tag:blogger.com,1999:blog-3971202189709462152.post5994810755839586463..comments2024-03-11T12:50:02.036+01:00Comments on PyPy Status Blog: A JIT Backend for ARM ProcessorsCarl Friedrich Bolz-Tereickhttp://www.blogger.com/profile/00518922641059511014noreply@blogger.comBlogger10125tag:blogger.com,1999:blog-3971202189709462152.post-17312180781125663682011-09-30T11:12:27.677+02:002011-09-30T11:12:27.677+02:00Sounds very cool, are there any updates?Sounds very cool, are there any updates?vakhttps://www.blogger.com/profile/13157594553222689990noreply@blogger.comtag:blogger.com,1999:blog-3971202189709462152.post-50527404978564443422011-06-08T21:41:42.438+02:002011-06-08T21:41:42.438+02:00@jamu: scratchbox 2 is currently the only option t...@jamu: scratchbox 2 is currently the only option to cross-translate pypy for ARM. You can find some documentation about the cross translation at https://bitbucket.org/pypy/pypy/src/arm-backend-2/pypy/doc/arm.rstDavid Schneiderhttps://www.blogger.com/profile/05365013582304921306noreply@blogger.comtag:blogger.com,1999:blog-3971202189709462152.post-91451696451506857722011-05-16T14:11:32.202+02:002011-05-16T14:11:32.202+02:00Hi,
Is there a way to cross compile on a host mach...Hi,<br />Is there a way to cross compile on a host machine (but not with scratch box) where I have tool chain and file system for the target?<br /><br />Any instructions for building with arm back-end?<br /><br />Cheersjamuhttps://www.blogger.com/profile/05321681453221610721noreply@blogger.comtag:blogger.com,1999:blog-3971202189709462152.post-39848414269806496962011-05-02T20:02:27.635+02:002011-05-02T20:02:27.635+02:00@Dan
Why are you so defensive? This benchmark is ...@Dan<br /><br />Why are you so defensive? This benchmark is clearly not about how fast Pyrolog is, but how the ARM JIT backend performs, using trivial Prolog microbenchmarks, with SWI to give a number to compare against.<br /><br />Pyrolog is a minimal Prolog implementation that is (at least so far) mostly an experiment to see how well PyPy's JIT technology can do on an non-imperative language. This paper contains more interesting benchmarks:<br /><br />http://portal.acm.org/citation.cfm?id=1836102Carl Friedrich Bolz-Tereickhttps://www.blogger.com/profile/00518922641059511014noreply@blogger.comtag:blogger.com,1999:blog-3971202189709462152.post-17925546860519123322011-04-30T17:40:00.166+02:002011-04-30T17:40:00.166+02:00Showing speedups over repetitive instructions (whi...Showing speedups over repetitive instructions (which caching & JIT are really good at) is irrelevant.<br /><br />What happens when people use real benchmarks, like constraint-based solvers and non-iterative stuff (maybe take a look at the other benchmarks) ...<br /><br />Prolog is a declative language, not a sysadmin scripting language.<br /><br />Also, the SWI implementation adds so many functionalities, it's like making a «Extract chars from an RDBMS vs Text files» benchmark.Dannoreply@blogger.comtag:blogger.com,1999:blog-3971202189709462152.post-7953902807377312752011-02-05T20:51:32.001+01:002011-02-05T20:51:32.001+01:00Martijn: you are describing the situation as well ...Martijn: you are describing the situation as well as we (at least I) know it so far: while PyPy has in many cases a lower non-JIT memory usage, the JIT adds some overhead. But it seems to be within ~200MB on "pypy translate.py", which is kind of the extreme example in hugeness. So already on today's high-end boards with 1GB of RAM, it should easily fit. Moreover it can be tweaked, e.g. it's probably better on these systems to increase the threshold at which JITting starts (which also reduces the number of JITted code paths). So I think that the possibility is real.Armin Rigohttps://www.blogger.com/profile/06300515270104686574noreply@blogger.comtag:blogger.com,1999:blog-3971202189709462152.post-63826045394503338422011-01-31T15:11:55.324+01:002011-01-31T15:11:55.324+01:00One would imagine conserving memory would be an im...One would imagine conserving memory would be an important factor on mobile devices. Even though mobile devices have a growing amount of memory available, it will still be less than desktops for the forseeable future. Memory pressure can create real slowdowns.<br /><br />A JIT normally takes more memory, but on the other hand PyPy offers features to reduce usage of memory. Could you share some of your thinking on this?Martijn Faassennoreply@blogger.comtag:blogger.com,1999:blog-3971202189709462152.post-57157383308226196232011-01-30T20:05:45.748+01:002011-01-30T20:05:45.748+01:00@mwhudson: thanks it would be great to be able to ...@mwhudson: thanks it would be great to be able to test on more hardware.<br /><br />For the float support we still need to investigate a bit, but if possible I would like to target hard floats.<br /><br />@dbrodie: currently we are targeting the arm state, so not at the moment.David Schneiderhttps://www.blogger.com/profile/05365013582304921306noreply@blogger.comtag:blogger.com,1999:blog-3971202189709462152.post-88690008274778062342011-01-30T12:47:17.055+01:002011-01-30T12:47:17.055+01:00I am curious if you had any use for ThumbEE (or Ja...I am curious if you had any use for ThumbEE (or Jazelle RCT) to speed up?dbrodiehttps://www.blogger.com/profile/15902030127951285361noreply@blogger.comtag:blogger.com,1999:blog-3971202189709462152.post-32470737726877635992011-01-30T11:01:42.902+01:002011-01-30T11:01:42.902+01:00Awesome stuff. I have a panda board and another x...Awesome stuff. I have a panda board and another xm that's usually not doing much if you want to borrow some cycles :-)<br /><br />When you support floats will you be aiming for hard float? It's the way of the future, I hear...Anonymousnoreply@blogger.com