Re: XO-1.75 relative performance
And note that Jon's original advice was based on the absence of *EGL* support in clutter at the present time. The fact that you can run/not run gnome-shell on desktops with full *GL* support is not relevant. This thread has diverged. GTK3 is not gnome3 is not gnome-shell; EGL is not GL; Sugar is not Gnome. --scott -- ( http://cscott.net ) ___ Devel mailing list Devel@lists.laptop.org http://lists.laptop.org/listinfo/devel
Re: XO-1.75 relative performance
On Mon, Nov 7, 2011 at 1:11 AM, Jon Nettleton jon.nettle...@gmail.com wrote: nouveau has been very usable for quite some time. I was using it without issues back in F-12/13 timeframe without too many issues. What have you been using it for? Gnome-shell didn't exist back then. They have been incrementally adding features but it has taken time. I have never used nouveau because there has been no power control features, not something we I can do without. I am not trying to say something negative on the project, I just think it is a good barometer for people to realistically grasp how long it takes to mature modern graphics drivers without documentation. Actually it did! It was the first release that Fedora has it in there [1] , I packaged all the dependencies [2] as I packaged Moblin 2. It worked fine for the testing of Moblin although as you mention the power management was limited. My point still remains it was usable a lot earlier than the 3-4 years you mentioned. They've also had to reverse engineer it without any form of documentation. The gnome team are working for a minimal subset of implemented features for less capable cards so they run faster using SW rendering. See some of the links I provided previously. There should be a distinction between GNOME 3 and gnome-shell. Gnome-shell is the only part of GNOME 3 that requires 3D acceleration. Could our hardware run gnome-shell? Well that would take a bit of time to figure out. To my knowledge nobody has shown gnome-shell running with clutter utilizing the OpenGLES backend. Last I remember clutter didn't support texture from pixmap capabilities with their EGL backend, so that may still have to be implemented. This may have changed in the last couple of months by I have definitely not seen it demonstrated or talked about anywhere. That's not exactly entirely true. There's a number of other apps that are making using of clutter through clutter-gtk, clutter-gst or MX. totem is one of these for example. Also before long gnome is planning on deprecating non gnome-shell based UXs and concentrating on getting sofware rendering up to a reasonable speed. We can start testing this in F-17 as it'll be a feature [1]. Phoronix has more details on llvmpipe [2] and the gallium3D bits [3] Is this argument for or against GNOME 3? You point out a lot of libraries that require clutter, but none that are hard dependencies of GNOME. I understand a lot of projects are dependant on clutter, but none are hard dependencies of the GNOME project. No, its not an argument about gnome 3. Its to point out that gnome-shell isn't the only bit of gnome-shell that uses/requires 3D/OpenGL GPU functionality. totem is one of them that we use. The use of software rendering via llvm is great, but unfortunately that is targeted at modern multi-core processors that have cycles to spare. This does not target at the limited resources an XO has available. I don't disagree, my point is though that this is the way the gnome project is going and that its likely fallback mode will soon disappear. Oh and that is just system RAM it doesn't take into account the memory that is needed for the actual graphics engine. Aren't the production 1.75s moving to 1Gb of RAM due to pricing of the different units? Not that I have heard but we will see. Regardless I don't see any justification that would suggest we should target gnome-shell as a desktop. I'm staying we should target gnome-shell, my point is that if we want to keep using the gnome desktop in upcoming releases we might not have a choice. Read the previous links and you'll actually see the details of the point that I raised. I understand the push to proliferate GNOME, however as Linus and many other GNOME expatriates have emphasized it is not the right fit for everyone. I have been a gnome-shell contributor and propenent from early on, but I can' t suggest it is a good alternative for limited resource computers, when it continually fails me on my quad-core desktop with a top of the line video card, which I originally ran the nouveau drivers on but had to switch to the binary nvidia drivers because it ran the fan at 100% the entire time. I'm not and have never said its the right and only desktop. On the flip side I've not had many issues with gnome-shell in the F-15/16 timeframe and regularly will suspend/resume my laptop for weeks on end without issues now. Moblin/Meego ran quite happily on my original atom netbook which is of similar vintage and speed as the XO 1.5 without massive issues. I have no doubt issues with some nouveau cards is largely due to they are reverse engineered. The ATI and Intel GPUs which have published docs don't seem to have nearly the amount of issues on the NV based one. Peter [1] http://archives.fedoraproject.org/pub/archive/fedora/linux/releases/12/Everything/source/SRPMS/gnome-shell-2.28.0-3.fc12.src.rpm [2]
