update izumi and implement intel20 workaround (#460)

cice.setup

@@ -572,6 +572,13 @@ EOF
       continue
     endif
 
+    # unset env variables that might not exist in env machine file
+    # to avoid any carry over during multi compiler suites
+    unsetenv ICE_MACHINE_MAXTHREADS
+    unsetenv ICE_MACHINE_MAXPES
+    unsetenv ICE_MACHINE_QUIETMODE
+    unsetenv ICE_MACHINE_CPPDEFS
+    unsetenv ICE_MACHINE_QSTAT
     source ${ICE_SCRIPTS}/machines/env.${machcomp} -nomodules || exit 2
 
     # Obtain the test name, sets, grid, and PE information from .ts file
@@ -782,6 +789,11 @@ EOF
       set quietmode = ${ICE_MACHINE_QUIETMODE}
     endif
 
+    set cppdefs = ""
+    if ($?ICE_MACHINE_CPPDEFS) then
+      set cppdefs = ${ICE_MACHINE_CPPDEFS}
+    endif
+
     if (${acct} == ${spval}) then
       if (-e ~/.cice_proj) then
         set acct = `head -1 ~/.cice_proj`
@@ -884,6 +896,7 @@ setenv ICE_BASELINE ${basedir_tmp}
 setenv ICE_BASEGEN  ${baseGen}
 setenv ICE_BASECOM  ${baseCom}
 setenv ICE_SPVAL    ${spval}
+setenv ICE_CPPDEFS  ${cppdefs}
 setenv ICE_QUIETMODE  ${quietmode}
 setenv ICE_TEST     ${test}
 setenv ICE_TESTNAME ${testname_noid}

cicecore/cicedynB/dynamics/ice_transport_remap.F90

@@ -30,13 +30,14 @@
       module ice_transport_remap
 
       use ice_kinds_mod
-      use ice_communicate, only: my_task
+      use ice_blocks, only: nx_block, ny_block
+      use ice_communicate, only: my_task, ice_barrier
       use ice_constants, only: c0, c1, c2, c12, p333, p4, p5, p6, &
           eps13, eps16, &
           field_loc_center, field_type_scalar, &
           field_loc_NEcorner, field_type_vector
       use ice_domain_size, only: max_blocks, ncat
-      use ice_fileunits, only: nu_diag
+      use ice_fileunits, only: nu_diag, flush_fileunit
       use ice_exit, only: abort_ice
       use icepack_intfc, only: icepack_warnings_flush, icepack_warnings_aborted
       use icepack_intfc, only: icepack_query_parameters
@@ -254,7 +255,6 @@ module ice_transport_remap
       subroutine init_remap
 
       use ice_domain, only: nblocks
-      use ice_blocks, only: nx_block, ny_block
       use ice_grid, only: xav, yav, xxav, yyav
 !                          dxt, dyt, xyav, &
 !                          xxxav, xxyav, xyyav, yyyav
@@ -324,7 +324,7 @@ subroutine horizontal_remap (dt,                ntrace,     &
       use ice_boundary, only: ice_halo, ice_HaloMask, ice_HaloUpdate, &
           ice_HaloDestroy
       use ice_domain, only: nblocks, blocks_ice, halo_info, maskhalo_remap
-      use ice_blocks, only: block, get_block, nghost, nx_block, ny_block
+      use ice_blocks, only: block, get_block, nghost
       use ice_grid, only: HTE, HTN, dxu, dyu,       &
                           tarear, hm,                  &
                           xav, yav, xxav, yyav
@@ -381,62 +381,129 @@ subroutine horizontal_remap (dt,                ntrace,     &
          ilo,ihi,jlo,jhi,&! beginning and end of physical domain
          n, m             ! ice category, tracer indices
 
+! tcraig, the intel 20.0.1 compiler generates a segfault when entering this subroutine
+! at runtime.
+! This is probably a compiler bug and a workaround is to allocate the temporary data 
+! rather than define it statically.  Initial results don't show any slowdown, but
+! to keep the issue highlighted, an ifdef was created as a workaround.
+
+#ifdef INTEL20_WORKAROUND
+      integer (kind=int_kind), dimension(:,:), allocatable ::     &
+#else
       integer (kind=int_kind), dimension(0:ncat,max_blocks) ::     &
+#endif
          icellsnc         ! number of cells with ice
 
