diff --git a/openmp/runtime/cmake/config-ix.cmake b/openmp/runtime/cmake/config-ix.cmake
--- a/openmp/runtime/cmake/config-ix.cmake
+++ b/openmp/runtime/cmake/config-ix.cmake
@@ -109,6 +109,23 @@
   set(CMAKE_REQUIRED_LIBRARIES)
 endif()
 
+# Check for aligned memory allocator function
+check_include_file(xmmintrin.h LIBOMP_HAVE_XMMINTRIN_H)
+set(OLD_CMAKE_REQUIRED_FLAGS ${CMAKE_REQUIRED_FLAGS})
+if (LIBOMP_HAVE_XMMINTRIN_H)
+  set(CMAKE_REQUIRED_FLAGS "${CMAKE_REQUIRED_FLAGS} -DLIBOMP_HAVE_XMMINTRIN_H")
+endif()
+set(source_code "// check for _mm_malloc
+    #ifdef LIBOMP_HAVE_XMMINTRIN_H
+    #include <xmmintrin.h>
+    #endif
+    int main() { void *ptr = _mm_malloc(sizeof(int) * 1000, 64); _mm_free(ptr); return 0; }")
+check_cxx_source_compiles("${source_code}" LIBOMP_HAVE__MM_MALLOC)
+set(CMAKE_REQUIRED_FLAGS ${OLD_CMAKE_REQUIRED_FLAGS})
+check_symbol_exists(aligned_alloc "stdlib.h" LIBOMP_HAVE_ALIGNED_ALLOC)
+check_symbol_exists(posix_memalign "stdlib.h" LIBOMP_HAVE_POSIX_MEMALIGN)
+check_symbol_exists(_aligned_malloc "malloc.h" LIBOMP_HAVE__ALIGNED_MALLOC)
+
 # Check linker flags
 if(WIN32)
   libomp_check_linker_flag(/SAFESEH LIBOMP_HAVE_SAFESEH_FLAG)
diff --git a/openmp/runtime/src/kmp_barrier.h b/openmp/runtime/src/kmp_barrier.h
--- a/openmp/runtime/src/kmp_barrier.h
+++ b/openmp/runtime/src/kmp_barrier.h
@@ -15,6 +15,34 @@
 
 #include "kmp.h"
 
+#if KMP_HAVE_XMMINTRIN_H && KMP_HAVE__MM_MALLOC
+#include <xmmintrin.h>
+#define KMP_ALIGNED_ALLOCATE(size, alignment) _mm_malloc(size, alignment)
+#define KMP_ALIGNED_FREE(ptr) _mm_free(ptr)
+#elif KMP_HAVE_ALIGNED_ALLOC
+#define KMP_ALIGNED_ALLOCATE(size, alignment) aligned_alloc(alignment, size)
+#define KMP_ALIGNED_FREE(ptr) free(ptr)
+#elif KMP_HAVE_POSIX_MEMALIGN
+#include "kmp_i18n.h"
+static inline void *KMP_ALIGNED_ALLOCATE(size_t size, size_t alignment) {
+  void *ptr;
+  int n = posix_memalign(&ptr, alignment, size);
+  if (n != 0) {
+    __kmp_fatal(KMP_MSG(FunctionError, "posix_memalign()"), KMP_ERR(errno),
+                __kmp_msg_null);
+  }
+  return ptr;
+}
+#define KMP_ALIGNED_FREE(ptr) free(ptr)
+#elif KMP_HAVE__ALIGNED_MALLOC
+#include <malloc.h>
+#define KMP_ALIGNED_ALLOCATE(size, alignment) _aligned_malloc(size, alignment)
+#define KMP_ALIGNED_FREE(ptr) _aligned_free(ptr)
+#else
+#define KMP_ALIGNED_ALLOCATE(size, alignment) KMP_INTERNAL_MALLOC(size)
+#define KMP_ALIGNED_FREE(ptr) KMP_INTERNAL_FREE(ptr)
+#endif
+
 // Use four cache lines: MLC tends to prefetch the next or previous cache line
 // creating a possible fake conflict between cores, so this is the only way to
 // guarantee that no such prefetch can happen.
@@ -79,7 +107,7 @@
 
   // Used instead of constructor to create aligned data
   static distributedBarrier *allocate(int nThreads) {
-    distributedBarrier *d = (distributedBarrier *)_mm_malloc(
+    distributedBarrier *d = (distributedBarrier *)KMP_ALIGNED_ALLOCATE(
         sizeof(distributedBarrier), 4 * CACHE_LINE);
     d->num_threads = 0;
     d->max_threads = 0;
@@ -96,7 +124,7 @@
     return d;
   }
 
-  static void deallocate(distributedBarrier *db) { _mm_free(db); }
+  static void deallocate(distributedBarrier *db) { KMP_ALIGNED_FREE(db); }
 
   void update_num_threads(size_t nthr) { init(nthr); }
 
diff --git a/openmp/runtime/src/kmp_config.h.cmake b/openmp/runtime/src/kmp_config.h.cmake
--- a/openmp/runtime/src/kmp_config.h.cmake
+++ b/openmp/runtime/src/kmp_config.h.cmake
@@ -88,6 +88,16 @@
 #define KMP_HAVE_ATTRIBUTE_RTM LIBOMP_HAVE_ATTRIBUTE_RTM
 #cmakedefine01 LIBOMP_ARCH_AARCH64_A64FX
 #define KMP_ARCH_AARCH64_A64FX LIBOMP_ARCH_AARCH64_A64FX
+#cmakedefine01 LIBOMP_HAVE_XMMINTRIN_H
+#define KMP_HAVE_XMMINTRIN_H LIBOMP_HAVE_XMMINTRIN_H
+#cmakedefine01 LIBOMP_HAVE__MM_MALLOC
+#define KMP_HAVE__MM_MALLOC LIBOMP_HAVE__MM_MALLOC
+#cmakedefine01 LIBOMP_HAVE_ALIGNED_ALLOC
+#define KMP_HAVE_ALIGNED_ALLOC LIBOMP_HAVE_ALIGNED_ALLOC
+#cmakedefine01 LIBOMP_HAVE_POSIX_MEMALIGN
+#define KMP_HAVE_POSIX_MEMALIGN LIBOMP_HAVE_POSIX_MEMALIGN
+#cmakedefine01 LIBOMP_HAVE__ALIGNED_MALLOC
+#define KMP_HAVE__ALIGNED_MALLOC LIBOMP_HAVE__ALIGNED_MALLOC
 
 // Configured cache line based on architecture
 #if KMP_ARCH_PPC64
diff --git a/openmp/runtime/src/kmp_os.h b/openmp/runtime/src/kmp_os.h
--- a/openmp/runtime/src/kmp_os.h
+++ b/openmp/runtime/src/kmp_os.h
@@ -1038,6 +1038,9 @@
     KMP_MFENCE_();                                                             \
   }
 #define KMP_SFENCE() KMP_SFENCE_()
+#else
+#define KMP_MFENCE() KMP_MB()
+#define KMP_SFENCE() KMP_MB()
 #endif
 
 #ifndef KMP_IMB