correct corrupted comments and whitespace in 127/147 changed files

Author: wilfonba

.github/CODEOWNERS

@@ -1,15 +1,3 @@
 # Spencer H. Bryngelson (sbryngelson) is the
 # default owner of all files in the repository.
 *                  @sbryngelson
-
-# @core-devs
-src/               @MFlowCode/core-devs
-docs/              @MFlowCode/core-devs
-toolchain/         @MFlowCode/core-devs
-tests/             @MFlowCode/core-devs
-benchmarks/        @MFlowCode/core-devs
-mfc.sh             @MFlowCode/core-devs
-CMakeLists.txt     @MFlowCode/core-devs
-
-# @physics-devs
-src/               @MFlowCode/physics-devs

mfc.sh

@@ -102,9 +102,12 @@ if [ $code -ne 0 ]; then
     error "main.py finished with a $code exit code."
 fi
 
-# Deactivate the Python virtualenv in case the user "source"'d this script
-log "(venv) Exiting the$MAGENTA Python$COLOR_RESET virtual environment."
-deactivate
+# Deactivate the Python virtualenv in case the user "source"'d this script.
+# Guard against the case where no venv was activated (e.g. system Python).
+if type deactivate > /dev/null 2>&1; then
+    log "(venv) Exiting the$MAGENTA Python$COLOR_RESET virtual environment."
+    deactivate
+fi
 
 # Exit with proper exit code
 exit $code

src/common/include/3dHardcodedIC.fpp

@@ -19,7 +19,7 @@
 
     eps = 1e-9_wp
 
-    if (patch_icpp(patch_id)%hcid == 303) then
+    if (patch_icpp(patch_id)%hcid == 303) then  ! IGR Multijet
         eps_smooth = 3._wp
         inquire (file="njet.txt", exist=file_exist)
         if (file_exist) then
@@ -75,7 +75,7 @@
         end if
     end if
 
-    if (patch_icpp(patch_id)%hcid == 304) then
+    if (patch_icpp(patch_id)%hcid == 304) then  ! 3D Cartesian interface from file
         @:ALLOCATE(ih(0:n_glb, 0:p_glb))
 
         if (interface_file == '.') then
@@ -108,7 +108,7 @@
         end if
     end if
 
-    if (patch_icpp(patch_id)%hcid == 305) then
+    if (patch_icpp(patch_id)%hcid == 305) then  ! 3D Axisymmetric interface from file
         @:ALLOCATE(ih(0:n_glb, 0:0))
         if (interface_file == '.') then
             call s_mpi_abort("Error: interface_file must be specified for hcid=305")
@@ -241,9 +241,6 @@
         q_prim_vf(eqn_idx%cont%beg)%sf(i, j, k) = q_prim_vf(eqn_idx%adv%beg)%sf(i, j, k)*(950._wp/1000._wp)
         q_prim_vf(eqn_idx%cont%end)%sf(i, j, k) = q_prim_vf(eqn_idx%adv%end)%sf(i, j, k)*(1._wp/1000._wp)
 
-        ! h = x_cc(i) - ih(start_idx(2) + j, start_idx(3) + k) q_prim_vf(momxb)%sf(i,j,k) = -1._wp * (ih(start_idx(2) + j,
-        ! start_idx(3) + k) - normFac) * exp(-h * h / 1000) / 100._wp
-
         q_prim_vf(eqn_idx%E)%sf(i, j, k) = p0_ic + (q_prim_vf(eqn_idx%cont%beg)%sf(i, j, k) + q_prim_vf(eqn_idx%cont%end)%sf(i, &
                   & j, k))*g0_ic*(ih(start_idx(2) + j, start_idx(3) + k) - x_cc(i))
 

src/common/include/ExtrusionHardcodedIC.fpp

@@ -1,4 +1,4 @@
-!> @brief Allocate memory and read initial condition data for IC extrusion.
+!> Allocate memory and read initial condition data for IC extrusion.
 !>
 !> @details
 !> This macro handles the complete initialization process for IC extrusion by:

src/common/include/macros.fpp

@@ -19,10 +19,7 @@
 #ifdef MFC_SIMULATION
 #ifdef __NVCOMPILER_GPU_UNIFIED_MEM
     block
-        ! Beginning in the 25.3 release, the structure of the cudafor module has been changed slightly. The module now includes, or
-        ! "uses" 3 submodules: cuda_runtime_api, gpu_reductions, and sort. The cudafor functionality has not changed. But for new
-        ! users, or users who have needed to work-around name conflicts in the module, it may be better to use cuda_runtime_api to
-        ! expose interfaces to the CUDA runtime calls described in Chapter 4 of this guide.
+        ! NVIDIA CUDA Fortran 25.3+: uses submodules (cuda_runtime_api, gpu_reductions, sort) See
         ! https://docs.nvidia.com/hpc-sdk/compilers/cuda-fortran-prog-guide/index.html#fortran-host-modules
 #if __NVCOMPILER_MAJOR__ < 25 || (__NVCOMPILER_MAJOR__ == 25 && __NVCOMPILER_MINOR__ < 3)
         use cudafor, gpu_sum => sum, gpu_maxval => maxval, gpu_minval => minval
@@ -58,6 +55,7 @@
 #endif
 #:enddef
 
