This will prevent LLVM optimization passes from creating illegal uses of the barrier() intrinsic (e.g. calling barrier() from a conditional that is not executed by all threads). llvm-svn: 193753
11 lines
242 B
Plaintext
11 lines
242 B
Plaintext
atomic/atomic.cl
|
|
math/nextafter.cl
|
|
workitem/get_num_groups.ll
|
|
workitem/get_group_id.ll
|
|
workitem/get_local_size.ll
|
|
workitem/get_local_id.ll
|
|
workitem/get_global_size.ll
|
|
synchronization/barrier.cl
|
|
synchronization/barrier_impl.ll
|
|
shared/vload.cl
|