Skip to content

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

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Aug 8, 2025
Merged

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

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions flang/module/cudadevice.f90
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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
Expand Down
7 changes: 7 additions & 0 deletions flang/test/Lower/CUDA/cuda-device-proc.cuf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,7 @@ attributes(global) subroutine devsub()
integer(8) :: al
integer(8) :: time
integer :: smalltime
integer(4) :: res

call syncthreads()
call syncwarp(1)
Expand Down Expand Up @@ -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>}
Expand Down Expand Up @@ -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
Expand Down