Re: XO-1.75 relative performance
It sounds like the XO-1.75 Sugar will not be operable on XO-1 (and possibly XO-1.5). I assume there is a clear commitment to continue support of Sugar for XO-1 and XO-1.5. Tony On 11/07/2011 03:26 AM, devel-requ...@lists.laptop.org wrote: Send Devel mailing list submissions to devel@lists.laptop.org To subscribe or unsubscribe via the World Wide Web, visit http://lists.laptop.org/listinfo/devel or, via email, send a message with subject or body 'help' to devel-requ...@lists.laptop.org You can reach the person managing the list at devel-ow...@lists.laptop.org When replying, please edit your Subject line so it is more specific than Re: Contents of Devel digest... Today's Topics: 1. Re: XO-1.75 relative performance (Peter Robinson) 2. Re: XO-1.75 relative performance (Jon Nettleton) 3. Re: Announcing the development of OLPC OS 11.3.1 (Simon Schampijer) 4. Re: Announcing the development of OLPC OS 11.3.1 (Peter Robinson) 5. Re: XO-1.75 relative performance (Peter Robinson) -- Message: 1 Date: Sun, 6 Nov 2011 22:19:36 + From: Peter Robinsonpbrobin...@gmail.com To: Jon Nettletonjon.nettle...@gmail.com Cc: Sridhar Dhanapalansrid...@laptop.org.au, Devel devel@lists.laptop.org Subject: Re: XO-1.75 relative performance Message-ID: CALeDE9PHfDegCJ=seyEecnw-MMrb=vzolhk9zizohwrfbgc...@mail.gmail.com Content-Type: text/plain; charset=ISO-8859-1 On Sun, Nov 6, 2011 at 4:51 PM, Jon Nettletonjon.nettle...@gmail.com wrote: Hi Jon, We are doing some forwards-planing with regards to the XO-1.75. Would you be able to tell us what kind of performance we can expect from the graphics driver that you are working on? Would it support 3D hardware acceleration? Well yes and no. ?The graphics hardware does support 3d acceleration, however currently that is only supported via a binary driver. ?We also don't have all the documentation nor man power to write a 3d driver. The nouveau team has had 3 to 4 people working full time on a driver for almost 4 years and their driver is just getting to a stable usage point for desktop compositing. nouveau has been very usable for quite some time. I was using it without issues back in F-12/13 timeframe without too many issues. For a general idea of performance our 3d graphics hardware will run Quake3 at native 1200x900 resolution with medium quality graphics at about 30fps on average. We are considering working to get GNOME 3 running, but for that to work well we'll need some good graphics capabilities. There should be a distinction between GNOME 3 and gnome-shell. Gnome-shell is the only part of GNOME 3 that requires 3D acceleration. ?Could our hardware run gnome-shell? ?Well that would take a bit of time to figure out. ?To my knowledge nobody has shown gnome-shell running with clutter utilizing the OpenGLES backend. ?Last I remember clutter didn't support texture from pixmap capabilities with their EGL backend, so that may still have to be implemented. ?This may have changed in the last couple of months by I have definitely not seen it demonstrated or talked about anywhere. That's not exactly entirely true. There's a number of other apps that are making using of clutter through clutter-gtk, clutter-gst or MX. totem is one of these for example. Also before long gnome is planning on deprecating non gnome-shell based UXs and concentrating on getting sofware rendering up to a reasonable speed. We can start testing this in F-17 as it'll be a feature [1]. Phoronix has more details on llvmpipe [2] and the gallium3D bits [3] The bigger concern I have with targeting a compositing window manager is the amount of RAM that it needs. ?Every window also has a duplicated texture in memory that is used to create the composited display. ?Generally gnome-shell will use 100+MB's of RAM just to display the desktop, and there is no way to tweak around this by using 16-bit colors as everything is an ARGB texture. ?On a machine with 1GB of RAM this isn't so bad, but that is a hefty chunk of memory for a machine with 512MB's of memory. ?Oh and that is