[flang-commits] [flang] df15c0d - [flang][cuda] Add interfaces for __dsqrt_rn and __dsqrt_rz (#153624)

[via flang-commits]

Author: Valentin Clement (バレンタイン クレメン)
Date: 2025-08-14T22:08:33Z
New Revision: df15c0d716fa0d84104b05937854becacbda6629

URL: https://github.com/llvm/llvm-project/commit/df15c0d716fa0d84104b05937854becacbda6629
DIFF: https://github.com/llvm/llvm-project/commit/df15c0d716fa0d84104b05937854becacbda6629.diff

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

Added: 
    

Modified: 
    flang/module/cudadevice.f90
    flang/test/Lower/CUDA/cuda-device-proc.cuf
    flang/test/Lower/CUDA/cuda-libdevice.cuf

Removed: 
    


################################################################################
diff  --git a/flang/module/cudadevice.f90 b/flang/module/cudadevice.f90
index 3e86dac5f5641..a8b1d19a4c1ff 100644
--- a/flang/module/cudadevice.f90
+++ b/flang/module/cudadevice.f90
@@ -814,6 +814,13 @@ 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
@@ -821,6 +828,13 @@ attributes(device) real(8) function sinpi(x) bind(c,name='__nv_sinpi')
     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

diff  --git a/flang/test/Lower/CUDA/cuda-device-proc.cuf b/flang/test/Lower/CUDA/cuda-device-proc.cuf
index ab90dec790046..a6e8c69b2e52e 100644
--- a/flang/test/Lower/CUDA/cuda-device-proc.cuf
+++ b/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

diff  --git a/flang/test/Lower/CUDA/cuda-libdevice.cuf b/flang/test/Lower/CUDA/cuda-libdevice.cuf
index 374d9f30ff008..447e09cad747b 100644
--- a/flang/test/Lower/CUDA/cuda-libdevice.cuf
+++ b/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
-