Use hyperbarrier by default on all architectures

All architectures except x86_64 used the linear barrier implementation
by default which doesn't give good performance for a larger number
of threads.

Improvements for PARALLEL overhead (EPCC) with this patch on a Power8
system (2 sockets x 10 cores x 8 threads, OMP_PLACES=cores)

 20 threads:  4.55us -> 3.49us
 40 threads:  8.84us -> 4.06us
 80 threads: 19.18us -> 4.74us
160 threads: 54.22us -> 6.73us

Differential Revision: https://reviews.llvm.org/D40358

llvm-svn: 320152

1 files changed, 6 insertions, 15 deletions

diff --git a/openmp/runtime/src/kmp_global.cpp b/openmp/runtime/src/kmp_global.cpp
index 81ec7e74225..ab14ddb1889 100644
--- a/openmp/runtime/src/kmp_global.cpp
+++ b/openmp/runtime/src/kmp_global.cpp
@@ -76,25 +76,16 @@ size_t __kmp_malloc_pool_incr = KMP_DEFAULT_MALLOC_POOL_INCR;
 
 // Barrier method defaults, settings, and strings.
 // branch factor = 2^branch_bits (only relevant for tree & hyper barrier types)
-#if KMP_ARCH_X86_64
 kmp_uint32 __kmp_barrier_gather_bb_dflt = 2;
 /* branch_factor = 4 */ /* hyper2: C78980 */
 kmp_uint32 __kmp_barrier_release_bb_dflt = 2;
 /* branch_factor = 4 */ /* hyper2: C78980 */
-#else
-kmp_uint32 __kmp_barrier_gather_bb_dflt = 2;
-/* branch_factor = 4 */ /* communication in core for MIC */
-kmp_uint32 __kmp_barrier_release_bb_dflt = 2;
-/* branch_factor = 4 */ /* communication in core for MIC */
-#endif // KMP_ARCH_X86_64
-#if KMP_ARCH_X86_64
-kmp_bar_pat_e __kmp_barrier_gather_pat_dflt = bp_hyper_bar; /* hyper2: C78980 */
-kmp_bar_pat_e __kmp_barrier_release_pat_dflt =
-    bp_hyper_bar; /* hyper2: C78980 */
-#else
-kmp_bar_pat_e __kmp_barrier_gather_pat_dflt = bp_linear_bar;
-kmp_bar_pat_e __kmp_barrier_release_pat_dflt = bp_linear_bar;
-#endif
+
+kmp_bar_pat_e __kmp_barrier_gather_pat_dflt = bp_hyper_bar;
+/* hyper2: C78980 */
+kmp_bar_pat_e __kmp_barrier_release_pat_dflt = bp_hyper_bar;
+/* hyper2: C78980 */
+
 kmp_uint32 __kmp_barrier_gather_branch_bits[bs_last_barrier] = {0};
 kmp_uint32 __kmp_barrier_release_branch_bits[bs_last_barrier] = {0};
 kmp_bar_pat_e __kmp_barrier_gather_pattern[bs_last_barrier] = {bp_linear_bar};