search for: schnetter

...tie breaking (towards even), round uses mathematical tie breaking (away from zero). The question here is: Is this optimization worthwhile, or would it surprise too many people? Depending on this, it should either be disallowed, or possibly implemented for other back-ends as well. -erik -- Erik Schnetter <schnetter at cct.lsu.edu> http://www.perimeterinstitute.ca/personal/eschnetter/ -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20130621/768d3be1/attachment.html>

On Fri, Jun 21, 2013 at 5:11 PM, Erik Schnetter <schnetter at cct.lsu.edu>wrote: > On Fri, Jun 21, 2013 at 7:54 AM, David Tweed <david.tweed at arm.com> wrote: > >> | LLVM does not currently have special lowering handling for round(), and >> I'll propose a patch to add that, but the larger question is this: sho...

----- Original Message ----- > > On Fri, Jun 21, 2013 at 5:11 PM, Erik Schnetter < > schnetter at cct.lsu.edu > wrote: > > > > > > > On Fri, Jun 21, 2013 at 7:54 AM, David Tweed < david.tweed at arm.com > > wrote: > > > > > > > | LLVM does not currently have special lowering handling for round(), > | and...

...6-64 should pass arguments in %xmm0, not %ymm0. Are there e.g. command line options, CPU attributes, or target triplets that would modify this? Or should this be filed as bug report? However, this may also be a bug in pocl as I haven't been able to reproduced this without pocl. -erik -- Erik Schnetter <schnetter at gmail.com> http://www.perimeterinstitute.ca/personal/eschnetter/ My email is as private as my paper mail. I therefore support encrypting and signing email messages. Get my PGP key from http://pgp.mit.edu/. -------------- next part -------------- A non-text attachment was scrub...

...uivalent of "void*" that can hold all kinds of pointers and address spaces. Casting forth and back must preserve the address space. If I read the standard correctly, the OpenCL compiler may also compile functions several times, once for each combination of address spaces. -erik -- Erik Schnetter <schnetter at gmail.com> http://www.perimeterinstitute.ca/personal/eschnetter/ My email is as private as my paper mail. I therefore support encrypting and signing email messages. Get my PGP key from http://pgp.mit.edu/.

...t; -- > > Thanks, > > > > Justin Holewinski > > > > _______________________________________________ > LLVM Developers mailing list > LLVMdev at cs.uiuc.edu http://llvm.cs.uiuc.edu > http://lists.cs.uiuc.edu/mailman/listinfo/llvmdev > > -- Erik Schnetter <schnetter at cct.lsu.edu> http://www.perimeterinstitute.ca/personal/eschnetter/ -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20130209/156ef16d/attachment.html>

On 08/07/2013 03:52 PM, Michele Scandale wrote: > > In the opencl specification is said that the four address spaces are > disjoint, so my conclusion of non aliasing with the others. In OpenCL 2.0, you can cast between the generic address space and global/local/private, so there's also that to consider.

...rticular hardware architectures where e.g. machine instructions are available. Support for x86_64 should be most complete (SSE2, AVX). Vecmathlib passes various correctness tests. I assume that many of its algorithms could stand improvement. I am still working on the documentation. -erik -- Erik Schnetter <schnetter at gmail.com> http://www.perimeterinstitute.ca/personal/eschnetter/ -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20130205/f88f8f86/attachment.html>

...mong others. Links ----- Home page: http://pocl.sourceforge.net/ This announcement: http://pocl.sourceforge.net/pocl-0.8.html Change log: http://pocl.sourceforge.net/downloads/CHANGES Download: http://pocl.sourceforge.net/downloads The pocl developers August 2013 -- Erik Schnetter <schnetter at gmail.com> http://www.perimeterinstitute.ca/personal/eschnetter/ My email is as private as my paper mail. I therefore support encrypting and signing email messages. Get my PGP key from http://pgp.mit.edu/.

