diff --git a/flang/module/cudadevice.f90 b/flang/module/cudadevice.f90
index 82571704032f0..cec1147ed5b21 100644
--- a/flang/module/cudadevice.f90
+++ b/flang/module/cudadevice.f90
@@ -507,28 +507,28 @@ attributes(device) real(8) function sinpi(x) bind(c,name='__nv_sinpi')
   end interface
 
   interface __double2float_rn
-    attributes(device) real function __double2float_rn(r) bind(c)
+    attributes(device) real function __double2float_rn(r) bind(c, name='__nv_double2float_rn')
       !dir$ ignore_tkr (d) r
       double precision, value :: r
     end function
   end interface
 
   interface __double2float_rz
-    attributes(device) real function __double2float_rz(r) bind(c)
+    attributes(device) real function __double2float_rz(r) bind(c, name='__nv_double2float_rz')
       !dir$ ignore_tkr (d) r
       double precision, value :: r
     end function
   end interface
 
   interface __double2float_ru
-    attributes(device) real function __double2float_ru(r) bind(c)
+    attributes(device) real function __double2float_ru(r) bind(c, name='__nv_double2float_ru')
       !dir$ ignore_tkr (d) r
       double precision, value :: r
     end function
   end interface
 
   interface __double2float_rd
-    attributes(device) real function __double2float_rd(r) bind(c)
+    attributes(device) real function __double2float_rd(r) bind(c, name='__nv_double2float_rd')
       !dir$ ignore_tkr (d) r
       double precision, value :: r
     end function
diff --git a/flang/test/Lower/CUDA/cuda-device-proc.cuf b/flang/test/Lower/CUDA/cuda-device-proc.cuf
index ae336445532b9..4fb658ecfdaed 100644
--- a/flang/test/Lower/CUDA/cuda-device-proc.cuf
+++ b/flang/test/Lower/CUDA/cuda-device-proc.cuf
@@ -65,10 +65,13 @@ attributes(global) subroutine devsub()
   ad = __ddiv_rz(ad, ad)
   ad = __ddiv_ru(ad, ad)
   ad = __ddiv_rd(ad, ad)
+  af = __double2float_rn(ad)
+  af = __double2float_rz(ad)
+  af = __double2float_ru(ad)
+  af = __double2float_rd(ad)
   ai = __mul24(ai, ai)
   ai = __umul24(ai, ai)
   af = __powf(af, af)
-
 end
 
 ! CHECK-LABEL: func.func @_QPdevsub() attributes {cuf.proc_attr = #cuf.cuda_proc<global>}
@@ -122,6 +125,10 @@ end
 ! CHECK: %{{.*}} = fir.call @__nv_ddiv_rz(%{{.*}}, %{{.*}}) proc_attrs<bind_c> fastmath<contract> : (f64, f64) -> f64
 ! CHECK: %{{.*}} = fir.call @__nv_ddiv_ru(%{{.*}}, %{{.*}}) proc_attrs<bind_c> fastmath<contract> : (f64, f64) -> f64
 ! CHECK: %{{.*}} = fir.call @__nv_ddiv_rd(%{{.*}}, %{{.*}}) proc_attrs<bind_c> fastmath<contract> : (f64, f64) -> f64
+! CHECK: %{{.*}} = fir.call @__nv_double2float_rn(%{{.*}}) proc_attrs<bind_c> fastmath<contract> : (f64) -> f32
+! CHECK: %{{.*}} = fir.call @__nv_double2float_rz(%{{.*}}) proc_attrs<bind_c> fastmath<contract> : (f64) -> f32
+! CHECK: %{{.*}} = fir.call @__nv_double2float_ru(%{{.*}}) proc_attrs<bind_c> fastmath<contract> : (f64) -> f32
+! CHECK: %{{.*}} = fir.call @__nv_double2float_rd(%{{.*}}) proc_attrs<bind_c> fastmath<contract> : (f64) -> f32
 ! CHECK: %{{.*}} = fir.call @__nv_mul24(%{{.*}}, %{{.*}}) proc_attrs<bind_c> fastmath<contract> : (i32, i32) -> i32
 ! CHECK: %{{.*}} = fir.call @__nv_umul24(%{{.*}}, %{{.*}}) proc_attrs<bind_c> fastmath<contract> : (i32, i32) -> i32
 ! CHECK: %{{.*}} = fir.call @__nv_powf(%{{.*}}, %{{.*}}) proc_attrs<bind_c> fastmath<contract> : (f32, f32) -> f32