aboutsummaryrefslogtreecommitdiffhomepage
path: root/third_party/gpus/crosstool/CROSSTOOL_nvcc.tpl
Commit message (Collapse)AuthorAge
* Unifiy the cuda toolchain definition of gcc/nvcc and cuda-clang.Gravatar A. Unique TensorFlower2018-05-22
| | | | | | | | | | | | | | | | | gcc >= 7 will change how it treats -pie [1]; passing -pie after -shared on the command line is not possible any more; given that the legacy way to configure flags in the gcc/nvcc toolchain does not allow control over where the flags go or how to provide -pie only for linking of binaries, we can prevent this from breaking in the future by also using the new feature mechanism for gcc/nvcc. In addition to moving the gcc-specific workarounds in the toolchain to cuda_configure.bzl, document them, so we don't need to rediscover them in the future. [1] https://gcc.gnu.org/bugzilla/show_bug.cgi?id=77464 PiperOrigin-RevId: 197522719
* Change creation of symlinks (via skylark method) in cuda_configure.bzl.tpl ↵Gravatar A. Unique TensorFlower2017-04-28
| | | | | | for creation of genrules (via _tpl) that do the equivalent symlinks, but during build (not during Skylark execution). Change: 154535355
* Add cuda_clang build configuration that allows to use clang as a CUDA compiler.Gravatar A. Unique TensorFlower2017-03-30
Change: 151705528