similar to: RFC: atomic operations on SI+

On Fri, Mar 25, 2016 at 02:22:11PM -0400, Jan Vesely wrote: > Hi Tom, Matt, > > I'm working on a project that needs few coherent atomic operations (HSA > mode: load, store, compare-and-swap) for std::atomic_uint in HCC. > > the attached patch implements atomic compare and swap for SI+ > (untested). I tried to stay within what was available, but there are > few issues

Hi, I've prepared patches for both LLVM and Clang to change the datalayout for R600. This may seem like a bold move, but I think it is warranted. R600/SI is a strange architecture in that it uses 64bit pointers but does not support 64 bit arithmetic except for load/store operations that roughly map onto getelementptr. The current datalayout for r600 includes n32:64, which is odd

Hi Christian, Ryan just reported to me that llvm-3.4 is no longer building on OS X Leopard (https://trac.macports.org/ticket/41548). It seems the issue is with a commit that you made back in April (referenced below) which added this to SIISelLowering.cpp: // Adjust the writemask in the node std::vector<SDValue> Ops; Ops.push_back(DAG.getTargetConstant(NewDmask, MVT::i32)); for

Hi Tom, Matt, I'm running into strange issues with the cos test (piglit generated_tests/cl/builtin/math/builtin-float-cos-1.0.generated.c) I have been seeing random failures (incorrect results) for some time and tried to investigate. the weird part is that the failures are not 100% reproducible, sometimes the tests pass, or partly pass (it's usually float8 and float16 subtests that

This looks like you're using the wrong repository. The 'git llvm' command only works with the new repository layout. Please clone https://github.com/llvm/llvm-project/ instead. *From: *Ryan Taylor via llvm-dev <llvm-dev at lists.llvm.org> *Date: *Tue, May 14, 2019 at 2:18 PM *To: * <paul.robinson at sony.com> *Cc: *llvm-dev It's both "No such file or

Thanks Paul but I saw that on a previous email chain and tried it, it did not work for me. I also saw there are issues with svn tags on some files? Thanks, Ryan On Tue, May 14, 2019, 1:30 PM <paul.robinson at sony.com> wrote: > It has been a while since I've seen "No such file or directory" although I > do still occasionally see "Patch doesn't apply"

Can't you just use &Ops[0] ? On Tue, Nov 26, 2013 at 12:03 PM, Jeremy Huddleston Sequoia <jeremyhu at apple.com> wrote: > Hi Christian, > > Ryan just reported to me that llvm-3.4 is no longer building on OS X Leopard (https://trac.macports.org/ticket/41548). It seems the issue is with a commit that you made back in April (referenced below) which added this to

Tom, I think it might be productive to fork this thread to discuss making the requirements for upstreaming a new LLVM target more explicit and open. I'd also like to gauge interest in an idea I've discussed privately with a few community members, namely the concept of having a semi-official "incubation" system whereby proposed backends could get a trial run before becoming part

On Nov 26, 2013, at 1:41, Anton Korobeynikov <anton at korobeynikov.info> wrote: > Can't you just use &Ops[0] ? Is that safely portable? ie is it required that pre-C++11 std:vector be implemented such that the data is stored contiguously in a realloc'd array? While I'm not sure anyone would do this (so perhaps the point is moot), it seems that one could use