Re: Performance tuning for the XO
> We make currently make heavy use of hashing in our upgrade & > verification infrastructure. I'd like to find the fastest possible > implementation of the SHA-256 and/or RIPEMD-160 algorithms. Can > anyone offer me advice on the proper compilation options and > strategies for maximum performance on the processor in the XO? I > don't see the -mxo option to gcc yet. That sounds like a good summer intern project. Or maybe a thesis topic. Is there a list of good projects that this should be added to? -- These are my opinions, not necessarily my employer's. I hate spam. ___ Devel mailing list Devel@lists.laptop.org http://lists.laptop.org/listinfo/devel
Performance tuning for the XO
We make currently make heavy use of hashing in our upgrade & verification infrastructure. I'd like to find the fastest possible implementation of the SHA-256 and/or RIPEMD-160 algorithms. Can anyone offer me advice on the proper compilation options and strategies for maximum performance on the processor in the XO? I don't see the -mxo option to gcc yet. --scott -- ( http://cscott.net/ ) ___ Devel mailing list Devel@lists.laptop.org http://lists.laptop.org/listinfo/devel
Re: PSS/USS
Andrew Morton wrote: > But otoh the patch at http://lkml.org/lkml/2007/8/16/306 looks sufficiently > simple that if people find it to be useful then the world wouldn't end if we > merged it. > > But it is a feature and hence isn't appropriate for 2.6.23. Yeah, I propose it for mm. > So. You _think_ that this feature might be useful to you. But are you > sure? Will it be 100% sufficient for your needs over the next N years? > Will it tell you everything which you want to know? Come on, we can't realistically be this much confident about anything we do, especially when it comes to software (-: PSS is the honest memory usage figure any user and developer always wanted to see in the top utility. Death to RSS and VM! -- \__/ |__| Bernardo Innocenti - http://www.codewiz.org/ \__\ One Laptop Per Child - http://www.laptop.org/ ___ Devel mailing list Devel@lists.laptop.org http://lists.laptop.org/listinfo/devel
Re: PSS/USS
On 09/21/2007 11:34 AM, Pádraig Brady wrote: > Oops sorry. > I saw the patch here and assumed it was going into 2.6.23: > http://lkml.org/lkml/2007/8/16/306 > > It would be great to get this in ASAP, > as it's a trivial but very useful extension to smaps Oh, I wasn't aware a subset of Matt Mackall's patch set was reiterated lately. Are these new patches in mm already? If not, would you like to pick them up, Andrew? -- \__/ |__| Bernardo Innocenti - http://www.codewiz.org/ \__\ One Laptop Per Child - http://www.laptop.org/ ___ Devel mailing list Devel@lists.laptop.org http://lists.laptop.org/listinfo/devel
Re: startup sound
In recent (more recent than c27) test builds, you can adjust the volume of the startup sound using the keyboard keys for sound volume. The volume thus established persists across reboot. If you turn the volume down all the way, the sound will be disabled completely. ___ Devel mailing list Devel@lists.laptop.org http://lists.laptop.org/listinfo/devel
Re: startup sound
Thanks for the replies which included the information i needed. I tried those instructions on the cheat page out - fun. The entry in the wiki about the 'Left directional pad' should probably be changed, since it seems to disable the pretty boot now. I changed that on the wiki please revert if this is not correct. Simon Kim Quirk wrote: > Please see the cheat codes for turning off sound and graphical boot: > http://wiki.laptop.org/go/Cheat_codes > > Hold down the 'rotate' screen button while you power up. We may also want a > command line to turn this off indefinately (for every boot), but I think > that has to come with the Control Panel. Requirements for this can be found > in the Requirements page of the wiki. I just added this request, 4.10: > http://wiki.laptop.org/go/Requirements > > Kim > > > On 9/21/07, Jim Gettys <[EMAIL PROTECTED]> wrote: >> On Fri, 2007-09-21 at 13:15 +0200, Simon Schamijer wrote: >>> I have been thinking about the startup sound. So is it really the idea >>> to have this be enabled by default? Are the laptops shipped like that or >>> is this for debugging purpose only? >>> >>> If yes, have we thought about those cases: >>> - 20 kids turn their laptop on in a class? >> We don't expect kids to be rebooting every day. That's what suspend is >> for. >> >>> - a kid comes late and has to turn on his laptop? >>> >>> Even if the idea is to have the kids be able to edit them, we will have >>> the 20 kids be playing their 'sound' each startup. Or are the machines >>> meant to go more often into sleep mode rather than a complete shutdown? >>> >>> If this has been thought through already and is all set sorry for the >> noise, >> >> There may still need to be a way to disable it. >>- Jim >> >>> Simon >>> >>> >>> Simon Schampijer wrote: Hi, since firmware q2c27 the startup sound is enabled by default. Are >> there or will there be ways to turn it off and edit it? If, can someone >> point me to documentation about it. Thanks, Simon ___ Devel mailing list Devel@lists.laptop.org http://lists.laptop.org/listinfo/devel >>> ___ >>> Devel mailing list >>> Devel@lists.laptop.org >>> http://lists.laptop.org/listinfo/devel >> -- >> Jim Gettys >> One Laptop Per Child >> >> >> ___ >> Devel mailing list >> Devel@lists.laptop.org >> http://lists.laptop.org/listinfo/devel >> > ___ Devel mailing list Devel@lists.laptop.org http://lists.laptop.org/listinfo/devel
