[flang][do concurent] Add saxpy offload tests for OpenMP mapping

[ergawy]

Adds end-to-end tests for do concurrent offloading to the device.

PR stack:

• [NFC][flang][OpenMP] Extract target region utils to map or clone outside values #155754
• [flang][OpenMP] Extend do concurrent mapping to device #155987
• [flang][OpenMP] do concurrent to device mapping lit tests #155992
• [flang][do concurent] Add saxpy offload tests for OpenMP mapping #155993 ◀️
• [flang][OpenMP] do concurrent: support local on device #156589
• [flang][OpenMP] do concurrent: support reduce on device #156610
• [flang][OpenMP] Support multi-block reduction combiner regions on the GPU #156837

[llvmbot]

@llvm/pr-subscribers-offload

Author: Kareem Ergawy (ergawy)

Changes

Adds end-to-end tests for do concurrent offloading to the device.

---

Full diff: https://github.com/llvm/llvm-project/pull/155993.diff

2 Files Affected:

• (added) offload/test/offloading/fortran/do-concurrent-to-omp-saxpy-2d.f90 (+53)
• (added) offload/test/offloading/fortran/do-concurrent-to-omp-saxpy.f90 (+53)

diff --git a/offload/test/offloading/fortran/do-concurrent-to-omp-saxpy-2d.f90 b/offload/test/offloading/fortran/do-concurrent-to-omp-saxpy-2d.f90
new file mode 100644
index 0000000000000..c6f576acb90b6
--- /dev/null
+++ b/offload/test/offloading/fortran/do-concurrent-to-omp-saxpy-2d.f90
@@ -0,0 +1,53 @@
+! REQUIRES: flang, amdgpu
+
+! RUN: %libomptarget-compile-fortran-generic -fdo-concurrent-to-openmp=device
+! RUN: env LIBOMPTARGET_INFO=16 %libomptarget-run-generic 2>&1 | %fcheck-generic
+module saxpymod
+   use iso_fortran_env
+   public :: saxpy
+contains
+
+subroutine saxpy(a, x, y, n, m)
+   use iso_fortran_env
+   implicit none
+   integer,intent(in) :: n, m
+   real(kind=real32),intent(in) :: a
+   real(kind=real32), dimension(:,:),intent(in) :: x
+   real(kind=real32), dimension(:,:),intent(inout) :: y
+   integer :: i, j
+
+   do concurrent(i=1:n, j=1:m)
+       y(i,j) = a * x(i,j) + y(i,j)
+   end do
+
+   write(*,*) "plausibility check:"
+   write(*,'("y(1,1) ",f8.6)') y(1,1)
+   write(*,'("y(n,m) ",f8.6)') y(n,m)
+end subroutine saxpy
+
+end module saxpymod
+
+program main
+   use iso_fortran_env
+   use saxpymod, ONLY:saxpy
+   implicit none
+
+   integer,parameter :: n = 1000, m=10000
+   real(kind=real32), allocatable, dimension(:,:) :: x, y
+   real(kind=real32) :: a
+   integer :: i
+
+   allocate(x(1:n,1:m), y(1:n,1:m))
+   a = 2.0_real32
+   x(:,:) = 1.0_real32
+   y(:,:) = 2.0_real32
+
+   call saxpy(a, x, y, n, m)
+
+   deallocate(x,y)
+end program main
+
+! CHECK:  "PluginInterface" device {{[0-9]+}} info: Launching kernel {{.*}}
+! CHECK:  plausibility check:
+! CHECK:  y(1,1) 4.0
+! CHECK:  y(n,m) 4.0
diff --git a/offload/test/offloading/fortran/do-concurrent-to-omp-saxpy.f90 b/offload/test/offloading/fortran/do-concurrent-to-omp-saxpy.f90
new file mode 100644
index 0000000000000..e094a1d7459ef
--- /dev/null
+++ b/offload/test/offloading/fortran/do-concurrent-to-omp-saxpy.f90
@@ -0,0 +1,53 @@
+! REQUIRES: flang, amdgpu
+
+! RUN: %libomptarget-compile-fortran-generic -fdo-concurrent-to-openmp=device
+! RUN: env LIBOMPTARGET_INFO=16 %libomptarget-run-generic 2>&1 | %fcheck-generic
+module saxpymod
+   use iso_fortran_env
+   public :: saxpy
+contains
+
+subroutine saxpy(a, x, y, n)
+   use iso_fortran_env
+   implicit none
+   integer,intent(in) :: n
+   real(kind=real32),intent(in) :: a
+   real(kind=real32), dimension(:),intent(in) :: x
+   real(kind=real32), dimension(:),intent(inout) :: y
+   integer :: i
+
+   do concurrent(i=1:n)
+       y(i) = a * x(i) + y(i)
+   end do
+
+   write(*,*) "plausibility check:"
+   write(*,'("y(1) ",f8.6)') y(1)
+   write(*,'("y(n) ",f8.6)') y(n)
+end subroutine saxpy
+
+end module saxpymod
+
+program main
+   use iso_fortran_env
+   use saxpymod, ONLY:saxpy
+   implicit none
+
+   integer,parameter :: n = 10000000
+   real(kind=real32), allocatable, dimension(:) :: x, y
+   real(kind=real32) :: a
+   integer :: i
+
+   allocate(x(1:n), y(1:n))
+   a = 2.0_real32
+   x(:) = 1.0_real32
+   y(:) = 2.0_real32
+
+   call saxpy(a, x, y, n)
+
+   deallocate(x,y)
+end program main
+
+! CHECK:  "PluginInterface" device {{[0-9]+}} info: Launching kernel {{.*}}
+! CHECK:  plausibility check:
+! CHECK:  y(1) 4.0
+! CHECK:  y(n) 4.0

[ergawy]

Ping! Please have a look when you have time.