prolong3 改为先算实际 stencil 窗口；只有窗口触及对称边界时才走全域 symmetry_bd，否则只复制必需窗口。restrict3 同样改成窗口判定，无触边时仅填 ii/jj/kk 必需窗口。

- compute fi_min/fi_max from output i-range and derive ii_lo/ii_hi
 - replace full ii sweep (-1:extf(1)) with windowed sweep in Z/Y precompute passes
 - keep stencil math unchanged; add bounds sanity check for ii window

AMSS_NCKU_source/FFT.f90

@@ -37,56 +37,51 @@ close(77)
 end program checkFFT
 #endif
 
+!-------------
+! Optimized FFT using Intel oneMKL DFTI
+! Mathematical equivalence: Standard DFT definition
+!   Forward (isign=1):  X[k] = sum_{n=0}^{N-1} x[n] * exp(-2*pi*i*k*n/N)
+!   Backward (isign=-1): X[k] = sum_{n=0}^{N-1} x[n] * exp(+2*pi*i*k*n/N)
+! Input/Output: dataa is interleaved complex array [Re(0),Im(0),Re(1),Im(1),...]
+!-------------
 SUBROUTINE four1(dataa,nn,isign)
+use MKL_DFTI
 implicit none
-INTEGER::isign,nn
+INTEGER, intent(in) :: isign, nn
-double precision,dimension(2*nn)::dataa
+DOUBLE PRECISION, dimension(2*nn), intent(inout) :: dataa
-INTEGER::i,istep,j,m,mmax,n
+
-double precision::tempi,tempr
+type(DFTI_DESCRIPTOR), pointer :: desc
-DOUBLE PRECISION::theta,wi,wpi,wpr,wr,wtemp
+integer :: status
-n=2*nn
+
-j=1
+! Create DFTI descriptor for 1D complex-to-complex transform
-do i=1,n,2
+status = DftiCreateDescriptor(desc, DFTI_DOUBLE, DFTI_COMPLEX, 1, nn)
-  if(j.gt.i)then
+if (status /= 0) return
-     tempr=dataa(j)
+
-     tempi=dataa(j+1)
+! Set input/output storage as interleaved complex (default)
-     dataa(j)=dataa(i)
+status = DftiSetValue(desc, DFTI_PLACEMENT, DFTI_INPLACE)
-     dataa(j+1)=dataa(i+1)
+if (status /= 0) then
-     dataa(i)=tempr
+   status = DftiFreeDescriptor(desc)
-     dataa(i+1)=tempi
+   return
-  endif
-  m=nn
-1 if ((m.ge.2).and.(j.gt.m)) then
-  j=j-m
-  m=m/2
-goto 1
-  endif
-j=j+m
-enddo
-mmax=2
-2  if (n.gt.mmax) then
-     istep=2*mmax
-     theta=6.28318530717959d0/(isign*mmax)
-     wpr=-2.d0*sin(0.5d0*theta)**2
-     wpi=sin(theta)
-     wr=1.d0
-     wi=0.d0
-     do m=1,mmax,2
-       do i=m,n,istep
-         j=i+mmax
-         tempr=sngl(wr)*dataa(j)-sngl(wi)*dataa(j+1)
-         tempi=sngl(wr)*dataa(j+1)+sngl(wi)*dataa(j)
-         dataa(j)=dataa(i)-tempr
-         dataa(j+1)=dataa(i+1)-tempi
-         dataa(i)=dataa(i)+tempr
-         dataa(i+1)=dataa(i+1)+tempi
-       enddo
-          wtemp=wr
-          wr=wr*wpr-wi*wpi+wr
-          wi=wi*wpr+wtemp*wpi+wi
-     enddo
-mmax=istep
-goto 2
 endif
+
+! Commit the descriptor
+status = DftiCommitDescriptor(desc)
+if (status /= 0) then
+   status = DftiFreeDescriptor(desc)
+   return
+endif
+
+! Execute FFT based on direction
+if (isign == 1) then
+   ! Forward FFT: exp(-2*pi*i*k*n/N)
+   status = DftiComputeForward(desc, dataa)
+else
+   ! Backward FFT: exp(+2*pi*i*k*n/N)
+   status = DftiComputeBackward(desc, dataa)
+endif
+
+! Free descriptor
+status = DftiFreeDescriptor(desc)
+
 return
 END SUBROUTINE four1

AMSS_NCKU_source/Parallel.C

@@ -4320,7 +4320,7 @@ Parallel::SyncCache::SyncCache()
     : valid(false), cpusize(0), combined_src(0), combined_dst(0),
       send_lengths(0), recv_lengths(0), send_bufs(0), recv_bufs(0),
       send_buf_caps(0), recv_buf_caps(0), reqs(0), stats(0), max_reqs(0),
-      lengths_valid(false), tc_req_node(0), tc_req_is_recv(0), tc_completed(0)
+      lengths_valid(false)
 {
 }
 // SyncCache invalidate: free grid segment lists but keep buffers
@@ -4359,15 +4359,11 @@ void Parallel::SyncCache::destroy()
   if (recv_bufs) delete[] recv_bufs;
   if (reqs) delete[] reqs;
   if (stats) delete[] stats;
-  if (tc_req_node) delete[] tc_req_node;
-  if (tc_req_is_recv) delete[] tc_req_is_recv;
-  if (tc_completed) delete[] tc_completed;
   combined_src = combined_dst = 0;
   send_lengths = recv_lengths = 0;
   send_buf_caps = recv_buf_caps = 0;
   send_bufs = recv_bufs = 0;
   reqs = 0; stats = 0;
-  tc_req_node = 0; tc_req_is_recv = 0; tc_completed = 0;
   cpusize = 0; max_reqs = 0;
 }
 // transfer_cached: reuse pre-allocated buffers from SyncCache
@@ -4383,9 +4379,9 @@ void Parallel::transfer_cached(MyList<Parallel::gridseg> **src, MyList<Parallel:
   int req_no = 0;
   int pending_recv = 0;
   int node;
-  int *req_node = cache.tc_req_node;
+  int *req_node = new int[cache.max_reqs];
-  int *req_is_recv = cache.tc_req_is_recv;
+  int *req_is_recv = new int[cache.max_reqs];
-  int *completed = cache.tc_completed;
+  int *completed = new int[cache.max_reqs];
 
   // Post receives first so peers can progress rendezvous early.
   for (node = 0; node < cpusize; node++)
@@ -4470,7 +4466,12 @@ void Parallel::transfer_cached(MyList<Parallel::gridseg> **src, MyList<Parallel:
 
   if (self_len > 0)
     data_packer(cache.recv_bufs[myrank], src[myrank], dst[myrank], myrank, UNPACK, VarList1, VarList2, Symmetry);
+
+  delete[] req_node;
+  delete[] req_is_recv;
+  delete[] completed;
 }
+// Sync_cached: build grid segment lists on first call, reuse on subsequent calls
 void Parallel::Sync_cached(MyList<Patch> *PatL, MyList<var> *VarList, int Symmetry, SyncCache &cache)
 {
   if (!cache.valid)
@@ -4498,9 +4499,6 @@ void Parallel::Sync_cached(MyList<Patch> *PatL, MyList<var> *VarList, int Symmet
       cache.max_reqs = 2 * cpusize;
       cache.reqs = new MPI_Request[cache.max_reqs];
       cache.stats = new MPI_Status[cache.max_reqs];
-      cache.tc_req_node = new int[cache.max_reqs];
-      cache.tc_req_is_recv = new int[cache.max_reqs];
-      cache.tc_completed = new int[cache.max_reqs];
     }
 
     for (int node = 0; node < cpusize; node++)
@@ -4601,9 +4599,6 @@ void Parallel::Sync_start(MyList<Patch> *PatL, MyList<var> *VarList, int Symmetr
       cache.max_reqs = 2 * cpusize;
       cache.reqs = new MPI_Request[cache.max_reqs];
       cache.stats = new MPI_Status[cache.max_reqs];
-      cache.tc_req_node = new int[cache.max_reqs];
-      cache.tc_req_is_recv = new int[cache.max_reqs];
-      cache.tc_completed = new int[cache.max_reqs];
     }
 
     for (int node = 0; node < cpusize; node++)
@@ -4674,11 +4669,6 @@ void Parallel::Sync_start(MyList<Patch> *PatL, MyList<var> *VarList, int Symmetr
   int cpusize = cache.cpusize;
   state.req_no = 0;
   state.active = true;
-  state.pending_recv = 0;
-  // Allocate tracking arrays
-  delete[] state.req_node; delete[] state.req_is_recv;
-  state.req_node = new int[cache.max_reqs];
-  state.req_is_recv = new int[cache.max_reqs];
 
   MyList<Parallel::gridseg> **src = cache.combined_src;
   MyList<Parallel::gridseg> **dst = cache.combined_dst;
@@ -4723,8 +4713,6 @@ void Parallel::Sync_start(MyList<Patch> *PatL, MyList<var> *VarList, int Symmetr
           cache.send_buf_caps[node] = slength;
         }
         data_packer(cache.send_bufs[node], src[myrank], dst[myrank], node, PACK, VarList, VarList, Symmetry);
-        state.req_node[state.req_no] = node;
-        state.req_is_recv[state.req_no] = 0;
         MPI_Isend((void *)cache.send_bufs[node], slength, MPI_DOUBLE, node, 2, MPI_COMM_WORLD, cache.reqs + state.req_no++);
       }
       int rlength;
@@ -4742,60 +4730,29 @@ void Parallel::Sync_start(MyList<Patch> *PatL, MyList<var> *VarList, int Symmetr
           cache.recv_bufs[node] = new double[rlength];
           cache.recv_buf_caps[node] = rlength;
         }
-        state.req_node[state.req_no] = node;
-        state.req_is_recv[state.req_no] = 1;
-        state.pending_recv++;
         MPI_Irecv((void *)cache.recv_bufs[node], rlength, MPI_DOUBLE, node, 2, MPI_COMM_WORLD, cache.reqs + state.req_no++);
       }
     }
   }
   cache.lengths_valid = true;
 }
-// Sync_finish: progressive unpack as receives complete, then wait for sends
+// Sync_finish: wait for async MPI operations and unpack
 void Parallel::Sync_finish(SyncCache &cache, AsyncSyncState &state,
                            MyList<var> *VarList, int Symmetry)
 {
   if (!state.active)
     return;
 
-  int myrank;
+  MPI_Waitall(state.req_no, cache.reqs, cache.stats);
-  MPI_Comm_rank(MPI_COMM_WORLD, &myrank);
+
+  int cpusize = cache.cpusize;
   MyList<Parallel::gridseg> **src = cache.combined_src;
   MyList<Parallel::gridseg> **dst = cache.combined_dst;
 
-  // Unpack local data first (no MPI needed)
+  for (int node = 0; node < cpusize; node++)
-  if (cache.recv_bufs[myrank] && cache.recv_lengths[myrank] > 0)
+    if (cache.recv_bufs[node] && cache.recv_lengths[node] > 0)
-    data_packer(cache.recv_bufs[myrank], src[myrank], dst[myrank], myrank, UNPACK, VarList, VarList, Symmetry);
+      data_packer(cache.recv_bufs[node], src[node], dst[node], node, UNPACK, VarList, VarList, Symmetry);
 
-  // Progressive unpack of remote receives
-  if (state.pending_recv > 0 && state.req_no > 0)
-  {
-    int pending = state.pending_recv;
-    int *completed = new int[cache.max_reqs];
-    while (pending > 0)
-    {
-      int outcount = 0;
-      MPI_Waitsome(state.req_no, cache.reqs, &outcount, completed, cache.stats);
-      if (outcount == MPI_UNDEFINED) break;
-      for (int i = 0; i < outcount; i++)
-      {
-        int idx = completed[i];
-        if (idx >= 0 && state.req_is_recv[idx])
-        {
-          int recv_node = state.req_node[idx];
-          data_packer(cache.recv_bufs[recv_node], src[recv_node], dst[recv_node], recv_node, UNPACK, VarList, VarList, Symmetry);
-          pending--;
-        }
-      }
-    }
-    delete[] completed;
-  }
-
-  // Wait for remaining sends
-  if (state.req_no > 0) MPI_Waitall(state.req_no, cache.reqs, cache.stats);
-
-  delete[] state.req_node; state.req_node = 0;
-  delete[] state.req_is_recv; state.req_is_recv = 0;
   state.active = false;
 }
 // collect buffer grid segments or blocks for the periodic boundary condition of given patch
@@ -5284,41 +5241,6 @@ double Parallel::L2Norm(Patch *Pat, var *vf)
 
   return tvf;
 }
-void Parallel::L2Norm7(Patch *Pat, var **vf, double *norms)
-{
-  int myrank;
-  MPI_Comm_rank(MPI_COMM_WORLD, &myrank);
-
-  double tvf[7], dtvf[7];
-  int BDW = ghost_width;
-  for (int i = 0; i < 7; i++)
-    dtvf[i] = 0;
-
-  MyList<Block> *BP = Pat->blb;
-  while (BP)
-  {
-    Block *cg = BP->data;
-    if (myrank == cg->rank)
-    {
-      f_l2normhelper7(cg->shape, cg->X[0], cg->X[1], cg->X[2],
-                      Pat->bbox[0], Pat->bbox[1], Pat->bbox[2],
-                      Pat->bbox[3], Pat->bbox[4], Pat->bbox[5],
-                      cg->fgfs[vf[0]->sgfn], cg->fgfs[vf[1]->sgfn], cg->fgfs[vf[2]->sgfn],
-                      cg->fgfs[vf[3]->sgfn], cg->fgfs[vf[4]->sgfn], cg->fgfs[vf[5]->sgfn],
-                      cg->fgfs[vf[6]->sgfn], tvf, BDW);
-      for (int i = 0; i < 7; i++)
-        dtvf[i] += tvf[i];
-    }
-    if (BP == Pat->ble)
-      break;
-    BP = BP->next;
-  }
-
-  MPI_Allreduce(dtvf, tvf, 7, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
-
-  for (int i = 0; i < 7; i++)
-    norms[i] = sqrt(tvf[i]);
-}
 double Parallel::L2Norm(Patch *Pat, var *vf, MPI_Comm Comm_here)
 {
   int myrank;
@@ -5350,41 +5272,6 @@ double Parallel::L2Norm(Patch *Pat, var *vf, MPI_Comm Comm_here)
 
   return tvf;
 }
-void Parallel::L2Norm7(Patch *Pat, var **vf, double *norms, MPI_Comm Comm_here)
-{
-  int myrank;
-  MPI_Comm_rank(MPI_COMM_WORLD, &myrank);
-
-  double tvf[7], dtvf[7];
-  int BDW = ghost_width;
-  for (int i = 0; i < 7; i++)
-    dtvf[i] = 0;
-
-  MyList<Block> *BP = Pat->blb;
-  while (BP)
-  {
-    Block *cg = BP->data;
-    if (myrank == cg->rank)
-    {
-      f_l2normhelper7(cg->shape, cg->X[0], cg->X[1], cg->X[2],
-                      Pat->bbox[0], Pat->bbox[1], Pat->bbox[2],
-                      Pat->bbox[3], Pat->bbox[4], Pat->bbox[5],
-                      cg->fgfs[vf[0]->sgfn], cg->fgfs[vf[1]->sgfn], cg->fgfs[vf[2]->sgfn],
-                      cg->fgfs[vf[3]->sgfn], cg->fgfs[vf[4]->sgfn], cg->fgfs[vf[5]->sgfn],
-                      cg->fgfs[vf[6]->sgfn], tvf, BDW);
-      for (int i = 0; i < 7; i++)
-        dtvf[i] += tvf[i];
-    }
-    if (BP == Pat->ble)
-      break;
-    BP = BP->next;
-  }
-
-  MPI_Allreduce(dtvf, tvf, 7, MPI_DOUBLE, MPI_SUM, Comm_here);
-
-  for (int i = 0; i < 7; i++)
-    norms[i] = sqrt(tvf[i]);
-}
 void Parallel::checkgsl(MyList<Parallel::gridseg> *pp, bool first_only)
 {
   int myrank = 0;
@@ -5932,9 +5819,6 @@ void Parallel::Restrict_cached(MyList<Patch> *PatcL, MyList<Patch> *PatfL,
       cache.max_reqs = 2 * cpusize;
       cache.reqs = new MPI_Request[cache.max_reqs];
       cache.stats = new MPI_Status[cache.max_reqs];
-      cache.tc_req_node = new int[cache.max_reqs];
-      cache.tc_req_is_recv = new int[cache.max_reqs];
-      cache.tc_completed = new int[cache.max_reqs];
     }
 
     MyList<Parallel::gridseg> *dst = build_complete_gsl(PatcL);
@@ -5981,9 +5865,6 @@ void Parallel::OutBdLow2Hi_cached(MyList<Patch> *PatcL, MyList<Patch> *PatfL,
       cache.max_reqs = 2 * cpusize;
       cache.reqs = new MPI_Request[cache.max_reqs];
       cache.stats = new MPI_Status[cache.max_reqs];
-      cache.tc_req_node = new int[cache.max_reqs];
-      cache.tc_req_is_recv = new int[cache.max_reqs];
-      cache.tc_completed = new int[cache.max_reqs];
     }
 
     MyList<Parallel::gridseg> *dst = build_buffer_gsl(PatfL);
@@ -6030,9 +5911,6 @@ void Parallel::OutBdLow2Himix_cached(MyList<Patch> *PatcL, MyList<Patch> *PatfL,
       cache.max_reqs = 2 * cpusize;
       cache.reqs = new MPI_Request[cache.max_reqs];
       cache.stats = new MPI_Status[cache.max_reqs];
-      cache.tc_req_node = new int[cache.max_reqs];
-      cache.tc_req_is_recv = new int[cache.max_reqs];
-      cache.tc_completed = new int[cache.max_reqs];
     }
 
     MyList<Parallel::gridseg> *dst = build_buffer_gsl(PatfL);

AMSS_NCKU_source/Parallel.h

@@ -108,9 +108,6 @@ namespace Parallel
     MPI_Status *stats;
     int max_reqs;
     bool lengths_valid;
-    int *tc_req_node;
-    int *tc_req_is_recv;
-    int *tc_completed;
     SyncCache();
     void invalidate();
     void destroy();
@@ -124,10 +121,7 @@ namespace Parallel
   struct AsyncSyncState {
     int req_no;
     bool active;
-    int *req_node;
+    AsyncSyncState() : req_no(0), active(false) {}
-    int *req_is_recv;
-    int pending_recv;
-    AsyncSyncState() : req_no(0), active(false), req_node(0), req_is_recv(0), pending_recv(0) {}
   };
 
   void Sync_start(MyList<Patch> *PatL, MyList<var> *VarList, int Symmetry,
@@ -183,7 +177,6 @@ namespace Parallel
                          MyList<Parallel::gridseg> **out_src, MyList<Parallel::gridseg> **out_dst);
   void PeriodicBD(Patch *Pat, MyList<var> *VarList, int Symmetry);
   double L2Norm(Patch *Pat, var *vf);
-  void L2Norm7(Patch *Pat, var **vf, double *norms);
   void checkgsl(MyList<Parallel::gridseg> *pp, bool first_only);
   void checkvarl(MyList<var> *pp, bool first_only);
   MyList<Parallel::gridseg> *divide_gsl(MyList<Parallel::gridseg> *p, Patch *Pat);
@@ -219,7 +212,6 @@ namespace Parallel
   void checkpatchlist(MyList<Patch> *PatL, bool buflog);
 
   double L2Norm(Patch *Pat, var *vf, MPI_Comm Comm_here);
-  void L2Norm7(Patch *Pat, var **vf, double *norms, MPI_Comm Comm_here);
   bool PatList_Interp_Points(MyList<Patch> *PatL, MyList<var> *VarList,
                              int NN, double **XX,
                              double *Shellf, int Symmetry, MPI_Comm Comm_here);

AMSS_NCKU_source/ShellPatch.C

@@ -3472,43 +3472,6 @@ double ShellPatch::L2Norm(var *vf)
 
   return tvf;
 }
-void ShellPatch::L2Norm7(var **vf, double *norms)
-{
-  double tvf[7], dtvf[7];
-  int BDW = overghost;
-  for (int i = 0; i < 7; i++)
-    dtvf[i] = 0;
-
-  MyList<ss_patch> *sPp = PatL;
-  while (sPp)
-  {
-    MyList<Block> *Bp = sPp->data->blb;
-    while (Bp)
-    {
-      Block *cg = Bp->data;
-      if (myrank == cg->rank)
-      {
-        f_l2normhelper7(cg->shape, cg->X[0], cg->X[1], cg->X[2],
-                        sPp->data->bbox[0], sPp->data->bbox[1], sPp->data->bbox[2],
-                        sPp->data->bbox[3], sPp->data->bbox[4], sPp->data->bbox[5],
-                        cg->fgfs[vf[0]->sgfn], cg->fgfs[vf[1]->sgfn], cg->fgfs[vf[2]->sgfn],
-                        cg->fgfs[vf[3]->sgfn], cg->fgfs[vf[4]->sgfn], cg->fgfs[vf[5]->sgfn],
-                        cg->fgfs[vf[6]->sgfn], tvf, BDW);
-        for (int i = 0; i < 7; i++)
-          dtvf[i] += tvf[i];
-      }
-      if (Bp == sPp->data->ble)
-        break;
-      Bp = Bp->next;
-    }
-    sPp = sPp->next;
-  }
-
-  MPI_Allreduce(dtvf, tvf, 7, MPI_DOUBLE, MPI_SUM, MPI_COMM_WORLD);
-
-  for (int i = 0; i < 7; i++)
-    norms[i] = sqrt(tvf[i]);
-}
 
 // find maximum of abstract value, XX store position for maximum, Shellf store maximum themselvs
 void ShellPatch::Find_Maximum(MyList<var> *VarList, double *XX,

AMSS_NCKU_source/ShellPatch.h

@@ -198,7 +198,6 @@ public:
    void write_Pablo_file_ss(int *ext, double xmin, double xmax, double ymin, double ymax, double zmin, double zmax,
                             char *filename, int sst);
    double L2Norm(var *vf);
-   void L2Norm7(var **vf, double *norms);
    void Find_Maximum(MyList<var> *VarList, double *XX, double *Shellf);
 };
 

AMSS_NCKU_source/TwoPunctures.C

@@ -27,21 +27,7 @@ using namespace std;
 #endif
 
 #include "TwoPunctures.h"
-
+#include <mkl_cblas.h>
-extern "C" {
-double cblas_ddot(const int, const double *, const int, const double *, const int);
-double cblas_dnrm2(const int, const double *, const int);
-void cblas_dgemm(const int, const int, const int,
-                 const int, const int, const int,
-                 const double, const double *, const int,
-                 const double *, const int, const double,
-                 double *, const int);
-}
-
-enum {
-  CblasRowMajor = 101,
-  CblasNoTrans = 111
-};
 
 TwoPunctures::TwoPunctures(double mp, double mm, double b,
                            double P_plusx, double P_plusy, double P_plusz,

AMSS_NCKU_source/bssn_class.C

@@ -41,239 +41,6 @@ using namespace std;
 #include "derivatives.h"
 #include "ricci_gamma.h"
 