just system RAM it doesn't take into account the memory that is needed for the actual graphics engine. Aren't the production 1.75s moving to 1Gb of RAM due to pricing of the different units? To sum things up. ?Yes the hardware should have the capabilities to run gnome-shell, again I say should as it is very untested. ?I would not recommend targetting it's use in any future plans unless you have GNOME and Xorg hackers lined up to spend a good chunk of time working on it. Peter [1] https://fedoraproject.org/wiki/Features/Gnome_shell_software_rendering [2] http://www.phoronix.com/scan.php?page=news_itempx=MTAxMTI [3] http://www.phoronix.com/scan.php?page=news_itempx=MTAwNTg -- Message: 2 Date: Sun, 6 Nov 2011 17:11:50 -0800 From: Jon Nettletonjon.nettle
Re: XO-1.75 relative performance
On Mon, Nov 7, 2011 at 9:06 AM, Tony Anderson tony_ander...@usa.net wrote: It sounds like the XO-1.75 Sugar will not be operable on XO-1 (and possibly XO-1.5). I assume there is a clear commitment to continue support of Sugar for XO-1 and XO-1.5. No issues with Sugar. The discussion here is about the conventional desktop. We currently ship Gnome, which is going very high-end in its hw requirements. The deep question at play is: can we wrangle Gnome 3 into being usable across our hw platforms? If not, will we switch desktop platform? If we switch desktop platform, do we do that for all platforms, or only the oldest ones? Are you personally prepared for the impending flamewar over the cute bikeshed about the choice of desktop platform? Stock up on popcorn! cheers, m -- martin.langh...@gmail.com mar...@laptop.org -- Software Architect - OLPC - ask interesting questions - don't get distracted with shiny stuff - working code first - http://wiki.laptop.org/go/User:Martinlanghoff ___ Devel mailing list Devel@lists.laptop.org http://lists.laptop.org/listinfo/devel
Re: XO-1.75 relative performance
Hi, I was referring, of course, to the need for a 1GB memory to support the 3D drivers which appear to be required by the future Fedora releases. That sound scary! Tony On 11/07/2011 09:10 AM, Walter Bender wrote: On Mon, Nov 7, 2011 at 9:06 AM, Tony Andersontony_ander...@usa.net wrote: It sounds like the XO-1.75 Sugar will not be operable on XO-1 (and possibly XO-1.5). I assume there is a clear commitment to continue support of Sugar for XO-1 and XO-1.5. Not sure why you say this. In any case, we (Sugar Labs) plan to continue support for XO-1 and XO-1.5 although we hope that over time that support is in the form of GTK-3-based systems. All my tests so far seem to suggest that things will run OK on the old hardware. -walter Tony On 11/07/2011 03:26 AM, devel-requ...@lists.laptop.org wrote: Send Devel mailing list submissions to devel@lists.laptop.org To subscribe or unsubscribe via the World Wide Web, visit http://lists.laptop.org/listinfo/devel or, via email, send a message with subject or body 'help' to devel-requ...@lists.laptop.org You can reach the person managing the list at devel-ow...@lists.laptop.org When replying, please edit your Subject line so it is more specific than Re: Contents of Devel digest... Today's Topics: 1. Re: XO-1.75 relative performance (Peter Robinson) 2. Re: XO-1.75 relative performance (Jon Nettleton) 3. Re: Announcing the development of OLPC OS 11.3.1 (Simon Schampijer) 4. Re: Announcing the development of OLPC OS 11.3.1 (Peter Robinson) 5. Re: XO-1.75 relative performance (Peter Robinson) -- Message: 1 Date: Sun, 6 Nov 2011 22:19:36 + From: Peter Robinsonpbrobin...@gmail.com To: Jon Nettletonjon.nettle...@gmail.com Cc: Sridhar Dhanapalansrid...@laptop.org.au, Devel devel@lists.laptop.org Subject: Re: XO-1.75 relative performance Message-ID: CALeDE9PHfDegCJ=seyEecnw-MMrb=vzolhk9zizohwrfbgc...@mail.gmail.com Content-Type: text/plain; charset=ISO-8859-1 On Sun, Nov 6, 2011 at 4:51 PM, Jon Nettletonjon.nettle...@gmail.com wrote: Hi Jon, We are doing some forwards-planing with regards to the XO-1.75. Would you be able to tell us what kind of performance we can expect from the graphics driver that you are working on? Would it support 3D hardware acceleration? Well yes and no. ?The graphics hardware does support 3d acceleration, however currently that is only supported via a binary driver. ?We also don't have all the documentation nor man power to write a 3d driver. The nouveau team has had 3 to 4 people working full time on a driver for almost 4 years and their driver is just getting to a stable usage point for desktop compositing. nouveau has been very usable for quite some time. I was using it without issues back in F-12/13 timeframe without too many issues. For a general idea of performance our 3d graphics hardware will run Quake3 