diff --git a/builtins-c.c b/builtins-c.c
index 676f5da3..f003bbb2 100644
--- a/builtins-c.c
+++ b/builtins-c.c
@@ -51,6 +51,12 @@
   */
 
 
+#ifdef _MSC_VER
+#include <windows.h>
+#else
+#include <unistd.h>
+#endif // !_MSC_VER
+
 #include <stdint.h>
 #include <stdio.h>
 #include <stdarg.h>
@@ -139,3 +145,14 @@ void __do_print(const char *format, const char *types, int width, int mask,
     }
     fflush(stdout);
 }
+
+
+int __num_cores() {
+#ifdef _MSC_VER
+    SYSTEM_INFO sysInfo;
+    GetSystemInfo(&sysInfo);
+    return sysInfo.dwNumberOfProcessors;
+#else
+    return sysconf(_SC_NPROCESSORS_ONLN);
+#endif // !_MSC_VER
+}
diff --git a/docs/ispc.txt b/docs/ispc.txt
index f6415e85..89249914 100644
--- a/docs/ispc.txt
+++ b/docs/ispc.txt
@@ -91,6 +91,7 @@ Contents:
   + `Conversions To and From Half-Precision Floats`_
   + `Atomic Operations and Memory Fences`_
   + `Prefetches`_
+  + `System Information`_
   + `Low-Level Bits`_
 
 * `Interoperability with the Application`_
@@ -2142,6 +2143,20 @@ These functions are available for all of the basic types in the
 language--``int8``, ``int16``, ``int32``, ``float``, and so forth.
 
 
+System Information
+------------------
+
+A routine is available to find the number of CPU cores available in the
+system:
+
+::
+
+    int num_cores()
+
+This value can be useful for adapting the granularity of parallel task
+decomposition depending on the number of processors in the system.
+
+
 Low-Level Bits
 --------------
 
diff --git a/stdlib.ispc b/stdlib.ispc
index 0b848422..40b4c9e8 100644
--- a/stdlib.ispc
+++ b/stdlib.ispc
@@ -568,6 +568,13 @@ static inline uniform int packed_store_active(uniform int a[], uniform int start
     return __packed_store_active(a, start, vals, __mask);
 }
 
+///////////////////////////////////////////////////////////////////////////
+// System information
+
+static inline int num_cores() {
+    return __num_cores();
+}
+
 ///////////////////////////////////////////////////////////////////////////
 // Atomics and memory barriers