-// Compile-time switch for per-timestep memory usage collection/printing.
-// Default is OFF to reduce overhead in production runs.
-#ifndef BSSN_ENABLE_MEM_USAGE_LOG
-#define BSSN_ENABLE_MEM_USAGE_LOG 0
-#endif
-
-#ifndef BSSN_FINE_TIMING
-#define BSSN_FINE_TIMING 0
-#endif
-
-#ifndef BSSN_FINE_TIMING_EVERY
-#define BSSN_FINE_TIMING_EVERY 1
-#endif
-
-#ifndef BSSN_FINE_TIMING_TOPN
-#define BSSN_FINE_TIMING_TOPN 8
-#endif
-
-#ifndef BSSN_KERNEL_FINE_TIMING
-#define BSSN_KERNEL_FINE_TIMING 0
-#endif
-
-#ifndef BSSN_ENABLE_STDIN_ABORT_POLL
-#define BSSN_ENABLE_STDIN_ABORT_POLL 0
-#endif
-
-#if BSSN_FINE_TIMING
-namespace step_timing
-{
-  enum Bucket
-  {
-    TB_ANALYSIS_PSI4 = 0,
-    TB_ANALYSIS_SURFACE,
-    TB_ANALYSIS_IO,
-    TB_BH_PREDICTOR,
-    TB_PREDICTOR_RHS,
-    TB_PREDICTOR_SYNC,
-    TB_BH_CORRECTOR,
-    TB_CORRECTOR_RHS,
-    TB_CORRECTOR_SYNC,
-    TB_STATE_SWAP,
-    TB_RESTRICT_PROLONG,
-    TB_CONSTRAINT_OUT,
-    TB_DUMP_3D,
-    TB_DUMP_2D,
-    TB_CHECKPOINT,
-    TB_REGRID,
-    TB_COUNT
-  };
-
-  static double local_bucket_seconds[TB_COUNT];
-
-  static const char *bucket_labels[TB_COUNT] =
-  {
-    "analysis_psi4",
-    "analysis_surface",
-    "analysis_io",
-    "bh_predictor",
-    "predictor_rhs",
-    "predictor_sync",
-    "bh_corrector",
-    "corrector_rhs",
-    "corrector_sync",
-    "state_swap",
-    "restrict_prolong",
-    "constraint_out",
-    "dump_3d",
-    "dump_2d",
-    "checkpoint",
-    "regrid"
-  };
-
-  void reset()
-  {
-    for (int i = 0; i < TB_COUNT; i++)
-      local_bucket_seconds[i] = 0.0;
-  }
-
-  void add(Bucket bucket, double seconds)
-  {
-    local_bucket_seconds[int(bucket)] += seconds;
-  }
-
-  void report(int myrank, int nprocs, monitor *TimingMonitor,
-              int step_index, double phys_time, double step_wall_seconds)
-  {
-    double max_bucket_seconds[TB_COUNT];
-    double avg_bucket_seconds[TB_COUNT];
-
-    MPI_Reduce(local_bucket_seconds, max_bucket_seconds, TB_COUNT, MPI_DOUBLE, MPI_MAX, 0, MPI_COMM_WORLD);
-    MPI_Reduce(local_bucket_seconds, avg_bucket_seconds, TB_COUNT, MPI_DOUBLE, MPI_SUM, 0, MPI_COMM_WORLD);
-
-    if (myrank != 0)
-      return;
-
-    for (int i = 0; i < TB_COUNT; i++)
-      avg_bucket_seconds[i] /= Mymax(1, nprocs);
-
-    if (TimingMonitor)
-    {
-      double row[2 + 2 * TB_COUNT];
-      row[0] = double(step_index);
-      row[1] = step_wall_seconds;
-      for (int i = 0; i < TB_COUNT; i++)
-      {
-        row[2 + i] = max_bucket_seconds[i];
-        row[2 + TB_COUNT + i] = avg_bucket_seconds[i];
-      }
-      TimingMonitor->writefile(phys_time, 2 + 2 * TB_COUNT, row);
-    }
-
-    double residual = step_wall_seconds;
-    for (int i = 0; i < TB_COUNT; i++)
-      residual -= max_bucket_seconds[i];
-    if (residual < 0.0)
-      residual = 0.0;
-
-    int order[TB_COUNT];
-    for (int i = 0; i < TB_COUNT; i++)
-      order[i] = i;
-
-    for (int i = 0; i < TB_COUNT - 1; i++)
-      for (int j = i + 1; j < TB_COUNT; j++)
-        if (max_bucket_seconds[order[j]] > max_bucket_seconds[order[i]])
-        {
-          int tmp = order[i];
-          order[i] = order[j];
-          order[j] = tmp;
-        }
-
-    ios::fmtflags old_flags = cout.flags();
-    streamsize old_precision = cout.precision();
-
-    cout << " Fine timing hot spots (max rank wall estimate):" << endl;
-    const int topn = Mymin(BSSN_FINE_TIMING_TOPN, TB_COUNT);
-    for (int i = 0; i < topn; i++)
-    {
-      const int ib = order[i];
-      const double frac = (step_wall_seconds > 0.0) ? (100.0 * max_bucket_seconds[ib] / step_wall_seconds) : 0.0;
-      cout << "  "
-           << setw(20) << left << bucket_labels[ib]
-           << " = " << setw(10) << right << setprecision(6) << max_bucket_seconds[ib]
-           << " s  (" << setw(6) << setprecision(4) << frac << "%)" << endl;
-    }
-    if (residual > 1.0e-6)
-    {
-      const double frac = (step_wall_seconds > 0.0) ? (100.0 * residual / step_wall_seconds) : 0.0;
-      cout << "  "
-           << setw(20) << left << "unprofiled_residual"
-           << " = " << setw(10) << right << setprecision(6) << residual
-           << " s  (" << setw(6) << setprecision(4) << frac << "%)" << endl;
-    }
-    cout << endl;
-    cout.flags(old_flags);
-    cout.precision(old_precision);
-  }
-}
-
-#define STEP_TIMER_DECL(var_name) const double var_name = MPI_Wtime()
-#define STEP_TIMER_ADD(bucket_name, var_name) step_timing::add(step_timing::bucket_name, MPI_Wtime() - (var_name))
-#else
-#define STEP_TIMER_DECL(var_name)
-#define STEP_TIMER_ADD(bucket_name, var_name)
-#endif
-
-#if BSSN_KERNEL_FINE_TIMING
-namespace rhs_kernel_timing_report
-{
-  void report(int myrank, int nprocs, int step_index, double step_wall_seconds)
-  {
-    const int bucket_count = f_bssn_rhs_kernel_timing_bucket_count();
-    const double *local_bucket_seconds = f_bssn_rhs_kernel_timing_local_seconds();
-
-    if (bucket_count <= 0 || !local_bucket_seconds)
-      return;
-
-    double *max_bucket_seconds = new double[bucket_count];
-    double *avg_bucket_seconds = new double[bucket_count];
-    int *order = new int[bucket_count];
-
-    MPI_Reduce((void *)local_bucket_seconds, max_bucket_seconds, bucket_count, MPI_DOUBLE, MPI_MAX, 0, MPI_COMM_WORLD);
-    MPI_Reduce((void *)local_bucket_seconds, avg_bucket_seconds, bucket_count, MPI_DOUBLE, MPI_SUM, 0, MPI_COMM_WORLD);
-
-    if (myrank == 0)
-    {
-      double kernel_total = 0.0;
-      for (int i = 0; i < bucket_count; ++i)
-      {
-        avg_bucket_seconds[i] /= Mymax(1, nprocs);
-        order[i] = i;
-        kernel_total += max_bucket_seconds[i];
-      }
-
-      for (int i = 0; i < bucket_count - 1; ++i)
-        for (int j = i + 1; j < bucket_count; ++j)
-          if (max_bucket_seconds[order[j]] > max_bucket_seconds[order[i]])
-          {
-            int tmp = order[i];
-            order[i] = order[j];
-            order[j] = tmp;
-          }
-
-      ios::fmtflags old_flags = cout.flags();
-      streamsize old_precision = cout.precision();
-
-      const double kernel_frac = (step_wall_seconds > 0.0) ? (100.0 * kernel_total / step_wall_seconds) : 0.0;
-      cout << " RHS kernel split (max-rank accumulated over step " << step_index << "): total "
-           << setprecision(6) << kernel_total << " s  (" << setprecision(4)
-           << kernel_frac << "% of coarse step)" << endl;
-
-      const int topn = Mymin(BSSN_FINE_TIMING_TOPN, bucket_count);
-      for (int i = 0; i < topn; ++i)
-      {
-        const int ib = order[i];
-        const double frac = (kernel_total > 0.0) ? (100.0 * max_bucket_seconds[ib] / kernel_total) : 0.0;
-        cout << "  "
-             << setw(20) << left << f_bssn_rhs_kernel_timing_label(ib)
-             << " = " << setw(10) << right << setprecision(6) << max_bucket_seconds[ib]
-             << " s  (" << setw(6) << setprecision(4) << frac << "% of kernel)" << endl;
-      }
-      cout << endl;
-
-      cout.flags(old_flags);
-      cout.precision(old_precision);
-    }
-
-    delete[] max_bucket_seconds;
-    delete[] avg_bucket_seconds;
-    delete[] order;
-  }
-}
-#endif
-
 //================================================================================================
 
 // define bssn_class
@@ -292,7 +59,6 @@ bssn_class::bssn_class(double Couranti, double StartTimei, double TotalTimei,
                          xc(0), yc(0), zc(0), xr(0), yr(0), zr(0), trigger(0), dTT(0), dumpid(0),
 #endif
                          a_lev(a_levi), maxl(maxli), decn(decni), maxrex(maxrexi), drex(drexi),
-                         ConstraintRefreshLevels(0),
                          CheckPoint(0)
                          // CheckPoint(0)
 {
@@ -335,24 +101,6 @@ bssn_class::bssn_class(double Couranti, double StartTimei, double TotalTimei,
     a_stream.str("");
     a_stream << setw(15) << "# time Ham Px Py Pz Gx Gy Gz";
     ConVMonitor = new monitor("bssn_constraint.dat", myrank, a_stream.str());
-
-#if BSSN_FINE_TIMING
-    a_stream.clear();
-    a_stream.str("");
-    a_stream << setw(8) << "# step";
-    a_stream << setw(14) << "wall";
-    for (int ib = 0; ib < step_timing::TB_COUNT; ib++)
-      a_stream << setw(18) << step_timing::bucket_labels[ib];
-    for (int ib = 0; ib < step_timing::TB_COUNT; ib++)
-    {
-      char str_avg[64];
-      sprintf(str_avg, "avg_%s", step_timing::bucket_labels[ib]);
-      a_stream << setw(18) << str_avg;
-    }
-    TimingMonitor = new monitor("bssn_step_timing.dat", myrank, a_stream.str());
-#else
-    TimingMonitor = 0;
-#endif
   }
   // setup sphere integration engine
   Waveshell = new surface_integral(Symmetry);
@@ -948,9 +696,6 @@ void bssn_class::Initialize()
     }
   }
   GH = new cgh(0, ngfs, Symmetry, pname, checkrun, ErrorMonitor);
-  ConstraintRefreshLevels = new int[GH->levels];
-  for (int il = 0; il < GH->levels; il++)
-    ConstraintRefreshLevels[il] = 0;
   if (checkrun)
     CheckPoint->readcheck_cgh(PhysTime, GH, myrank, nprocs, Symmetry);
   else
@@ -991,8 +736,6 @@ void bssn_class::Initialize()
   sync_cache_cor = new Parallel::SyncCache[GH->levels];
   sync_cache_rp_coarse = new Parallel::SyncCache[GH->levels];
   sync_cache_rp_fine = new Parallel::SyncCache[GH->levels];
-  sync_cache_restrict = new Parallel::SyncCache[GH->levels];
-  sync_cache_outbd = new Parallel::SyncCache[GH->levels];
 }
 
 //================================================================================================
@@ -1040,8 +783,6 @@ bssn_class::~bssn_class()
   DumpList->clearList();
   ConstraintList->clearList();
 
-  delete[] ConstraintRefreshLevels;
-
   delete phio;
   delete trKo;
   delete gxxo;
@@ -1301,7 +1042,6 @@ bssn_class::~bssn_class()
   delete BHMonitor;
   delete MAPMonitor;
   delete ConVMonitor;
-  delete TimingMonitor;
   delete Waveshell;
 
   delete CheckPoint;
@@ -2387,10 +2127,8 @@ void bssn_class::Evolve(int Steps)
   #endif
   */
   
-#if BSSN_ENABLE_MEM_USAGE_LOG
   perf bssn_perf;
   size_t current_min, current_avg, current_max, peak_min, peak_avg, peak_max;
-#endif
 
   for (int lev = 0; lev < GH->levels; lev++)
     GH->Lt[lev] = PhysTime;
@@ -2399,15 +2137,6 @@ void bssn_class::Evolve(int Steps)
 
   for (int ncount = 1; ncount < Steps + 1; ncount++)
   {
-#if BSSN_FINE_TIMING
-    step_timing::reset();
-#endif
-#if BSSN_KERNEL_FINE_TIMING
-    f_bssn_rhs_kernel_timing_reset();
-#endif
-#if (BSSN_FINE_TIMING || BSSN_KERNEL_FINE_TIMING)
-    const double step_wall_start = MPI_Wtime();
-#endif
     // special for large mass ratio consideration
     //     if(fabs(Porg0[0][0]-Porg0[1][0])+fabs(Porg0[0][1]-Porg0[1][1])+fabs(Porg0[0][2]-Porg0[1][2])<1e-6) 
     //     { GH->levels=GH->movls; }
@@ -2434,7 +2163,6 @@ void bssn_class::Evolve(int Steps)
     // When LastDump >= DumpTime, output corresponding binary data
     if (LastDump >= DumpTime)
     {
-      STEP_TIMER_DECL(timer_dump3d);
       //       misc::tillherecheck("before Dump_Data");
 
       for (int lev = 0; lev < GH->levels; lev++)
@@ -2442,7 +2170,6 @@ void bssn_class::Evolve(int Steps)
 #ifdef WithShell
       SH->Dump_Data(DumpList, 0, PhysTime, dT_mon);
 #endif
-      STEP_TIMER_ADD(TB_DUMP_3D, timer_dump3d);
 
       LastDump = 0;
 
@@ -2455,12 +2182,10 @@ void bssn_class::Evolve(int Steps)
     // When Last2dDump >= d2DumpTime, output corresponding 2D data
     if (Last2dDump >= d2DumpTime)
     {
-      STEP_TIMER_DECL(timer_dump2d);
       //       misc::tillherecheck("before 2dDump_Data");
 
       for (int lev = 0; lev < GH->levels; lev++)
         Parallel::d2Dump_Data(GH->PatL[lev], DumpList, 0, PhysTime, dT_mon);
-      STEP_TIMER_ADD(TB_DUMP_2D, timer_dump2d);
 
       Last2dDump = 0;
 
@@ -2485,12 +2210,10 @@ void bssn_class::Evolve(int Steps)
       break;
 
 #if (REGLEV == 1)
-    STEP_TIMER_DECL(timer_regrid);
     GH->Regrid(Symmetry, BH_num, Porgbr, Porg0,
                SynchList_cor, OldStateList, StateList, SynchList_pre,
                fgt(PhysTime - dT_mon, StartTime, dT_mon / 2), ErrorMonitor);
-    for (int il = 0; il < GH->levels; il++) { sync_cache_pre[il].invalidate(); sync_cache_cor[il].invalidate(); sync_cache_rp_coarse[il].invalidate(); sync_cache_rp_fine[il].invalidate(); sync_cache_restrict[il].invalidate(); sync_cache_outbd[il].invalidate(); }
+    for (int il = 0; il < GH->levels; il++) { sync_cache_pre[il].invalidate(); sync_cache_cor[il].invalidate(); sync_cache_rp_coarse[il].invalidate(); sync_cache_rp_fine[il].invalidate(); }
-    STEP_TIMER_ADD(TB_REGRID, timer_regrid);
 #endif
 
 #if (REGLEV == 0 && (PSTR == 1 || PSTR == 2))
@@ -2499,7 +2222,6 @@ void bssn_class::Evolve(int Steps)
 //		fgt(PhysTime-dT_mon,StartTime,dT_mon/2),ErrorMonitor);
 #endif
 
-#if BSSN_ENABLE_MEM_USAGE_LOG
     // Retrieve memory usage information used during computation; master process prints it
     bssn_perf.MemoryUsage(&current_min, &current_avg, &current_max,
                           &peak_min, &peak_avg, &peak_max, nprocs);
@@ -2515,7 +2237,6 @@ void bssn_class::Evolve(int Steps)
              (double)peak_max / (1024.0 * 1024.0));
       cout << endl;
     }
-#endif
     
     // Output puncture positions at each step
     if (myrank == 0)
@@ -2530,13 +2251,10 @@ void bssn_class::Evolve(int Steps)
              << endl;
       }
       cout << endl;
-#if BSSN_ENABLE_STDIN_ABORT_POLL
       cout << " If you think the physical evolution time is enough for this simulation, please input 'stop' in the terminal to stop the MPI processes in the next evolution step ! " << endl;
-#endif
       // cout << endl;
     }
     
-#if BSSN_ENABLE_STDIN_ABORT_POLL
     ////////////////////////////////////////////////////////////
     // If an "abort" command is detected on stdin, terminate MPI processes
     ////////////////////////////////////////////////////////////
@@ -2564,12 +2282,10 @@ void bssn_class::Evolve(int Steps)
     }
         
     ////////////////////////////////////////////////////////////
-#endif
 
     // When LastCheck >= CheckTime, perform runtime checks and output status data
     if (LastCheck >= CheckTime)
     {
-      STEP_TIMER_DECL(timer_checkpoint);
       LastCheck = 0;
 
       CheckPoint->write_Black_Hole_position(BH_num_input, BH_num, Porg0, Porgbr, Mass);
@@ -2578,20 +2294,7 @@ void bssn_class::Evolve(int Steps)
       CheckPoint->writecheck_sh(PhysTime, SH);
 #endif
       CheckPoint->write_bssn(LastDump, Last2dDump, LastAnas);
-      STEP_TIMER_ADD(TB_CHECKPOINT, timer_checkpoint);
     }
-
-#if (BSSN_FINE_TIMING || BSSN_KERNEL_FINE_TIMING)
-    const double step_wall_seconds = MPI_Wtime() - step_wall_start;
-#endif
-#if BSSN_FINE_TIMING
-    if (ncount % BSSN_FINE_TIMING_EVERY == 0)
-      step_timing::report(myrank, nprocs, TimingMonitor, ncount, PhysTime, step_wall_seconds);
-#endif
-#if BSSN_KERNEL_FINE_TIMING
-    if (ncount % BSSN_FINE_TIMING_EVERY == 0)
-      rhs_kernel_timing_report::report(myrank, nprocs, ncount, step_wall_seconds);
-#endif
   }
   /*
   #ifdef With_AHF
@@ -2723,16 +2426,10 @@ void bssn_class::RecursiveStep(int lev)
 #endif
 
 #if (REGLEV == 0)
-  STEP_TIMER_DECL(timer_regrid_onelevel);
   if (GH->Regrid_Onelevel(lev, Symmetry, BH_num, Porgbr, Porg0,
                       SynchList_cor, OldStateList, StateList, SynchList_pre,
                       fgt(PhysTime - dT_lev, StartTime, dT_lev / 2), ErrorMonitor))
-  {
+  for (int il = 0; il < GH->levels; il++) { sync_cache_pre[il].invalidate(); sync_cache_cor[il].invalidate(); sync_cache_rp_coarse[il].invalidate(); sync_cache_rp_fine[il].invalidate(); }
-  if (ConstraintRefreshLevels)
-    ConstraintRefreshLevels[lev] = 1;
-  for (int il = 0; il < GH->levels; il++) { sync_cache_pre[il].invalidate(); sync_cache_cor[il].invalidate(); sync_cache_rp_coarse[il].invalidate(); sync_cache_rp_fine[il].invalidate(); sync_cache_restrict[il].invalidate(); sync_cache_outbd[il].invalidate(); }
-  }
-  STEP_TIMER_ADD(TB_REGRID, timer_regrid_onelevel);
 #endif
 }
 
@@ -2911,7 +2608,7 @@ void bssn_class::ParallelStep()
   if (GH->Regrid_Onelevel(GH->mylev, Symmetry, BH_num, Porgbr, Porg0,
                       SynchList_cor, OldStateList, StateList, SynchList_pre,
                       fgt(PhysTime - dT_lev, StartTime, dT_lev / 2), ErrorMonitor))
-  for (int il = 0; il < GH->levels; il++) { sync_cache_pre[il].invalidate(); sync_cache_cor[il].invalidate(); sync_cache_rp_coarse[il].invalidate(); sync_cache_rp_fine[il].invalidate(); sync_cache_restrict[il].invalidate(); sync_cache_outbd[il].invalidate(); }
+  for (int il = 0; il < GH->levels; il++) { sync_cache_pre[il].invalidate(); sync_cache_cor[il].invalidate(); sync_cache_rp_coarse[il].invalidate(); sync_cache_rp_fine[il].invalidate(); }
 #endif
 }
 
@@ -3078,7 +2775,7 @@ void bssn_class::ParallelStep()
         if (GH->Regrid_Onelevel(lev + 1, Symmetry, BH_num, Porgbr, Porg0,
                             SynchList_cor, OldStateList, StateList, SynchList_pre,
                             fgt(PhysTime - dT_levp1, StartTime, dT_levp1 / 2), ErrorMonitor))
-        for (int il = 0; il < GH->levels; il++) { sync_cache_pre[il].invalidate(); sync_cache_cor[il].invalidate(); sync_cache_rp_coarse[il].invalidate(); sync_cache_rp_fine[il].invalidate(); sync_cache_restrict[il].invalidate(); sync_cache_outbd[il].invalidate(); }
+        for (int il = 0; il < GH->levels; il++) { sync_cache_pre[il].invalidate(); sync_cache_cor[il].invalidate(); sync_cache_rp_coarse[il].invalidate(); sync_cache_rp_fine[il].invalidate(); }
 
         //               a_stream.clear();
         //               a_stream.str("");
@@ -3093,7 +2790,7 @@ void bssn_class::ParallelStep()
       if (GH->Regrid_Onelevel(lev, Symmetry, BH_num, Porgbr, Porg0,
                           SynchList_cor, OldStateList, StateList, SynchList_pre,
                           fgt(PhysTime - dT_lev, StartTime, dT_lev / 2), ErrorMonitor))
-      for (int il = 0; il < GH->levels; il++) { sync_cache_pre[il].invalidate(); sync_cache_cor[il].invalidate(); sync_cache_rp_coarse[il].invalidate(); sync_cache_rp_fine[il].invalidate(); sync_cache_restrict[il].invalidate(); sync_cache_outbd[il].invalidate(); }
+      for (int il = 0; il < GH->levels; il++) { sync_cache_pre[il].invalidate(); sync_cache_cor[il].invalidate(); sync_cache_rp_coarse[il].invalidate(); sync_cache_rp_fine[il].invalidate(); }
 
       //               a_stream.clear();
       //               a_stream.str("");
@@ -3112,7 +2809,7 @@ void bssn_class::ParallelStep()
           if (GH->Regrid_Onelevel(lev - 1, Symmetry, BH_num, Porgbr, Porg0,
                               SynchList_cor, OldStateList, StateList, SynchList_pre,
                               fgt(PhysTime - dT_lev, StartTime, dT_levm1 / 2), ErrorMonitor))
-          for (int il = 0; il < GH->levels; il++) { sync_cache_pre[il].invalidate(); sync_cache_cor[il].invalidate(); sync_cache_rp_coarse[il].invalidate(); sync_cache_rp_fine[il].invalidate(); sync_cache_restrict[il].invalidate(); sync_cache_outbd[il].invalidate(); }
+          for (int il = 0; il < GH->levels; il++) { sync_cache_pre[il].invalidate(); sync_cache_cor[il].invalidate(); sync_cache_rp_coarse[il].invalidate(); sync_cache_rp_fine[il].invalidate(); }
 
           //               a_stream.clear();
           //               a_stream.str("");
@@ -3128,7 +2825,7 @@ void bssn_class::ParallelStep()
           if (GH->Regrid_Onelevel(lev - 1, Symmetry, BH_num, Porgbr, Porg0,
                               SynchList_cor, OldStateList, StateList, SynchList_pre,
                               fgt(PhysTime - dT_lev, StartTime, dT_levm1 / 2), ErrorMonitor))
-          for (int il = 0; il < GH->levels; il++) { sync_cache_pre[il].invalidate(); sync_cache_cor[il].invalidate(); sync_cache_rp_coarse[il].invalidate(); sync_cache_rp_fine[il].invalidate(); sync_cache_restrict[il].invalidate(); sync_cache_outbd[il].invalidate(); }
+          for (int il = 0; il < GH->levels; il++) { sync_cache_pre[il].invalidate(); sync_cache_cor[il].invalidate(); sync_cache_rp_coarse[il].invalidate(); sync_cache_rp_fine[il].invalidate(); }
 
           //               a_stream.clear();
           //               a_stream.str("");
@@ -3325,7 +3022,6 @@ void bssn_class::Step(int lev, int YN)
 
 // new code 2013-2-15, zjcao
 #if (MAPBH == 1)
-  STEP_TIMER_DECL(timer_bh_predictor);
   // for black hole position
   if (BH_num > 0 && lev == GH->levels - 1)
   {
@@ -3356,7 +3052,6 @@ void bssn_class::Step(int lev, int YN)
       }
     }
   }
-  STEP_TIMER_ADD(TB_BH_PREDICTOR, timer_bh_predictor);
 
   // data analysis part
   // Warning NOTE: the variables1 are used as temp storege room
@@ -3379,7 +3074,6 @@ void bssn_class::Step(int lev, int YN)
   int ERROR = 0;
 
   MyList<ss_patch> *sPp;
-  STEP_TIMER_DECL(timer_predictor_rhs);
   // Predictor
   MyList<Patch> *Pp = GH->PatL[lev];
   while (Pp)
@@ -3655,9 +3349,6 @@ void bssn_class::Step(int lev, int YN)
   }
 #endif
 
-  STEP_TIMER_ADD(TB_PREDICTOR_RHS, timer_predictor_rhs);
-
-  STEP_TIMER_DECL(timer_predictor_sync);
   Parallel::AsyncSyncState async_pre;
   Parallel::Sync_start(GH->PatL[lev], SynchList_pre, Symmetry, sync_cache_pre[lev], async_pre);
 
@@ -3695,7 +3386,6 @@ void bssn_class::Step(int lev, int YN)
     }
   }
 #endif
-  STEP_TIMER_ADD(TB_PREDICTOR_SYNC, timer_predictor_sync);
 
 #if (MAPBH == 0)
   // for black hole position
@@ -3740,7 +3430,6 @@ void bssn_class::Step(int lev, int YN)
   // corrector
   for (iter_count = 1; iter_count < 4; iter_count++)
   {
-    STEP_TIMER_DECL(timer_corrector_rhs);
     // for RK4: t0, t0+dt/2, t0+dt/2, t0+dt;
     if (iter_count == 1 || iter_count == 3)
       TRK4 += dT_lev / 2;
@@ -4020,9 +3709,6 @@ void bssn_class::Step(int lev, int YN)
     }
 #endif
 
-    STEP_TIMER_ADD(TB_CORRECTOR_RHS, timer_corrector_rhs);
-
-    STEP_TIMER_DECL(timer_corrector_sync);
     Parallel::AsyncSyncState async_cor;
     Parallel::Sync_start(GH->PatL[lev], SynchList_cor, Symmetry, sync_cache_cor[lev], async_cor);
 
@@ -4062,10 +3748,8 @@ void bssn_class::Step(int lev, int YN)
       }
     }
 #endif
-    STEP_TIMER_ADD(TB_CORRECTOR_SYNC, timer_corrector_sync);
 
 #if (MAPBH == 0)
-    STEP_TIMER_DECL(timer_bh_corrector);
     // for black hole position
     if (BH_num > 0 && lev == GH->levels - 1)
     {
@@ -4098,13 +3782,11 @@ void bssn_class::Step(int lev, int YN)
         }
       }
     }
-    STEP_TIMER_ADD(TB_BH_CORRECTOR, timer_bh_corrector);
 #endif
 
     // swap time level
     if (iter_count < 3)
     {
-      STEP_TIMER_DECL(timer_state_swap);
       Pp = GH->PatL[lev];
       while (Pp)
       {
@@ -4151,11 +3833,9 @@ void bssn_class::Step(int lev, int YN)
         }
       }
 #endif
-      STEP_TIMER_ADD(TB_STATE_SWAP, timer_state_swap);
     }
   }
 #if (RPS == 0)
-  STEP_TIMER_DECL(timer_restrict_prolong);
   // mesh refinement boundary part
   RestrictProlong(lev, YN, BB);
 
@@ -4176,7 +3856,6 @@ void bssn_class::Step(int lev, int YN)
   }
 #endif
 
-  STEP_TIMER_ADD(TB_RESTRICT_PROLONG, timer_restrict_prolong);
 #endif
   // note the data structure before update
   // SynchList_cor 1   -----------
@@ -4185,7 +3864,6 @@ void bssn_class::Step(int lev, int YN)
   //
   // OldStateList  old -----------
   // update
-  STEP_TIMER_DECL(timer_state_commit);
   Pp = GH->PatL[lev];
   while (Pp)
   {
@@ -4242,7 +3920,6 @@ void bssn_class::Step(int lev, int YN)
       Porg0[ithBH][2] = Porg1[ithBH][2];
     }
   }
-  STEP_TIMER_ADD(TB_STATE_SWAP, timer_state_commit);
 }
 
 //================================================================================================
@@ -4569,9 +4246,7 @@ void bssn_class::Step(int lev, int YN)
     }
   }
 #endif
-  STEP_TIMER_ADD(TB_PREDICTOR_SYNC, timer_predictor_sync);
 
-  STEP_TIMER_DECL(timer_bh_predictor);
   // for black hole position
   if (BH_num > 0 && lev == GH->levels - 1)
   {
@@ -4610,7 +4285,6 @@ void bssn_class::Step(int lev, int YN)
   {
     AnalysisStuff(lev, dT_lev);
   }
-  STEP_TIMER_ADD(TB_BH_PREDICTOR, timer_bh_predictor);
   // corrector
   for (iter_count = 1; iter_count < 3; iter_count++)
   {
@@ -6081,7 +5755,6 @@ void bssn_class::RestrictProlong(int lev, int YN, bool BB,
 //
 // SynchList_cor  old -----------
 {
-  STEP_TIMER_DECL(timer_restrict_prolong);
 #if (PSTR == 1 || PSTR == 2)
 //  stringstream a_stream;
 //  a_stream.setf(ios::left);
@@ -6123,7 +5796,7 @@ void bssn_class::RestrictProlong(int lev, int YN, bool BB,
 #endif
 
 #if (RPB == 0)
-      Parallel::Restrict_cached(GH->PatL[lev - 1], GH->PatL[lev], SL, SynchList_pre, Symmetry, sync_cache_restrict[lev]);
+      Parallel::Restrict(GH->PatL[lev - 1], GH->PatL[lev], SL, SynchList_pre, Symmetry);
 #elif (RPB == 1)
       //       Parallel::Restrict_bam(GH->PatL[lev-1],GH->PatL[lev],SL,SynchList_pre,Symmetry);
       Parallel::Restrict_bam(GH->PatL[lev - 1], GH->PatL[lev], SL, SynchList_pre, GH->rsul[lev], Symmetry);
@@ -6147,7 +5820,7 @@ void bssn_class::RestrictProlong(int lev, int YN, bool BB,
 