at native 1200x900 resolution with medium quality graphics at about 30fps on average. We are considering working to get GNOME 3 running, but for that to work well we'll need some good graphics capabilities. There should be a distinction between GNOME 3 and gnome-shell. Gnome-shell is the only part of GNOME 3 that requires 3D acceleration. ?Could our hardware run gnome-shell? ?Well that would take a bit of time to figure out. ?To my knowledge nobody has shown gnome-shell running with clutter utilizing the OpenGLES backend. ?Last I remember clutter didn't support texture from pixmap capabilities with their EGL backend, so that may still have to be implemented. ?This may have changed in the last couple of months by I have definitely not seen it demonstrated or talked about anywhere. That's not exactly entirely true. There's a number of other apps that are making using of clutter through clutter-gtk, clutter-gst or MX. totem is one of these for example. Also before long gnome is planning on deprecating non gnome-shell based UXs and concentrating on getting sofware rendering up to a reasonable speed. We can start testing this in F-17 as it'll be a feature [1]. Phoronix has more details on llvmpipe [2] and the gallium3D bits [3] The bigger concern I have with targeting a compositing window manager is the amount of RAM that it needs. ?Every window also has a duplicated texture in memory that is used to create the composited display. ?Generally gnome-shell will use 100+MB's of RAM just to display the desktop, and there is no way to tweak around this by using 16-bit colors as everything is an ARGB texture. ?On a machine with 1GB of RAM this isn't so bad, but that is a hefty chunk of memory for a machine with 512MB's of memory. ?Oh and that is just system RAM it doesn't take into account the memory that is needed for the actual graphics engine. Aren't the production 1.75s moving to 1Gb of RAM due to pricing of the different units? To sum things up. ?Yes the hardware
Re: XO-1.75 relative performance
On Mon, Nov 7, 2011 at 6:36 AM, Tony Anderson tony_ander...@usa.net wrote: Hi, I was referring, of course, to the need for a 1GB memory to support the 3D drivers which appear to be required by the future Fedora releases. That sound scary! This configuration would largely be recommended for supporting GNOME 3 on Fedora. It will be possible to look at alternative desktops (XFCE, LXDE) that don't have quite the high end requirements. -Jon ___ Devel mailing list Devel@lists.laptop.org http://lists.laptop.org/listinfo/devel
Re: XO-1.75 relative performance
On Mon, Nov 7, 2011 at 9:57 AM, Jon Nettleton jon.nettle...@gmail.comwrote: On Mon, Nov 7, 2011 at 6:36 AM, Tony Anderson tony_ander...@usa.net wrote: Hi, I was referring, of course, to the need for a 1GB memory to support the 3D drivers which appear to be required by the future Fedora releases. That sound scary! On the 1gb XO 1.5, I have experimented in loading up many applications concurrently, and have never seen any usage of a linux-swap partition that is installed and mounted on the SD card. On the other hand, on the 256Mb XO-1, that swap partition gets used regularly when I have multiple applications open. I am hoping that if the 1.75 goes back to 512Mb, that this won't mean that one will need a swap partition again for multi-app performance. Just my 1.9 cents worth. This configuration would largely be recommended for supporting GNOME 3 on Fedora. It will be possible to look at alternative desktops (XFCE, LXDE) that don't have quite the high end requirements. -Jon ___ 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: XO-1.75 relative performance
Hi Jon, We are doing some forwards-planing with regards to the XO-1.75. Would you be able to tell us what kind of performance we can expect from the graphics driver that you are working on? Would it support 3D hardware acceleration? Well yes and no. The graphics hardware does support 3d acceleration, however currently that is only supported via a binary driver. We also don't have all the documentation nor man power to write a 3d driver. The nouveau team has had 3 to 4 people working full time on a driver for almost 4 years and their driver is just getting to a stable usage point for desktop compositing. For a general idea of performance our 3d graphics hardware will run Quake3 at native 1200x900 resolution with medium quality graphics at about 30fps on average. We are considering working to get GNOME 3 running, but for that to work well we'll need some good graphics capabilities. There should be a distinction between GNOME 3 and gnome-shell. Gnome-shell is the only part of GNOME 3 that requires 3D acceleration. Could our hardware run