[OpenMP][VE] Limit the number of threads to create (#66729)

VE supports up to 64 threads per a VE process. So, we limit the number
of threads defined by KMP_MAX_NTH. We also modify the __kmp_sys_max_nth
initialization to use KMP_MAX_NTH as a limit.

Author: kaz7

openmp/runtime/src/kmp.h

@@ -1153,8 +1153,15 @@ extern void __kmp_init_target_task();
 #if defined(PTHREAD_THREADS_MAX) && PTHREAD_THREADS_MAX < INT_MAX
 #define KMP_MAX_NTH PTHREAD_THREADS_MAX
 #else
+#ifdef __ve__
+// VE's pthread supports only up to 64 threads per a VE process.
+// Please check p. 14 of following documentation for more details.
+// https://sxauroratsubasa.sakura.ne.jp/documents/veos/en/VEOS_high_level_design.pdf
+#define KMP_MAX_NTH 64
+#else
 #define KMP_MAX_NTH INT_MAX
 #endif
+#endif
 #endif /* KMP_MAX_NTH */
 
 #ifdef PTHREAD_STACK_MIN

openmp/runtime/src/z_Linux_util.cpp

@@ -1894,13 +1894,21 @@ void __kmp_runtime_initialize(void) {
 
     /* Query the maximum number of threads */
     __kmp_type_convert(sysconf(_SC_THREAD_THREADS_MAX), &(__kmp_sys_max_nth));
+#ifdef __ve__
+    if (__kmp_sys_max_nth == -1) {
+      // VE's pthread supports only up to 64 threads per a VE process.
+      // So we use that KMP_MAX_NTH (predefined as 64) here.
+      __kmp_sys_max_nth = KMP_MAX_NTH;
+    }
+#else
     if (__kmp_sys_max_nth == -1) {
       /* Unlimited threads for NPTL */
       __kmp_sys_max_nth = INT_MAX;
     } else if (__kmp_sys_max_nth <= 1) {
       /* Can't tell, just use PTHREAD_THREADS_MAX */
       __kmp_sys_max_nth = KMP_MAX_NTH;
     }
+#endif
 
     /* Query the minimum stack size */
     __kmp_sys_min_stksize = sysconf(_SC_THREAD_STACK_MIN);