 #if (RPB == 0)
 #if (MIXOUTB == 0)
-      Parallel::OutBdLow2Hi_cached(GH->PatL[lev - 1], GH->PatL[lev], SynchList_pre, SL, Symmetry, sync_cache_outbd[lev]);
+      Parallel::OutBdLow2Hi(GH->PatL[lev - 1], GH->PatL[lev], SynchList_pre, SL, Symmetry);
 #elif (MIXOUTB == 1)
       Parallel::OutBdLow2Himix(GH->PatL[lev - 1], GH->PatL[lev], SynchList_pre, SL, Symmetry);
 #endif
@@ -6174,7 +5847,7 @@ void bssn_class::RestrictProlong(int lev, int YN, bool BB,
 #endif
 
 #if (RPB == 0)
-      Parallel::Restrict_cached(GH->PatL[lev - 1], GH->PatL[lev], SL, SL, Symmetry, sync_cache_restrict[lev]);
+      Parallel::Restrict(GH->PatL[lev - 1], GH->PatL[lev], SL, SL, Symmetry);
 #elif (RPB == 1)
       //       Parallel::Restrict_bam(GH->PatL[lev-1],GH->PatL[lev],SL,SL,Symmetry);
       Parallel::Restrict_bam(GH->PatL[lev - 1], GH->PatL[lev], SL, SL, GH->rsul[lev], Symmetry);
@@ -6198,7 +5871,7 @@ void bssn_class::RestrictProlong(int lev, int YN, bool BB,
 
 #if (RPB == 0)
 #if (MIXOUTB == 0)
-      Parallel::OutBdLow2Hi_cached(GH->PatL[lev - 1], GH->PatL[lev], SL, SL, Symmetry, sync_cache_outbd[lev]);
+      Parallel::OutBdLow2Hi(GH->PatL[lev - 1], GH->PatL[lev], SL, SL, Symmetry);
 #elif (MIXOUTB == 1)
       Parallel::OutBdLow2Himix(GH->PatL[lev - 1], GH->PatL[lev], SL, SL, Symmetry);
 #endif
@@ -6224,7 +5897,6 @@ void bssn_class::RestrictProlong(int lev, int YN, bool BB,
 //    misc::tillherecheck(GH->Commlev[GH->mylev],GH->start_rank[GH->mylev],a_stream.str());
 #endif
   }
-  STEP_TIMER_ADD(TB_RESTRICT_PROLONG, timer_restrict_prolong);
 }
 
 //================================================================================================
@@ -6244,7 +5916,6 @@ void bssn_class::RestrictProlong_aux(int lev, int YN, bool BB,
 //
 // SynchList_cor  old -----------
 {
-  STEP_TIMER_DECL(timer_restrict_prolong);
   //  misc::tillherecheck(GH->Commlev[lev],GH->start_rank[lev],"starting RestrictProlong_aux");
 
   if (lev >= GH->levels - 1)
@@ -6269,7 +5940,7 @@ void bssn_class::RestrictProlong_aux(int lev, int YN, bool BB,
       }
 
 #if (RPB == 0)
-      Parallel::Restrict_cached(GH->PatL[lev - 1], GH->PatL[lev], SL, SynchList_pre, Symmetry, sync_cache_restrict[lev]);
+      Parallel::Restrict(GH->PatL[lev - 1], GH->PatL[lev], SL, SynchList_pre, Symmetry);
 #elif (RPB == 1)
       //       Parallel::Restrict_bam(GH->PatL[lev-1],GH->PatL[lev],SL,SynchList_pre,Symmetry);
       Parallel::Restrict_bam(GH->PatL[lev - 1], GH->PatL[lev], SL, SynchList_pre, GH->rsul[lev], Symmetry);
@@ -6279,7 +5950,7 @@ void bssn_class::RestrictProlong_aux(int lev, int YN, bool BB,
 
 #if (RPB == 0)
 #if (MIXOUTB == 0)
-      Parallel::OutBdLow2Hi_cached(GH->PatL[lev - 1], GH->PatL[lev], SynchList_pre, SL, Symmetry, sync_cache_outbd[lev]);
+      Parallel::OutBdLow2Hi(GH->PatL[lev - 1], GH->PatL[lev], SynchList_pre, SL, Symmetry);
 #elif (MIXOUTB == 1)
       Parallel::OutBdLow2Himix(GH->PatL[lev - 1], GH->PatL[lev], SynchList_pre, SL, Symmetry);
 #endif
@@ -6291,7 +5962,7 @@ void bssn_class::RestrictProlong_aux(int lev, int YN, bool BB,
     else // no time refinement levels and for all same time levels
     {
 #if (RPB == 0)
-      Parallel::Restrict_cached(GH->PatL[lev - 1], GH->PatL[lev], SL, SL, Symmetry, sync_cache_restrict[lev]);
+      Parallel::Restrict(GH->PatL[lev - 1], GH->PatL[lev], SL, SL, Symmetry);
 #elif (RPB == 1)
       //       Parallel::Restrict_bam(GH->PatL[lev-1],GH->PatL[lev],SL,SL,Symmetry);
       Parallel::Restrict_bam(GH->PatL[lev - 1], GH->PatL[lev], SL, SL, GH->rsul[lev], Symmetry);
@@ -6301,7 +5972,7 @@ void bssn_class::RestrictProlong_aux(int lev, int YN, bool BB,
 
 #if (RPB == 0)
 #if (MIXOUTB == 0)
-      Parallel::OutBdLow2Hi_cached(GH->PatL[lev - 1], GH->PatL[lev], SL, SL, Symmetry, sync_cache_outbd[lev]);
+      Parallel::OutBdLow2Hi(GH->PatL[lev - 1], GH->PatL[lev], SL, SL, Symmetry);
 #elif (MIXOUTB == 1)
       Parallel::OutBdLow2Himix(GH->PatL[lev - 1], GH->PatL[lev], SL, SL, Symmetry);
 #endif
@@ -6313,7 +5984,6 @@ void bssn_class::RestrictProlong_aux(int lev, int YN, bool BB,
 
     Parallel::Sync_cached(GH->PatL[lev], SL, Symmetry, sync_cache_rp_fine[lev]);
   }
-  STEP_TIMER_ADD(TB_RESTRICT_PROLONG, timer_restrict_prolong);
 }
 
 //================================================================================================
@@ -6324,7 +5994,6 @@ void bssn_class::RestrictProlong_aux(int lev, int YN, bool BB,
 
 void bssn_class::RestrictProlong(int lev, int YN, bool BB)
 {
-  STEP_TIMER_DECL(timer_restrict_prolong);
   double dT_lev = dT * pow(0.5, Mymax(lev, trfls));
   // we assume  for fine
   // SynchList_cor 1   -----------
@@ -6358,7 +6027,7 @@ void bssn_class::RestrictProlong(int lev, int YN, bool BB)
       }
 
 #if (RPB == 0)
-      Parallel::Restrict_cached(GH->PatL[lev - 1], GH->PatL[lev], SynchList_cor, SynchList_pre, Symmetry, sync_cache_restrict[lev]);
+      Parallel::Restrict(GH->PatL[lev - 1], GH->PatL[lev], SynchList_cor, SynchList_pre, Symmetry);
 #elif (RPB == 1)
       //       Parallel::Restrict_bam(GH->PatL[lev-1],GH->PatL[lev],SynchList_cor,SynchList_pre,Symmetry);
       Parallel::Restrict_bam(GH->PatL[lev - 1], GH->PatL[lev], SynchList_cor, SynchList_pre, GH->rsul[lev], Symmetry);
@@ -6368,7 +6037,7 @@ void bssn_class::RestrictProlong(int lev, int YN, bool BB)
 
 #if (RPB == 0)
 #if (MIXOUTB == 0)
-      Parallel::OutBdLow2Hi_cached(GH->PatL[lev - 1], GH->PatL[lev], SynchList_pre, SynchList_cor, Symmetry, sync_cache_outbd[lev]);
+      Parallel::OutBdLow2Hi(GH->PatL[lev - 1], GH->PatL[lev], SynchList_pre, SynchList_cor, Symmetry);
 #elif (MIXOUTB == 1)
       Parallel::OutBdLow2Himix(GH->PatL[lev - 1], GH->PatL[lev], SynchList_pre, SynchList_cor, Symmetry);
 #endif
@@ -6382,7 +6051,7 @@ void bssn_class::RestrictProlong(int lev, int YN, bool BB)
       if (myrank == 0)
         cout << "===: " << GH->Lt[lev - 1] << "," << GH->Lt[lev] + dT_lev << endl;
 #if (RPB == 0)
-      Parallel::Restrict_cached(GH->PatL[lev - 1], GH->PatL[lev], SynchList_cor, StateList, Symmetry, sync_cache_restrict[lev]);
+      Parallel::Restrict(GH->PatL[lev - 1], GH->PatL[lev], SynchList_cor, StateList, Symmetry);
 #elif (RPB == 1)
       //       Parallel::Restrict_bam(GH->PatL[lev-1],GH->PatL[lev],SynchList_cor,StateList,Symmetry);
       Parallel::Restrict_bam(GH->PatL[lev - 1], GH->PatL[lev], SynchList_cor, StateList, GH->rsul[lev], Symmetry);
@@ -6392,7 +6061,7 @@ void bssn_class::RestrictProlong(int lev, int YN, bool BB)
 
 #if (RPB == 0)
 #if (MIXOUTB == 0)
-      Parallel::OutBdLow2Hi_cached(GH->PatL[lev - 1], GH->PatL[lev], StateList, SynchList_cor, Symmetry, sync_cache_outbd[lev]);
+      Parallel::OutBdLow2Hi(GH->PatL[lev - 1], GH->PatL[lev], StateList, SynchList_cor, Symmetry);
 #elif (MIXOUTB == 1)
       Parallel::OutBdLow2Himix(GH->PatL[lev - 1], GH->PatL[lev], StateList, SynchList_cor, Symmetry);
 #endif
@@ -6404,7 +6073,6 @@ void bssn_class::RestrictProlong(int lev, int YN, bool BB)
 
     Parallel::Sync_cached(GH->PatL[lev], SynchList_cor, Symmetry, sync_cache_rp_fine[lev]);
   }
-  STEP_TIMER_ADD(TB_RESTRICT_PROLONG, timer_restrict_prolong);
 }
 
 //================================================================================================
@@ -6434,7 +6102,7 @@ void bssn_class::ProlongRestrict(int lev, int YN, bool BB)
 
 #if (RPB == 0)
 #if (MIXOUTB == 0)
-      Parallel::OutBdLow2Hi_cached(GH->PatL[lev - 1], GH->PatL[lev], SynchList_pre, SynchList_cor, Symmetry, sync_cache_outbd[lev]);
+      Parallel::OutBdLow2Hi(GH->PatL[lev - 1], GH->PatL[lev], SynchList_pre, SynchList_cor, Symmetry);
 #elif (MIXOUTB == 1)
       Parallel::OutBdLow2Himix(GH->PatL[lev - 1], GH->PatL[lev], SynchList_pre, SynchList_cor, Symmetry);
 #endif
@@ -6447,7 +6115,7 @@ void bssn_class::ProlongRestrict(int lev, int YN, bool BB)
     {
 #if (RPB == 0)
 #if (MIXOUTB == 0)
-      Parallel::OutBdLow2Hi_cached(GH->PatL[lev - 1], GH->PatL[lev], StateList, SynchList_cor, Symmetry, sync_cache_outbd[lev]);
+      Parallel::OutBdLow2Hi(GH->PatL[lev - 1], GH->PatL[lev], StateList, SynchList_cor, Symmetry);
 #elif (MIXOUTB == 1)
       Parallel::OutBdLow2Himix(GH->PatL[lev - 1], GH->PatL[lev], StateList, SynchList_cor, Symmetry);
 #endif
@@ -7155,15 +6823,18 @@ void bssn_class::compute_Porg_rhs(double **BH_PS,double **BH_RHS,var *forx,var *
 
 void bssn_class::compute_Porg_rhs(double **BH_PS, double **BH_RHS, var *forx, var *fory, var *forz, int ilev)
 {
-  MyList<var> DG_List_x(forx);
+  const int InList = 3;
-  MyList<var> DG_List_y(fory);
-  MyList<var> DG_List_z(forz);
-  DG_List_x.next = &DG_List_y;
-  DG_List_y.next = &DG_List_z;
 
-  double shellf[3];
+  MyList<var> *DG_List = new MyList<var>(forx);
-  double pox_buf[3][1];
+  DG_List->insert(fory);
-  double *pox[3] = {pox_buf[0], pox_buf[1], pox_buf[2]};
+  DG_List->insert(forz);
+
+  double *x1, *y1, *z1;
+  double *shellf;
+  shellf = new double[3];
+  double *pox[3];
+  for (int i = 0; i < 3; i++)
+    pox[i] = new double[1];
 
   for (int n = 0; n < BH_num; n++)
   {
@@ -7174,9 +6845,9 @@ void bssn_class::compute_Porg_rhs(double **BH_PS, double **BH_RHS, var *forx, va
     int lev = ilev;
 
 #if (PSTR == 0)
-    while (!Parallel::PatList_Interp_Points(GH->PatL[lev], &DG_List_x, 1, pox, shellf, Symmetry))
+    while (!Parallel::PatList_Interp_Points(GH->PatL[lev], DG_List, 1, pox, shellf, Symmetry))
 #elif (PSTR == 1 || PSTR == 2 || PSTR == 3)
-    while (!Parallel::PatList_Interp_Points(GH->PatL[lev], &DG_List_x, 1, pox, shellf, Symmetry, GH->Commlev[lev]))
+    while (!Parallel::PatList_Interp_Points(GH->PatL[lev], DG_List, 1, pox, shellf, Symmetry, GH->Commlev[lev]))
 #endif
     {
       lev--;
@@ -7185,7 +6856,7 @@ void bssn_class::compute_Porg_rhs(double **BH_PS, double **BH_RHS, var *forx, va
         ErrorMonitor->outfile << "fail to find black holes at t = " << PhysTime << endl;
         for (n = 0; n < BH_num; n++)
           ErrorMonitor->outfile << "(x,y,z) = (" 
-                                << BH_PS[n][0] << "," << BH_PS[n][1] << "," << BH_PS[n][2] 
+                                << pox[0][n] << "," << pox[1][n] << "," << pox[2][n] 
                                 << ")" << endl;
         break;
       }
@@ -7198,6 +6869,11 @@ void bssn_class::compute_Porg_rhs(double **BH_PS, double **BH_RHS, var *forx, va
       BH_RHS[n][2] = -shellf[2];
     }
   }
+
+  DG_List->clearList();
+  delete[] shellf;
+  for (int i = 0; i < 3; i++)
+    delete[] pox[i];
 }
 #endif
 
@@ -7420,10 +7096,6 @@ void bssn_class::AnalysisStuff(int lev, double dT_lev)
     IP = new double[NN];
     RoutMAP = new double[7];
     double Rex = maxrex;
-    bool patch_mass_prepared = false;
-#ifdef WithShell
-    bool shell_mass_prepared = false;
-#endif
     for (int i = 0; i < decn; i++)
     {
 #ifdef Point_Psi4
@@ -7451,8 +7123,7 @@ void bssn_class::AnalysisStuff(int lev, double dT_lev)
                                  gxx0, gxy0, gxz0, gyy0, gyz0, gzz0,
                                  Axx0, Axy0, Axz0, Ayy0, Ayz0, Azz0,
                                  Gmx0, Gmy0, Gmz0, Sfx1, Sfy1, Sfz1, // here we can not touch rhs variables, but 1 variables
-                                 RoutMAP, ErrorMonitor, !patch_mass_prepared);
+                                 RoutMAP, ErrorMonitor);
-        patch_mass_prepared = true;
       }
       else
       {
@@ -7460,52 +7131,44 @@ void bssn_class::AnalysisStuff(int lev, double dT_lev)
                                  gxx0, gxy0, gxz0, gyy0, gyz0, gzz0,
                                  Axx0, Axy0, Axz0, Ayy0, Ayz0, Azz0,
                                  Gmx0, Gmy0, Gmz0, Sfx1, Sfy1, Sfz1, // here we can not touch rhs variables, but 1 variables
-                                 RoutMAP, ErrorMonitor, !shell_mass_prepared);
+                                 RoutMAP, ErrorMonitor);
-        shell_mass_prepared = true;
       }
 #else
       Waveshell->surf_MassPAng(Rex, lev, GH, phi0, trK0,
                                gxx0, gxy0, gxz0, gyy0, gyz0, gzz0,
                                Axx0, Axy0, Axz0, Ayy0, Ayz0, Azz0,
                                Gmx0, Gmy0, Gmz0, Sfx1, Sfy1, Sfz1, // here we can not touch rhs variables, but 1 variables
-                               RoutMAP, ErrorMonitor, !patch_mass_prepared);
+                               RoutMAP, ErrorMonitor);
-      patch_mass_prepared = true;
 #endif
 #else
 //        misc::tillherecheck(GH->Commlev[lev],GH->start_rank[lev],"before surface integral");
 #ifdef WithShell
       if (lev > 0 || Rex < GH->bbox[0][0][3])
       {
-        Waveshell->surf_WaveMassPAng(Rex, lev, GH,
+        Waveshell->surf_Wave(Rex, lev, GH, Rpsi4, Ipsi4, 2, maxl, NN, RP, IP, ErrorMonitor);
-                                     Rpsi4, Ipsi4, 2, maxl, NN, RP, IP,
+        Waveshell->surf_MassPAng(Rex, lev, GH, phi0, trK0,
-                                     phi0, trK0,
+                                 gxx0, gxy0, gxz0, gyy0, gyz0, gzz0,
-                                     gxx0, gxy0, gxz0, gyy0, gyz0, gzz0,
+                                 Axx0, Axy0, Axz0, Ayy0, Ayz0, Azz0,
-                                     Axx0, Axy0, Axz0, Ayy0, Ayz0, Azz0,
+                                 Gmx0, Gmy0, Gmz0, Sfx1, Sfy1, Sfz1, // here we can not touch rhs variables, but 1 variables
-                                     Gmx0, Gmy0, Gmz0, Sfx1, Sfy1, Sfz1,
+                                 RoutMAP, ErrorMonitor);
-                                     RoutMAP, ErrorMonitor, !patch_mass_prepared);
-        patch_mass_prepared = true;
       }
       else
       {
-        Waveshell->surf_WaveMassPAng(Rex, lev, SH,
+        Waveshell->surf_Wave(Rex, lev, SH, Rpsi4, Ipsi4, 2, maxl, NN, RP, IP, ErrorMonitor);
-                                     Rpsi4, Ipsi4, 2, maxl, NN, RP, IP,
+        Waveshell->surf_MassPAng(Rex, lev, SH, phi0, trK0,
-                                     phi0, trK0,
+                                 gxx0, gxy0, gxz0, gyy0, gyz0, gzz0,
-                                     gxx0, gxy0, gxz0, gyy0, gyz0, gzz0,
+                                 Axx0, Axy0, Axz0, Ayy0, Ayz0, Azz0,
-                                     Axx0, Axy0, Axz0, Ayy0, Ayz0, Azz0,
+                                 Gmx0, Gmy0, Gmz0, Sfx1, Sfy1, Sfz1, // here we can not touch rhs variables, but 1 variables
-                                     Gmx0, Gmy0, Gmz0, Sfx1, Sfy1, Sfz1,
+                                 RoutMAP, ErrorMonitor);
-                                     RoutMAP, ErrorMonitor, !shell_mass_prepared);
-        shell_mass_prepared = true;
       }
 #else
 #if (PSTR == 0)
-      Waveshell->surf_WaveMassPAng(Rex, lev, GH,
+      Waveshell->surf_Wave(Rex, lev, GH, Rpsi4, Ipsi4, 2, maxl, NN, RP, IP, ErrorMonitor);
-                                   Rpsi4, Ipsi4, 2, maxl, NN, RP, IP,
+      Waveshell->surf_MassPAng(Rex, lev, GH, phi0, trK0,
-                                   phi0, trK0,
+                               gxx0, gxy0, gxz0, gyy0, gyz0, gzz0,
-                                   gxx0, gxy0, gxz0, gyy0, gyz0, gzz0,
+                               Axx0, Axy0, Axz0, Ayy0, Ayz0, Azz0,
-                                   Axx0, Axy0, Axz0, Ayy0, Ayz0, Azz0,
+                               Gmx0, Gmy0, Gmz0, Sfx1, Sfy1, Sfz1, // here we can not touch rhs variables, but 1 variables
-                                   Gmx0, Gmy0, Gmz0, Sfx1, Sfy1, Sfz1,
+                               RoutMAP, ErrorMonitor);
-                                   RoutMAP, ErrorMonitor, !patch_mass_prepared);
-      patch_mass_prepared = true;
 #elif (PSTR == 1 || PSTR == 2)
       Waveshell->surf_Wave(Rex, lev, GH, Rpsi4, Ipsi4, 2, maxl, NN, RP, IP, ErrorMonitor, GH->Commlev[lev]);
       //        misc::tillherecheck(GH->Commlev[lev],GH->start_rank[lev],"after surf_Wave");
@@ -7513,8 +7176,7 @@ void bssn_class::AnalysisStuff(int lev, double dT_lev)
                                gxx0, gxy0, gxz0, gyy0, gyz0, gzz0,
                                Axx0, Axy0, Axz0, Ayy0, Ayz0, Azz0,
                                Gmx0, Gmy0, Gmz0, Sfx1, Sfy1, Sfz1, // here we can not touch rhs variables, but 1 variables
-                               RoutMAP, ErrorMonitor, GH->Commlev[lev], !patch_mass_prepared);
+                               RoutMAP, ErrorMonitor, GH->Commlev[lev]);
-      patch_mass_prepared = true;
 #endif
 #endif
 //        misc::tillherecheck(GH->Commlev[lev],GH->start_rank[lev],"end surface integral");
@@ -7587,7 +7249,7 @@ void bssn_class::Constraint_Out()
     for (int lev = 0; lev < GH->levels; lev++)
     {
       // make sure the data consistent for higher levels
-      if (lev > 0 && ConstraintRefreshLevels && ConstraintRefreshLevels[lev]) // only refresh levels whose grid layout changed after evolution
+      if (lev > 0) // if the constrait quantities can be reused from the step rhs calculation
       {
         double TRK4 = PhysTime;
         double ndeps = numepsb;
@@ -7741,18 +7403,35 @@ void bssn_class::Constraint_Out()
 #if (PSTR == 1 || PSTR == 2)
     double ConV_h[7];
 #endif
-    var *ConstraintVars[7] = {Cons_Ham, Cons_Px, Cons_Py, Cons_Pz, Cons_Gx, Cons_Gy, Cons_Gz};
 
 #ifdef WithShell
-    SH->L2Norm7(ConstraintVars, ConV);
+    ConV[0] = SH->L2Norm(Cons_Ham);
+    ConV[1] = SH->L2Norm(Cons_Px);
+    ConV[2] = SH->L2Norm(Cons_Py);
+    ConV[3] = SH->L2Norm(Cons_Pz);
+    ConV[4] = SH->L2Norm(Cons_Gx);
+    ConV[5] = SH->L2Norm(Cons_Gy);
+    ConV[6] = SH->L2Norm(Cons_Gz);
     ConVMonitor->writefile(PhysTime, 7, ConV);
 #endif
     for (int levi = 0; levi < GH->levels; levi++)
     {
 #if (PSTR == 0)
-      Parallel::L2Norm7(GH->PatL[levi]->data, ConstraintVars, ConV);
+      ConV[0] = Parallel::L2Norm(GH->PatL[levi]->data, Cons_Ham);
+      ConV[1] = Parallel::L2Norm(GH->PatL[levi]->data, Cons_Px);
+      ConV[2] = Parallel::L2Norm(GH->PatL[levi]->data, Cons_Py);
+      ConV[3] = Parallel::L2Norm(GH->PatL[levi]->data, Cons_Pz);
+      ConV[4] = Parallel::L2Norm(GH->PatL[levi]->data, Cons_Gx);
+      ConV[5] = Parallel::L2Norm(GH->PatL[levi]->data, Cons_Gy);
+      ConV[6] = Parallel::L2Norm(GH->PatL[levi]->data, Cons_Gz);
 #elif (PSTR == 1 || PSTR == 2)
-      Parallel::L2Norm7(GH->PatL[levi]->data, ConstraintVars, ConV, GH->Commlev[levi]);
+      ConV[0] = Parallel::L2Norm(GH->PatL[levi]->data, Cons_Ham, GH->Commlev[levi]);
+      ConV[1] = Parallel::L2Norm(GH->PatL[levi]->data, Cons_Px, GH->Commlev[levi]);
+      ConV[2] = Parallel::L2Norm(GH->PatL[levi]->data, Cons_Py, GH->Commlev[levi]);
+      ConV[3] = Parallel::L2Norm(GH->PatL[levi]->data, Cons_Pz, GH->Commlev[levi]);
+      ConV[4] = Parallel::L2Norm(GH->PatL[levi]->data, Cons_Gx, GH->Commlev[levi]);
+      ConV[5] = Parallel::L2Norm(GH->PatL[levi]->data, Cons_Gy, GH->Commlev[levi]);
+      ConV[6] = Parallel::L2Norm(GH->PatL[levi]->data, Cons_Gz, GH->Commlev[levi]);
       //        misc::tillherecheck("before collect data to cpu0");
       // MPI_ALLREDUCE( sendbuf, recvbuf, count, datatype, op, comm), sendbu and recvbuf must be different
       if (levi > 0)
@@ -7783,9 +7462,6 @@ void bssn_class::Constraint_Out()
     Interp_Constraint(false);
 
     LastConsOut = 0;
-    if (ConstraintRefreshLevels)
-      for (int lev = 0; lev < GH->levels; lev++)
-        ConstraintRefreshLevels[lev] = 0;
   }
 }
 

AMSS_NCKU_source/bssn_class.h

@@ -48,7 +48,6 @@ public:
        double StartTime, TotalTime;
        double AnasTime, DumpTime, d2DumpTime, CheckTime;
        double LastAnas, LastConsOut;
-       int *ConstraintRefreshLevels;
        double Courant;
        double numepss, numepsb, numepsh;
        int Symmetry;
@@ -131,11 +130,9 @@ public:
        Parallel::SyncCache *sync_cache_cor;  // per-level cache for corrector sync
        Parallel::SyncCache *sync_cache_rp_coarse;  // RestrictProlong sync on PatL[lev-1]
        Parallel::SyncCache *sync_cache_rp_fine;    // RestrictProlong sync on PatL[lev]
-       Parallel::SyncCache *sync_cache_restrict;   // cached Restrict in RestrictProlong
-       Parallel::SyncCache *sync_cache_outbd;      // cached OutBdLow2Hi in RestrictProlong
 
        monitor *ErrorMonitor, *Psi4Monitor, *BHMonitor, *MAPMonitor;
-       monitor *ConVMonitor, *TimingMonitor;
+       monitor *ConVMonitor;
        surface_integral *Waveshell;
        checkpoint *CheckPoint;
 

AMSS_NCKU_source/bssn_rhs.f90

@@ -62,7 +62,6 @@
   real*8, dimension(ex(1),ex(2),ex(3)),intent(inout) :: Gmx_Res, Gmy_Res, Gmz_Res
 !  gont = 0: success; gont = 1: something wrong
   integer::gont
-  integer :: i,j,k
 