gnome-shell? Well that would take a bit of time to figure out. To my knowledge nobody has shown gnome-shell running with clutter utilizing the OpenGLES backend. Last I remember clutter didn't support texture from pixmap capabilities with their EGL backend, so that may still have to be implemented. This may have changed in the last couple of months by I have definitely not seen it demonstrated or talked about anywhere. The bigger concern I have with targeting a compositing window manager is the amount of RAM that it needs. Every window also has a duplicated texture in memory that is used to create the composited display. Generally gnome-shell will use 100+MB's of RAM just to display the desktop, and there is no way to tweak around this by using 16-bit colors as everything is an ARGB texture. On a machine with 1GB of RAM this isn't so bad, but that is a hefty chunk of memory for a machine with 512MB's of memory. Oh and that is just system RAM it doesn't take into account the memory that is needed for the actual graphics engine. To sum things up. Yes the hardware should have the capabilities to run gnome-shell, again I say should as it is very untested. I would not recommend targetting it's use in any future plans unless you have GNOME and Xorg hackers lined up to spend a good chunk of time working on it. -Jon ___ Devel mailing list Devel@lists.laptop.org http://lists.laptop.org/listinfo/devel
Re: XO-1.75 relative performance
On Sun, Nov 6, 2011 at 4:51 PM, Jon Nettleton jon.nettle...@gmail.com wrote: Hi Jon, We are doing some forwards-planing with regards to the XO-1.75. Would you be able to tell us what kind of performance we can expect from the graphics driver that you are working on? Would it support 3D hardware acceleration? Well yes and no. The graphics hardware does support 3d acceleration, however currently that is only supported via a binary driver. We also don't have all the documentation nor man power to write a 3d driver. The nouveau team has had 3 to 4 people working full time on a driver for almost 4 years and their driver is just getting to a stable usage point for desktop compositing. nouveau has been very usable for quite some time. I was using it without issues back in F-12/13 timeframe without too many issues. For a general idea of performance our 3d graphics hardware will run Quake3 at native 1200x900 resolution with medium quality graphics at about 30fps on average. We are considering working to get GNOME 3 running, but for that to work well we'll need some good graphics capabilities. There should be a distinction between GNOME 3 and gnome-shell. Gnome-shell is the only part of GNOME 3 that requires 3D acceleration. Could our hardware run gnome-shell? Well that would take a bit of time to figure out. To my knowledge nobody has shown gnome-shell running with clutter utilizing the OpenGLES backend. Last I remember clutter didn't support texture from pixmap capabilities with their EGL backend, so that may still have to be implemented. This may have changed in the last couple of months by I have definitely not seen it demonstrated or talked about anywhere. That's not exactly entirely true. There's a number of other apps that are making using of clutter through clutter-gtk, clutter-gst or MX. totem is one of these for example. Also before long gnome is planning on deprecating non gnome-shell based UXs and concentrating on getting sofware rendering up to a reasonable speed. We can start testing this in F-17 as it'll be a feature [1]. Phoronix has more details on llvmpipe [2] and the gallium3D bits [3] The bigger concern I have with targeting a compositing window manager is the amount of RAM that it needs. Every window also has a duplicated texture in memory that is used to create the composited display. Generally gnome-shell will use 100+MB's of RAM just to display the desktop, and there is no way to tweak around this by using 16-bit colors as everything is an ARGB texture. On a machine with 1GB of RAM this isn't so bad, but that is a hefty chunk of memory for a machine with 512MB's of memory. Oh and that is just system RAM it doesn't take into account the memory that is needed for the actual graphics engine. Aren't the production 1.75s moving to 1Gb of RAM due to pricing of the different units? To sum things up. Yes the hardware should have the capabilities to run gnome-shell, again I say should as it is very untested. I would not recommend targetting it's use in any future plans unless you have GNOME and Xorg hackers lined up to spend a good chunk of time working on it. Peter [1] https://fedoraproject.org/wiki/Features/Gnome_shell_software_rendering [2] http://www.phoronix.com/scan.php?page=news_itempx=MTAxMTI [3] http://www.phoronix.com/scan.php?page=news_itempx=MTAwNTg ___ Devel mailing list Devel@lists.laptop.org http://lists.laptop.org/listinfo/devel
