[flang][cuda] Add interfaces for __dsqrt_rn and __dsqrt_rz (#153624)

Author: clementval

flang/module/cudadevice.f90

@@ -814,13 +814,27 @@ attributes(device) real(8) function sinpi(x) bind(c,name='__nv_sinpi')
     end function
   end interface
 
+  interface __dsqrt_rn
+    attributes(device) double precision function __dsqrt_rn(x) bind(c, name='__nv_dsqrt_rn')
+      !dir$ ignore_tkr (d) x
+      double precision, value :: x
+    end function
+  end interface
+
   interface __dsqrt_ru
     attributes(device) double precision function __dsqrt_ru(x) bind(c, name='__nv_dsqrt_ru')
       !dir$ ignore_tkr (d) x
       double precision, value :: x
     end function
   end interface
 
+  interface __dsqrt_rz
+    attributes(device) double precision function __dsqrt_rz(x) bind(c, name='__nv_dsqrt_rz')
+      !dir$ ignore_tkr (d) x
+      double precision, value :: x
+    end function
+  end interface
+
   interface __ddiv_rn
     attributes(device) double precision function __ddiv_rn(x,y) bind(c, name='__nv_ddiv_rn')
       !dir$ ignore_tkr (d) x, (d) y

flang/test/Lower/CUDA/cuda-device-proc.cuf

@@ -82,8 +82,6 @@ attributes(global) subroutine devsub()
   ai = __mul24(ai, ai)
   ai = __umul24(ai, ai)
   af = __powf(af, af)
-  ad = __dsqrt_rd(ad)
-  ad = __dsqrt_ru(ad)
   ad = __ull2double_rd(al)
   ad = __ull2double_rn(al)
   ad = __ull2double_ru(al)
@@ -162,8 +160,6 @@ end
 ! 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
-! CHECK: %{{.*}} = fir.call @__nv_dsqrt_rd(%{{.*}}) proc_attrs<bind_c> fastmath<contract> : (f64) -> f64
-! CHECK: %{{.*}} = fir.call @__nv_dsqrt_ru(%{{.*}}) proc_attrs<bind_c> fastmath<contract> : (f64) -> f64
 ! CHECK: %{{.*}} = fir.call @__nv_ull2double_rd(%{{.*}}) proc_attrs<bind_c> fastmath<contract> : (i64) -> f64
 ! CHECK: %{{.*}} = fir.call @__nv_ull2double_rn(%{{.*}}) proc_attrs<bind_c> fastmath<contract> : (i64) -> f64
 ! CHECK: %{{.*}} = fir.call @__nv_ull2double_ru(%{{.*}}) proc_attrs<bind_c> fastmath<contract> : (i64) -> f64

flang/test/Lower/CUDA/cuda-libdevice.cuf

@@ -20,6 +20,21 @@ end subroutine
 ! CHECK-LABEL: _QPtest_usad
 ! CHECK: %{{.*}} = fir.call @__nv_usad(%{{.*}}, %{{.*}}, %{{.*}}) proc_attrs<bind_c> fastmath<contract> : (i32, i32, i32) -> i32
 
+attributes(global) subroutine test_dsqrt_rX()
+  double precision :: res
+  double precision :: p
+  res = __dsqrt_rd(p)
+  res = __dsqrt_rn(p)
+  res = __dsqrt_ru(p)
+  res = __dsqrt_rz(p)
+end subroutine
+
+! CHECK-LABEL: _QPtest_dsqrt_rx
+! CHECK: %{{.*}} = fir.call @__nv_dsqrt_rd(%{{.*}}) proc_attrs<bind_c> fastmath<contract> : (f64) -> f64
+! CHECK: %{{.*}} = fir.call @__nv_dsqrt_rn(%{{.*}}) proc_attrs<bind_c> fastmath<contract> : (f64) -> f64
+! CHECK: %{{.*}} = fir.call @__nv_dsqrt_ru(%{{.*}}) proc_attrs<bind_c> fastmath<contract> : (f64) -> f64
+! CHECK: %{{.*}} = fir.call @__nv_dsqrt_rz(%{{.*}}) proc_attrs<bind_c> fastmath<contract> : (f64) -> f64
+
 attributes(global) subroutine test_uint2float_rX()
   real :: res
   integer :: i
@@ -146,4 +161,3 @@ end subroutine
 ! CHECK: %{{.*}} = fir.call @__nv_double2ull_rn(%{{.*}}) proc_attrs<bind_c> fastmath<contract> : (f64) -> i64
 ! CHECK: %{{.*}} = fir.call @__nv_double2ull_ru(%{{.*}}) proc_attrs<bind_c> fastmath<contract> : (f64) -> i64
 ! CHECK: %{{.*}} = fir.call @__nv_double2ull_rz(%{{.*}}) proc_attrs<bind_c> fastmath<contract> : (f64) -> i64
-