 !~~~~~~> Other variables:
 
@@ -86,13 +85,6 @@
 
   real*8,dimension(3) ::SSS,AAS,ASA,SAA,ASS,SAS,SSA
   real*8            :: dX, dY, dZ, PI
-  real*8            :: divb_loc,det_loc
-  real*8            :: gupxx_loc,gupxy_loc,gupxz_loc,gupyy_loc,gupyz_loc,gupzz_loc
-  real*8            :: Rxx_loc,Rxy_loc,Rxz_loc,Ryy_loc,Ryz_loc,Rzz_loc
-  real*8            :: fxx_loc,fxy_loc,fxz_loc
-  real*8            :: Gamxa_loc,Gamya_loc,Gamza_loc
-  real*8            :: f_loc,chin_loc
-  real*8            :: l_fxx,l_fxy,l_fxz,l_fyy,l_fyz,l_fzz,S_loc
   real*8, parameter :: ZEO = 0.d0,ONE = 1.D0, TWO = 2.D0, FOUR = 4.D0
   real*8, parameter :: EIGHT = 8.D0, HALF = 0.5D0, THR = 3.d0
   real*8, parameter :: SYM = 1.D0, ANTI= - 1.D0
@@ -105,7 +97,7 @@
 #endif
 
 #if (GAUGE == 6 || GAUGE == 7)
-  integer :: BHN
+  integer :: BHN,i,j,k
   real*8, dimension(9) :: Porg
   real*8, dimension(3) :: Mass
   real*8 :: r1,r2,M,A,w1,w2,C1,C2
@@ -153,24 +145,22 @@
   dY = Y(2) - Y(1)
   dZ = Z(2) - Z(1)
 
-  do k=1,ex(3)
+  alpn1 = Lap + ONE
-  do j=1,ex(2)
+  chin1 = chi + ONE
-  do i=1,ex(1)
+  gxx = dxx + ONE
-    alpn1(i,j,k) = Lap(i,j,k) + ONE
+  gyy = dyy + ONE
-    chin1(i,j,k) = chi(i,j,k) + ONE
+  gzz = dzz + ONE
-    gxx(i,j,k) = dxx(i,j,k) + ONE
-    gyy(i,j,k) = dyy(i,j,k) + ONE
-    gzz(i,j,k) = dzz(i,j,k) + ONE
-  enddo
-  enddo
-  enddo
 
   call fderivs(ex,betax,betaxx,betaxy,betaxz,X,Y,Z,ANTI, SYM, SYM,Symmetry,Lev)
   call fderivs(ex,betay,betayx,betayy,betayz,X,Y,Z, SYM,ANTI, SYM,Symmetry,Lev)
   call fderivs(ex,betaz,betazx,betazy,betazz,X,Y,Z, SYM, SYM,ANTI,Symmetry,Lev)
   
+  div_beta = betaxx + betayy + betazz
+ 
   call fderivs(ex,chi,chix,chiy,chiz,X,Y,Z,SYM,SYM,SYM,symmetry,Lev)
 
+  chi_rhs = F2o3 *chin1*( alpn1 * trK - div_beta ) !rhs for chi
+
   call fderivs(ex,dxx,gxxx,gxxy,gxxz,X,Y,Z,SYM ,SYM ,SYM ,Symmetry,Lev)
   call fderivs(ex,gxy,gxyx,gxyy,gxyz,X,Y,Z,ANTI,ANTI,SYM ,Symmetry,Lev)
   call fderivs(ex,gxz,gxzx,gxzy,gxzz,X,Y,Z,ANTI,SYM ,ANTI,Symmetry,Lev)
@@ -178,179 +168,151 @@
   call fderivs(ex,gyz,gyzx,gyzy,gyzz,X,Y,Z,SYM ,ANTI,ANTI,Symmetry,Lev)
   call fderivs(ex,dzz,gzzx,gzzy,gzzz,X,Y,Z,SYM ,SYM ,SYM ,Symmetry,Lev)
 
-  do k=1,ex(3)
+  gxx_rhs = - TWO * alpn1 * Axx    -  F2o3 * gxx * div_beta          + &
-  do j=1,ex(2)
+              TWO *(  gxx * betaxx +   gxy * betayx +   gxz * betazx)
-  do i=1,ex(1)
-    divb_loc = betaxx(i,j,k) + betayy(i,j,k) + betazz(i,j,k)
-    div_beta(i,j,k) = divb_loc
 
-    chi_rhs(i,j,k) = F2o3 * chin1(i,j,k) * (alpn1(i,j,k) * trK(i,j,k) - divb_loc)
+  gyy_rhs = - TWO * alpn1 * Ayy    -  F2o3 * gyy * div_beta          + &
+              TWO *(  gxy * betaxy +   gyy * betayy +   gyz * betazy)
 
-    gxx_rhs(i,j,k) = - TWO * alpn1(i,j,k) * Axx(i,j,k) - F2o3 * gxx(i,j,k) * divb_loc + &
+  gzz_rhs = - TWO * alpn1 * Azz    -  F2o3 * gzz * div_beta          + &
-         TWO * ( gxx(i,j,k) * betaxx(i,j,k) + gxy(i,j,k) * betayx(i,j,k) + gxz(i,j,k) * betazx(i,j,k) )
+              TWO *(  gxz * betaxz +   gyz * betayz +   gzz * betazz)
 
-    gyy_rhs(i,j,k) = - TWO * alpn1(i,j,k) * Ayy(i,j,k) - F2o3 * gyy(i,j,k) * divb_loc + &
+  gxy_rhs = - TWO * alpn1 * Axy    +  F1o3 * gxy    * div_beta       + &
-         TWO * ( gxy(i,j,k) * betaxy(i,j,k) + gyy(i,j,k) * betayy(i,j,k) + gyz(i,j,k) * betazy(i,j,k) )
+                      gxx * betaxy                  +   gxz * betazy + &
+                                       gyy * betayx +   gyz * betazx   &
+                                                    -   gxy * betazz
 
-    gzz_rhs(i,j,k) = - TWO * alpn1(i,j,k) * Azz(i,j,k) - F2o3 * gzz(i,j,k) * divb_loc + &
+  gyz_rhs = - TWO * alpn1 * Ayz    +  F1o3 * gyz    * div_beta       + &
-         TWO * ( gxz(i,j,k) * betaxz(i,j,k) + gyz(i,j,k) * betayz(i,j,k) + gzz(i,j,k) * betazz(i,j,k) )
+                      gxy * betaxz +   gyy * betayz                  + &
+                      gxz * betaxy                  +   gzz * betazy   &
+                                                    -   gyz * betaxx
  
-    gxy_rhs(i,j,k) = - TWO * alpn1(i,j,k) * Axy(i,j,k) + F1o3 * gxy(i,j,k) * divb_loc + &
+  gxz_rhs = - TWO * alpn1 * Axz    +  F1o3 * gxz    * div_beta       + &
-         gxx(i,j,k) * betaxy(i,j,k) + gxz(i,j,k) * betazy(i,j,k) + gyy(i,j,k) * betayx(i,j,k) + &
+                      gxx * betaxz +   gxy * betayz                  + &
-         gyz(i,j,k) * betazx(i,j,k) - gxy(i,j,k) * betazz(i,j,k)
+                                       gyz * betayx +   gzz * betazx   &
+                                                    -   gxz * betayy     !rhs for gij
 
-    gyz_rhs(i,j,k) = - TWO * alpn1(i,j,k) * Ayz(i,j,k) + F1o3 * gyz(i,j,k) * divb_loc + &
+! invert tilted metric
-         gxy(i,j,k) * betaxz(i,j,k) + gyy(i,j,k) * betayz(i,j,k) + gxz(i,j,k) * betaxy(i,j,k) + &
+  gupzz =  gxx * gyy * gzz + gxy * gyz * gxz + gxz * gxy * gyz - &
-         gzz(i,j,k) * betazy(i,j,k) - gyz(i,j,k) * betaxx(i,j,k)
+           gxz * gyy * gxz - gxy * gxy * gzz - gxx * gyz * gyz
+  gupxx =   ( gyy * gzz - gyz * gyz ) / gupzz
+  gupxy = - ( gxy * gzz - gyz * gxz ) / gupzz
+  gupxz =   ( gxy * gyz - gyy * gxz ) / gupzz
+  gupyy =   ( gxx * gzz - gxz * gxz ) / gupzz
+  gupyz = - ( gxx * gyz - gxy * gxz ) / gupzz
+  gupzz =   ( gxx * gyy - gxy * gxy ) / gupzz
 
-    gxz_rhs(i,j,k) = - TWO * alpn1(i,j,k) * Axz(i,j,k) + F1o3 * gxz(i,j,k) * divb_loc + &
+  if(co == 0)then
-         gxx(i,j,k) * betaxz(i,j,k) + gxy(i,j,k) * betayz(i,j,k) + gyz(i,j,k) * betayx(i,j,k) + &
+! Gam^i_Res = Gam^i + gup^ij_,j
-         gzz(i,j,k) * betazx(i,j,k) - gxz(i,j,k) * betayy(i,j,k)
+  Gmx_Res = Gamx - (gupxx*(gupxx*gxxx+gupxy*gxyx+gupxz*gxzx)&
+                   +gupxy*(gupxx*gxyx+gupxy*gyyx+gupxz*gyzx)&
+                   +gupxz*(gupxx*gxzx+gupxy*gyzx+gupxz*gzzx)&
+                   +gupxx*(gupxy*gxxy+gupyy*gxyy+gupyz*gxzy)&
+                   +gupxy*(gupxy*gxyy+gupyy*gyyy+gupyz*gyzy)&
+                   +gupxz*(gupxy*gxzy+gupyy*gyzy+gupyz*gzzy)&
+                   +gupxx*(gupxz*gxxz+gupyz*gxyz+gupzz*gxzz)&
+                   +gupxy*(gupxz*gxyz+gupyz*gyyz+gupzz*gyzz)&
+                   +gupxz*(gupxz*gxzz+gupyz*gyzz+gupzz*gzzz))
+  Gmy_Res = Gamy - (gupxx*(gupxy*gxxx+gupyy*gxyx+gupyz*gxzx)&
+                   +gupxy*(gupxy*gxyx+gupyy*gyyx+gupyz*gyzx)&
+                   +gupxz*(gupxy*gxzx+gupyy*gyzx+gupyz*gzzx)&
+                   +gupxy*(gupxy*gxxy+gupyy*gxyy+gupyz*gxzy)&
+                   +gupyy*(gupxy*gxyy+gupyy*gyyy+gupyz*gyzy)&
+                   +gupyz*(gupxy*gxzy+gupyy*gyzy+gupyz*gzzy)&
+                   +gupxy*(gupxz*gxxz+gupyz*gxyz+gupzz*gxzz)&
+                   +gupyy*(gupxz*gxyz+gupyz*gyyz+gupzz*gyzz)&
+                   +gupyz*(gupxz*gxzz+gupyz*gyzz+gupzz*gzzz))
+  Gmz_Res = Gamz - (gupxx*(gupxz*gxxx+gupyz*gxyx+gupzz*gxzx)&
+                   +gupxy*(gupxz*gxyx+gupyz*gyyx+gupzz*gyzx)&
+                   +gupxz*(gupxz*gxzx+gupyz*gyzx+gupzz*gzzx)&
+                   +gupxy*(gupxz*gxxy+gupyz*gxyy+gupzz*gxzy)&
+                   +gupyy*(gupxz*gxyy+gupyz*gyyy+gupzz*gyzy)&
+                   +gupyz*(gupxz*gxzy+gupyz*gyzy+gupzz*gzzy)&
+                   +gupxz*(gupxz*gxxz+gupyz*gxyz+gupzz*gxzz)&
+                   +gupyz*(gupxz*gxyz+gupyz*gyyz+gupzz*gyzz)&
+                   +gupzz*(gupxz*gxzz+gupyz*gyzz+gupzz*gzzz))
+  endif
 
-    det_loc = gxx(i,j,k) * gyy(i,j,k) * gzz(i,j,k) + gxy(i,j,k) * gyz(i,j,k) * gxz(i,j,k) + &
+! second kind of connection
-         gxz(i,j,k) * gxy(i,j,k) * gyz(i,j,k) - gxz(i,j,k) * gyy(i,j,k) * gxz(i,j,k) - &
+  Gamxxx =HALF*( gupxx*gxxx + gupxy*(TWO*gxyx - gxxy ) + gupxz*(TWO*gxzx - gxxz ))
-         gxy(i,j,k) * gxy(i,j,k) * gzz(i,j,k) - gxx(i,j,k) * gyz(i,j,k) * gyz(i,j,k)
+  Gamyxx =HALF*( gupxy*gxxx + gupyy*(TWO*gxyx - gxxy ) + gupyz*(TWO*gxzx - gxxz ))
-    gupxx_loc = ( gyy(i,j,k) * gzz(i,j,k) - gyz(i,j,k) * gyz(i,j,k) ) / det_loc
+  Gamzxx =HALF*( gupxz*gxxx + gupyz*(TWO*gxyx - gxxy ) + gupzz*(TWO*gxzx - gxxz ))
-    gupxy_loc = - ( gxy(i,j,k) * gzz(i,j,k) - gyz(i,j,k) * gxz(i,j,k) ) / det_loc
-    gupxz_loc = ( gxy(i,j,k) * gyz(i,j,k) - gyy(i,j,k) * gxz(i,j,k) ) / det_loc
-    gupyy_loc = ( gxx(i,j,k) * gzz(i,j,k) - gxz(i,j,k) * gxz(i,j,k) ) / det_loc
-    gupyz_loc = - ( gxx(i,j,k) * gyz(i,j,k) - gxy(i,j,k) * gxz(i,j,k) ) / det_loc
-    gupzz_loc = ( gxx(i,j,k) * gyy(i,j,k) - gxy(i,j,k) * gxy(i,j,k) ) / det_loc
-    gupxx(i,j,k) = gupxx_loc
-    gupxy(i,j,k) = gupxy_loc
-    gupxz(i,j,k) = gupxz_loc
-    gupyy(i,j,k) = gupyy_loc
-    gupyz(i,j,k) = gupyz_loc
-    gupzz(i,j,k) = gupzz_loc
  
-    if(co == 0)then
+  Gamxyy =HALF*( gupxx*(TWO*gxyy - gyyx ) + gupxy*gyyy + gupxz*(TWO*gyzy - gyyz ))
-      Gmx_Res(i,j,k) = Gamx(i,j,k) - ( &
+  Gamyyy =HALF*( gupxy*(TWO*gxyy - gyyx ) + gupyy*gyyy + gupyz*(TWO*gyzy - gyyz ))
-           gupxx_loc*(gupxx_loc*gxxx(i,j,k)+gupxy_loc*gxyx(i,j,k)+gupxz_loc*gxzx(i,j,k)) + &
+  Gamzyy =HALF*( gupxz*(TWO*gxyy - gyyx ) + gupyz*gyyy + gupzz*(TWO*gyzy - gyyz ))
-           gupxy_loc*(gupxx_loc*gxyx(i,j,k)+gupxy_loc*gyyx(i,j,k)+gupxz_loc*gyzx(i,j,k)) + &
-           gupxz_loc*(gupxx_loc*gxzx(i,j,k)+gupxy_loc*gyzx(i,j,k)+gupxz_loc*gzzx(i,j,k)) + &
-           gupxx_loc*(gupxy_loc*gxxy(i,j,k)+gupyy_loc*gxyy(i,j,k)+gupyz_loc*gxzy(i,j,k)) + &
-           gupxy_loc*(gupxy_loc*gxyy(i,j,k)+gupyy_loc*gyyy(i,j,k)+gupyz_loc*gyzy(i,j,k)) + &
-           gupxz_loc*(gupxy_loc*gxzy(i,j,k)+gupyy_loc*gyzy(i,j,k)+gupyz_loc*gzzy(i,j,k)) + &
-           gupxx_loc*(gupxz_loc*gxxz(i,j,k)+gupyz_loc*gxyz(i,j,k)+gupzz_loc*gxzz(i,j,k)) + &
-           gupxy_loc*(gupxz_loc*gxyz(i,j,k)+gupyz_loc*gyyz(i,j,k)+gupzz_loc*gyzz(i,j,k)) + &
-           gupxz_loc*(gupxz_loc*gxzz(i,j,k)+gupyz_loc*gyzz(i,j,k)+gupzz_loc*gzzz(i,j,k)))
-      Gmy_Res(i,j,k) = Gamy(i,j,k) - ( &
-           gupxx_loc*(gupxy_loc*gxxx(i,j,k)+gupyy_loc*gxyx(i,j,k)+gupyz_loc*gxzx(i,j,k)) + &
-           gupxy_loc*(gupxy_loc*gxyx(i,j,k)+gupyy_loc*gyyx(i,j,k)+gupyz_loc*gyzx(i,j,k)) + &
-           gupxz_loc*(gupxy_loc*gxzx(i,j,k)+gupyy_loc*gyzx(i,j,k)+gupyz_loc*gzzx(i,j,k)) + &
-           gupxy_loc*(gupxy_loc*gxxy(i,j,k)+gupyy_loc*gxyy(i,j,k)+gupyz_loc*gxzy(i,j,k)) + &
-           gupyy_loc*(gupxy_loc*gxyy(i,j,k)+gupyy_loc*gyyy(i,j,k)+gupyz_loc*gyzy(i,j,k)) + &
-           gupyz_loc*(gupxy_loc*gxzy(i,j,k)+gupyy_loc*gyzy(i,j,k)+gupyz_loc*gzzy(i,j,k)) + &
-           gupxy_loc*(gupxz_loc*gxxz(i,j,k)+gupyz_loc*gxyz(i,j,k)+gupzz_loc*gxzz(i,j,k)) + &
-           gupyy_loc*(gupxz_loc*gxyz(i,j,k)+gupyz_loc*gyyz(i,j,k)+gupzz_loc*gyzz(i,j,k)) + &
-           gupyz_loc*(gupxz_loc*gxzz(i,j,k)+gupyz_loc*gyzz(i,j,k)+gupzz_loc*gzzz(i,j,k)))
-      Gmz_Res(i,j,k) = Gamz(i,j,k) - ( &
-           gupxx_loc*(gupxz_loc*gxxx(i,j,k)+gupyz_loc*gxyx(i,j,k)+gupzz_loc*gxzx(i,j,k)) + &
-           gupxy_loc*(gupxz_loc*gxyx(i,j,k)+gupyz_loc*gyyx(i,j,k)+gupzz_loc*gyzx(i,j,k)) + &
-           gupxz_loc*(gupxz_loc*gxzx(i,j,k)+gupyz_loc*gyzx(i,j,k)+gupzz_loc*gzzx(i,j,k)) + &
-           gupxy_loc*(gupxz_loc*gxxy(i,j,k)+gupyz_loc*gxyy(i,j,k)+gupzz_loc*gxzy(i,j,k)) + &
-           gupyy_loc*(gupxz_loc*gxyy(i,j,k)+gupyz_loc*gyyy(i,j,k)+gupzz_loc*gyzy(i,j,k)) + &
-           gupyz_loc*(gupxz_loc*gxzy(i,j,k)+gupyz_loc*gyzy(i,j,k)+gupzz_loc*gzzy(i,j,k)) + &
-           gupxz_loc*(gupxz_loc*gxxz(i,j,k)+gupyz_loc*gxyz(i,j,k)+gupzz_loc*gxzz(i,j,k)) + &
-           gupyz_loc*(gupxz_loc*gxyz(i,j,k)+gupyz_loc*gyyz(i,j,k)+gupzz_loc*gyzz(i,j,k)) + &
-           gupzz_loc*(gupxz_loc*gxzz(i,j,k)+gupyz_loc*gyzz(i,j,k)+gupzz_loc*gzzz(i,j,k)))
-    endif
 
-    Gamxxx(i,j,k)=HALF*( gupxx_loc*gxxx(i,j,k) + gupxy_loc*(TWO*gxyx(i,j,k) - gxxy(i,j,k)) + gupxz_loc*(TWO*gxzx(i,j,k) - gxxz(i,j,k)))
+  Gamxzz =HALF*( gupxx*(TWO*gxzz - gzzx ) + gupxy*(TWO*gyzz - gzzy ) + gupxz*gzzz)
-    Gamyxx(i,j,k)=HALF*( gupxy_loc*gxxx(i,j,k) + gupyy_loc*(TWO*gxyx(i,j,k) - gxxy(i,j,k)) + gupyz_loc*(TWO*gxzx(i,j,k) - gxxz(i,j,k)))
+  Gamyzz =HALF*( gupxy*(TWO*gxzz - gzzx ) + gupyy*(TWO*gyzz - gzzy ) + gupyz*gzzz)
-    Gamzxx(i,j,k)=HALF*( gupxz_loc*gxxx(i,j,k) + gupyz_loc*(TWO*gxyx(i,j,k) - gxxy(i,j,k)) + gupzz_loc*(TWO*gxzx(i,j,k) - gxxz(i,j,k)))
+  Gamzzz =HALF*( gupxz*(TWO*gxzz - gzzx ) + gupyz*(TWO*gyzz - gzzy ) + gupzz*gzzz)
 
-    Gamxyy(i,j,k)=HALF*( gupxx_loc*(TWO*gxyy(i,j,k) - gyyx(i,j,k)) + gupxy_loc*gyyy(i,j,k) + gupxz_loc*(TWO*gyzy(i,j,k) - gyyz(i,j,k)))
+  Gamxxy =HALF*( gupxx*gxxy + gupxy*gyyx + gupxz*( gxzy + gyzx - gxyz ) )
-    Gamyyy(i,j,k)=HALF*( gupxy_loc*(TWO*gxyy(i,j,k) - gyyx(i,j,k)) + gupyy_loc*gyyy(i,j,k) + gupyz_loc*(TWO*gyzy(i,j,k) - gyyz(i,j,k)))
+  Gamyxy =HALF*( gupxy*gxxy + gupyy*gyyx + gupyz*( gxzy + gyzx - gxyz ) )
-    Gamzyy(i,j,k)=HALF*( gupxz_loc*(TWO*gxyy(i,j,k) - gyyx(i,j,k)) + gupyz_loc*gyyy(i,j,k) + gupzz_loc*(TWO*gyzy(i,j,k) - gyyz(i,j,k)))
+  Gamzxy =HALF*( gupxz*gxxy + gupyz*gyyx + gupzz*( gxzy + gyzx - gxyz ) )
 
-    Gamxzz(i,j,k)=HALF*( gupxx_loc*(TWO*gxzz(i,j,k) - gzzx(i,j,k)) + gupxy_loc*(TWO*gyzz(i,j,k) - gzzy(i,j,k)) + gupxz_loc*gzzz(i,j,k))
+  Gamxxz =HALF*( gupxx*gxxz + gupxy*( gxyz + gyzx - gxzy ) + gupxz*gzzx )
-    Gamyzz(i,j,k)=HALF*( gupxy_loc*(TWO*gxzz(i,j,k) - gzzx(i,j,k)) + gupyy_loc*(TWO*gyzz(i,j,k) - gzzy(i,j,k)) + gupyz_loc*gzzz(i,j,k))
+  Gamyxz =HALF*( gupxy*gxxz + gupyy*( gxyz + gyzx - gxzy ) + gupyz*gzzx )
-    Gamzzz(i,j,k)=HALF*( gupxz_loc*(TWO*gxzz(i,j,k) - gzzx(i,j,k)) + gupyz_loc*(TWO*gyzz(i,j,k) - gzzy(i,j,k)) + gupzz_loc*gzzz(i,j,k))
+  Gamzxz =HALF*( gupxz*gxxz + gupyz*( gxyz + gyzx - gxzy ) + gupzz*gzzx )
 
-    Gamxxy(i,j,k)=HALF*( gupxx_loc*gxxy(i,j,k) + gupxy_loc*gyyx(i,j,k) + gupxz_loc*(gxzy(i,j,k) + gyzx(i,j,k) - gxyz(i,j,k)) )
+  Gamxyz =HALF*( gupxx*( gxyz + gxzy - gyzx ) + gupxy*gyyz + gupxz*gzzy )
-    Gamyxy(i,j,k)=HALF*( gupxy_loc*gxxy(i,j,k) + gupyy_loc*gyyx(i,j,k) + gupyz_loc*(gxzy(i,j,k) + gyzx(i,j,k) - gxyz(i,j,k)) )
+  Gamyyz =HALF*( gupxy*( gxyz + gxzy - gyzx ) + gupyy*gyyz + gupyz*gzzy )
-    Gamzxy(i,j,k)=HALF*( gupxz_loc*gxxy(i,j,k) + gupyz_loc*gyyx(i,j,k) + gupzz_loc*(gxzy(i,j,k) + gyzx(i,j,k) - gxyz(i,j,k)) )
+  Gamzyz =HALF*( gupxz*( gxyz + gxzy - gyzx ) + gupyz*gyyz + gupzz*gzzy )
-
-    Gamxxz(i,j,k)=HALF*( gupxx_loc*gxxz(i,j,k) + gupxy_loc*(gxyz(i,j,k) + gyzx(i,j,k) - gxzy(i,j,k)) + gupxz_loc*gzzx(i,j,k) )
-    Gamyxz(i,j,k)=HALF*( gupxy_loc*gxxz(i,j,k) + gupyy_loc*(gxyz(i,j,k) + gyzx(i,j,k) - gxzy(i,j,k)) + gupyz_loc*gzzx(i,j,k) )
-    Gamzxz(i,j,k)=HALF*( gupxz_loc*gxxz(i,j,k) + gupyz_loc*(gxyz(i,j,k) + gyzx(i,j,k) - gxzy(i,j,k)) + gupzz_loc*gzzx(i,j,k) )
-
-    Gamxyz(i,j,k)=HALF*( gupxx_loc*(gxyz(i,j,k) + gxzy(i,j,k) - gyzx(i,j,k)) + gupxy_loc*gyyz(i,j,k) + gupxz_loc*gzzy(i,j,k) )
-    Gamyyz(i,j,k)=HALF*( gupxy_loc*(gxyz(i,j,k) + gxzy(i,j,k) - gyzx(i,j,k)) + gupyy_loc*gyyz(i,j,k) + gupyz_loc*gzzy(i,j,k) )
-    Gamzyz(i,j,k)=HALF*( gupxz_loc*(gxyz(i,j,k) + gxzy(i,j,k) - gyzx(i,j,k)) + gupyz_loc*gyyz(i,j,k) + gupzz_loc*gzzy(i,j,k) )
-  enddo
-  enddo
-  enddo
 ! Raise indices of \tilde A_{ij} and store in R_ij
 