Re: XO-1.75 relative performance
nouveau has been very usable for quite some time. I was using it without issues back in F-12/13 timeframe without too many issues. What have you been using it for? Gnome-shell didn't exist back then. They have been incrementally adding features but it has taken time. I have never used nouveau because there has been no power control features, not something we I can do without. I am not trying to say something negative on the project, I just think it is a good barometer for people to realistically grasp how long it takes to mature modern graphics drivers without documentation. There should be a distinction between GNOME 3 and gnome-shell. Gnome-shell is the only part of GNOME 3 that requires 3D acceleration. Could our hardware run gnome-shell? Well that would take a bit of time to figure out. To my knowledge nobody has shown gnome-shell running with clutter utilizing the OpenGLES backend. Last I remember clutter didn't support texture from pixmap capabilities with their EGL backend, so that may still have to be implemented. This may have changed in the last couple of months by I have definitely not seen it demonstrated or talked about anywhere. That's not exactly entirely true. There's a number of other apps that are making using of clutter through clutter-gtk, clutter-gst or MX. totem is one of these for example. Also before long gnome is planning on deprecating non gnome-shell based UXs and concentrating on getting sofware rendering up to a reasonable speed. We can start testing this in F-17 as it'll be a feature [1]. Phoronix has more details on llvmpipe [2] and the gallium3D bits [3] Is this argument for or against GNOME 3? You point out a lot of libraries that require clutter, but none that are hard dependencies of GNOME. I understand a lot of projects are dependant on clutter, but none are hard dependencies of the GNOME project. The use of software rendering via llvm is great, but unfortunately that is targeted at modern multi-core processors that have cycles to spare. This does not target at the limited resources an XO has available. Oh and that is just system RAM it doesn't take into account the memory that is needed for the actual graphics engine. Aren't the production 1.75s moving to 1Gb of RAM due to pricing of the different units? Not that I have heard but we will see. Regardless I don't see any justification that would suggest we should target gnome-shell as a desktop. I understand the push to proliferate GNOME, however as Linus and many other GNOME expatriates have emphasized it is not the right fit for everyone. I have been a gnome-shell contributor and propenent from early on, but I can' t suggest it is a good alternative for limited resource computers, when it continually fails me on my quad-core desktop with a top of the line video card, which I originally ran the nouveau drivers on but had to switch to the binary nvidia drivers because it ran the fan at 100% the entire time. -Jon ___ Devel mailing list Devel@lists.laptop.org http://lists.laptop.org/listinfo/devel
Re: XO-1.75 relative performance
Excerpts from C. Scott Ananian's message of 2011-11-02 05:58:42 +0100: A pure-CPU benchmark (maybe something in Pippy?) would be a little more reliable. === Begin facspeed.py === #!/usr/bin/env python import time def factorial(n): result = 1 while n 1: result *= n n -= 1 return result n = 10 start_time = time.time() factorial(n) time_diff = time.time() - start_time print '%d! computed in %.3fs' % (n, time_diff) === End facspeed.py === System SoC/CPU OS + arch time XO-1.75 Armada 610 @ 0.8GHz Debian armel199.108s XO-1.5 VIA C7-M @ 1GHz Debian i386 199.285s OpenRD 88F6281 @ 1.2GHzDebian armel181.277s Desktop PC Athlon BE-2300 @ 1.9GHz Debian amd64 34.180s I must admit I'm surprised by the result. sup (my MUA of choice) feels much slower on XO-1.75 than on XO-1.5 - and that's even though dstat reports higher SD card write throughput (with a different card). Maybe I should do some side-by-side comparisons. Sascha -- http://sascha.silbe.org/ http://www.infra-silbe.de/ signature.asc Description: PGP signature ___ Devel mailing list Devel@lists.laptop.org http://lists.laptop.org/listinfo/devel
XO-1.75 relative performance
