[flang-commits] [flang] 1acb101 - [flang][cuda] Set correct bind(c) name for __popc (#152795)

[via flang-commits]

Author: Valentin Clement (バレンタイン クレメン)
Date: 2025-08-08T16:49:45-07:00
New Revision: 1acb1018d2ad8db4aaf5686b4f749e632828e690

URL: https://github.com/llvm/llvm-project/commit/1acb1018d2ad8db4aaf5686b4f749e632828e690
DIFF: https://github.com/llvm/llvm-project/commit/1acb1018d2ad8db4aaf5686b4f749e632828e690.diff

LOG: [flang][cuda] Set correct bind(c) name for __popc (#152795)

Added: 
    

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

Removed: 
    


################################################################################
diff  --git a/flang/module/cudadevice.f90 b/flang/module/cudadevice.f90
index d0c312c09353f..dc72fc52c7345 100644
--- a/flang/module/cudadevice.f90
+++ b/flang/module/cudadevice.f90
@@ -754,11 +754,11 @@ attributes(device) real(8) function sinpi(x) bind(c,name='__nv_sinpi')
   end interface
 
   interface __popc
-    attributes(device) integer function __popc(i) bind(c)
+    attributes(device) integer function __popc(i) bind(c, name='__nv_popc')
       !dir$ ignore_tkr (d) i
       integer, value :: i
     end function
-    attributes(device) integer function __popcll(i) bind(c)
+    attributes(device) integer function __popcll(i) bind(c, name='__nv_popcll')
       !dir$ ignore_tkr (d) i
       integer(8), value :: i
     end function

diff  --git a/flang/test/Lower/CUDA/cuda-device-proc.cuf b/flang/test/Lower/CUDA/cuda-device-proc.cuf
index d5e614a83b354..a8cc5034a9348 100644
--- a/flang/test/Lower/CUDA/cuda-device-proc.cuf
+++ b/flang/test/Lower/CUDA/cuda-device-proc.cuf
@@ -11,6 +11,7 @@ attributes(global) subroutine devsub()
   integer(8) :: al
   integer(8) :: time
   integer :: smalltime
+  integer(4) :: res
 
   call syncthreads()
   call syncwarp(1)
@@ -49,6 +50,9 @@ attributes(global) subroutine devsub()
   smalltime = clock()
   time = clock64()
   time = globalTimer()
+
+  res = __popc(ai)
+  res = __popc(al)
 end
 
 ! CHECK-LABEL: func.func @_QPdevsub() attributes {cuf.proc_attr = #cuf.cuda_proc<global>}
@@ -89,6 +93,9 @@ end
 ! CHECK: %{{.*}} = nvvm.read.ptx.sreg.clock64 : i64
 ! CHECK: %{{.*}} = nvvm.read.ptx.sreg.globaltimer : i64
 
+! CHECK: %{{.*}} = fir.call @__nv_popc(%{{.*}}) proc_attrs<bind_c> fastmath<contract> : (i32) -> i32
+! CHECK: %{{.*}} = fir.call @__nv_popcll(%{{.*}}) proc_attrs<bind_c> fastmath<contract> : (i64) -> i32
+
 subroutine host1()
   integer, device :: a(32)
   integer, device :: ret