+  Rxx =    gupxx * gupxx * Axx + gupxy * gupxy * Ayy + gupxz * gupxz * Azz + &
+      TWO*(gupxx * gupxy * Axy + gupxx * gupxz * Axz + gupxy * gupxz * Ayz)
+
+  Ryy =    gupxy * gupxy * Axx + gupyy * gupyy * Ayy + gupyz * gupyz * Azz + &
+      TWO*(gupxy * gupyy * Axy + gupxy * gupyz * Axz + gupyy * gupyz * Ayz)
+
+  Rzz =    gupxz * gupxz * Axx + gupyz * gupyz * Ayy + gupzz * gupzz * Azz + &
+      TWO*(gupxz * gupyz * Axy + gupxz * gupzz * Axz + gupyz * gupzz * Ayz)
+
+  Rxy =    gupxx * gupxy * Axx + gupxy * gupyy * Ayy + gupxz * gupyz * Azz + &
+          (gupxx * gupyy       + gupxy * gupxy)* Axy                       + &
+          (gupxx * gupyz       + gupxz * gupxy)* Axz                       + &
+          (gupxy * gupyz       + gupxz * gupyy)* Ayz
+
+  Rxz =    gupxx * gupxz * Axx + gupxy * gupyz * Ayy + gupxz * gupzz * Azz + &
+          (gupxx * gupyz       + gupxy * gupxz)* Axy                       + &
+          (gupxx * gupzz       + gupxz * gupxz)* Axz                       + &
+          (gupxy * gupzz       + gupxz * gupyz)* Ayz
+
+  Ryz =    gupxy * gupxz * Axx + gupyy * gupyz * Ayy + gupyz * gupzz * Azz + &
+          (gupxy * gupyz       + gupyy * gupxz)* Axy                       + &
+          (gupxy * gupzz       + gupyz * gupxz)* Axz                       + &
+          (gupyy * gupzz       + gupyz * gupyz)* Ayz
+
 ! Right hand side for Gam^i without shift terms...
   call fderivs(ex,Lap,Lapx,Lapy,Lapz,X,Y,Z,SYM,SYM,SYM,Symmetry,Lev)
   call fderivs(ex,trK,Kx,Ky,Kz,X,Y,Z,SYM,SYM,SYM,symmetry,Lev)
-  do k=1,ex(3)
-  do j=1,ex(2)
-  do i=1,ex(1)
-    gupxx_loc = gupxx(i,j,k)
-    gupxy_loc = gupxy(i,j,k)
-    gupxz_loc = gupxz(i,j,k)
-    gupyy_loc = gupyy(i,j,k)
-    gupyz_loc = gupyz(i,j,k)
-    gupzz_loc = gupzz(i,j,k)
 
-    Rxx_loc = gupxx_loc * gupxx_loc * Axx(i,j,k) + gupxy_loc * gupxy_loc * Ayy(i,j,k) + gupxz_loc * gupxz_loc * Azz(i,j,k) + &
+   Gamx_rhs = - TWO * (   Lapx * Rxx +   Lapy * Rxy +   Lapz * Rxz ) + &
-         TWO * (gupxx_loc * gupxy_loc * Axy(i,j,k) + gupxx_loc * gupxz_loc * Axz(i,j,k) + gupxy_loc * gupxz_loc * Ayz(i,j,k))
+        TWO * alpn1 * (                                                &
-    Ryy_loc = gupxy_loc * gupxy_loc * Axx(i,j,k) + gupyy_loc * gupyy_loc * Ayy(i,j,k) + gupyz_loc * gupyz_loc * Azz(i,j,k) + &
+        -F3o2/chin1 * (   chix * Rxx +   chiy * Rxy +   chiz * Rxz ) - &
-         TWO * (gupxy_loc * gupyy_loc * Axy(i,j,k) + gupxy_loc * gupyz_loc * Axz(i,j,k) + gupyy_loc * gupyz_loc * Ayz(i,j,k))
+              gupxx * (   F2o3 * Kx  +  EIGHT * PI * Sx            ) - &
-    Rzz_loc = gupxz_loc * gupxz_loc * Axx(i,j,k) + gupyz_loc * gupyz_loc * Ayy(i,j,k) + gupzz_loc * gupzz_loc * Azz(i,j,k) + &
+              gupxy * (   F2o3 * Ky  +  EIGHT * PI * Sy            ) - &
-         TWO * (gupxz_loc * gupyz_loc * Axy(i,j,k) + gupxz_loc * gupzz_loc * Axz(i,j,k) + gupyz_loc * gupzz_loc * Ayz(i,j,k))
+              gupxz * (   F2o3 * Kz  +  EIGHT * PI * Sz            ) + &
-    Rxy_loc = gupxx_loc * gupxy_loc * Axx(i,j,k) + gupxy_loc * gupyy_loc * Ayy(i,j,k) + gupxz_loc * gupyz_loc * Azz(i,j,k) + &
+                        Gamxxx * Rxx + Gamxyy * Ryy + Gamxzz * Rzz   + &
-         (gupxx_loc * gupyy_loc + gupxy_loc * gupxy_loc) * Axy(i,j,k) + &
+                TWO * ( Gamxxy * Rxy + Gamxxz * Rxz + Gamxyz * Ryz ) )
-         (gupxx_loc * gupyz_loc + gupxz_loc * gupxy_loc) * Axz(i,j,k) + &
-         (gupxy_loc * gupyz_loc + gupxz_loc * gupyy_loc) * Ayz(i,j,k)
-    Rxz_loc = gupxx_loc * gupxz_loc * Axx(i,j,k) + gupxy_loc * gupyz_loc * Ayy(i,j,k) + gupxz_loc * gupzz_loc * Azz(i,j,k) + &
-         (gupxx_loc * gupyz_loc + gupxy_loc * gupxz_loc) * Axy(i,j,k) + &
-         (gupxx_loc * gupzz_loc + gupxz_loc * gupxz_loc) * Axz(i,j,k) + &
-         (gupxy_loc * gupzz_loc + gupxz_loc * gupyz_loc) * Ayz(i,j,k)
-    Ryz_loc = gupxy_loc * gupxz_loc * Axx(i,j,k) + gupyy_loc * gupyz_loc * Ayy(i,j,k) + gupyz_loc * gupzz_loc * Azz(i,j,k) + &
-         (gupxy_loc * gupyz_loc + gupyy_loc * gupxz_loc) * Axy(i,j,k) + &
-         (gupxy_loc * gupzz_loc + gupyz_loc * gupxz_loc) * Axz(i,j,k) + &
-         (gupyy_loc * gupzz_loc + gupyz_loc * gupyz_loc) * Ayz(i,j,k)
-    Rxx(i,j,k) = Rxx_loc
-    Ryy(i,j,k) = Ryy_loc
-    Rzz(i,j,k) = Rzz_loc
-    Rxy(i,j,k) = Rxy_loc
-    Rxz(i,j,k) = Rxz_loc
-    Ryz(i,j,k) = Ryz_loc
 
-    Gamx_rhs(i,j,k) = - TWO * (Lapx(i,j,k) * Rxx_loc + Lapy(i,j,k) * Rxy_loc + Lapz(i,j,k) * Rxz_loc) + &
+   Gamy_rhs = - TWO * (   Lapx * Rxy +   Lapy * Ryy +   Lapz * Ryz ) + &
-         TWO * alpn1(i,j,k) * ( &
+        TWO * alpn1 * (                                                &
-         -F3o2/chin1(i,j,k) * (chix(i,j,k) * Rxx_loc + chiy(i,j,k) * Rxy_loc + chiz(i,j,k) * Rxz_loc) - &
+        -F3o2/chin1 * (   chix * Rxy +  chiy * Ryy +    chiz * Ryz ) - &
-         gupxx_loc * (F2o3 * Kx(i,j,k) + EIGHT * PI * Sx(i,j,k)) - &
+              gupxy * (   F2o3 * Kx  +  EIGHT * PI * Sx            ) - &
-         gupxy_loc * (F2o3 * Ky(i,j,k) + EIGHT * PI * Sy(i,j,k)) - &
+              gupyy * (   F2o3 * Ky  +  EIGHT * PI * Sy            ) - &
-         gupxz_loc * (F2o3 * Kz(i,j,k) + EIGHT * PI * Sz(i,j,k)) + &
+              gupyz * (   F2o3 * Kz  +  EIGHT * PI * Sz            ) + &
-         Gamxxx(i,j,k) * Rxx_loc + Gamxyy(i,j,k) * Ryy_loc + Gamxzz(i,j,k) * Rzz_loc + &
+                        Gamyxx * Rxx + Gamyyy * Ryy + Gamyzz * Rzz   + &
-         TWO * (Gamxxy(i,j,k) * Rxy_loc + Gamxxz(i,j,k) * Rxz_loc + Gamxyz(i,j,k) * Ryz_loc))
+                TWO * ( Gamyxy * Rxy + Gamyxz * Rxz + Gamyyz * Ryz ) )
 
-    Gamy_rhs(i,j,k) = - TWO * (Lapx(i,j,k) * Rxy_loc + Lapy(i,j,k) * Ryy_loc + Lapz(i,j,k) * Ryz_loc) + &
+   Gamz_rhs = - TWO * (   Lapx * Rxz +   Lapy * Ryz +   Lapz * Rzz ) + &
-         TWO * alpn1(i,j,k) * ( &
+        TWO * alpn1 * (                                                &
-         -F3o2/chin1(i,j,k) * (chix(i,j,k) * Rxy_loc + chiy(i,j,k) * Ryy_loc + chiz(i,j,k) * Ryz_loc) - &
+        -F3o2/chin1 * (   chix * Rxz +  chiy * Ryz +    chiz * Rzz ) - &
-         gupxy_loc * (F2o3 * Kx(i,j,k) + EIGHT * PI * Sx(i,j,k)) - &
+              gupxz * (   F2o3 * Kx  +  EIGHT * PI * Sx            ) - &
-         gupyy_loc * (F2o3 * Ky(i,j,k) + EIGHT * PI * Sy(i,j,k)) - &
+              gupyz * (   F2o3 * Ky  +  EIGHT * PI * Sy            ) - &
-         gupyz_loc * (F2o3 * Kz(i,j,k) + EIGHT * PI * Sz(i,j,k)) + &
+              gupzz * (   F2o3 * Kz  +  EIGHT * PI * Sz            ) + &
-         Gamyxx(i,j,k) * Rxx_loc + Gamyyy(i,j,k) * Ryy_loc + Gamyzz(i,j,k) * Rzz_loc + &
+                        Gamzxx * Rxx + Gamzyy * Ryy + Gamzzz * Rzz   + &
-         TWO * (Gamyxy(i,j,k) * Rxy_loc + Gamyxz(i,j,k) * Rxz_loc + Gamyyz(i,j,k) * Ryz_loc))
+                TWO * ( Gamzxy * Rxy + Gamzxz * Rxz + Gamzyz * Ryz ) )
-
-    Gamz_rhs(i,j,k) = - TWO * (Lapx(i,j,k) * Rxz_loc + Lapy(i,j,k) * Ryz_loc + Lapz(i,j,k) * Rzz_loc) + &
-         TWO * alpn1(i,j,k) * ( &
-         -F3o2/chin1(i,j,k) * (chix(i,j,k) * Rxz_loc + chiy(i,j,k) * Ryz_loc + chiz(i,j,k) * Rzz_loc) - &
-         gupxz_loc * (F2o3 * Kx(i,j,k) + EIGHT * PI * Sx(i,j,k)) - &
-         gupyz_loc * (F2o3 * Ky(i,j,k) + EIGHT * PI * Sy(i,j,k)) - &
-         gupzz_loc * (F2o3 * Kz(i,j,k) + EIGHT * PI * Sz(i,j,k)) + &
-         Gamzxx(i,j,k) * Rxx_loc + Gamzyy(i,j,k) * Ryy_loc + Gamzzz(i,j,k) * Rzz_loc + &
-         TWO * (Gamzxy(i,j,k) * Rxy_loc + Gamzxz(i,j,k) * Rxz_loc + Gamzyz(i,j,k) * Ryz_loc))
-  enddo
-  enddo
-  enddo
 
   call fdderivs(ex,betax,gxxx,gxyx,gxzx,gyyx,gyzx,gzzx,&
                 X,Y,Z,ANTI,SYM, SYM ,Symmetry,Lev)
@@ -359,54 +321,38 @@
   call fdderivs(ex,betaz,gxxz,gxyz,gxzz,gyyz,gyzz,gzzz,&
                 X,Y,Z,SYM ,SYM, ANTI,Symmetry,Lev)
 
+  fxx = gxxx + gxyy + gxzz
+  fxy = gxyx + gyyy + gyzz
+  fxz = gxzx + gyzy + gzzz
+
+  Gamxa =       gupxx * Gamxxx + gupyy * Gamxyy + gupzz * Gamxzz + &
+          TWO*( gupxy * Gamxxy + gupxz * Gamxxz + gupyz * Gamxyz )
+  Gamya =       gupxx * Gamyxx + gupyy * Gamyyy + gupzz * Gamyzz + &
+          TWO*( gupxy * Gamyxy + gupxz * Gamyxz + gupyz * Gamyyz )
+  Gamza =       gupxx * Gamzxx + gupyy * Gamzyy + gupzz * Gamzzz + &
+          TWO*( gupxy * Gamzxy + gupxz * Gamzxz + gupyz * Gamzyz )
+
   call fderivs(ex,Gamx,Gamxx,Gamxy,Gamxz,X,Y,Z,ANTI,SYM ,SYM ,Symmetry,Lev)
   call fderivs(ex,Gamy,Gamyx,Gamyy,Gamyz,X,Y,Z,SYM ,ANTI,SYM ,Symmetry,Lev)
   call fderivs(ex,Gamz,Gamzx,Gamzy,Gamzz,X,Y,Z,SYM ,SYM ,ANTI,Symmetry,Lev)
-  do k=1,ex(3)
-  do j=1,ex(2)
-  do i=1,ex(1)
-    divb_loc = div_beta(i,j,k)
-    fxx_loc = gxxx(i,j,k) + gxyy(i,j,k) + gxzz(i,j,k)
-    fxy_loc = gxyx(i,j,k) + gyyy(i,j,k) + gyzz(i,j,k)
-    fxz_loc = gxzx(i,j,k) + gyzy(i,j,k) + gzzz(i,j,k)
 
-    gupxx_loc = gupxx(i,j,k)
+  Gamx_rhs =               Gamx_rhs +  F2o3 *  Gamxa * div_beta        - &
-    gupxy_loc = gupxy(i,j,k)
+                     Gamxa * betaxx - Gamya * betaxy - Gamza * betaxz  + &
-    gupxz_loc = gupxz(i,j,k)
+             F1o3 * (gupxx * fxx    + gupxy * fxy    + gupxz * fxz    ) + &
-    gupyy_loc = gupyy(i,j,k)
+                     gupxx * gxxx   + gupyy * gyyx   + gupzz * gzzx    + &
-    gupyz_loc = gupyz(i,j,k)
+              TWO * (gupxy * gxyx   + gupxz * gxzx   + gupyz * gyzx  )
-    gupzz_loc = gupzz(i,j,k)
 
-    Gamxa_loc = gupxx_loc * Gamxxx(i,j,k) + gupyy_loc * Gamxyy(i,j,k) + gupzz_loc * Gamxzz(i,j,k) + &
+  Gamy_rhs =               Gamy_rhs +  F2o3 *  Gamya * div_beta        - &
-         TWO * (gupxy_loc * Gamxxy(i,j,k) + gupxz_loc * Gamxxz(i,j,k) + gupyz_loc * Gamxyz(i,j,k))
+                     Gamxa * betayx - Gamya * betayy - Gamza * betayz  + &
-    Gamya_loc = gupxx_loc * Gamyxx(i,j,k) + gupyy_loc * Gamyyy(i,j,k) + gupzz_loc * Gamyzz(i,j,k) + &
+             F1o3 * (gupxy * fxx    + gupyy * fxy    + gupyz * fxz    ) + &
-         TWO * (gupxy_loc * Gamyxy(i,j,k) + gupxz_loc * Gamyxz(i,j,k) + gupyz_loc * Gamyyz(i,j,k))
+                     gupxx * gxxy   + gupyy * gyyy   + gupzz * gzzy    + &
-    Gamza_loc = gupxx_loc * Gamzxx(i,j,k) + gupyy_loc * Gamzyy(i,j,k) + gupzz_loc * Gamzzz(i,j,k) + &
+              TWO * (gupxy * gxyy   + gupxz * gxzy   + gupyz * gyzy  )
-         TWO * (gupxy_loc * Gamzxy(i,j,k) + gupxz_loc * Gamzxz(i,j,k) + gupyz_loc * Gamzyz(i,j,k))
-    Gamxa(i,j,k) = Gamxa_loc
-    Gamya(i,j,k) = Gamya_loc
-    Gamza(i,j,k) = Gamza_loc
 
-    Gamx_rhs(i,j,k) = Gamx_rhs(i,j,k) + F2o3 * Gamxa_loc * divb_loc - &
+  Gamz_rhs =               Gamz_rhs +  F2o3 *  Gamza * div_beta        - &
-         Gamxa_loc * betaxx(i,j,k) - Gamya_loc * betaxy(i,j,k) - Gamza_loc * betaxz(i,j,k) + &
+                     Gamxa * betazx - Gamya * betazy - Gamza * betazz  + &
-         F1o3 * (gupxx_loc * fxx_loc + gupxy_loc * fxy_loc + gupxz_loc * fxz_loc) + &
+             F1o3 * (gupxz * fxx    + gupyz * fxy    + gupzz * fxz    ) + &
-         gupxx_loc * gxxx(i,j,k) + gupyy_loc * gyyx(i,j,k) + gupzz_loc * gzzx(i,j,k) + &
+                     gupxx * gxxz   + gupyy * gyyz   + gupzz * gzzz    + &
-         TWO * (gupxy_loc * gxyx(i,j,k) + gupxz_loc * gxzx(i,j,k) + gupyz_loc * gyzx(i,j,k))
+              TWO * (gupxy * gxyz   + gupxz * gxzz   + gupyz * gyzz  )    !rhs for Gam^i
-
-    Gamy_rhs(i,j,k) = Gamy_rhs(i,j,k) + F2o3 * Gamya_loc * divb_loc - &
-         Gamxa_loc * betayx(i,j,k) - Gamya_loc * betayy(i,j,k) - Gamza_loc * betayz(i,j,k) + &
-         F1o3 * (gupxy_loc * fxx_loc + gupyy_loc * fxy_loc + gupyz_loc * fxz_loc) + &
-         gupxx_loc * gxxy(i,j,k) + gupyy_loc * gyyy(i,j,k) + gupzz_loc * gzzy(i,j,k) + &
-         TWO * (gupxy_loc * gxyy(i,j,k) + gupxz_loc * gxzy(i,j,k) + gupyz_loc * gyzy(i,j,k))
-
-    Gamz_rhs(i,j,k) = Gamz_rhs(i,j,k) + F2o3 * Gamza_loc * divb_loc - &
-         Gamxa_loc * betazx(i,j,k) - Gamya_loc * betazy(i,j,k) - Gamza_loc * betazz(i,j,k) + &
-         F1o3 * (gupxz_loc * fxx_loc + gupyz_loc * fxy_loc + gupzz_loc * fxz_loc) + &
-         gupxx_loc * gxxz(i,j,k) + gupyy_loc * gyyz(i,j,k) + gupzz_loc * gzzz(i,j,k) + &
-         TWO * (gupxy_loc * gxyz(i,j,k) + gupxz_loc * gxzz(i,j,k) + gupyz_loc * gyzz(i,j,k))
-  enddo
-  enddo
-  enddo
 
 !first kind of connection stored in gij,k
   gxxx = gxx * Gamxxx + gxy * Gamyxx + gxz * Gamzxx
@@ -658,187 +604,189 @@
 !covariant second derivative of chi respect to tilted metric
   call fdderivs(ex,chi,fxx,fxy,fxz,fyy,fyz,fzz,X,Y,Z,SYM,SYM,SYM,Symmetry,Lev)
 
-  do k=1,ex(3)
+  fxx = fxx - Gamxxx * chix - Gamyxx * chiy - Gamzxx * chiz
-  do j=1,ex(2)
+  fxy = fxy - Gamxxy * chix - Gamyxy * chiy - Gamzxy * chiz
-  do i=1,ex(1)
+  fxz = fxz - Gamxxz * chix - Gamyxz * chiy - Gamzxz * chiz
-    fxx(i,j,k) = fxx(i,j,k) - Gamxxx(i,j,k) * chix(i,j,k) - Gamyxx(i,j,k) * chiy(i,j,k) - Gamzxx(i,j,k) * chiz(i,j,k)
+  fyy = fyy - Gamxyy * chix - Gamyyy * chiy - Gamzyy * chiz
-    fxy(i,j,k) = fxy(i,j,k) - Gamxxy(i,j,k) * chix(i,j,k) - Gamyxy(i,j,k) * chiy(i,j,k) - Gamzxy(i,j,k) * chiz(i,j,k)
+  fyz = fyz - Gamxyz * chix - Gamyyz * chiy - Gamzyz * chiz
-    fxz(i,j,k) = fxz(i,j,k) - Gamxxz(i,j,k) * chix(i,j,k) - Gamyxz(i,j,k) * chiy(i,j,k) - Gamzxz(i,j,k) * chiz(i,j,k)
+  fzz = fzz - Gamxzz * chix - Gamyzz * chiy - Gamzzz * chiz
-    fyy(i,j,k) = fyy(i,j,k) - Gamxyy(i,j,k) * chix(i,j,k) - Gamyyy(i,j,k) * chiy(i,j,k) - Gamzyy(i,j,k) * chiz(i,j,k)
+! Store D^l D_l chi - 3/(2*chi) D^l chi D_l chi in f
-    fyz(i,j,k) = fyz(i,j,k) - Gamxyz(i,j,k) * chix(i,j,k) - Gamyyz(i,j,k) * chiy(i,j,k) - Gamzyz(i,j,k) * chiz(i,j,k)
-    fzz(i,j,k) = fzz(i,j,k) - Gamxzz(i,j,k) * chix(i,j,k) - Gamyzz(i,j,k) * chiy(i,j,k) - Gamzzz(i,j,k) * chiz(i,j,k)
 
-    chin_loc = chin1(i,j,k)
+  f =        gupxx * ( fxx - F3o2/chin1 * chix * chix ) + &
-    f_loc = gupxx(i,j,k) * (fxx(i,j,k) - F3o2/chin_loc * chix(i,j,k) * chix(i,j,k)) + &
+             gupyy * ( fyy - F3o2/chin1 * chiy * chiy ) + &
-            gupyy(i,j,k) * (fyy(i,j,k) - F3o2/chin_loc * chiy(i,j,k) * chiy(i,j,k)) + &
+             gupzz * ( fzz - F3o2/chin1 * chiz * chiz ) + &
-            gupzz(i,j,k) * (fzz(i,j,k) - F3o2/chin_loc * chiz(i,j,k) * chiz(i,j,k)) + &
+       TWO * gupxy * ( fxy - F3o2/chin1 * chix * chiy ) + &
-            TWO * gupxy(i,j,k) * (fxy(i,j,k) - F3o2/chin_loc * chix(i,j,k) * chiy(i,j,k)) + &
+       TWO * gupxz * ( fxz - F3o2/chin1 * chix * chiz ) + &
-            TWO * gupxz(i,j,k) * (fxz(i,j,k) - F3o2/chin_loc * chix(i,j,k) * chiz(i,j,k)) + &
+       TWO * gupyz * ( fyz - F3o2/chin1 * chiy * chiz ) 
-            TWO * gupyz(i,j,k) * (fyz(i,j,k) - F3o2/chin_loc * chiy(i,j,k) * chiz(i,j,k))
+! Add chi part to Ricci tensor:
-    f(i,j,k) = f_loc
 
-    Rxx(i,j,k) = Rxx(i,j,k) + (fxx(i,j,k) - chix(i,j,k)*chix(i,j,k)/chin_loc/TWO + gxx(i,j,k) * f_loc)/chin_loc/TWO
+  Rxx = Rxx + (fxx - chix*chix/chin1/TWO + gxx * f)/chin1/TWO
-    Ryy(i,j,k) = Ryy(i,j,k) + (fyy(i,j,k) - chiy(i,j,k)*chiy(i,j,k)/chin_loc/TWO + gyy(i,j,k) * f_loc)/chin_loc/TWO
+  Ryy = Ryy + (fyy - chiy*chiy/chin1/TWO + gyy * f)/chin1/TWO
-    Rzz(i,j,k) = Rzz(i,j,k) + (fzz(i,j,k) - chiz(i,j,k)*chiz(i,j,k)/chin_loc/TWO + gzz(i,j,k) * f_loc)/chin_loc/TWO
+  Rzz = Rzz + (fzz - chiz*chiz/chin1/TWO + gzz * f)/chin1/TWO
-    Rxy(i,j,k) = Rxy(i,j,k) + (fxy(i,j,k) - chix(i,j,k)*chiy(i,j,k)/chin_loc/TWO + gxy(i,j,k) * f_loc)/chin_loc/TWO
+  Rxy = Rxy + (fxy - chix*chiy/chin1/TWO + gxy * f)/chin1/TWO
-    Rxz(i,j,k) = Rxz(i,j,k) + (fxz(i,j,k) - chix(i,j,k)*chiz(i,j,k)/chin_loc/TWO + gxz(i,j,k) * f_loc)/chin_loc/TWO
+  Rxz = Rxz + (fxz - chix*chiz/chin1/TWO + gxz * f)/chin1/TWO
-    Ryz(i,j,k) = Ryz(i,j,k) + (fyz(i,j,k) - chiy(i,j,k)*chiz(i,j,k)/chin_loc/TWO + gyz(i,j,k) * f_loc)/chin_loc/TWO
+  Ryz = Ryz + (fyz - chiy*chiz/chin1/TWO + gyz * f)/chin1/TWO
-  enddo
-  enddo
-  enddo
 
 ! covariant second derivatives of the lapse respect to physical metric
   call fdderivs(ex,Lap,fxx,fxy,fxz,fyy,fyz,fzz,X,Y,Z, &
                 SYM,SYM,SYM,symmetry,Lev)
 
-  do k=1,ex(3)
+  gxxx = (gupxx * chix + gupxy * chiy + gupxz * chiz)/chin1
-  do j=1,ex(2)
+  gxxy = (gupxy * chix + gupyy * chiy + gupyz * chiz)/chin1
-  do i=1,ex(1)
+  gxxz = (gupxz * chix + gupyz * chiy + gupzz * chiz)/chin1
-    chin_loc = chin1(i,j,k)
+! now get physical second kind of connection
-    gxxx(i,j,k) = (gupxx(i,j,k) * chix(i,j,k) + gupxy(i,j,k) * chiy(i,j,k) + gupxz(i,j,k) * chiz(i,j,k)) / chin_loc
+  Gamxxx = Gamxxx - ( (chix + chix)/chin1 - gxx * gxxx )*HALF
-    gxxy(i,j,k) = (gupxy(i,j,k) * chix(i,j,k) + gupyy(i,j,k) * chiy(i,j,k) + gupyz(i,j,k) * chiz(i,j,k)) / chin_loc
+  Gamyxx = Gamyxx - (                     - gxx * gxxy )*HALF
-    gxxz(i,j,k) = (gupxz(i,j,k) * chix(i,j,k) + gupyz(i,j,k) * chiy(i,j,k) + gupzz(i,j,k) * chiz(i,j,k)) / chin_loc
+  Gamzxx = Gamzxx - (                     - gxx * gxxz )*HALF
+  Gamxyy = Gamxyy - (                     - gyy * gxxx )*HALF
+  Gamyyy = Gamyyy - ( (chiy + chiy)/chin1 - gyy * gxxy )*HALF
+  Gamzyy = Gamzyy - (                     - gyy * gxxz )*HALF
+  Gamxzz = Gamxzz - (                     - gzz * gxxx )*HALF
+  Gamyzz = Gamyzz - (                     - gzz * gxxy )*HALF
+  Gamzzz = Gamzzz - ( (chiz + chiz)/chin1 - gzz * gxxz )*HALF
+  Gamxxy = Gamxxy - (  chiy        /chin1 - gxy * gxxx )*HALF
+  Gamyxy = Gamyxy - (         chix /chin1 - gxy * gxxy )*HALF
+  Gamzxy = Gamzxy - (                     - gxy * gxxz )*HALF
+  Gamxxz = Gamxxz - (  chiz        /chin1 - gxz * gxxx )*HALF
+  Gamyxz = Gamyxz - (                     - gxz * gxxy )*HALF
+  Gamzxz = Gamzxz - (         chix /chin1 - gxz * gxxz )*HALF
+  Gamxyz = Gamxyz - (                     - gyz * gxxx )*HALF
+  Gamyyz = Gamyyz - (  chiz        /chin1 - gyz * gxxy )*HALF
+  Gamzyz = Gamzyz - (         chiy /chin1 - gyz * gxxz )*HALF
 