Re: PSS/USS (Was: The "iGoogle bug")
Bernardo Innocenti wrote: > Pádraig Brady wrote: > >>> This gives even better results: >>> >>> http://lwn.net/Articles/230975/ >>> http://www.linuxworld.com/news/2007/042407-kernel.html >>> >>> The PSS and USS are are the Right Thing: they give users and >>> developers a honest and accurate figure. >>> >>> The downside is that it would require a very fresh kernel or 13 >>> invasive VM patches. >>> >> I've just updated my ps_mem.py tool to use PSS when available: >> http://www.pixelbeat.org/scripts/ps_mem.py > > Cool! > > But I don't see the PSS support in 2.6.23, and the patchset originally > posted on the lkml is stale. > > Where does up-to-date kernel support for PSS live? Oops sorry. I saw the patch here and assumed it was going into 2.6.23: http://lkml.org/lkml/2007/8/16/306 It would be great to get this in ASAP, as it's a trivial but very useful extension to smaps cheers, Pádraig. ___ Devel mailing list Devel@lists.laptop.org http://lists.laptop.org/listinfo/devel
Re: Downloaded files
Hi, How do i add items to the clipboard on the XO? Thanks! Ankita On 9/20/07, Samuel Klein <[EMAIL PROTECTED]> wrote: > > They are stored in /tmp . SJ > > On 9/20/07, ankita prasad <[EMAIL PROTECTED]> wrote: > > Hi, > > > > When i download a file from the internet, i can see the file on the > desktop > > of the sugar interface(the options shown are "remove" and "add to > journal"). > > How do I access that file from the terminal as in where are these files > > stored? > > > > Thanks! > > Ankita > > > > ___ > > Devel mailing list > > Devel@lists.laptop.org > > http://lists.laptop.org/listinfo/devel > > > > > ___ Devel mailing list Devel@lists.laptop.org http://lists.laptop.org/listinfo/devel
Re: MMU vs GPU (Was: The "iGoogle bug")
Of course, writing code for this would be kind of stupid one month before shipping. From my side it was just a thought whether it could be done at all (it can). Jim Gettys wrote: > Right now, the X kernel driver infrastructure and memory management > isn't adequate, and is being worked on actively elsewhere. > > Until that is done (or nearly done, to where the feedback to those > people would have value), work in this area isn't worth our time. > > But someday. > - Jim > > ___ Devel mailing list Devel@lists.laptop.org http://lists.laptop.org/listinfo/devel
Re: startup sound
Please see the cheat codes for turning off sound and graphical boot: http://wiki.laptop.org/go/Cheat_codes Hold down the 'rotate' screen button while you power up. We may also want a command line to turn this off indefinately (for every boot), but I think that has to come with the Control Panel. Requirements for this can be found in the Requirements page of the wiki. I just added this request, 4.10: http://wiki.laptop.org/go/Requirements Kim On 9/21/07, Jim Gettys <[EMAIL PROTECTED]> wrote: > > On Fri, 2007-09-21 at 13:15 +0200, Simon Schamijer wrote: > > I have been thinking about the startup sound. So is it really the idea > > to have this be enabled by default? Are the laptops shipped like that or > > is this for debugging purpose only? > > > > If yes, have we thought about those cases: > > - 20 kids turn their laptop on in a class? > > We don't expect kids to be rebooting every day. That's what suspend is > for. > > > - a kid comes late and has to turn on his laptop? > > > > Even if the idea is to have the kids be able to edit them, we will have > > the 20 kids be playing their 'sound' each startup. Or are the machines > > meant to go more often into sleep mode rather than a complete shutdown? > > > > If this has been thought through already and is all set sorry for the > noise, > > There may still need to be a way to disable it. >- Jim > > > Simon > > > > > > Simon Schampijer wrote: > > > Hi, > > > > > > since firmware q2c27 the startup sound is enabled by default. Are > there > > > or will there be ways to turn it off and edit it? If, can someone > point > > > me to documentation about it. > > > > > > Thanks, > > > Simon > > > ___ > > > Devel mailing list > > > Devel@lists.laptop.org > > > http://lists.laptop.org/listinfo/devel > > > > > > > ___ > > Devel mailing list > > Devel@lists.laptop.org > > http://lists.laptop.org/listinfo/devel > -- > Jim Gettys > One Laptop Per Child > > > ___ > Devel mailing list > Devel@lists.laptop.org > http://lists.laptop.org/listinfo/devel > ___ Devel mailing list Devel@lists.laptop.org http://lists.laptop.org/listinfo/devel
Re: MMU vs GPU (Was: The "iGoogle bug")