-      integer (kind=int_kind),     &
-         dimension(nx_block*ny_block,0:ncat) ::     &
+#ifdef INTEL20_WORKAROUND
+      integer (kind=int_kind), dimension(:,:), allocatable ::     &
+#else
+      integer (kind=int_kind), dimension(nx_block*ny_block,0:ncat) ::     &
+#endif
          indxinc, indxjnc   ! compressed i/j indices
 
+#ifdef INTEL20_WORKAROUND
+      real (kind=dbl_kind), dimension(:,:), allocatable ::  &
+#else
       real (kind=dbl_kind), dimension(nx_block,ny_block) ::  &
+#endif
          edgearea_e     ,&! area of departure regions for east edges
          edgearea_n       ! area of departure regions for north edges
 
+#ifdef INTEL20_WORKAROUND
+      real (kind=dbl_kind), dimension (:,:,:), allocatable ::     &
+#else
       real (kind=dbl_kind), dimension (nx_block,ny_block,max_blocks) ::     &
+#endif
          dpx            ,&! x coordinates of departure points at cell corners
          dpy              ! y coordinates of departure points at cell corners
 
+#ifdef INTEL20_WORKAROUND
+      real (kind=dbl_kind), dimension(:,:,:,:), allocatable :: &
+#else
       real (kind=dbl_kind), dimension(nx_block,ny_block,0:ncat,max_blocks) :: &
+#endif
          mc             ,&! mass at geometric center of cell
          mx, my           ! limited derivative of mass wrt x and y
 
+#ifdef INTEL20_WORKAROUND
+      real (kind=dbl_kind), dimension(:,:,:), allocatable :: &
+#else
       real (kind=dbl_kind), dimension(nx_block,ny_block,0:ncat) :: &
+#endif
          mmask            ! = 1. if mass is present, = 0. otherwise
 
-      real (kind=dbl_kind), &
-         dimension (nx_block,ny_block,ntrace,ncat,max_blocks) :: &
+#ifdef INTEL20_WORKAROUND
+      real (kind=dbl_kind), dimension (:,:,:,:,:), allocatable :: &
+#else
+      real (kind=dbl_kind), dimension (nx_block,ny_block,ntrace,ncat,max_blocks) :: &
+#endif
          tc             ,&! tracer values at geometric center of cell
          tx, ty           ! limited derivative of tracer wrt x and y
 
-      real (kind=dbl_kind), &
-         dimension (nx_block,ny_block,ntrace,ncat) ::     &
+#ifdef INTEL20_WORKAROUND
+      real (kind=dbl_kind), dimension (:,:,:,:), allocatable ::     &
+#else
+      real (kind=dbl_kind), dimension (nx_block,ny_block,ntrace,ncat) ::     &
+#endif
          tmask            ! = 1. if tracer is present, = 0. otherwise
 
+#ifdef INTEL20_WORKAROUND
+      real (kind=dbl_kind), dimension (:,:,:), allocatable ::     &
+#else
       real (kind=dbl_kind), dimension (nx_block,ny_block,0:ncat) ::     &
+#endif
          mflxe, mflxn     ! mass transports across E and N cell edges
 
+#ifdef INTEL20_WORKAROUND
+      real (kind=dbl_kind), dimension (:,:,:,:), allocatable :: &
+#else
       real (kind=dbl_kind), dimension (nx_block,ny_block,ntrace,ncat) :: &
+#endif
          mtflxe, mtflxn   ! mass*tracer transports across E and N cell edges
 
+#ifdef INTEL20_WORKAROUND
+      real (kind=dbl_kind), dimension (:,:,:), allocatable ::     &
+#else
       real (kind=dbl_kind), dimension (nx_block,ny_block,ngroups) ::     &
+#endif
          triarea          ! area of east-edge departure triangle
 