-    Gamxxx(i,j,k) = Gamxxx(i,j,k) - ( (chix(i,j,k) + chix(i,j,k))/chin_loc - gxx(i,j,k) * gxxx(i,j,k) )*HALF
+  fxx = fxx - Gamxxx*Lapx - Gamyxx*Lapy - Gamzxx*Lapz
-    Gamyxx(i,j,k) = Gamyxx(i,j,k) - (                                   - gxx(i,j,k) * gxxy(i,j,k) )*HALF
+  fyy = fyy - Gamxyy*Lapx - Gamyyy*Lapy - Gamzyy*Lapz
-    Gamzxx(i,j,k) = Gamzxx(i,j,k) - (                                   - gxx(i,j,k) * gxxz(i,j,k) )*HALF
+  fzz = fzz - Gamxzz*Lapx - Gamyzz*Lapy - Gamzzz*Lapz
-    Gamxyy(i,j,k) = Gamxyy(i,j,k) - (                                   - gyy(i,j,k) * gxxx(i,j,k) )*HALF
+  fxy = fxy - Gamxxy*Lapx - Gamyxy*Lapy - Gamzxy*Lapz
-    Gamyyy(i,j,k) = Gamyyy(i,j,k) - ( (chiy(i,j,k) + chiy(i,j,k))/chin_loc - gyy(i,j,k) * gxxy(i,j,k) )*HALF
+  fxz = fxz - Gamxxz*Lapx - Gamyxz*Lapy - Gamzxz*Lapz
-    Gamzyy(i,j,k) = Gamzyy(i,j,k) - (                                   - gyy(i,j,k) * gxxz(i,j,k) )*HALF
+  fyz = fyz - Gamxyz*Lapx - Gamyyz*Lapy - Gamzyz*Lapz
-    Gamxzz(i,j,k) = Gamxzz(i,j,k) - (                                   - gzz(i,j,k) * gxxx(i,j,k) )*HALF
-    Gamyzz(i,j,k) = Gamyzz(i,j,k) - (                                   - gzz(i,j,k) * gxxy(i,j,k) )*HALF
-    Gamzzz(i,j,k) = Gamzzz(i,j,k) - ( (chiz(i,j,k) + chiz(i,j,k))/chin_loc - gzz(i,j,k) * gxxz(i,j,k) )*HALF
-    Gamxxy(i,j,k) = Gamxxy(i,j,k) - ( chiy(i,j,k) /chin_loc - gxy(i,j,k) * gxxx(i,j,k) )*HALF
-    Gamyxy(i,j,k) = Gamyxy(i,j,k) - ( chix(i,j,k) /chin_loc - gxy(i,j,k) * gxxy(i,j,k) )*HALF
-    Gamzxy(i,j,k) = Gamzxy(i,j,k) - (                     - gxy(i,j,k) * gxxz(i,j,k) )*HALF
-    Gamxxz(i,j,k) = Gamxxz(i,j,k) - ( chiz(i,j,k) /chin_loc - gxz(i,j,k) * gxxx(i,j,k) )*HALF
-    Gamyxz(i,j,k) = Gamyxz(i,j,k) - (                     - gxz(i,j,k) * gxxy(i,j,k) )*HALF
-    Gamzxz(i,j,k) = Gamzxz(i,j,k) - ( chix(i,j,k) /chin_loc - gxz(i,j,k) * gxxz(i,j,k) )*HALF
-    Gamxyz(i,j,k) = Gamxyz(i,j,k) - (                     - gyz(i,j,k) * gxxx(i,j,k) )*HALF
-    Gamyyz(i,j,k) = Gamyyz(i,j,k) - ( chiz(i,j,k) /chin_loc - gyz(i,j,k) * gxxy(i,j,k) )*HALF
-    Gamzyz(i,j,k) = Gamzyz(i,j,k) - ( chiy(i,j,k) /chin_loc - gyz(i,j,k) * gxxz(i,j,k) )*HALF
 
-    fxx(i,j,k) = fxx(i,j,k) - Gamxxx(i,j,k)*Lapx(i,j,k) - Gamyxx(i,j,k)*Lapy(i,j,k) - Gamzxx(i,j,k)*Lapz(i,j,k)
+! store D^i D_i Lap in trK_rhs upto chi
-    fyy(i,j,k) = fyy(i,j,k) - Gamxyy(i,j,k)*Lapx(i,j,k) - Gamyyy(i,j,k)*Lapy(i,j,k) - Gamzyy(i,j,k)*Lapz(i,j,k)
+  trK_rhs =    gupxx * fxx + gupyy * fyy + gupzz * fzz + &
-    fzz(i,j,k) = fzz(i,j,k) - Gamxzz(i,j,k)*Lapx(i,j,k) - Gamyzz(i,j,k)*Lapy(i,j,k) - Gamzzz(i,j,k)*Lapz(i,j,k)
+        TWO* ( gupxy * fxy + gupxz * fxz + gupyz * fyz )
-    fxy(i,j,k) = fxy(i,j,k) - Gamxxy(i,j,k)*Lapx(i,j,k) - Gamyxy(i,j,k)*Lapy(i,j,k) - Gamzxy(i,j,k)*Lapz(i,j,k)
+#if 1        
-    fxz(i,j,k) = fxz(i,j,k) - Gamxxz(i,j,k)*Lapx(i,j,k) - Gamyxz(i,j,k)*Lapy(i,j,k) - Gamzxz(i,j,k)*Lapz(i,j,k)
+!! follow bam code
-    fyz(i,j,k) = fyz(i,j,k) - Gamxyz(i,j,k)*Lapx(i,j,k) - Gamyyz(i,j,k)*Lapy(i,j,k) - Gamzyz(i,j,k)*Lapz(i,j,k)
+  S =  chin1 * ( gupxx * Sxx + gupyy * Syy + gupzz * Szz + &
+     TWO * ( gupxy * Sxy + gupxz * Sxz + gupyz * Syz ) )
+  f = F2o3 * trK * trK -(&
+       gupxx * ( &
+       gupxx * Axx * Axx + gupyy * Axy * Axy + gupzz * Axz * Axz + &
+       TWO * (gupxy * Axx * Axy + gupxz * Axx * Axz + gupyz * Axy * Axz) ) + &
+       gupyy * ( &
+       gupxx * Axy * Axy + gupyy * Ayy * Ayy + gupzz * Ayz * Ayz + &
+       TWO * (gupxy * Axy * Ayy + gupxz * Axy * Ayz + gupyz * Ayy * Ayz) ) + &
+       gupzz * ( &
+       gupxx * Axz * Axz + gupyy * Ayz * Ayz + gupzz * Azz * Azz + &
+       TWO * (gupxy * Axz * Ayz + gupxz * Axz * Azz + gupyz * Ayz * Azz) ) + &
+       TWO * ( &
+       gupxy * ( &
+       gupxx * Axx * Axy + gupyy * Axy * Ayy + gupzz * Axz * Ayz + &
+       gupxy * (Axx * Ayy + Axy * Axy) + &
+       gupxz * (Axx * Ayz + Axz * Axy) + &
+       gupyz * (Axy * Ayz + Axz * Ayy) ) + &
+       gupxz * ( &
+       gupxx * Axx * Axz + gupyy * Axy * Ayz + gupzz * Axz * Azz + &
+       gupxy * (Axx * Ayz + Axy * Axz) + &
+       gupxz * (Axx * Azz + Axz * Axz) + &
+       gupyz * (Axy * Azz + Axz * Ayz) ) + &
+       gupyz * ( &
+       gupxx * Axy * Axz + gupyy * Ayy * Ayz + gupzz * Ayz * Azz + &
+       gupxy * (Axy * Ayz + Ayy * Axz) + &
+       gupxz * (Axy * Azz + Ayz * Axz) + &
+       gupyz * (Ayy * Azz + Ayz * Ayz) ) )) -1.6d1*PI*rho + EIGHT * PI * S
+  f = - F1o3 *(  gupxx * fxx + gupyy * fyy + gupzz * fzz + &
+        TWO* ( gupxy * fxy + gupxz * fxz + gupyz * fyz ) + alpn1/chin1*f)
   
-    trK_rhs(i,j,k) = gupxx(i,j,k) * fxx(i,j,k) + gupyy(i,j,k) * fyy(i,j,k) + gupzz(i,j,k) * fzz(i,j,k) + &
+  fxx = alpn1 * (Rxx - EIGHT * PI * Sxx) - fxx
-                     TWO * (gupxy(i,j,k) * fxy(i,j,k) + gupxz(i,j,k) * fxz(i,j,k) + gupyz(i,j,k) * fyz(i,j,k))
+  fxy = alpn1 * (Rxy - EIGHT * PI * Sxy) - fxy
-  enddo
+  fxz = alpn1 * (Rxz - EIGHT * PI * Sxz) - fxz
-  enddo
+  fyy = alpn1 * (Ryy - EIGHT * PI * Syy) - fyy
-  enddo
+  fyz = alpn1 * (Ryz - EIGHT * PI * Syz) - fyz
-  do k=1,ex(3)
+  fzz = alpn1 * (Rzz - EIGHT * PI * Szz) - fzz
-  do j=1,ex(2)
+#else        
-  do i=1,ex(1)
+! Add lapse and S_ij parts to Ricci tensor:
-    divb_loc = div_beta(i,j,k)
-    chin_loc = chin1(i,j,k)
 
-    S_loc = chin_loc * ( gupxx(i,j,k) * Sxx(i,j,k) + gupyy(i,j,k) * Syy(i,j,k) + gupzz(i,j,k) * Szz(i,j,k) + &
+  fxx = alpn1 * (Rxx - EIGHT * PI * Sxx) - fxx
-           TWO * (gupxy(i,j,k) * Sxy(i,j,k) + gupxz(i,j,k) * Sxz(i,j,k) + gupyz(i,j,k) * Syz(i,j,k)) )
+  fxy = alpn1 * (Rxy - EIGHT * PI * Sxy) - fxy
-    S(i,j,k) = S_loc
+  fxz = alpn1 * (Rxz - EIGHT * PI * Sxz) - fxz
+  fyy = alpn1 * (Ryy - EIGHT * PI * Syy) - fyy
+  fyz = alpn1 * (Ryz - EIGHT * PI * Syz) - fyz
+  fzz = alpn1 * (Rzz - EIGHT * PI * Szz) - fzz
 
-    f_loc = F2o3 * trK(i,j,k) * trK(i,j,k) - ( &
+! Compute trace-free part (note: chi^-1 and chi cancel!):
-            gupxx(i,j,k) * ( gupxx(i,j,k) * Axx(i,j,k) * Axx(i,j,k) + gupyy(i,j,k) * Axy(i,j,k) * Axy(i,j,k) + &
-                             gupzz(i,j,k) * Axz(i,j,k) * Axz(i,j,k) + &
-                             TWO * (gupxy(i,j,k) * Axx(i,j,k) * Axy(i,j,k) + gupxz(i,j,k) * Axx(i,j,k) * Axz(i,j,k) + &
-                                    gupyz(i,j,k) * Axy(i,j,k) * Axz(i,j,k)) ) + &
-            gupyy(i,j,k) * ( gupxx(i,j,k) * Axy(i,j,k) * Axy(i,j,k) + gupyy(i,j,k) * Ayy(i,j,k) * Ayy(i,j,k) + &
-                             gupzz(i,j,k) * Ayz(i,j,k) * Ayz(i,j,k) + &
-                             TWO * (gupxy(i,j,k) * Axy(i,j,k) * Ayy(i,j,k) + gupxz(i,j,k) * Axy(i,j,k) * Ayz(i,j,k) + &
-                                    gupyz(i,j,k) * Ayy(i,j,k) * Ayz(i,j,k)) ) + &
-            gupzz(i,j,k) * ( gupxx(i,j,k) * Axz(i,j,k) * Axz(i,j,k) + gupyy(i,j,k) * Ayz(i,j,k) * Ayz(i,j,k) + &
-                             gupzz(i,j,k) * Azz(i,j,k) * Azz(i,j,k) + &
-                             TWO * (gupxy(i,j,k) * Axz(i,j,k) * Ayz(i,j,k) + gupxz(i,j,k) * Axz(i,j,k) * Azz(i,j,k) + &
-                                    gupyz(i,j,k) * Ayz(i,j,k) * Azz(i,j,k)) ) + &
-            TWO * ( gupxy(i,j,k) * ( gupxx(i,j,k) * Axx(i,j,k) * Axy(i,j,k) + gupyy(i,j,k) * Axy(i,j,k) * Ayy(i,j,k) + &
-                                     gupzz(i,j,k) * Axz(i,j,k) * Ayz(i,j,k) + &
-                                     gupxy(i,j,k) * (Axx(i,j,k) * Ayy(i,j,k) + Axy(i,j,k) * Axy(i,j,k)) + &
-                                     gupxz(i,j,k) * (Axx(i,j,k) * Ayz(i,j,k) + Axz(i,j,k) * Axy(i,j,k)) + &
-                                     gupyz(i,j,k) * (Axy(i,j,k) * Ayz(i,j,k) + Axz(i,j,k) * Ayy(i,j,k)) ) + &
-                    gupxz(i,j,k) * ( gupxx(i,j,k) * Axx(i,j,k) * Axz(i,j,k) + gupyy(i,j,k) * Axy(i,j,k) * Ayz(i,j,k) + &
-                                     gupzz(i,j,k) * Axz(i,j,k) * Azz(i,j,k) + &
-                                     gupxy(i,j,k) * (Axx(i,j,k) * Ayz(i,j,k) + Axy(i,j,k) * Axz(i,j,k)) + &
-                                     gupxz(i,j,k) * (Axx(i,j,k) * Azz(i,j,k) + Axz(i,j,k) * Axz(i,j,k)) + &
-                                     gupyz(i,j,k) * (Axy(i,j,k) * Azz(i,j,k) + Axz(i,j,k) * Ayz(i,j,k)) ) + &
-                    gupyz(i,j,k) * ( gupxx(i,j,k) * Axy(i,j,k) * Axz(i,j,k) + gupyy(i,j,k) * Ayy(i,j,k) * Ayz(i,j,k) + &
-                                     gupzz(i,j,k) * Ayz(i,j,k) * Azz(i,j,k) + &
-                                     gupxy(i,j,k) * (Axy(i,j,k) * Ayz(i,j,k) + Ayy(i,j,k) * Axz(i,j,k)) + &
-                                     gupxz(i,j,k) * (Axy(i,j,k) * Azz(i,j,k) + Ayz(i,j,k) * Axz(i,j,k)) + &
-                                     gupyz(i,j,k) * (Ayy(i,j,k) * Azz(i,j,k) + Ayz(i,j,k) * Ayz(i,j,k)) ) ) ) - &
-            F16 * PI * rho(i,j,k) + EIGHT * PI * S_loc
 
-    f_loc = -F1o3 * ( gupxx(i,j,k) * fxx(i,j,k) + gupyy(i,j,k) * fyy(i,j,k) + gupzz(i,j,k) * fzz(i,j,k) + &
+  f = F1o3 *(  gupxx * fxx + gupyy * fyy + gupzz * fzz + &
-            TWO * (gupxy(i,j,k) * fxy(i,j,k) + gupxz(i,j,k) * fxz(i,j,k) + gupyz(i,j,k) * fyz(i,j,k)) + &
+        TWO* ( gupxy * fxy + gupxz * fxz + gupyz * fyz ) )
-            alpn1(i,j,k)/chin_loc * f_loc )
+#endif
-    f(i,j,k) = f_loc
 
-    l_fxx = alpn1(i,j,k) * (Rxx(i,j,k) - EIGHT * PI * Sxx(i,j,k)) - fxx(i,j,k)
+  Axx_rhs = fxx - gxx * f
-    l_fxy = alpn1(i,j,k) * (Rxy(i,j,k) - EIGHT * PI * Sxy(i,j,k)) - fxy(i,j,k)
+  Ayy_rhs = fyy - gyy * f
-    l_fxz = alpn1(i,j,k) * (Rxz(i,j,k) - EIGHT * PI * Sxz(i,j,k)) - fxz(i,j,k)
+  Azz_rhs = fzz - gzz * f
-    l_fyy = alpn1(i,j,k) * (Ryy(i,j,k) - EIGHT * PI * Syy(i,j,k)) - fyy(i,j,k)
+  Axy_rhs = fxy - gxy * f
-    l_fyz = alpn1(i,j,k) * (Ryz(i,j,k) - EIGHT * PI * Syz(i,j,k)) - fyz(i,j,k)
+  Axz_rhs = fxz - gxz * f
-    l_fzz = alpn1(i,j,k) * (Rzz(i,j,k) - EIGHT * PI * Szz(i,j,k)) - fzz(i,j,k)
+  Ayz_rhs = fyz - gyz * f
 
-    Axx_rhs(i,j,k) = l_fxx - gxx(i,j,k) * f_loc
+! Now: store A_il A^l_j into fij:
-    Ayy_rhs(i,j,k) = l_fyy - gyy(i,j,k) * f_loc
-    Azz_rhs(i,j,k) = l_fzz - gzz(i,j,k) * f_loc
-    Axy_rhs(i,j,k) = l_fxy - gxy(i,j,k) * f_loc
-    Axz_rhs(i,j,k) = l_fxz - gxz(i,j,k) * f_loc
-    Ayz_rhs(i,j,k) = l_fyz - gyz(i,j,k) * f_loc
 
-    fxx(i,j,k) = gupxx(i,j,k) * Axx(i,j,k) * Axx(i,j,k) + gupyy(i,j,k) * Axy(i,j,k) * Axy(i,j,k) + &
+  fxx =       gupxx * Axx * Axx + gupyy * Axy * Axy + gupzz * Axz * Axz + &
-                 gupzz(i,j,k) * Axz(i,j,k) * Axz(i,j,k) + TWO * (gupxy(i,j,k) * Axx(i,j,k) * Axy(i,j,k) + &
+       TWO * (gupxy * Axx * Axy + gupxz * Axx * Axz + gupyz * Axy * Axz)
-                 gupxz(i,j,k) * Axx(i,j,k) * Axz(i,j,k) + gupyz(i,j,k) * Axy(i,j,k) * Axz(i,j,k))
+  fyy =       gupxx * Axy * Axy + gupyy * Ayy * Ayy + gupzz * Ayz * Ayz + &
-    fyy(i,j,k) = gupxx(i,j,k) * Axy(i,j,k) * Axy(i,j,k) + gupyy(i,j,k) * Ayy(i,j,k) * Ayy(i,j,k) + &
+       TWO * (gupxy * Axy * Ayy + gupxz * Axy * Ayz + gupyz * Ayy * Ayz)
-                 gupzz(i,j,k) * Ayz(i,j,k) * Ayz(i,j,k) + TWO * (gupxy(i,j,k) * Axy(i,j,k) * Ayy(i,j,k) + &
+  fzz =       gupxx * Axz * Axz + gupyy * Ayz * Ayz + gupzz * Azz * Azz + &
-                 gupxz(i,j,k) * Axy(i,j,k) * Ayz(i,j,k) + gupyz(i,j,k) * Ayy(i,j,k) * Ayz(i,j,k))
+       TWO * (gupxy * Axz * Ayz + gupxz * Axz * Azz + gupyz * Ayz * Azz)
-    fzz(i,j,k) = gupxx(i,j,k) * Axz(i,j,k) * Axz(i,j,k) + gupyy(i,j,k) * Ayz(i,j,k) * Ayz(i,j,k) + &
+  fxy =       gupxx * Axx * Axy + gupyy * Axy * Ayy + gupzz * Axz * Ayz + &
-                 gupzz(i,j,k) * Azz(i,j,k) * Azz(i,j,k) + TWO * (gupxy(i,j,k) * Axz(i,j,k) * Ayz(i,j,k) + &
+              gupxy *(Axx * Ayy + Axy * Axy)                            + &
-                 gupxz(i,j,k) * Axz(i,j,k) * Azz(i,j,k) + gupyz(i,j,k) * Ayz(i,j,k) * Azz(i,j,k))
+              gupxz *(Axx * Ayz + Axz * Axy)                            + &
-    fxy(i,j,k) = gupxx(i,j,k) * Axx(i,j,k) * Axy(i,j,k) + gupyy(i,j,k) * Axy(i,j,k) * Ayy(i,j,k) + &
+              gupyz *(Axy * Ayz + Axz * Ayy)
-                 gupzz(i,j,k) * Axz(i,j,k) * Ayz(i,j,k) + gupxy(i,j,k) * (Axx(i,j,k) * Ayy(i,j,k) + Axy(i,j,k) * Axy(i,j,k)) + &
+  fxz =       gupxx * Axx * Axz + gupyy * Axy * Ayz + gupzz * Axz * Azz + &
-                 gupxz(i,j,k) * (Axx(i,j,k) * Ayz(i,j,k) + Axz(i,j,k) * Axy(i,j,k)) + &
+              gupxy *(Axx * Ayz + Axy * Axz)                            + &
-                 gupyz(i,j,k) * (Axy(i,j,k) * Ayz(i,j,k) + Axz(i,j,k) * Ayy(i,j,k))
+              gupxz *(Axx * Azz + Axz * Axz)                            + &
-    fxz(i,j,k) = gupxx(i,j,k) * Axx(i,j,k) * Axz(i,j,k) + gupyy(i,j,k) * Axy(i,j,k) * Ayz(i,j,k) + &
+              gupyz *(Axy * Azz + Axz * Ayz)
-                 gupzz(i,j,k) * Axz(i,j,k) * Azz(i,j,k) + gupxy(i,j,k) * (Axx(i,j,k) * Ayz(i,j,k) + Axy(i,j,k) * Axz(i,j,k)) + &
+  fyz =       gupxx * Axy * Axz + gupyy * Ayy * Ayz + gupzz * Ayz * Azz + &
-                 gupxz(i,j,k) * (Axx(i,j,k) * Azz(i,j,k) + Axz(i,j,k) * Axz(i,j,k)) + &
+              gupxy *(Axy * Ayz + Ayy * Axz)                            + &
-                 gupyz(i,j,k) * (Axy(i,j,k) * Azz(i,j,k) + Axz(i,j,k) * Ayz(i,j,k))
+              gupxz *(Axy * Azz + Ayz * Axz)                            + &
-    fyz(i,j,k) = gupxx(i,j,k) * Axy(i,j,k) * Axz(i,j,k) + gupyy(i,j,k) * Ayy(i,j,k) * Ayz(i,j,k) + &
+              gupyz *(Ayy * Azz + Ayz * Ayz)
-                 gupzz(i,j,k) * Ayz(i,j,k) * Azz(i,j,k) + gupxy(i,j,k) * (Axy(i,j,k) * Ayz(i,j,k) + Ayy(i,j,k) * Axz(i,j,k)) + &
-                 gupxz(i,j,k) * (Axy(i,j,k) * Azz(i,j,k) + Ayz(i,j,k) * Axz(i,j,k)) + &
-                 gupyz(i,j,k) * (Ayy(i,j,k) * Azz(i,j,k) + Ayz(i,j,k) * Ayz(i,j,k))
 
-    trK_rhs(i,j,k) = chin_loc * trK_rhs(i,j,k)
+  f = chin1
+! store D^i D_i Lap in trK_rhs
+  trK_rhs = f*trK_rhs
           
-    Axx_rhs(i,j,k) = chin_loc * Axx_rhs(i,j,k) + alpn1(i,j,k) * (trK(i,j,k) * Axx(i,j,k) - TWO * fxx(i,j,k)) + &
+  Axx_rhs =           f * Axx_rhs+ alpn1 * (trK * Axx - TWO * fxx)  + &
-                     TWO * (Axx(i,j,k) * betaxx(i,j,k) + Axy(i,j,k) * betayx(i,j,k) + Axz(i,j,k) * betazx(i,j,k)) - &
+           TWO * (  Axx * betaxx +   Axy * betayx +   Axz * betazx )- &
-                     F2o3 * Axx(i,j,k) * divb_loc
+             F2o3 * Axx * div_beta
-    Ayy_rhs(i,j,k) = chin_loc * Ayy_rhs(i,j,k) + alpn1(i,j,k) * (trK(i,j,k) * Ayy(i,j,k) - TWO * fyy(i,j,k)) + &
-                     TWO * (Axy(i,j,k) * betaxy(i,j,k) + Ayy(i,j,k) * betayy(i,j,k) + Ayz(i,j,k) * betazy(i,j,k)) - &
-                     F2o3 * Ayy(i,j,k) * divb_loc
-    Azz_rhs(i,j,k) = chin_loc * Azz_rhs(i,j,k) + alpn1(i,j,k) * (trK(i,j,k) * Azz(i,j,k) - TWO * fzz(i,j,k)) + &
-                     TWO * (Axz(i,j,k) * betaxz(i,j,k) + Ayz(i,j,k) * betayz(i,j,k) + Azz(i,j,k) * betazz(i,j,k)) - &
-                     F2o3 * Azz(i,j,k) * divb_loc
-    Axy_rhs(i,j,k) = chin_loc * Axy_rhs(i,j,k) + alpn1(i,j,k) * (trK(i,j,k) * Axy(i,j,k) - TWO * fxy(i,j,k)) + &
-                     Axx(i,j,k) * betaxy(i,j,k) + Axz(i,j,k) * betazy(i,j,k) + Ayy(i,j,k) * betayx(i,j,k) + &
-                     Ayz(i,j,k) * betazx(i,j,k) + F1o3 * Axy(i,j,k) * divb_loc - Axy(i,j,k) * betazz(i,j,k)
-    Ayz_rhs(i,j,k) = chin_loc * Ayz_rhs(i,j,k) + alpn1(i,j,k) * (trK(i,j,k) * Ayz(i,j,k) - TWO * fyz(i,j,k)) + &
-                     Axy(i,j,k) * betaxz(i,j,k) + Ayy(i,j,k) * betayz(i,j,k) + Axz(i,j,k) * betaxy(i,j,k) + &
-                     Azz(i,j,k) * betazy(i,j,k) + F1o3 * Ayz(i,j,k) * divb_loc - Ayz(i,j,k) * betaxx(i,j,k)
-    Axz_rhs(i,j,k) = chin_loc * Axz_rhs(i,j,k) + alpn1(i,j,k) * (trK(i,j,k) * Axz(i,j,k) - TWO * fxz(i,j,k)) + &
-                     Axx(i,j,k) * betaxz(i,j,k) + Axy(i,j,k) * betayz(i,j,k) + Ayz(i,j,k) * betayx(i,j,k) + &
-                     Azz(i,j,k) * betazx(i,j,k) + F1o3 * Axz(i,j,k) * divb_loc - Axz(i,j,k) * betayy(i,j,k)
 
-    trK_rhs(i,j,k) = - trK_rhs(i,j,k) + alpn1(i,j,k) * ( F1o3 * trK(i,j,k) * trK(i,j,k) + &
+  Ayy_rhs =           f * Ayy_rhs+ alpn1 * (trK * Ayy - TWO * fyy)  + &
-                    gupxx(i,j,k) * fxx(i,j,k) + gupyy(i,j,k) * fyy(i,j,k) + gupzz(i,j,k) * fzz(i,j,k) + &
+           TWO * (  Axy * betaxy +   Ayy * betayy +   Ayz * betazy )- &
-                    TWO * (gupxy(i,j,k) * fxy(i,j,k) + gupxz(i,j,k) * fxz(i,j,k) + gupyz(i,j,k) * fyz(i,j,k)) + &
+             F2o3 * Ayy * div_beta
-                    FOUR * PI * (rho(i,j,k) + S_loc) )
+
-  enddo
+  Azz_rhs =           f * Azz_rhs+ alpn1 * (trK * Azz - TWO * fzz)  + &
-  enddo
+           TWO * (  Axz * betaxz +   Ayz * betayz +   Azz * betazz )- &
-  enddo
+             F2o3 * Azz * div_beta
+
+  Axy_rhs =           f * Axy_rhs+ alpn1 *( trK * Axy  - TWO * fxy )+ &
+                    Axx * betaxy                  +   Axz * betazy  + &
+                                     Ayy * betayx +   Ayz * betazx  + &
+             F1o3 * Axy * div_beta                -   Axy * betazz
+
+  Ayz_rhs =           f * Ayz_rhs+ alpn1 *( trK * Ayz  - TWO * fyz )+ &
+                    Axy * betaxz +   Ayy * betayz                   + &
+                    Axz * betaxy                  +   Azz * betazy  + &
+             F1o3 * Ayz * div_beta                -   Ayz * betaxx
+ 
+  Axz_rhs =           f * Axz_rhs+ alpn1 *( trK * Axz  - TWO * fxz )+ &
+                    Axx * betaxz +   Axy * betayz                   + &
+                                     Ayz * betayx +   Azz * betazx  + &
+             F1o3 * Axz * div_beta                -   Axz * betayy      !rhs for Aij
+
+! Compute trace of S_ij
+
+  S =  f * ( gupxx * Sxx + gupyy * Syy + gupzz * Szz + &
+     TWO * ( gupxy * Sxy + gupxz * Sxz + gupyz * Syz ) )
+
+  trK_rhs = - trK_rhs + alpn1 *( F1o3 * trK * trK         + &
+                gupxx * fxx + gupyy * fyy + gupzz * fzz   + &
+        TWO * ( gupxy * fxy + gupxz * fxz + gupyz * fyz ) + &
+       FOUR * PI * ( rho + S ))                                !rhs for trK
   
 !!!! gauge variable part
 
@@ -1000,15 +948,15 @@
 !!!!!!!!!advection term + Kreiss-Oliger dissipation (merged for cache efficiency)
 ! lopsided_kodis shares the symmetry_bd buffer between advection and
 ! dissipation, eliminating redundant full-grid copies. For metric variables
-! gxx/gyy/gzz (=dxx/dyy/dzz+1): stencil coefficients sum to zero,
+! gxx/gyy/gzz (=dxx/dyy/dzz+1): kodis stencil coefficients sum to zero,
 ! so the constant offset has no effect on dissipation.
 