+! Allocate and create GPU device memory
 #:def ALLOCATE(*args)
     @:LOG({'@:ALLOCATE(${re.sub(' +', ' ', ', '.join(args))}$)'})
     #:set allocated_variables = ', '.join(args)
@@ -77,13 +75,15 @@
     $:GPU_ENTER_DATA(create='[' + joined + ']')
 #:enddef ALLOCATE
 
+! Free GPU device memory and deallocate
 #:def DEALLOCATE(*args)
     @:LOG({'@:DEALLOCATE(${re.sub(' +', ' ', ', '.join(args))}$)'})
     #:set allocated_variables = ', '.join(args)
     $:GPU_EXIT_DATA(delete=('[' + allocated_variables + ']'))
     deallocate (${allocated_variables}$)
 #:enddef DEALLOCATE
 
+! Cray-specific GPU pointer setup for vector fields
 #:def ACC_SETUP_VFs(*args)
 #ifdef _CRAYFTN
     block
@@ -107,6 +107,7 @@
 #endif
 #:enddef
 
+! Cray-specific GPU pointer setup for scalar fields
 #:def ACC_SETUP_SFs(*args)
 #ifdef _CRAYFTN
     block
@@ -122,6 +123,7 @@
 #endif
 #:enddef
 
+! Cray-specific GPU pointer setup for acoustic source spatials
 #:def ACC_SETUP_source_spatials(*args)
 #ifdef _CRAYFTN
     block

src/common/include/parallel_macros.fpp

@@ -2,6 +2,7 @@
 #:include 'omp_macros.fpp'
 #:include 'acc_macros.fpp'
 
+! GPU parallel region (scalar reductions, maxval/minval)
 #:def GPU_PARALLEL(code, private=None, default='present', firstprivate=None, reduction=None, reductionOp=None, &
     & copy=None, copyin=None, copyinReadOnly=None, copyout=None, create=None, &
     & no_create=None, present=None, deviceptr=None, attach=None, extraAccArgs=None, extraOmpArgs=None)
@@ -20,6 +21,7 @@
 #endif
 #:enddef
 
+! GPU parallel loop over threads (most common GPU macro)
 #:def GPU_PARALLEL_LOOP(collapse=None, private=None, parallelism='[gang, vector]', &
     & default='present', firstprivate=None, reduction=None, reductionOp=None, &
     & copy=None, copyin=None, copyinReadOnly=None, copyout=None, create=None, &
@@ -39,6 +41,7 @@
 #endif
 #:enddef
 
+! Required closing for GPU_PARALLEL_LOOP
 #:def END_GPU_PARALLEL_LOOP()
     #:set acc_end_directive = '!$acc end parallel loop'
     #:set omp_end_directive = END_OMP_PARALLEL_LOOP()
@@ -50,6 +53,7 @@
 #endif
 #:enddef
 
+! Mark routine for device compilation
 #:def GPU_ROUTINE(function_name=None, parallelism=None, nohost=False, cray_inline=False, cray_noinline=False, extraAccArgs=None, &
                   & extraOmpArgs=None)
     #:assert isinstance(cray_inline, bool)
@@ -106,6 +110,7 @@
     #:endif
 #:enddef
 
+! Declare device-resident data
 #:def GPU_DECLARE(copy=None, copyin=None, copyinReadOnly=None, copyout=None, create=None, present=None, deviceptr=None, &
                   & link=None, extraAccArgs=None, extraOmpArgs=None)
     #:set acc_code = ACC_DECLARE(copy=copy, copyin=copyin, copyinReadOnly=copyinReadOnly, copyout=copyout, create=create, &
@@ -123,6 +128,7 @@
 #endif
 #:enddef
 
+! Inner loop within a GPU parallel region
 #:def GPU_LOOP(collapse=None, parallelism=None, data_dependency=None, reduction=None, reductionOp=None, private=None, &
                & extraAccArgs=None, extraOmpArgs=None)
     #:set acc_code = ACC_LOOP(collapse=collapse, parallelism=parallelism, data_dependency=data_dependency, reduction=reduction, &
@@ -137,6 +143,7 @@
 #endif
 #:enddef
 