Right now, the X kernel driver infrastructure and memory management isn't adequate, and is being worked on actively elsewhere. Until that is done (or nearly done, to where the feedback to those people would have value), work in this area isn't worth our time. But someday. - Jim On Fri, 2007-09-21 at 13:31 +0200, NoiseEHC wrote: > According to the databook, GP_BASE_OFFSET (page 270) is included in the > command buffer (page 239). If you push the command buffer into the > kernel then implementing that should be trivial. (Now I have realized > that X runs in user mode and this amd driver is not a kernel driver but > an X driver. What a stupid architecture...) Since GP_BASE_OFFSET defines > a 16MB long buffer on a 4MB boundary, if the driver rejects bitmaps > larger than 12MB then you do not even have to split at 16MB boundary > (only at every 4KB). Of course, you have to split at page boundary > anyway so you can just calculate GP_BASE_OFFSET every time... > However it is not clear if it would increase speed enough that it would > worth implementing, after all one line of data will be held in the L1/L2 > cache so the video processor does not need to fetch memory. Keeping > buffers in the X client's memory space would speed up things but I think > that it would break some X semantics (for example if you push something > to the X server, it would became a NOP but after that the client should > not modify the bitmap). Now this would take a looong time to implement. > I wanted to look at X.org's implementation but their servers seems to be > down. > > Bernardo Innocenti wrote: > > NoiseEHC wrote: > > > > > >>> - Seeing if we can get the blitter to read source data directly from > >>> system > >>>memory. I'd be very surprised if there was no way to make it work > >>>with virtual memory enabled, because, without such a mechanism, the > >>>blitter would be less than fully useful. > >>> > >>> > >> Could somebody shed some light on this, please? > >> > >> I think that probably the Linux kernel has some page locking function > >> which returns a list of physical addresses from a virtual address has > >> not it? > >> > > > > That's virt_to_phys(), yes... but it's not available in userspace. > > All the people I've consulted agreed it's not easy to translate > > virtual addresses from within a process. > > > > > > > >> The Channel 3 DMA can be programmed to read from any 16MB block > >> from the 32 bit address space. Why is it hard to combine the two? > >> Why is it even necessary to upload bitmaps to "video memory"? > >> > > > > Yes... UMA systems already pay a price in terms of memory bandwidth, > > they should at least be compensated with the advantage of not having > > to do the migration crap. > > > > It's very likely a leftover from the original PC architecture with > > separate CGA/EGA/VGA cards. Even now that GPUs are being integrated > > on the same physical die of the CPU, they still look and act like > > external PCI devices :-) > > > > DRM is supposed to help solve the virt_to_phys() problem. > > But if we could do as you suggest and just use bitmaps scattered > > through memory pages, we'd be *much* faster. > > > > > ___ > Devel mailing list > Devel@lists.laptop.org > http://lists.laptop.org/listinfo/devel -- Jim Gettys One Laptop Per Child ___ Devel mailing list Devel@lists.laptop.org http://lists.laptop.org/listinfo/devel
Re: startup sound
On Fri, 2007-09-21 at 13:15 +0200, Simon Schamijer wrote: > I have been thinking about the startup sound. So is it really the idea > to have this be enabled by default? Are the laptops shipped like that or > is this for debugging purpose only? > > If yes, have we thought about those cases: > - 20 kids turn their laptop on in a class? We don't expect kids to be rebooting every day. That's what suspend is for. > - a kid comes late and has to turn on his laptop? > > Even if the idea is to have the kids be able to edit them, we will have > the 20 kids be playing their 'sound' each startup. Or are the machines > meant to go more often into sleep mode rather than a complete shutdown? > > If this has been thought through already and is all set sorry for the noise, There may still need to be a way to disable it. - Jim > Simon > > > Simon Schampijer wrote: > > Hi, > > > > since firmware q2c27 the startup sound is enabled by default. Are there > > or will there be ways to turn it off and edit it? If, can someone point > > me to documentation about it. > > > > Thanks, > > Simon > > ___ > > Devel mailing list > > Devel@lists.laptop.org > > http://lists.laptop.org/listinfo/devel > > > > ___ > Devel mailing list > Devel@lists.laptop.org > http://lists.laptop.org/listinfo/devel -- Jim Gettys One Laptop Per Child ___ Devel mailing list Devel@lists.laptop.org http://lists.laptop.org/listinfo/devel
Re: MMU vs GPU (Was: The "iGoogle bug")