-  call lopsided_kodis(ex,X,Y,Z,dxx,gxx_rhs,betax,betay,betaz,Symmetry,SSS,eps)
+  call lopsided_kodis(ex,X,Y,Z,gxx,gxx_rhs,betax,betay,betaz,Symmetry,SSS,eps)
   call lopsided_kodis(ex,X,Y,Z,gxy,gxy_rhs,betax,betay,betaz,Symmetry,AAS,eps)
   call lopsided_kodis(ex,X,Y,Z,gxz,gxz_rhs,betax,betay,betaz,Symmetry,ASA,eps)
-  call lopsided_kodis(ex,X,Y,Z,dyy,gyy_rhs,betax,betay,betaz,Symmetry,SSS,eps)
+  call lopsided_kodis(ex,X,Y,Z,gyy,gyy_rhs,betax,betay,betaz,Symmetry,SSS,eps)
   call lopsided_kodis(ex,X,Y,Z,gyz,gyz_rhs,betax,betay,betaz,Symmetry,SAA,eps)
-  call lopsided_kodis(ex,X,Y,Z,dzz,gzz_rhs,betax,betay,betaz,Symmetry,SSS,eps)
+  call lopsided_kodis(ex,X,Y,Z,gzz,gzz_rhs,betax,betay,betaz,Symmetry,SSS,eps)
 
   call lopsided_kodis(ex,X,Y,Z,Axx,Axx_rhs,betax,betay,betaz,Symmetry,SSS,eps)
   call lopsided_kodis(ex,X,Y,Z,Axy,Axy_rhs,betax,betay,betaz,Symmetry,AAS,eps)

AMSS_NCKU_source/bssn_rhs.h

@@ -32,19 +32,6 @@
 #define f_compute_rhs_Z4c_ss compute_rhs_z4c_ss_
 #define f_compute_constraint_fr compute_constraint_fr_
 #endif
-
-#ifdef __cplusplus
-extern "C"
-{
-#endif
-        void f_bssn_rhs_kernel_timing_reset();
-        int f_bssn_rhs_kernel_timing_bucket_count();
-        const double *f_bssn_rhs_kernel_timing_local_seconds();
-        const char *f_bssn_rhs_kernel_timing_label(int);
-#ifdef __cplusplus
-}
-#endif
-
 extern "C"
 {
         int f_compute_rhs_bssn(int *, double &, double *, double *, double *,                                                      // ex,T,X,Y,Z

AMSS_NCKU_source/bssn_rhs_cuda.h

@@ -0,0 +1,36 @@
+#ifndef BSSN_RHS_CUDA_H
+#define BSSN_RHS_CUDA_H
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+int f_compute_rhs_bssn(int *ex, double &T,
+                       double *X, double *Y, double *Z,
+                       double *chi, double *trK,
+                       double *dxx, double *gxy, double *gxz, double *dyy, double *gyz, double *dzz,
+                       double *Axx, double *Axy, double *Axz, double *Ayy, double *Ayz, double *Azz,
+                       double *Gamx, double *Gamy, double *Gamz,
+                       double *Lap, double *betax, double *betay, double *betaz,
+                       double *dtSfx, double *dtSfy, double *dtSfz,
+                       double *chi_rhs, double *trK_rhs,
+                       double *gxx_rhs, double *gxy_rhs, double *gxz_rhs, double *gyy_rhs, double *gyz_rhs, double *gzz_rhs,
+                       double *Axx_rhs, double *Axy_rhs, double *Axz_rhs, double *Ayy_rhs, double *Ayz_rhs, double *Azz_rhs,
+                       double *Gamx_rhs, double *Gamy_rhs, double *Gamz_rhs,
+                       double *Lap_rhs, double *betax_rhs, double *betay_rhs, double *betaz_rhs,
+                       double *dtSfx_rhs, double *dtSfy_rhs, double *dtSfz_rhs,
+                       double *rho, double *Sx, double *Sy, double *Sz,
+                       double *Sxx, double *Sxy, double *Sxz, double *Syy, double *Syz, double *Szz,
+                       double *Gamxxx, double *Gamxxy, double *Gamxxz, double *Gamxyy, double *Gamxyz, double *Gamxzz,
+                       double *Gamyxx, double *Gamyxy, double *Gamyxz, double *Gamyyy, double *Gamyyz, double *Gamyzz,
+                       double *Gamzxx, double *Gamzxy, double *Gamzxz, double *Gamzyy, double *Gamzyz, double *Gamzzz,
+                       double *Rxx, double *Rxy, double *Rxz, double *Ryy, double *Ryz, double *Rzz,
+                       double *ham_Res, double *movx_Res, double *movy_Res, double *movz_Res,
+                       double *Gmx_Res, double *Gmy_Res, double *Gmz_Res,
+                       int &Symmetry, int &Lev, double &eps, int &co);
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif

AMSS_NCKU_source/diff_newwb.f90

@@ -1513,7 +1513,6 @@
   real*8,dimension(-1:ex(1),-1:ex(2),-1:ex(3))   :: fh
   real*8, dimension(3) :: SoA
   integer :: imin,jmin,kmin,imax,jmax,kmax,i,j,k
-  integer :: i_core_min,i_core_max,j_core_min,j_core_max,k_core_min,k_core_max
   real*8  :: Sdxdx,Sdydy,Sdzdz,Fdxdx,Fdydy,Fdzdz
   real*8  :: Sdxdy,Sdxdz,Sdydz,Fdxdy,Fdxdz,Fdydz
   integer, parameter :: NO_SYMM = 0, EQ_SYMM = 1, OCTANT = 2
@@ -1566,47 +1565,9 @@
   fxz = ZEO
   fyz = ZEO
 
-  i_core_min = max(1, imin+2)
-  i_core_max = min(ex(1), imax-2)
-  j_core_min = max(1, jmin+2)
-  j_core_max = min(ex(2), jmax-2)
-  k_core_min = max(1, kmin+2)
-  k_core_max = min(ex(3), kmax-2)
-
-  if(i_core_min <= i_core_max .and. j_core_min <= j_core_max .and. k_core_min <= k_core_max)then
-   do k=k_core_min,k_core_max
-   do j=j_core_min,j_core_max
-   do i=i_core_min,i_core_max
-! interior points always use 4th-order stencils without branch checks
-      fxx(i,j,k) = Fdxdx*(-fh(i-2,j,k)+F16*fh(i-1,j,k)-F30*fh(i,j,k) &
-                          -fh(i+2,j,k)+F16*fh(i+1,j,k)              )
-      fyy(i,j,k) = Fdydy*(-fh(i,j-2,k)+F16*fh(i,j-1,k)-F30*fh(i,j,k) &
-                          -fh(i,j+2,k)+F16*fh(i,j+1,k)              )
-      fzz(i,j,k) = Fdzdz*(-fh(i,j,k-2)+F16*fh(i,j,k-1)-F30*fh(i,j,k) &
-                          -fh(i,j,k+2)+F16*fh(i,j,k+1)              )
-      fxy(i,j,k) = Fdxdy*(     (fh(i-2,j-2,k)-F8*fh(i-1,j-2,k)+F8*fh(i+1,j-2,k)-fh(i+2,j-2,k))  &
-                          -F8 *(fh(i-2,j-1,k)-F8*fh(i-1,j-1,k)+F8*fh(i+1,j-1,k)-fh(i+2,j-1,k))  &
-                          +F8 *(fh(i-2,j+1,k)-F8*fh(i-1,j+1,k)+F8*fh(i+1,j+1,k)-fh(i+2,j+1,k))  &
-                          -    (fh(i-2,j+2,k)-F8*fh(i-1,j+2,k)+F8*fh(i+1,j+2,k)-fh(i+2,j+2,k)))
-      fxz(i,j,k) = Fdxdz*(     (fh(i-2,j,k-2)-F8*fh(i-1,j,k-2)+F8*fh(i+1,j,k-2)-fh(i+2,j,k-2))  &
-                          -F8 *(fh(i-2,j,k-1)-F8*fh(i-1,j,k-1)+F8*fh(i+1,j,k-1)-fh(i+2,j,k-1))  &
-                          +F8 *(fh(i-2,j,k+1)-F8*fh(i-1,j,k+1)+F8*fh(i+1,j,k+1)-fh(i+2,j,k+1))  &
-                          -    (fh(i-2,j,k+2)-F8*fh(i-1,j,k+2)+F8*fh(i+1,j,k+2)-fh(i+2,j,k+2)))
-      fyz(i,j,k) = Fdydz*(     (fh(i,j-2,k-2)-F8*fh(i,j-1,k-2)+F8*fh(i,j+1,k-2)-fh(i,j+2,k-2))  &
-                          -F8 *(fh(i,j-2,k-1)-F8*fh(i,j-1,k-1)+F8*fh(i,j+1,k-1)-fh(i,j+2,k-1))  &
-                          +F8 *(fh(i,j-2,k+1)-F8*fh(i,j-1,k+1)+F8*fh(i,j+1,k+1)-fh(i,j+2,k+1))  &
-                          -    (fh(i,j-2,k+2)-F8*fh(i,j-1,k+2)+F8*fh(i,j+1,k+2)-fh(i,j+2,k+2)))
-   enddo
-   enddo
-   enddo
-  endif
-
   do k=1,ex(3)
   do j=1,ex(2)
   do i=1,ex(1)
-      if(i>=i_core_min .and. i<=i_core_max .and. &
-         j>=j_core_min .and. j<=j_core_max .and. &
-         k>=k_core_min .and. k<=k_core_max) cycle
 !~~~~~~ fxx
         if(i+2 <= imax .and. i-2 >= imin)then
 !

AMSS_NCKU_source/fderivs_c.C

@@ -81,63 +81,26 @@ void fderivs(const int ex[3],
     }
 
     /*
-     * 两段式：
+     * Fortran loops:
-     * 1) 先在二阶可用区域计算二阶模板
+     * do k=1,ex3-1
-     * 2) 再在高阶可用区域覆盖为四阶模板
+     * do j=1,ex2-1
+     * do i=1,ex1-1
      *
-     * 与原 if/elseif 逻辑等价，但减少逐点分支判断。
+     * C: k0=0..ex3-2, j0=0..ex2-2, i0=0..ex1-2
      */
-    const int i2_lo = (iminF > 0) ? iminF : 0;
+    for (int k0 = 0; k0 <= ex3 - 2; ++k0) {
-    const int j2_lo = (jminF > 0) ? jminF : 0;
+        const int kF = k0 + 1;
-    const int k2_lo = (kminF > 0) ? kminF : 0;
+        for (int j0 = 0; j0 <= ex2 - 2; ++j0) {
-    const int i2_hi = ex1 - 2;
+            const int jF = j0 + 1;
-    const int j2_hi = ex2 - 2;
+            for (int i0 = 0; i0 <= ex1 - 2; ++i0) {
-    const int k2_hi = ex3 - 2;
+                const int iF = i0 + 1;
-
+                const size_t p = idx_ex(i0, j0, k0, ex);
-    const int i4_lo = (iminF + 1 > 0) ? (iminF + 1) : 0;
-    const int j4_lo = (jminF + 1 > 0) ? (jminF + 1) : 0;
-    const int k4_lo = (kminF + 1 > 0) ? (kminF + 1) : 0;
-    const int i4_hi = ex1 - 3;
-    const int j4_hi = ex2 - 3;
-    const int k4_hi = ex3 - 3;
-
-    if (i2_lo <= i2_hi && j2_lo <= j2_hi && k2_lo <= k2_hi) {
-        for (int k0 = k2_lo; k0 <= k2_hi; ++k0) {
-            const int kF = k0 + 1;
-            for (int j0 = j2_lo; j0 <= j2_hi; ++j0) {
-                const int jF = j0 + 1;
-                for (int i0 = i2_lo; i0 <= i2_hi; ++i0) {
-                    const int iF = i0 + 1;
-                    const size_t p = idx_ex(i0, j0, k0, ex);
-
-                    fx[p] = d2dx * (
-                        -fh[idx_fh_F_ord2(iF - 1, jF,     kF,     ex)] +
-                         fh[idx_fh_F_ord2(iF + 1, jF,     kF,     ex)]
-                    );
-
-                    fy[p] = d2dy * (
-                        -fh[idx_fh_F_ord2(iF,     jF - 1, kF,     ex)] +
-                         fh[idx_fh_F_ord2(iF,     jF + 1, kF,     ex)]
-                    );
-
-                    fz[p] = d2dz * (
-                        -fh[idx_fh_F_ord2(iF,     jF,     kF - 1, ex)] +
-                         fh[idx_fh_F_ord2(iF,     jF,     kF + 1, ex)]
-                    );
-                }
-            }
-        }
-    }
-
-    if (i4_lo <= i4_hi && j4_lo <= j4_hi && k4_lo <= k4_hi) {
-        for (int k0 = k4_lo; k0 <= k4_hi; ++k0) {
-            const int kF = k0 + 1;
-            for (int j0 = j4_lo; j0 <= j4_hi; ++j0) {
-                const int jF = j0 + 1;
-                for (int i0 = i4_lo; i0 <= i4_hi; ++i0) {
-                    const int iF = i0 + 1;
-                    const size_t p = idx_ex(i0, j0, k0, ex);
 
+                // if(i+2 <= imax .and. i-2 >= imin ... )  (全是 Fortran 索引)
+                if ((iF + 2) <= imaxF && (iF - 2) >= iminF &&
+                    (jF + 2) <= jmaxF && (jF - 2) >= jminF &&
+                    (kF + 2) <= kmaxF && (kF - 2) >= kminF)
+                {
                     fx[p] = d12dx * (
                         fh[idx_fh_F_ord2(iF - 2, jF,     kF,     ex)] -
                         EIT * fh[idx_fh_F_ord2(iF - 1, jF,     kF,     ex)] +
@@ -159,6 +122,26 @@ void fderivs(const int ex[3],
                         fh[idx_fh_F_ord2(iF,     jF,     kF + 2, ex)]
                     );
                 }
+                // elseif(i+1 <= imax .and. i-1 >= imin ...)
+                else if ((iF + 1) <= imaxF && (iF - 1) >= iminF &&
+                         (jF + 1) <= jmaxF && (jF - 1) >= jminF &&
+                         (kF + 1) <= kmaxF && (kF - 1) >= kminF)
+                {
+                    fx[p] = d2dx * (
+                        -fh[idx_fh_F_ord2(iF - 1, jF,     kF,     ex)] +
+                         fh[idx_fh_F_ord2(iF + 1, jF,     kF,     ex)]
+                    );
+
+                    fy[p] = d2dy * (
+                        -fh[idx_fh_F_ord2(iF,     jF - 1, kF,     ex)] +
+                         fh[idx_fh_F_ord2(iF,     jF + 1, kF,     ex)]
+                    );
+
+                    fz[p] = d2dz * (
+                        -fh[idx_fh_F_ord2(iF,     jF,     kF - 1, ex)] +
+                         fh[idx_fh_F_ord2(iF,     jF,     kF + 1, ex)]
+                    );
+                }
             }
         }
     }

AMSS_NCKU_source/fmisc.f90

@@ -1327,6 +1327,35 @@ end subroutine d2dump
 
   return
   end subroutine polint
+
+  subroutine polint0(xa, ya, y, ordn)
+  ! Lagrange interpolation at x=0, O(n) direct formula
+  implicit none
+  integer, intent(in) :: ordn
+  real*8, dimension(ordn), intent(in) :: xa, ya
+  real*8, intent(out) :: y
+
+  integer :: j, k
+  real*8 :: wj
+
+  y = 0.d0
+  do j = 1, ordn
+    wj = 1.d0
+    do k = 1, ordn
+      if (k .ne. j) then
+        wj = wj * xa(k) / (xa(k) - xa(j))
+      endif
+    enddo
+    y = y + wj * ya(j)
+  enddo
+
+  return
+  end subroutine polint0
+!------------------------------------------------------------------------------
+!
+! interpolation in 2 dimensions, follow yx order
+!
+!------------------------------------------------------------------------------
 !------------------------------------------------------------------------------
 ! Compute Lagrange interpolation basis weights for one target point.
 !------------------------------------------------------------------------------
@@ -1514,81 +1543,6 @@ f_out = f_out*dX*dY*dZ
   return
 
   end subroutine l2normhelper
-!--------------------------------------------------------------------------------------
-  subroutine l2normhelper7(ex, X, Y, Z,xmin,ymin,zmin,xmax,ymax,zmax,&
-                           f1,f2,f3,f4,f5,f6,f7,f_out,gw)
-
-  implicit none
-!~~~~~~> Input parameters:
-  integer,intent(in ):: ex(1:3)
-  real*8, intent(in ):: X(1:ex(1)),Y(1:ex(2)),Z(1:ex(3)),xmin,ymin,zmin,xmax,ymax,zmax
-  integer,intent(in)::gw
-  real*8, dimension(ex(1),ex(2),ex(3)),intent(in) :: f1,f2,f3,f4,f5,f6,f7
-  real*8, intent(out) :: f_out(7)
-!~~~~~~> Other variables:
-
-  real*8            :: dX, dY, dZ
-  integer::imin,jmin,kmin
-  integer::imax,jmax,kmax
-  integer::i,j,k
-  real*8 :: s1,s2,s3,s4,s5,s6,s7
-
-  dX = X(2) - X(1)
-  dY = Y(2) - Y(1)
-  dZ = Z(2) - Z(1)
-
-! for ghost zone
-   imin = gw+1
-   jmin = gw+1
-   kmin = gw+1
-
-   imax = ex(1) - gw
-   jmax = ex(2) - gw
-   kmax = ex(3) - gw
-
-!for patch boundary (i.e., not ghost boundary)
-
-if(dabs(X(ex(1))-xmax) < dX) imax = ex(1)
-if(dabs(Y(ex(2))-ymax) < dY) jmax = ex(2)
-if(dabs(Z(ex(3))-zmax) < dZ) kmax = ex(3)
-if(dabs(X(1)-xmin) < dX) imin = 1
-if(dabs(Y(1)-ymin) < dY) jmin = 1
-if(dabs(Z(1)-zmin) < dZ) kmin = 1
-
-  s1 = 0.d0
-  s2 = 0.d0
-  s3 = 0.d0
-  s4 = 0.d0
-  s5 = 0.d0
-  s6 = 0.d0
-  s7 = 0.d0
-
-  do k=kmin,kmax
-    do j=jmin,jmax
-!DIR$ SIMD REDUCTION(+:s1,s2,s3,s4,s5,s6,s7)
-      do i=imin,imax
-        s1 = s1 + f1(i,j,k)*f1(i,j,k)
-        s2 = s2 + f2(i,j,k)*f2(i,j,k)
-        s3 = s3 + f3(i,j,k)*f3(i,j,k)
-        s4 = s4 + f4(i,j,k)*f4(i,j,k)
-        s5 = s5 + f5(i,j,k)*f5(i,j,k)
-        s6 = s6 + f6(i,j,k)*f6(i,j,k)
-        s7 = s7 + f7(i,j,k)*f7(i,j,k)
-      enddo
-    enddo
-  enddo
-
-  f_out(1) = s1*dX*dY*dZ
-  f_out(2) = s2*dX*dY*dZ
-  f_out(3) = s3*dX*dY*dZ
-  f_out(4) = s4*dX*dY*dZ
-  f_out(5) = s5*dX*dY*dZ
-  f_out(6) = s6*dX*dY*dZ
-  f_out(7) = s7*dX*dY*dZ
-
-  return
-
-  end subroutine l2normhelper7
 !--------------------------------------------------------------------------------------
 ! calculate L2norm especially for shell Blocks
   subroutine l2normhelper_sh(ex, X, Y, Z,xmin,ymin,zmin,xmax,ymax,zmax,&

AMSS_NCKU_source/fmisc.h

@@ -13,7 +13,6 @@
 #define f_global_interpind2d global_interpind2d
 #define f_global_interpind1d global_interpind1d
 #define f_l2normhelper l2normhelper
-#define f_l2normhelper7 l2normhelper7
 #define f_l2normhelper_sh l2normhelper_sh
 #define f_l2normhelper_sh_rms l2normhelper_sh_rms
 #define f_average average
@@ -43,7 +42,6 @@
 #define f_global_interpind2d GLOBAL_INTERPIND2D
 #define f_global_interpind1d GLOBAL_INTERPIND1D
 #define f_l2normhelper L2NORMHELPER
-#define f_l2normhelper7 L2NORMHELPER7
 #define f_l2normhelper_sh L2NORMHELPER_SH
 #define f_l2normhelper_sh_rms L2NORMHELPER_SH_RMS
 #define f_average AVERAGE
@@ -73,7 +71,6 @@
 #define f_global_interpind2d global_interpind2d_
 #define f_global_interpind1d global_interpind1d_
 #define f_l2normhelper l2normhelper_
-#define f_l2normhelper7 l2normhelper7_
 #define f_l2normhelper_sh l2normhelper_sh_
 #define f_l2normhelper_sh_rms l2normhelper_sh_rms_
 #define f_average average_
@@ -167,15 +164,6 @@ extern "C"
 						double *, double &, int &);
 }
 
-extern "C"
-{
-	void f_l2normhelper7(int *, double *, double *, double *,
-						 double &, double &, double &,
-						 double &, double &, double &,
-						 double *, double *, double *, double *,
-						 double *, double *, double *, double *, int &);
-}
-
 extern "C"
 {
 	void f_l2normhelper_sh(int *, double *, double *, double *,

AMSS_NCKU_source/gaussj.C

@@ -17,103 +17,65 @@ using namespace std;
 #include <math.h>
 #endif
 
-/* Linear equation solution by Gauss-Jordan elimination.
+// Intel oneMKL LAPACK interface
+#include <mkl_lapacke.h>
+/* Linear equation solution using Intel oneMKL LAPACK.
 a[0..n-1][0..n-1] is the input matrix. b[0..n-1] is input
 containing the right-hand side vectors. On output a is
 replaced by its matrix inverse, and b is replaced by the
-corresponding set of solution vectors. */
+corresponding set of solution vectors.
+
+Mathematical equivalence:
+  Solves: A * x = b  =>  x = A^(-1) * b
+  Original Gauss-Jordan and LAPACK dgesv/dgetri produce identical results
+  within numerical precision. */
 
 int gaussj(double *a, double *b, int n)
 {
-  double swap;
+  // Allocate pivot array and workspace
+  lapack_int *ipiv = new lapack_int[n];
+  lapack_int info;
 
-  int *indxc, *indxr, *ipiv;
+  // Make a copy of matrix a for solving (dgesv modifies it to LU form)
-  indxc = new int[n];
+  double *a_copy = new double[n * n];
-  indxr = new int[n];
+  for (int i = 0; i < n * n; i++) {
-  ipiv = new int[n];
+    a_copy[i] = a[i];
-
-  int i, icol, irow, j, k, l, ll;
-  double big, dum, pivinv;
-
-  for (j = 0; j < n; j++)
-    ipiv[j] = 0;
-  for (i = 0; i < n; i++)
-  {
-    big = 0.0;
-    for (j = 0; j < n; j++)
-      if (ipiv[j] != 1)
-        for (k = 0; k < n; k++)
-        {
-          if (ipiv[k] == 0)
-          {
-            if (fabs(a[j * n + k]) >= big)
-            {
-              big = fabs(a[j * n + k]);
-              irow = j;
-              icol = k;
-            }
-          }
-          else if (ipiv[k] > 1)
-          {
-            cout << "gaussj: Singular Matrix-1" << endl;
-            return 1;
-          }
-        }
-
-    ipiv[icol] = ipiv[icol] + 1;
-    if (irow != icol)
-    {
-      for (l = 0; l < n; l++)
-      {
-        swap = a[irow * n + l];
-        a[irow * n + l] = a[icol * n + l];
-        a[icol * n + l] = swap;
-      }
-
-      swap = b[irow];
-      b[irow] = b[icol];
-      b[icol] = swap;
-    }
-
-    indxr[i] = irow;
-    indxc[i] = icol;
-
-    if (a[icol * n + icol] == 0.0)
-    {
-      cout << "gaussj: Singular Matrix-2" << endl;
-      return 1;
-    }
-
-    pivinv = 1.0 / a[icol * n + icol];
-    a[icol * n + icol] = 1.0;
-    for (l = 0; l < n; l++)
-      a[icol * n + l] *= pivinv;
-    b[icol] *= pivinv;
-    for (ll = 0; ll < n; ll++)
-      if (ll != icol)
-      {
-        dum = a[ll * n + icol];
-        a[ll * n + icol] = 0.0;
-        for (l = 0; l < n; l++)
-          a[ll * n + l] -= a[icol * n + l] * dum;
-        b[ll] -= b[icol] * dum;
-      }
   }
 
