bcm5719-llvm/libclc/generic/lib/async, branch meklort-10.0.1Project Ortega BCM5719 LLVMhttps://git.raptorcs.com/git/bcm5719-llvm/atom?h=meklort-10.0.12018-03-06T17:48:35+00:00Move cl_khr_fp64 exntension enablement to gentype include lists2018-03-06T17:48:35+00:00Jan Veselyjan.vesely@rutgers.edu2018-03-06T17:48:35+00:00urn:sha1:dbaf6d0f7ce8d4f590e0ec929726b3085ffc1799
This will make adding cl_khr_fp16 support easier
Reviewed-by: Aaron Watry <awatry@gmail.com>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 326816
Implement async_work_group_copy builtin v32014-10-03T19:49:39+00:00Tom Stellardthomas.stellard@amd.com2014-10-03T19:49:39+00:00urn:sha1:081e778d2224c6f281168c1336cf9503e65dccb7
This is a simple implementation which just copies data synchronously.
v2:
- Use size_t.
v3:
- Fix possible race condition by splitting the copy among multiple
work items.
llvm-svn: 219008
Implement async_work_group_strided_copy builtin v22014-10-03T19:49:37+00:00Tom Stellardthomas.stellard@amd.com2014-10-03T19:49:37+00:00urn:sha1:ed5bbfdb1b5d3b7d76352c37e187663c1b06b06f
This is a simple implementation which just copies data synchronously.
v2:
- Use size_t.
llvm-svn: 219007
Implement wait_group_events builtin v22014-10-03T19:49:34+00:00Tom Stellardthomas.stellard@amd.com2014-10-03T19:49:34+00:00urn:sha1:b5064f79efadaef7822be7427a30a6bd273a9d50
This is a simple default implemetation which just calls barrier().
v2:
- Only call barrier() once.
llvm-svn: 219006
Implement prefetch builtin2014-08-20T21:23:03+00:00Tom Stellardthomas.stellard@amd.com2014-08-20T21:23:03+00:00urn:sha1:2ad4243bf784527f3c6e3514d94411332bc1cfae
The default implementation is a no-op. Targets should override this
with their own implementations.
llvm-svn: 216127