forked from OSchip/llvm-project
ca2b951cbc
__global__ functions are a special case in CUDA. Even when the symbol would normally not be externally visible according to C++ rules, they still must be visible in CUDA GPU object so host-side stub can launch them. Differential Revision: http://reviews.llvm.org/D19748 llvm-svn: 268299 |
||
---|---|---|
.. | ||
Inputs | ||
address-spaces.cu | ||
alias.cu | ||
convergent.cu | ||
cuda-builtin-vars.cu | ||
device-stub.cu | ||
device-var-init.cu | ||
device-vtable.cu | ||
filter-decl.cu | ||
flush-denormals.cu | ||
function-overload.cu | ||
host-device-calls-host.cu | ||
kernel-call.cu | ||
launch-bounds.cu | ||
link-device-bitcode.cu | ||
llvm-used.cu | ||
printf-aggregate.cu | ||
printf.cu | ||
ptx-kernels.cu |