diff --git a/opt.cpp b/opt.cpp
index 7a471e89..9ddbdd11 100644
--- a/opt.cpp
+++ b/opt.cpp
@@ -2568,7 +2568,7 @@ llvm::RegisterPass<MakeInternalFuncsStaticPass>
 bool
 MakeInternalFuncsStaticPass::runOnModule(llvm::Module &module) {
     const char *names[] = {
-        "__do_print", "__fast_masked_vload",
+        "__do_print", "__fast_masked_vload", "__num_cores",
         "__gather_base_offsets_i8", "__gather_base_offsets_i16",
         "__gather_base_offsets_i32", "__gather_base_offsets_i64",
         "__gather_elt_8", "__gather_elt_16", 
diff --git a/stdlib.ispc b/stdlib.ispc
index 40b4c9e8..1e8ddc4f 100644
--- a/stdlib.ispc
+++ b/stdlib.ispc
@@ -638,24 +638,24 @@ DEFINE_ATOMIC_OP(unsigned int32,int32,swap,swap,int32)
 
 DEFINE_ATOMIC_OP(float,float,swap,swap,int32)
 
-DEFINE_ATOMIC_OP(int64,int64,add,add,int64)
-DEFINE_ATOMIC_OP(int64,int64,subtract,sub,int64)
+DEFINE_ATOMIC_OP(int64,int64,add,add,int32)
+DEFINE_ATOMIC_OP(int64,int64,subtract,sub,int32)
 DEFINE_ATOMIC_MINMAX_OP(int64,int64,min,min)
 DEFINE_ATOMIC_MINMAX_OP(int64,int64,max,max)
-DEFINE_ATOMIC_OP(int64,int64,and,and,int64)
-DEFINE_ATOMIC_OP(int64,int64,or,or,int64)
-DEFINE_ATOMIC_OP(int64,int64,xor,xor,int64)
+DEFINE_ATOMIC_OP(int64,int64,and,and,int32)
+DEFINE_ATOMIC_OP(int64,int64,or,or,int32)
+DEFINE_ATOMIC_OP(int64,int64,xor,xor,int32)
 DEFINE_ATOMIC_OP(int64,int64,swap,swap,int32)
 
 // For everything but atomic min and max, we can use the same
 // implementations for unsigned as for signed.
-DEFINE_ATOMIC_OP(unsigned int64,int64,add,add,int64)
-DEFINE_ATOMIC_OP(unsigned int64,int64,subtract,sub,int64)
+DEFINE_ATOMIC_OP(unsigned int64,int64,add,add,int32)
+DEFINE_ATOMIC_OP(unsigned int64,int64,subtract,sub,int32)
 DEFINE_ATOMIC_MINMAX_OP(unsigned int64,uint64,min,umin)
 DEFINE_ATOMIC_MINMAX_OP(unsigned int64,uint64,max,umax)
-DEFINE_ATOMIC_OP(unsigned int64,int64,and,and,int64)
-DEFINE_ATOMIC_OP(unsigned int64,int64,or,or,int64)
-DEFINE_ATOMIC_OP(unsigned int64,int64,xor,xor,int64)
+DEFINE_ATOMIC_OP(unsigned int64,int64,and,and,int32)
+DEFINE_ATOMIC_OP(unsigned int64,int64,or,or,int32)
+DEFINE_ATOMIC_OP(unsigned int64,int64,xor,xor,int32)
 DEFINE_ATOMIC_OP(unsigned int64,int64,swap,swap,int32)
 
 DEFINE_ATOMIC_OP(double,double,swap,swap,int32)