emscripten-fastcomp-clang/test/CodeGenCUDA, branch master emscripten clang https://git.amat.us/emscripten-fastcomp-clang/atom/test/CodeGenCUDA?h=master 2013-03-30T14:38:24Z Use kernel metadata to differentiate between kernel and device 2013-03-30T14:38:24Z Justin Holewinski jholewinski@nvidia.com 2013-03-30T14:38:24Z urn:sha1:dca8f336e6da2b50eb965535d81d603e39294f9c functions for the NVPTX target. git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@178418 91177308-0d34-0410-b5e6-96231b3b80d8 CUDA: give static storage class to __shared__ and __constant__ 2012-08-28T20:37:50Z Peter Collingbourne peter@pcc.me.uk 2012-08-28T20:37:50Z urn:sha1:c0c00664887f5d99780c9b3e33e2f204712823b7 variables without a storage class within a function, to implement CUDA B.2.5: "__shared__ and __constant__ variables have implied static storage [duration]." git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@162788 91177308-0d34-0410-b5e6-96231b3b80d8 CUDA: give correct address space to globals declared in functions 2012-08-28T20:37:10Z Peter Collingbourne peter@pcc.me.uk 2012-08-28T20:37:10Z urn:sha1:1aba7783ad8fe326f10f5aa494721db23bdd593e git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@162787 91177308-0d34-0410-b5e6-96231b3b80d8 Replace PTX back-end with NVPTX back-end in all places where Clang cares 2012-05-24T17:43:12Z Justin Holewinski jholewinski@nvidia.com 2012-05-24T17:43:12Z urn:sha1:2c585b991596859f39860b6094247ba027a03530 NV_CONTRIB git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@157403 91177308-0d34-0410-b5e6-96231b3b80d8 CUDA: add CodeGen support for global variable address spaces. 2012-05-20T21:08:35Z Peter Collingbourne peter@pcc.me.uk 2012-05-20T21:08:35Z urn:sha1:4dc34ebf2a0716bf77ba110dab6777a3fc4397dd Because in CUDA types do not have associated address spaces, globals are declared in their "native" address space, and accessed by bitcasting the pointer to address space 0. This relies on address space 0 being a unified address space. git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@157167 91177308-0d34-0410-b5e6-96231b3b80d8 CUDA: IR generation support for device stubs 2011-10-06T18:51:56Z Peter Collingbourne peter@pcc.me.uk 2011-10-06T18:51:56Z urn:sha1:a4ae2294b6ebfb2554aacb6a6a0682fb5ed1f276 git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@141304 91177308-0d34-0410-b5e6-96231b3b80d8 CUDA: add -fcuda-is-device flag 2011-10-06T18:29:46Z Peter Collingbourne peter@pcc.me.uk 2011-10-06T18:29:46Z urn:sha1:d51e43af0b3a6897b971f316c4de2035ec82d1f2 This frontend-only flag is used by the IR generator to determine whether to filter CUDA declarations for the host or for the device. git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@141301 91177308-0d34-0410-b5e6-96231b3b80d8 CUDA: IR generation support for kernel call expressions 2011-10-06T18:29:37Z Peter Collingbourne peter@pcc.me.uk 2011-10-06T18:29:37Z urn:sha1:6c0aa5ff6e6253db0f993053599e2a52b5b93b2d git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@141300 91177308-0d34-0410-b5e6-96231b3b80d8 CUDA: set proper calling conventions for PTX 2011-10-06T16:49:54Z Peter Collingbourne peter@pcc.me.uk 2011-10-06T16:49:54Z urn:sha1:744d90bfe2a43847764a707b1bee7ef1e30ad5f2 git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@141296 91177308-0d34-0410-b5e6-96231b3b80d8