I am trying to get some idea of the performance of the XO-1.75 relative to other devices on the market. For instance, how would it compare against an iPad 1/2 and iPhone 4/4S? My guess is that the Armada 610 SoC that we use would come out somewhere in between the A4 chip used in the original iPad and iPhone 4, and the A5 chip used in the iPad 2 and iPhone 4S. Do we have any more accurate figures? How does the state of our software (quality of drivers, etc.) affect this? There's a cool demo online showing the graphics capabilities of the Armada 610[0]. Is this achievable on the XO-1.75? Thanks, Sridhar [0] http://www.youtube.com/watch?v=1s17KwfzTFY ___ Devel mailing list Devel@lists.laptop.org http://lists.laptop.org/listinfo/devel
Re: [OLPC-AU] XO-1.75 relative performance
I'm not aware of any comprehensive performance assessments. Have you got an XO-1.75 yet? Performance is a design goal of OLPC, but it isn't first in the list. The full list is: 1. Safe -- no children should be harmed 2. Stylish and Usable -- something children want to own 3. Lowest Power -- low power means longer run-time 4. Lowest Cost -- a lower cost means more children can have one 5. Robust and Maintainable -- children drop things 6. Performance (speed) If we find we are sacrificing, say, Lowest Power for Performance reasons, we would be obliged to think again. -- James Cameron http://quozl.linux.org.au/ ___ Devel mailing list Devel@lists.laptop.org http://lists.laptop.org/listinfo/devel
Re: XO-1.75 relative performance
For what its worth, the XO-1.75 is currently about half the speed of the XO1.5 Measured with Turtle Art repeat 5000 fwd 100 back 100 print time but as said, its early days for the 1.75 with optimization to come Tony I am trying to get some idea of the performance of the XO-1.75 relative to other devices on the market. For instance, how would it compare against an iPad 1/2 and iPhone 4/4S? My guess is that the Armada 610 SoC that we use would come out somewhere in between the A4 chip used in the original iPad and iPhone 4, and the A5 chip used in the iPad 2 and iPhone 4S. Do we have any more accurate figures? How does the state of our software (quality of drivers, etc.) affect this? There's a cool demo online showing the graphics capabilities of the Armada 610[0]. Is this achievable on the XO-1.75? Thanks, Sridhar [0] http://www.youtube.com/watch?v=1s17KwfzTFY ___ Devel mailing list Devel@lists.laptop.org http://lists.laptop.org/listinfo/devel _ This mail has been virus scanned by Australia On Line see http://www.australiaonline.net.au/mailscanning ___ Devel mailing list Devel@lists.laptop.org http://lists.laptop.org/listinfo/devel
Re: XO-1.75 relative performance
On Wed, Nov 2, 2011 at 12:49 AM, fors...@ozonline.com.au wrote: For what its worth, the XO-1.75 is currently about half the speed of the XO1.5 Measured with Turtle Art repeat 5000 fwd 100 back 100 print time but as said, its early days for the 1.75 with optimization to come Yeah, this is almost certainly due to the terrible graphics driver performance which jon nettleton is working to fix. A pure-CPU benchmark (maybe something in Pippy?) would be a little more reliable. But anything involving floating point will suck, because we're not using the hardware floating point support yet. So much software to tune... --scott -- ( http://cscott.net ) ___ Devel mailing list Devel@lists.laptop.org http://lists.laptop.org/listinfo/devel
Re: [OLPC-AU] XO-1.75 relative performance
On 11/01/2011 08:54 PM, C. Scott Ananian wrote: the online benchmarks will probably be Android-based, and won't tell you anything about battery life and power consumption, where OLPC has put its focus and made great improvements.) I suppose Its probably time to start throwing out some worst case battery life numbers. We have built enough revs of the 1.75 now that the works case numbers aren't going to change. My battery logs show that the minimum useful Wh we get out of our battery is 18Wh. Fully loaded I've yet to see the XO-1.75 draw more than 5W [1]. So 18Wh/5W is 3.6h. I feel safe in saying that regardless of what you do on the 1.75 you are going to get 3.5 hours of battery life. Period. Thats a lot better than the worst case values of 1.5 which was difficult to pin down. Since suspend/resume is still undergoing heavy development I don't have any good estimates yet for user based workloads but early indicators look promising. In the coming weeks I'll get some good numbers. An interesting data point is that the 1.75 is the first laptop of the XO series that has ran 100% from a solar panel for an extended period. During my solar testing I often swap in different batteries. The 1.75 can consistently survive battery removal under moderate solar conditions when connected to the OLPC 10W solar panel. [1] Excluding connecting an external USB device drawing full power which would be an extra 5W. -- Richard A. Smith rich...@laptop.org One Laptop per Child ___ Devel mailing list Devel@lists.laptop.org http://lists.laptop.org/listinfo/devel