+#ifdef INTEL20_WORKAROUND
+      real (kind=dbl_kind), dimension (:,:,:,:), allocatable ::  &
+#else
       real (kind=dbl_kind), dimension (nx_block,ny_block,0:nvert,ngroups) ::  &
+#endif
          xp, yp           ! x and y coordinates of special triangle points
                           ! (need 4 points for triangle integrals)
-
-      integer (kind=int_kind),     &
-         dimension (nx_block,ny_block,ngroups) ::     &
+#ifdef INTEL20_WORKAROUND
+      integer (kind=int_kind), dimension (:,:,:), allocatable ::     &
+#else
+      integer (kind=int_kind), dimension (nx_block,ny_block,ngroups) ::     &
+#endif
          iflux          ,&! i index of cell contributing transport
          jflux            ! j index of cell contributing transport
 
+#ifdef INTEL20_WORKAROUND
+      integer (kind=int_kind), dimension(:,:), allocatable ::     &
+#else
       integer (kind=int_kind), dimension(ngroups,max_blocks) ::     &
+#endif
          icellsng         ! number of cells with ice
 
-      integer (kind=int_kind),     &
-         dimension(nx_block*ny_block,ngroups) ::     &
+#ifdef INTEL20_WORKAROUND
+      integer (kind=int_kind), dimension(:,:), allocatable ::     &
+#else
+      integer (kind=int_kind), dimension(nx_block*ny_block,ngroups) ::     &
+#endif
          indxing, indxjng ! compressed i/j indices
 
+#ifdef INTEL20_WORKAROUND
+      integer (kind=int_kind), dimension(:,:,:), allocatable :: &
+#else
+      integer (kind=int_kind), dimension(nx_block,ny_block,max_blocks) :: &
+#endif
+         halomask         ! temporary mask for fast halo updates
+
       logical (kind=log_kind) ::     &
          l_stop           ! if true, abort the model
 
@@ -446,9 +513,6 @@ subroutine horizontal_remap (dt,                ntrace,     &
       character (len=char_len) ::   &
          edge             ! 'north' or 'east'
 
-      integer (kind=int_kind), &
-         dimension(nx_block,ny_block,max_blocks) :: halomask
-
       type (ice_halo) :: halo_info_tracer
 
       type (block) ::     &
@@ -461,6 +525,37 @@ subroutine horizontal_remap (dt,                ntrace,     &
 !---! Remap the open water area (without tracers).
 !---!-------------------------------------------------------------------
 
+#ifdef INTEL20_WORKAROUND
+      allocate(icellsnc(0:ncat,max_blocks))
+      allocate(indxinc(nx_block*ny_block,0:ncat))
+      allocate(indxjnc(nx_block*ny_block,0:ncat))
+      allocate(edgearea_e(nx_block,ny_block))
+      allocate(edgearea_n(nx_block,ny_block))
+      allocate(dpx(nx_block,ny_block,max_blocks))
+      allocate(dpy(nx_block,ny_block,max_blocks))
+      allocate(mc(nx_block,ny_block,0:ncat,max_blocks))
+      allocate(mx(nx_block,ny_block,0:ncat,max_blocks))
+      allocate(my(nx_block,ny_block,0:ncat,max_blocks))
+      allocate(mmask(nx_block,ny_block,0:ncat))
+      allocate(tc(nx_block,ny_block,ntrace,ncat,max_blocks))
+      allocate(tx(nx_block,ny_block,ntrace,ncat,max_blocks))
+      allocate(ty(nx_block,ny_block,ntrace,ncat,max_blocks))
+      allocate(tmask(nx_block,ny_block,ntrace,ncat))
+      allocate(mflxe(nx_block,ny_block,0:ncat))
+      allocate(mflxn(nx_block,ny_block,0:ncat))
+      allocate(mtflxe(nx_block,ny_block,ntrace,ncat))
+      allocate(mtflxn(nx_block,ny_block,ntrace,ncat))
+      allocate(triarea(nx_block,ny_block,ngroups))
+      allocate(xp(nx_block,ny_block,0:nvert,ngroups))
+      allocate(yp(nx_block,ny_block,0:nvert,ngroups))
+      allocate(iflux(nx_block,ny_block,ngroups))
+      allocate(jflux(nx_block,ny_block,ngroups))
+      allocate(icellsng(ngroups,max_blocks))
+      allocate(indxing(nx_block*ny_block,ngroups))
+      allocate(indxjng(nx_block*ny_block,ngroups))
+      allocate(halomask(nx_block,ny_block,max_blocks))
+#endif
+
       !--- tcraig, tcx, this omp loop leads to a seg fault in gnu
       !--- need to check private variables and debug further
       !$TCXOMP PARALLEL DO PRIVATE(iblk,ilo,ihi,jlo,jhi,this_block,n,m, &
@@ -515,6 +610,7 @@ subroutine horizontal_remap (dt,                ntrace,     &
                                mmask (:,:,0) )
 
