the thresholds, ratios etc are all funny numbers that is a bit conspicuous. I understand the whole file is like this, so I guess we just have to do it that way Sun
On Fri, May 20, 2011 at 8:03 AM, David Coakley <dcoak...@gmail.com> wrote: > Could a gatekeeper please review the attached patch? > > Here is the proposed commit message: > > > Improve code alignment of basic blocks for x86 targets. > > Use the "maximum number of bytes that should be skipped" parameter > to the .p2align assembler directive to provide better performance > for generated code. If the branch-in frequency to the BB is higher, > then more padding bytes are allowed to align the BB, and vice-versa. > The exact values to use are determined empirically. > > > Thanks, > > -David Coakley / AMD Open Source Compiler Engineering > > ------------------------------------------------------------------------------ > What Every C/C++ and Fortran developer Should Know! > Read this article and learn how Intel has extended the reach of its > next-generation tools to help Windows* and Linux* C/C++ and Fortran > developers boost performance applications - including clusters. > http://p.sf.net/sfu/intel-dev2devmay > _______________________________________________ > Open64-devel mailing list > Open64-devel@lists.sourceforge.net > https://lists.sourceforge.net/lists/listinfo/open64-devel > > ------------------------------------------------------------------------------ What Every C/C++ and Fortran developer Should Know! Read this article and learn how Intel has extended the reach of its next-generation tools to help Windows* and Linux* C/C++ and Fortran developers boost performance applications - including clusters. http://p.sf.net/sfu/intel-dev2devmay _______________________________________________ Open64-devel mailing list Open64-devel@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/open64-devel