+! Scoped GPU data region
 #:def GPU_DATA(code, copy=None, copyin=None, copyinReadOnly=None, copyout=None, create=None, no_create=None, present=None, &
                & deviceptr=None, attach=None, default=None, extraAccArgs=None, extraOmpArgs=None)
     #:set acc_code = ACC_DATA(code=code, copy=copy, copyin=copyin, copyinReadOnly=copyinReadOnly, copyout=copyout, create=create, &
@@ -155,6 +162,7 @@
 #endif
 #:enddef
 
+! Host code with device pointers (for MPI with GPU buffers)
 #:def GPU_HOST_DATA(code, use_device_addr=None, use_device_ptr=None, extraAccArgs=None, extraOmpArgs=None)
     #:if use_device_addr is not None and use_device_ptr is not None
         #:set use_device_addr_end_index = len(use_device_addr) - 1
@@ -183,6 +191,7 @@
 #endif
 #:enddef
 
+! Allocate device memory (unscoped)
 #:def GPU_ENTER_DATA(copyin=None, copyinReadOnly=None, create=None, attach=None, extraAccArgs=None, extraOmpArgs=None)
     #:set acc_code = ACC_ENTER_DATA(copyin=copyin, copyinReadOnly=copyinReadOnly, create=create, attach=attach, &
                                     & extraAccArgs=extraAccArgs)
@@ -196,6 +205,7 @@
 #endif
 #:enddef
 
+! Free device memory
 #:def GPU_EXIT_DATA(copyout=None, delete=None, detach=None, extraAccArgs=None, extraOmpArgs=None)
     #:set acc_code = ACC_EXIT_DATA(copyout=copyout, delete=delete, detach=detach, extraAccArgs=extraAccArgs)
     #:set omp_code = OMP_EXIT_DATA(copyout=copyout, delete=delete, detach=detach, extraOmpArgs=extraOmpArgs)
@@ -207,6 +217,7 @@
 #endif
 #:enddef
 
+! Atomic operation on device
 #:def GPU_ATOMIC(atomic, extraAccArgs=None, extraOmpArgs=None)
     #:set acc_code = ACC_ATOMIC(atomic=atomic, extraAccArgs=extraAccArgs)
     #:set omp_code = OMP_ATOMIC(atomic=atomic, extraOmpArgs=extraOmpArgs)
@@ -218,6 +229,7 @@
 #endif
 #:enddef
 
+! End atomic capture block
 #:def END_GPU_ATOMIC_CAPTURE()
     #:set acc_end_directive = '!$acc end atomic'
     #:set omp_end_directive = '!$omp end atomic'
@@ -228,6 +240,7 @@
 #endif
 #:enddef
 
+! Copy data between host and device
 #:def GPU_UPDATE(host=None, device=None, extraAccArgs=None, extraOmpArgs=None)
     #:set acc_code = ACC_UPDATE(host=host, device=device, extraAccArgs=extraAccArgs)
     #:set omp_code = OMP_UPDATE(host=host, device=device, extraOmpArgs=extraOmpArgs)
@@ -239,6 +252,7 @@
 #endif
 #:enddef
 
+! Synchronization barrier
 #:def GPU_WAIT(extraAccArgs=None, extraOmpArgs=None)
     #:set acc_code = ACC_WAIT(extraAccArgs=extraAccArgs)
     #:set omp_code = OMP_WAIT(extraOmpArgs=extraOmpArgs)
@@ -250,6 +264,7 @@
 #endif
 #:enddef
 
+! Import GPU library module (openacc or omp_lib)
 #:def USE_GPU_MODULE()
 #if defined(MFC_OpenACC)
     use openacc
@@ -258,24 +273,28 @@
 #endif
 #:enddef
 
+! Emit code only for AMD compiler
 #:def DEF_AMD(code)
     #:if MFC_COMPILER == AMD_COMPILER_ID
         $:code
     #:endif
 #:enddef
 
+! Emit code for non-Cray compilers
 #:def UNDEF_CCE(code)
     #:if MFC_COMPILER != CCE_COMPILER_ID
         $:code
     #:endif
 #:enddef
 
+! Emit code only for Cray compiler
 #:def DEF_CCE(code)
     #:if MFC_COMPILER == CCE_COMPILER_ID
         $:code
     #:endif
 #:enddef
 
+! Emit code for non-NVIDIA compilers
 #:def UNDEF_NVIDIA(code)
     #:if MFC_COMPILER != NVIDIA_COMPILER_ID and MFC_COMPILER != PGI_COMPILER_ID
         $:code