          ! ice categories
+
          do n = 1, ncat
 
             call construct_fields(nx_block,            ny_block,            &
@@ -852,6 +948,37 @@ subroutine horizontal_remap (dt,                ntrace,     &
       enddo                     ! iblk
       !$TCXOMP END PARALLEL DO
 
+#ifdef INTEL20_WORKAROUND
+      deallocate(icellsnc)
+      deallocate(indxinc)
+      deallocate(indxjnc)
+      deallocate(edgearea_e)
+      deallocate(edgearea_n)
+      deallocate(dpx)
+      deallocate(dpy)
+      deallocate(mc)
+      deallocate(mx)
+      deallocate(my)
+      deallocate(mmask)
+      deallocate(tc)
+      deallocate(tx)
+      deallocate(ty)
+      deallocate(tmask)
+      deallocate(mflxe)
+      deallocate(mflxn)
+      deallocate(mtflxe)
+      deallocate(mtflxn)
+      deallocate(triarea)
+      deallocate(xp)
+      deallocate(yp)
+      deallocate(iflux)
+      deallocate(jflux)
+      deallocate(icellsng)
+      deallocate(indxing)
+      deallocate(indxjng)
+      deallocate(halomask)
+#endif
+
       end subroutine horizontal_remap
 
 !=======================================================================

cicecore/shared/ice_init_column.F90

@@ -1937,6 +1937,7 @@ subroutine count_tracers
 
       nbtrcr = 0
       nbtrcr_sw = 0
+      nt_zbgc_frac = 0
 
       ! vectors of size icepack_max_algae
       nlt_bgc_N(:) = 0
@@ -2184,7 +2185,6 @@ subroutine count_tracers
             enddo   ! mm
          endif      ! tr_zaero
 
-         nt_zbgc_frac = 0
          if (nbtrcr > 0) then
             nt_zbgc_frac = ntrcr + 1
             ntrcr = ntrcr + nbtrcr

configuration/scripts/machines/env.izumi_gnu

@@ -10,7 +10,7 @@ if ("$inp" != "-nomodules") then
 source /usr/share/Modules/init/csh
 
 module purge
-module load compiler/gnu/8.2.0
+module load compiler/gnu/9.3.0
 
 setenv OMP_STACKSIZE 64M
 

configuration/scripts/machines/env.izumi_intel

@@ -10,7 +10,7 @@ if ("$inp" != "-nomodules") then
 source /usr/share/Modules/init/csh
 
 module purge
-module load compiler/intel/19.0.2
+module load compiler/intel/20.0.1
 
 setenv OMP_STACKSIZE 64M
 
@@ -19,6 +19,7 @@ endif
 setenv ICE_MACHINE_ENVNAME izumi
 setenv ICE_MACHINE_COMPILER intel
 setenv ICE_MACHINE_MAKE gmake
+setenv ICE_MACHINE_CPPDEFS '"-DINTEL20_WORKAROUND"'
 setenv ICE_MACHINE_WKDIR /scratch/cluster/$user/CICE_RUNS
 setenv ICE_MACHINE_INPUTDATA /fs/cgd/csm/inputdata
 setenv ICE_MACHINE_BASELINE /scratch/cluster/$user/CICE_BASELINE

configuration/scripts/machines/env.izumi_nag

@@ -10,7 +10,8 @@ if ("$inp" != "-nomodules") then
 source /usr/share/Modules/init/csh
 
 module purge
-module load compiler/nag/6.2
+#module load compiler/nag/7.0
+module load compiler/nag/6.2-8.1.0 
 
 setenv OMP_STACKSIZE 64M
 

configuration/scripts/machines/env.izumi_pgi

@@ -10,7 +10,7 @@ if ("$inp" != "-nomodules") then
 source /usr/share/Modules/init/csh
 
 module purge
-module load compiler/pgi/18.10
+module load compiler/pgi/20.1
 
 setenv OMP_STACKSIZE 64M