On May 23, 2013, at 10:37 AM, Cameron McInally <cameron.mcinally at nyu.edu> wrote: > In all fairness, I do not believe that ivdep is an ICC-specific pragma. There are many compilers that support ivdep and lots of legacy (and modern) codes that benefit from it. Seems silly, to me at least, to reinvent the wheel. Hi Cameron, The history of the idvep pragma is fascinating. I did not

Hi Justin, gentlemen, I'm afraid I have to escalate this issue at this point. Since it was discussed for the first time last summer, it was sufficient for us for a while to have lowering of math calls into intrinsics disabled at DragonEgg level, and link them against CUDA math functions at LLVM IR level. Now I can say: this is not sufficient any longer, and we need NVPTX backend to deal with

...ences/?conf=llvmhpc3 Proceedings: The proceedings will be archived in both the ACM Digital Library and IEEE Xplore through SIGHPC. Organizer: Hal Finkel, Argonne National Laboratory, hfinkel at anl.gov Program Committee: Andrew Trick, Apple Cameron McInally, Cray Chandler Carruth, Google Erik Schnetter, Perimeter Institute for Theoretical Physics Frank Winter, Thomas Jefferson National Accelerator Facility Gary Funck, Intrepid Technology James Brodman, Intel Jeff Hammond, Intel Jim Cownie, Intel John Mellor-Crummey, Rice University Keno Fischer, Julia Computing, Inc. Michael Wong, Codeplay Nadav...

...nde, University of Oregon Tobias Grosser, INRIA Gary Funck, Intrepid Technology Ralf Karrenberg, Weta Digital Nadav Rotem, Apple Andrew Trick, Apple J Nelson Amaral, University of Alberta Michael Wong, IBM Frank Winter, Thomas Jefferson National Accelerator Facility ("Jefferson Lab") Erik Schnetter, Perimeter Institute for Theoretical Physics David Tweed, ARM Cameron McInally, Cray Keno Fischer, Harvard University Stefan Karpinski, MIT / Julia Michael McCool, Intel Torsten Hoefler, ETH Zürich -- Hal Finkel Assistant Computational Scientist Leadership Computing Facility Argonne National Labo...

...ences/?conf=llvmhpc2 Proceedings: The proceedings will be archived in both the ACM Digital Library and IEEE Xplore through SIGHPC. Organizer: Hal Finkel, Argonne National Laboratory, hfinkel at anl.gov Program Committee: Andrew Trick, Apple Cameron McInally, Cray Chandler Carruth, Google Erik Schnetter, Perimeter Institute for Theoretical Physics Frank Winter, Thomas Jefferson National Accelerator Facility Gary Funck, Intrepid Technology James Brodman, Intel Jeff Hammond, Intel John Mellor-Crummey, Rice University Keno Fischer, Harvard University Michael Wong, IBM Michelle Strout, Colorado State...

We already decide on a default. For these three targets is “whatever the user is running on.” For all the other targets it’s something the backend selects. I’m proposing we, as you say, remove the uncertainty and have the default always be the same from one run to the next even (especially) when those runs are on different machines. For X86, there’s two options, the “generic” target that backend

...mory buffers (code 22) Product: rsync Version: 3.0.2 Platform: Other OS/Version: AIX Status: NEW Severity: major Priority: P3 Component: core AssignedTo: wayned@samba.org ReportedBy: schnetter@cct.lsu.edu QAContact: rsync-qa@samba.org I am using rsync 3.0.2 (on both ends) to copy a source tree from Mac OS (Intel) to AIX (Power 5). My command is rsync --rsync-path=/work/default/eschnett/rsync-3.0.2/bin/rsync --rsh ssh --archive --hard-links --sparse --verbose --progress --par...

...s, Alexander -----Original Message----- From: Tobias Grosser [mailto:tobias at grosser.es] Sent: Tuesday, October 07, 2014 11:22 AM To: Hal Finkel; Andrew Trick Cc: doerfert at cs.uni-saarland.de; zinovy nis; Arnold Schwaighofer; llvmdev at cs.uiuc.edu Dev; Bataev, Alexey; Musman, Alexander; Erik Schnetter Subject: Re: llvm.loop metadata placement and critical edge splitting On 06/10/2014 23:56, Hal Finkel wrote: > ----- Original Message ----- >> From: "Andrew Trick" <atrick at apple.com> >> To: "llvmdev at cs.uiuc.edu Dev" <llvmdev at cs.uiuc.edu> >...