[OPENMP] Treat local variables in CUDA mode as thread local.

Description

[OPENMP] Treat local variables in CUDA mode as thread local.

In CUDA mode all local variables are actually thread
local|threadprivate, not private, and, thus, they cannot be shared
between threads|lanes.

Details

Committed
ABataevMar 2 2018, 9:17 AM
Parents
rL326589: AMDGPU/GlobalISel: InstrMapping for G_ZEXT
Branches
Unknown
Tags
Unknown