Upstream mnerge

Author: danieljvickers

src/common/include/parallel_macros.fpp

@@ -24,26 +24,28 @@
     & copy=None, copyin=None, copyinReadOnly=None, copyout=None, create=None, &
     & no_create=None, present=None, deviceptr=None, attach=None, extraAccArgs=None, extraOmpArgs=None)
 
+    #:set acc_directive = ACC_PARALLEL_LOOP(collapse, private, parallelism, default, firstprivate, reduction, reductionOp, copy, copyin, copyinReadOnly, copyout, create, no_create, present, deviceptr, attach, extraAccArgs)
+    #:set omp_directive = OMP_PARALLEL_LOOP(collapse, private, parallelism, default, firstprivate, reduction, reductionOp, copy, copyin, copyinReadOnly, copyout, create, no_create, present, deviceptr, attach, extraOmpArgs)
+
 #if defined(MFC_OpenACC)
-    #:set directive = ACC_PARALLEL_LOOP(collapse, private, parallelism, default, firstprivate, reduction, reductionOp, copy, copyin, copyinReadOnly, copyout, create, no_create, present, deviceptr, attach, extraAccArgs)
+    $:acc_directive
 #elif defined(MFC_OpenMP)
-    #:set directive = OMP_PARALLEL_LOOP(collapse, private, parallelism, default, firstprivate, reduction, reductionOp, copy, copyin, copyinReadOnly, copyout, create, no_create, present, deviceptr, attach, extraOmpArgs)
+    $:omp_directive
 #endif
 
-    $:directive
-
 #:enddef
 
 #:def END_GPU_PARALLEL_LOOP()
 
+    #:set acc_end_directive = '!$acc end parallel loop'
+    #:set omp_end_directive = END_OMP_PARALLEL_LOOP()
+
 #if defined(MFC_OpenACC)
-    #:set end_directive = '!$acc end parallel loop'
+    $:acc_end_directive
 #elif defined(MFC_OpenMP)
-    #:set end_directive = END_OMP_PARALLEL_LOOP()
+    $:omp_end_directive
 #endif
 
-    $:end_directive
-
 #:enddef
 
 #:def GPU_ROUTINE(function_name=None, parallelism=None, nohost=False, cray_inline=False, extraAccArgs=None, extraOmpArgs=None)

src/common/m_chemistry.fpp

@@ -129,7 +129,7 @@ contains
         real(wp), dimension(num_species) :: Ys
         real(wp), dimension(num_species) :: omega
 
-       $:GPU_PARALLEL_LOOP(collapse=3, private='[Ys, omega, eqn, T, rho, omega_m]', copyin='[bounds]')
+       $:GPU_PARALLEL_LOOP(collapse=3, private='[Ys, omega, eqn, T, rho, omega, omega_m]', copyin='[bounds]')
             do z = bounds(3)%beg, bounds(3)%end
                 do y = bounds(2)%beg, bounds(2)%end
                     do x = bounds(1)%beg, bounds(1)%end

src/simulation/m_bubbles_EE.fpp

@@ -177,7 +177,7 @@ contains
         integer :: dmBub_id !< Dummy variables for unified subgrid bubble subroutines
         real(wp) :: dmMass_v, dmMass_n, dmBeta_c, dmBeta_t, dmCson
 
-        $:GPU_PARALLEL_LOOP(private='[j,k,l]', collapse=3)
+        $:GPU_PARALLEL_LOOP(private='[j,k,l,q]', collapse=3)
         do l = 0, p
             do k = 0, n
                 do j = 0, m
@@ -333,7 +333,7 @@ contains
         if (adap_dt .and. adap_dt_stop_max > 0) call s_mpi_abort("Adaptive time stepping failed to converge.")
 
         if (.not. adap_dt) then
-            $:GPU_PARALLEL_LOOP(private='[i,l,q]', collapse=3)
+            $:GPU_PARALLEL_LOOP(private='[i,k,l,q]', collapse=3)
             do l = 0, p
                 do q = 0, n
                     do i = 0, m

src/simulation/m_bubbles_EL.fpp

@@ -617,7 +617,7 @@ contains
 
         ! Radial motion model
         adap_dt_stop_max = 0
-        $:GPU_PARALLEL_LOOP(private='[k,myalpha_rho,myalpha,Re,cell]', &
+        $:GPU_PARALLEL_LOOP(private='[k,i,myalpha_rho,myalpha,Re,cell]', &
             & reduction='[[adap_dt_stop_max]]',reductionOp='[MAX]', &
             & copy='[adap_dt_stop_max]',copyin='[stage]')
         do k = 1, nBubs

src/simulation/m_bubbles_EL_kernels.fpp

@@ -121,6 +121,7 @@ contains
         smearGridz = smearGrid
         if (p == 0) smearGridz = 1
 
+<<<<<<< HEAD
         $:GPU_PARALLEL_LOOP(private='[nodecoord,l,s_coord,cell,center]', copyin='[smearGrid,smearGridz]')
             do l = 1, nBubs
                 nodecoord(1:3) = 0
@@ -131,6 +132,18 @@ contains
                 if (p > 0) center(3) = lbk_pos(l, 3, 2)
                 call s_get_cell(s_coord, cell)
                 call s_compute_stddsv(cell, volpart, stddsv)
+=======
+        $:GPU_PARALLEL_LOOP(private='[nodecoord,i,j,k,l,s_coord,cell,center]', copyin='[smearGrid,smearGridz]')
+        do l = 1, nBubs
+            nodecoord(1:3) = 0
+            center(1:3) = 0._wp
+            volpart = 4._wp/3._wp*pi*lbk_rad(l, 2)**3._wp
+            s_coord(1:3) = lbk_s(l, 1:3, 2)
+            center(1:2) = lbk_pos(l, 1:2, 2)
+            if (p > 0) center(3) = lbk_pos(l, 3, 2)
+            call s_get_cell(s_coord, cell)
+            call s_compute_stddsv(cell, volpart, stddsv)
+>>>>>>> 723822d0b71c437e734f7ca0fcd386b0e3884a79
 
                 strength_vol = volpart
                 strength_vel = 4._wp*pi*lbk_rad(l, 2)**2._wp*lbk_vel(l, 2)
@@ -381,7 +394,7 @@ contains
     !> The purpose of this procedure is to calculate the characteristic cell volume
             !! @param cell Computational coordinates (x, y, z)
             !! @param Charvol Characteristic volume
-    elemental subroutine s_get_char_vol(cellx, celly, cellz, Charvol)
+    subroutine s_get_char_vol(cellx, celly, cellz, Charvol)
         $:GPU_ROUTINE(function_name='s_get_char_vol',parallelism='[seq]', &
             & cray_inline=True)