.org http://lists.openmoko.org/mailman/listinfo/community