According to the databook, GP_BASE_OFFSET (page 270) is included in the command buffer (page 239). If you push the command buffer into the kernel then implementing that should be trivial. (Now I have realized that X runs in user mode and this amd driver is not a kernel driver but an X driver. What a stupid architecture...) Since GP_BASE_OFFSET defines a 16MB long buffer on a 4MB boundary, if the driver rejects bitmaps larger than 12MB then you do not even have to split at 16MB boundary (only at every 4KB). Of course, you have to split at page boundary anyway so you can just calculate GP_BASE_OFFSET every time... However it is not clear if it would increase speed enough that it would worth implementing, after all one line of data will be held in the L1/L2 cache so the video processor does not need to fetch memory. Keeping buffers in the X client's memory space would speed up things but I think that it would break some X semantics (for example if you push something to the X server, it would became a NOP but after that the client should not modify the bitmap). Now this would take a looong time to implement. I wanted to look at X.org's implementation but their servers seems to be down. Bernardo Innocenti wrote: > NoiseEHC wrote: > > >>> - Seeing if we can get the blitter to read source data directly from system >>>memory. I'd be very surprised if there was no way to make it work >>>with virtual memory enabled, because, without such a mechanism, the >>>blitter would be less than fully useful. >>> >>> >> Could somebody shed some light on this, please? >> >> I think that probably the Linux kernel has some page locking function >> which returns a list of physical addresses from a virtual address has >> not it? >> > > That's virt_to_phys(), yes... but it's not available in userspace. > All the people I've consulted agreed it's not easy to translate > virtual addresses from within a process. > > > >> The Channel 3 DMA can be programmed to read from any 16MB block >> from the 32 bit address space. Why is it hard to combine the two? >> Why is it even necessary to upload bitmaps to "video memory"? >> > > Yes... UMA systems already pay a price in terms of memory bandwidth, > they should at least be compensated with the advantage of not having > to do the migration crap. > > It's very likely a leftover from the original PC architecture with > separate CGA/EGA/VGA cards. Even now that GPUs are being integrated > on the same physical die of the CPU, they still look and act like > external PCI devices :-) > > DRM is supposed to help solve the virt_to_phys() problem. > But if we could do as you suggest and just use bitmaps scattered > through memory pages, we'd be *much* faster. > > ___ Devel mailing list Devel@lists.laptop.org http://lists.laptop.org/listinfo/devel
Re: startup sound
I have been thinking about the startup sound. So is it really the idea to have this be enabled by default? Are the laptops shipped like that or is this for debugging purpose only? If yes, have we thought about those cases: - 20 kids turn their laptop on in a class? - a kid comes late and has to turn on his laptop? Even if the idea is to have the kids be able to edit them, we will have the 20 kids be playing their 'sound' each startup. Or are the machines meant to go more often into sleep mode rather than a complete shutdown? If this has been thought through already and is all set sorry for the noise, Simon Simon Schampijer wrote: > Hi, > > since firmware q2c27 the startup sound is enabled by default. Are there > or will there be ways to turn it off and edit it? If, can someone point > me to documentation about it. > > Thanks, > Simon > ___ > Devel mailing list > Devel@lists.laptop.org > http://lists.laptop.org/listinfo/devel > ___ Devel mailing list Devel@lists.laptop.org http://lists.laptop.org/listinfo/devel
startup sound
Hi, since firmware q2c27 the startup sound is enabled by default. Are there or will there be ways to turn it off and edit it? If, can someone point me to documentation about it. Thanks, Simon ___ Devel mailing list Devel@lists.laptop.org http://lists.laptop.org/listinfo/devel
Re: PATCH: suspend and poweroff (#3603 candidate)
Bernardo Innocenti wrote: > Jordan Crouse wrote: > >> Two comments inline - this looks good to me, but i'll need to apply it >> to see whats up with GX. Next step is to toss it into the playground, >> I guess to get some miles on it before Andres pulls it in. It turns out that the security system had just been enabled in the latest builds and due to magical hardlink-fu, my kernel in /boot/vmlinuz was never being executed all this time! I realized it late today, when my debug printk()'s wouldn't ever output anything, no matter what I did. The regressions I observed on B2's and B4's were probably already there. Now I'm really running my patched kernel and the DCON part works, but Sugar won't start any more, barfing X socket errors. Perhaps because running my unsigned kernel disabled the security system? Tomorrow I'll try to make sense of all this with the help of the other developers. -- \__/ |__| Bernardo Innocenti - http://www.codewiz.org/ \__\ One Laptop Per Child - http://www.laptop.org/ ___ Devel mailing list Devel@lists.laptop.org http://lists.laptop.org/listinfo/devel