-  for (l = n - 1; l >= 0; l--)
+  // Step 1: Solve linear system A*x = b using LU decomposition
-  {
+  // LAPACKE_dgesv uses column-major by default, but we use row-major
-    if (indxr[l] != indxc[l])
+  info = LAPACKE_dgesv(LAPACK_ROW_MAJOR, n, 1, a_copy, n, ipiv, b, 1);
-      for (k = 0; k < n; k++)
+
-      {
+  if (info != 0) {
-        swap = a[k * n + indxr[l]];
+    cout << "gaussj: Singular Matrix (dgesv info=" << info << ")" << endl;
-        a[k * n + indxr[l]] = a[k * n + indxc[l]];
+    delete[] ipiv;
-        a[k * n + indxc[l]] = swap;
+    delete[] a_copy;
-      }
+    return 1;
+  }
+
+  // Step 2: Compute matrix inverse A^(-1) using LU factorization
+  // First do LU factorization of original matrix a
+  info = LAPACKE_dgetrf(LAPACK_ROW_MAJOR, n, n, a, n, ipiv);
+
+  if (info != 0) {
+    cout << "gaussj: Singular Matrix (dgetrf info=" << info << ")" << endl;
+    delete[] ipiv;
+    delete[] a_copy;
+    return 1;
+  }
+
+  // Then compute inverse from LU factorization
+  info = LAPACKE_dgetri(LAPACK_ROW_MAJOR, n, a, n, ipiv);
+
+  if (info != 0) {
+    cout << "gaussj: Singular Matrix (dgetri info=" << info << ")" << endl;
+    delete[] ipiv;
+    delete[] a_copy;
+    return 1;
   }
 
-  delete[] indxc;
-  delete[] indxr;
   delete[] ipiv;
+  delete[] a_copy;
 
   return 0;
 }

AMSS_NCKU_source/interp_lb_profile_data.h

@@ -1,5 +1,3 @@
-/* 本头文件由自订profile框架自动生成并非人工硬编码针对Case优化 */
-/* 更新：负载均衡问题已经通过优化插值函数解决，此profile静态均衡方案已弃用，本头文件现在未参与编译 */
 /* Auto-generated from interp_lb_profile.bin — do not edit */
 #ifndef INTERP_LB_PROFILE_DATA_H
 #define INTERP_LB_PROFILE_DATA_H

AMSS_NCKU_source/kodiss_c.C

@@ -63,28 +63,19 @@ void kodis(const int ex[3],
      * C: k0=0..ex3-1, j0=0..ex2-1, i0=0..ex1-1
      * 并定义 Fortran index: iF=i0+1, ...
      */
-    // 收紧循环范围：只遍历满足 iF±3/jF±3/kF±3 条件的内部点
+    for (int k0 = 0; k0 < ex3; ++k0) {
-    // iF-3 >= iminF => iF >= iminF+3 => i0 >= iminF+2 (因为 iF=i0+1)
-    // iF+3 <= imaxF => iF <= imaxF-3 => i0 <= imaxF-4
-    const int i0_lo = (iminF + 2 > 0) ? iminF + 2 : 0;
-    const int j0_lo = (jminF + 2 > 0) ? jminF + 2 : 0;
-    const int k0_lo = (kminF + 2 > 0) ? kminF + 2 : 0;
-    const int i0_hi = imaxF - 4;  // inclusive
-    const int j0_hi = jmaxF - 4;
-    const int k0_hi = kmaxF - 4;
-
-    if (i0_lo > i0_hi || j0_lo > j0_hi || k0_lo > k0_hi) {
-        free(fh);
-        return;
-    }
-
-    for (int k0 = k0_lo; k0 <= k0_hi; ++k0) {
         const int kF = k0 + 1;
-        for (int j0 = j0_lo; j0 <= j0_hi; ++j0) {
+        for (int j0 = 0; j0 < ex2; ++j0) {
             const int jF = j0 + 1;
-            for (int i0 = i0_lo; i0 <= i0_hi; ++i0) {
+            for (int i0 = 0; i0 < ex1; ++i0) {
                 const int iF = i0 + 1;
 
+                // Fortran if 条件：
+                // i-3 >= imin .and. i+3 <= imax  等（都是 Fortran 索引）
+                if ((iF - 3) >= iminF && (iF + 3) <= imaxF &&
+                    (jF - 3) >= jminF && (jF + 3) <= jmaxF &&
+                    (kF - 3) >= kminF && (kF + 3) <= kmaxF)
+                {
                     const size_t p = idx_ex(i0, j0, k0, ex);
 
                     // 三个方向各一份同型的 7 点组合（实际上是对称的 6th-order dissipation/filter 核）
@@ -109,6 +100,7 @@ void kodis(const int ex[3],
                     // Fortran:
                     // f_rhs(i,j,k) = f_rhs(i,j,k) + eps/cof*(Dx_term + Dy_term + Dz_term)
                     f_rhs[p] += (eps / cof) * (Dx_term + Dy_term + Dz_term);
+                }
             }
         }
     }

AMSS_NCKU_source/lopsided_kodis_c.C

@@ -1,248 +0,0 @@
-#include "tool.h"
-
-/*
- * Combined advection (lopsided) + KO dissipation (kodis).
- * Uses one shared symmetry_bd buffer per call.
- */
-void lopsided_kodis(const int ex[3],
-                    const double *X, const double *Y, const double *Z,
-                    const double *f, double *f_rhs,
-                    const double *Sfx, const double *Sfy, const double *Sfz,
-                    int Symmetry, const double SoA[3], double eps)
-{
-    const double ZEO = 0.0, ONE = 1.0, F3 = 3.0;
-    const double F6 = 6.0, F18 = 18.0;
-    const double F12 = 12.0, F10 = 10.0, EIT = 8.0;
-    const double SIX = 6.0, FIT = 15.0, TWT = 20.0;
-    const double cof = 64.0; // 2^6
-
-    const int NO_SYMM = 0, EQ_SYMM = 1;
-
-    const int ex1 = ex[0], ex2 = ex[1], ex3 = ex[2];
-
-    const double dX = X[1] - X[0];
-    const double dY = Y[1] - Y[0];
-    const double dZ = Z[1] - Z[0];
-
-    const double d12dx = ONE / F12 / dX;
-    const double d12dy = ONE / F12 / dY;
-    const double d12dz = ONE / F12 / dZ;
-
-    const int imaxF = ex1;
-    const int jmaxF = ex2;
-    const int kmaxF = ex3;
-
-    int iminF = 1, jminF = 1, kminF = 1;
-    if (Symmetry > NO_SYMM && fabs(Z[0]) < dZ) kminF = -2;
-    if (Symmetry > EQ_SYMM && fabs(X[0]) < dX) iminF = -2;
-    if (Symmetry > EQ_SYMM && fabs(Y[0]) < dY) jminF = -2;
-
-    // fh for Fortran-style domain (-2:ex1,-2:ex2,-2:ex3)
-    const size_t nx = (size_t)ex1 + 3;
-    const size_t ny = (size_t)ex2 + 3;
-    const size_t nz = (size_t)ex3 + 3;
-    const size_t fh_size = nx * ny * nz;
-
-    double *fh = (double*)malloc(fh_size * sizeof(double));
-    if (!fh) return;
-
-    symmetry_bd(3, ex, f, fh, SoA);
-
-    // Advection (same stencil logic as lopsided_c.C)
-    for (int k0 = 0; k0 <= ex3 - 2; ++k0) {
-        const int kF = k0 + 1;
-        for (int j0 = 0; j0 <= ex2 - 2; ++j0) {
-            const int jF = j0 + 1;
-            for (int i0 = 0; i0 <= ex1 - 2; ++i0) {
-                const int iF = i0 + 1;
-                const size_t p = idx_ex(i0, j0, k0, ex);
-
-                const double sfx = Sfx[p];
-                if (sfx > ZEO) {
-                    if (i0 <= ex1 - 4) {
-                        f_rhs[p] += sfx * d12dx *
-                            (-F3  * fh[idx_fh_F(iF - 1, jF, kF, ex)]
-                             -F10 * fh[idx_fh_F(iF    , jF, kF, ex)]
-                             +F18 * fh[idx_fh_F(iF + 1, jF, kF, ex)]
-                             -F6  * fh[idx_fh_F(iF + 2, jF, kF, ex)]
-                             +      fh[idx_fh_F(iF + 3, jF, kF, ex)]);
-                    } else if (i0 <= ex1 - 3) {
-                        f_rhs[p] += sfx * d12dx *
-                            ( fh[idx_fh_F(iF - 2, jF, kF, ex)]
-                             -EIT * fh[idx_fh_F(iF - 1, jF, kF, ex)]
-                             +EIT * fh[idx_fh_F(iF + 1, jF, kF, ex)]
-                             -      fh[idx_fh_F(iF + 2, jF, kF, ex)]);
-                    } else if (i0 <= ex1 - 2) {
-                        f_rhs[p] -= sfx * d12dx *
-                            (-F3  * fh[idx_fh_F(iF + 1, jF, kF, ex)]
-                             -F10 * fh[idx_fh_F(iF    , jF, kF, ex)]
-                             +F18 * fh[idx_fh_F(iF - 1, jF, kF, ex)]
-                             -F6  * fh[idx_fh_F(iF - 2, jF, kF, ex)]
-                             +      fh[idx_fh_F(iF - 3, jF, kF, ex)]);
-                    }
-                } else if (sfx < ZEO) {
-                    if ((i0 - 2) >= iminF) {
-                        f_rhs[p] -= sfx * d12dx *
-                            (-F3  * fh[idx_fh_F(iF + 1, jF, kF, ex)]
-                             -F10 * fh[idx_fh_F(iF    , jF, kF, ex)]
-                             +F18 * fh[idx_fh_F(iF - 1, jF, kF, ex)]
-                             -F6  * fh[idx_fh_F(iF - 2, jF, kF, ex)]
-                             +      fh[idx_fh_F(iF - 3, jF, kF, ex)]);
-                    } else if ((i0 - 1) >= iminF) {
-                        f_rhs[p] += sfx * d12dx *
-                            ( fh[idx_fh_F(iF - 2, jF, kF, ex)]
-                             -EIT * fh[idx_fh_F(iF - 1, jF, kF, ex)]
-                             +EIT * fh[idx_fh_F(iF + 1, jF, kF, ex)]
-                             -      fh[idx_fh_F(iF + 2, jF, kF, ex)]);
-                    } else if (i0 >= iminF) {
-                        f_rhs[p] += sfx * d12dx *
-                            (-F3  * fh[idx_fh_F(iF - 1, jF, kF, ex)]
-                             -F10 * fh[idx_fh_F(iF    , jF, kF, ex)]
-                             +F18 * fh[idx_fh_F(iF + 1, jF, kF, ex)]
-                             -F6  * fh[idx_fh_F(iF + 2, jF, kF, ex)]
-                             +      fh[idx_fh_F(iF + 3, jF, kF, ex)]);
-                    }
-                }
-
-                const double sfy = Sfy[p];
-                if (sfy > ZEO) {
-                    if (j0 <= ex2 - 4) {
-                        f_rhs[p] += sfy * d12dy *
-                            (-F3  * fh[idx_fh_F(iF, jF - 1, kF, ex)]
-                             -F10 * fh[idx_fh_F(iF, jF    , kF, ex)]
-                             +F18 * fh[idx_fh_F(iF, jF + 1, kF, ex)]
-                             -F6  * fh[idx_fh_F(iF, jF + 2, kF, ex)]
-                             +      fh[idx_fh_F(iF, jF + 3, kF, ex)]);
-                    } else if (j0 <= ex2 - 3) {
-                        f_rhs[p] += sfy * d12dy *
-                            ( fh[idx_fh_F(iF, jF - 2, kF, ex)]
-                             -EIT * fh[idx_fh_F(iF, jF - 1, kF, ex)]
-                             +EIT * fh[idx_fh_F(iF, jF + 1, kF, ex)]
-                             -      fh[idx_fh_F(iF, jF + 2, kF, ex)]);
-                    } else if (j0 <= ex2 - 2) {
-                        f_rhs[p] -= sfy * d12dy *
-                            (-F3  * fh[idx_fh_F(iF, jF + 1, kF, ex)]
-                             -F10 * fh[idx_fh_F(iF, jF    , kF, ex)]
-                             +F18 * fh[idx_fh_F(iF, jF - 1, kF, ex)]
-                             -F6  * fh[idx_fh_F(iF, jF - 2, kF, ex)]
-                             +      fh[idx_fh_F(iF, jF - 3, kF, ex)]);
-                    }
-                } else if (sfy < ZEO) {
-                    if ((j0 - 2) >= jminF) {
-                        f_rhs[p] -= sfy * d12dy *
-                            (-F3  * fh[idx_fh_F(iF, jF + 1, kF, ex)]
-                             -F10 * fh[idx_fh_F(iF, jF    , kF, ex)]
-                             +F18 * fh[idx_fh_F(iF, jF - 1, kF, ex)]
-                             -F6  * fh[idx_fh_F(iF, jF - 2, kF, ex)]
-                             +      fh[idx_fh_F(iF, jF - 3, kF, ex)]);
-                    } else if ((j0 - 1) >= jminF) {
-                        f_rhs[p] += sfy * d12dy *
-                            ( fh[idx_fh_F(iF, jF - 2, kF, ex)]
-                             -EIT * fh[idx_fh_F(iF, jF - 1, kF, ex)]
-                             +EIT * fh[idx_fh_F(iF, jF + 1, kF, ex)]
-                             -      fh[idx_fh_F(iF, jF + 2, kF, ex)]);
-                    } else if (j0 >= jminF) {
-                        f_rhs[p] += sfy * d12dy *
-                            (-F3  * fh[idx_fh_F(iF, jF - 1, kF, ex)]
-                             -F10 * fh[idx_fh_F(iF, jF    , kF, ex)]
-                             +F18 * fh[idx_fh_F(iF, jF + 1, kF, ex)]
-                             -F6  * fh[idx_fh_F(iF, jF + 2, kF, ex)]
-                             +      fh[idx_fh_F(iF, jF + 3, kF, ex)]);
-                    }
-                }
-
-                const double sfz = Sfz[p];
-                if (sfz > ZEO) {
-                    if (k0 <= ex3 - 4) {
-                        f_rhs[p] += sfz * d12dz *
-                            (-F3  * fh[idx_fh_F(iF, jF, kF - 1, ex)]
-                             -F10 * fh[idx_fh_F(iF, jF, kF    , ex)]
-                             +F18 * fh[idx_fh_F(iF, jF, kF + 1, ex)]
-                             -F6  * fh[idx_fh_F(iF, jF, kF + 2, ex)]
-                             +      fh[idx_fh_F(iF, jF, kF + 3, ex)]);
-                    } else if (k0 <= ex3 - 3) {
-                        f_rhs[p] += sfz * d12dz *
-                            ( fh[idx_fh_F(iF, jF, kF - 2, ex)]
-                             -EIT * fh[idx_fh_F(iF, jF, kF - 1, ex)]
-                             +EIT * fh[idx_fh_F(iF, jF, kF + 1, ex)]
-                             -      fh[idx_fh_F(iF, jF, kF + 2, ex)]);
-                    } else if (k0 <= ex3 - 2) {
-                        f_rhs[p] -= sfz * d12dz *
-                            (-F3  * fh[idx_fh_F(iF, jF, kF + 1, ex)]
-                             -F10 * fh[idx_fh_F(iF, jF, kF    , ex)]
-                             +F18 * fh[idx_fh_F(iF, jF, kF - 1, ex)]
-                             -F6  * fh[idx_fh_F(iF, jF, kF - 2, ex)]
-                             +      fh[idx_fh_F(iF, jF, kF - 3, ex)]);
-                    }
-                } else if (sfz < ZEO) {
-                    if ((k0 - 2) >= kminF) {
-                        f_rhs[p] -= sfz * d12dz *
-                            (-F3  * fh[idx_fh_F(iF, jF, kF + 1, ex)]
-                             -F10 * fh[idx_fh_F(iF, jF, kF    , ex)]
-                             +F18 * fh[idx_fh_F(iF, jF, kF - 1, ex)]
-                             -F6  * fh[idx_fh_F(iF, jF, kF - 2, ex)]
-                             +      fh[idx_fh_F(iF, jF, kF - 3, ex)]);
-                    } else if ((k0 - 1) >= kminF) {
-                        f_rhs[p] += sfz * d12dz *
-                            ( fh[idx_fh_F(iF, jF, kF - 2, ex)]
-                             -EIT * fh[idx_fh_F(iF, jF, kF - 1, ex)]
-                             +EIT * fh[idx_fh_F(iF, jF, kF + 1, ex)]
-                             -      fh[idx_fh_F(iF, jF, kF + 2, ex)]);
-                    } else if (k0 >= kminF) {
-                        f_rhs[p] += sfz * d12dz *
-                            (-F3  * fh[idx_fh_F(iF, jF, kF - 1, ex)]
-                             -F10 * fh[idx_fh_F(iF, jF, kF    , ex)]
-                             +F18 * fh[idx_fh_F(iF, jF, kF + 1, ex)]
-                             -F6  * fh[idx_fh_F(iF, jF, kF + 2, ex)]
-                             +      fh[idx_fh_F(iF, jF, kF + 3, ex)]);
-                    }
-                }
-            }
-        }
-    }
-
-    // KO dissipation (same domain restriction as kodiss_c.C)
-    if (eps > ZEO) {
-        const int i0_lo = (iminF + 2 > 0) ? iminF + 2 : 0;
-        const int j0_lo = (jminF + 2 > 0) ? jminF + 2 : 0;
-        const int k0_lo = (kminF + 2 > 0) ? kminF + 2 : 0;
-        const int i0_hi = imaxF - 4; // inclusive
-        const int j0_hi = jmaxF - 4;
-        const int k0_hi = kmaxF - 4;
-
-        if (!(i0_lo > i0_hi || j0_lo > j0_hi || k0_lo > k0_hi)) {
-            for (int k0 = k0_lo; k0 <= k0_hi; ++k0) {
-                const int kF = k0 + 1;
-                for (int j0 = j0_lo; j0 <= j0_hi; ++j0) {
-                    const int jF = j0 + 1;
-                    for (int i0 = i0_lo; i0 <= i0_hi; ++i0) {
-                        const int iF = i0 + 1;
-                        const size_t p = idx_ex(i0, j0, k0, ex);
-
-                        const double Dx_term =
-                            ((fh[idx_fh_F(iF - 3, jF, kF, ex)] + fh[idx_fh_F(iF + 3, jF, kF, ex)]) -
-                             SIX * (fh[idx_fh_F(iF - 2, jF, kF, ex)] + fh[idx_fh_F(iF + 2, jF, kF, ex)]) +
-                             FIT * (fh[idx_fh_F(iF - 1, jF, kF, ex)] + fh[idx_fh_F(iF + 1, jF, kF, ex)]) -
-                             TWT *  fh[idx_fh_F(iF,     jF, kF, ex)]) / dX;
-
-                        const double Dy_term =
-                            ((fh[idx_fh_F(iF, jF - 3, kF, ex)] + fh[idx_fh_F(iF, jF + 3, kF, ex)]) -
-                             SIX * (fh[idx_fh_F(iF, jF - 2, kF, ex)] + fh[idx_fh_F(iF, jF + 2, kF, ex)]) +
-                             FIT * (fh[idx_fh_F(iF, jF - 1, kF, ex)] + fh[idx_fh_F(iF, jF + 1, kF, ex)]) -
-                             TWT *  fh[idx_fh_F(iF, jF,     kF, ex)]) / dY;
-
-                        const double Dz_term =
-                            ((fh[idx_fh_F(iF, jF, kF - 3, ex)] + fh[idx_fh_F(iF, jF, kF + 3, ex)]) -
-                             SIX * (fh[idx_fh_F(iF, jF, kF - 2, ex)] + fh[idx_fh_F(iF, jF, kF + 2, ex)]) +
-                             FIT * (fh[idx_fh_F(iF, jF, kF - 1, ex)] + fh[idx_fh_F(iF, jF, kF + 1, ex)]) -
-                             TWT *  fh[idx_fh_F(iF, jF, kF,     ex)]) / dZ;
-
-                        f_rhs[p] += (eps / cof) * (Dx_term + Dy_term + Dz_term);
-                    }
-                }
-            }
-        }
-    }
-
-    free(fh);
-}

AMSS_NCKU_source/macrodef.h

@@ -29,16 +29,6 @@
 
 #define REGLEV 0
 
-#define BSSN_FINE_TIMING 0
-
-#define BSSN_FINE_TIMING_EVERY 1
-
-#define BSSN_FINE_TIMING_TOPN 8
-
-#define BSSN_KERNEL_FINE_TIMING 0
-
-#define BSSN_ENABLE_STDIN_ABORT_POLL 0
-
 //#define USE_GPU
 
 //#define CHECKDETAIL
@@ -98,21 +88,6 @@
 //     0: for every level;
 //     1: for all
 //
-// define BSSN_FINE_TIMING
-//     enable fine-grained per-timestep timing monitor
-//
-// define BSSN_FINE_TIMING_EVERY
-//     report timing every N coarse timesteps
-//
-// define BSSN_FINE_TIMING_TOPN
-//     number of hottest timing buckets shown in stdout
-//
-// define BSSN_KERNEL_FINE_TIMING
-//     enable split timing inside compute_rhs_bssn
-//
-// define BSSN_ENABLE_STDIN_ABORT_POLL
-//     poll stdin and broadcast abort flag every coarse step
-//
 // define USE_GPU
 //     use gpu or not
 //
@@ -167,3 +142,4 @@
 #define TINY 1e-10
 
 #endif   /* MICRODEF_H */
+

AMSS_NCKU_source/makefile

@@ -8,16 +8,25 @@ include makefile.inc
 POLINT6_USE_BARY ?= 1
 POLINT6_FLAG = -DPOLINT6_USE_BARYCENTRIC=$(POLINT6_USE_BARY)
 
-## Legacy GNU/OpenMPI flags
+## ABE build flags selected by PGO_MODE (set in makefile.inc, default: opt)
-CXXBASEFLAGS = -O3 -march=native -Wno-deprecated -Dfortran3 -Dnewc $(INTERP_LB_FLAGS)
+##   make                        -> opt  (PGO-guided, maximum performance)
-F90BASEFLAGS = -O3 -march=native -cpp -fallow-argument-mismatch $(POLINT6_FLAG)
+##   make PGO_MODE=instrument    -> instrument (Phase 1: collect fresh profile data)
+PROFDATA = /home/$(shell whoami)/AMSS-NCKU/pgo_profile/default.profdata
 
 ifeq ($(PGO_MODE),instrument)
-CXXAPPFLAGS = $(CXXBASEFLAGS)
+## Phase 1: instrumentation — omit -ipo/-fp-model fast=2 for faster build and numerical stability
-f90appflags = $(F90BASEFLAGS)
+CXXAPPFLAGS = -O3 -xHost -fma -fprofile-instr-generate -ipo \
+              -Dfortran3 -Dnewc -I${MKLROOT}/include $(INTERP_LB_FLAGS)
+f90appflags = -O3 -xHost -fma -fprofile-instr-generate -ipo \
+              -align array64byte -fpp -I${MKLROOT}/include $(POLINT6_FLAG)
 else
-CXXAPPFLAGS = $(CXXBASEFLAGS)
+## opt (default): maximum performance with PGO profile data
-f90appflags = $(F90BASEFLAGS)
+CXXAPPFLAGS = -O3 -xHost -fp-model fast=2 -fma -ipo \
+              -fprofile-instr-use=$(PROFDATA) \
+              -Dfortran3 -Dnewc -I${MKLROOT}/include $(INTERP_LB_FLAGS)
+f90appflags = -O3 -xHost -fp-model fast=2 -fma -ipo \
+              -fprofile-instr-use=$(PROFDATA) \
+              -align array64byte -fpp -I${MKLROOT}/include $(POLINT6_FLAG)
 endif
 
 .SUFFIXES: .o .f90 .C .for .cu
@@ -34,6 +43,10 @@ endif
 .cu.o:
 	$(Cu) $(CUDA_APP_FLAGS) -c $< -o $@ $(CUDA_LIB_PATH)
 
+# CUDA rewrite of BSSN RHS (drop-in replacement for bssn_rhs_c + stencil helpers)
+bssn_rhs_cuda.o: bssn_rhs_cuda.cu macrodef.h
+	$(Cu) $(CUDA_APP_FLAGS) -c $< -o $@ $(CUDA_LIB_PATH)
+
 # C rewrite of BSSN RHS kernel and helpers
 bssn_rhs_c.o: bssn_rhs_c.C
 	${CXX} $(CXXAPPFLAGS) -c $< $(filein) -o $@
@@ -50,20 +63,20 @@ kodiss_c.o: kodiss_c.C
 lopsided_c.o: lopsided_c.C
 	${CXX} $(CXXAPPFLAGS) -c $< $(filein) -o $@
 
-lopsided_kodis_c.o: lopsided_kodis_c.C
+interp_lb_profile.o: interp_lb_profile.C interp_lb_profile.h
 	${CXX} $(CXXAPPFLAGS) -c $< $(filein) -o $@
 
-#interp_lb_profile.o: interp_lb_profile.C interp_lb_profile.h
-#	${CXX} $(CXXAPPFLAGS) -c $< $(filein) -o $@
-
 ## TwoPunctureABE uses fixed optimal flags with its own PGO profile, independent of CXXAPPFLAGS
-TP_OPTFLAGS = $(CXXBASEFLAGS) $(TP_OPENMP_FLAGS)
+TP_PROFDATA = /home/$(shell whoami)/AMSS-NCKU/pgo_profile/TwoPunctureABE.profdata
+TP_OPTFLAGS = -O3 -xHost -fp-model fast=2 -fma -ipo \
+              -fprofile-instr-use=$(TP_PROFDATA) \
+              -Dfortran3 -Dnewc -I${MKLROOT}/include
 
 TwoPunctures.o: TwoPunctures.C
-	${CXX} $(TP_OPTFLAGS) -c $< -o $@
+	${CXX} $(TP_OPTFLAGS) -qopenmp -c $< -o $@
 
 TwoPunctureABE.o: TwoPunctureABE.C
-	${CXX} $(TP_OPTFLAGS) -c $< -o $@
+	${CXX} $(TP_OPTFLAGS) -qopenmp -c $< -o $@
 
 # Input files
 
@@ -73,12 +86,16 @@ ifeq ($(USE_CXX_KERNELS),0)
 CFILES =
 else
 # C++ mode (default): C rewrite of bssn_rhs and helper kernels
-CFILES = bssn_rhs_c.o fderivs_c.o fdderivs_c.o kodiss_c.o lopsided_c.o lopsided_kodis_c.o
+CFILES = bssn_rhs_c.o fderivs_c.o fdderivs_c.o kodiss_c.o lopsided_c.o
 endif
 
+# CUDA rewrite: bssn_rhs_cuda.o replaces all CFILES (stencils are built-in)
+CFILES_CUDA = bssn_rhs_cuda.o
+
 ## RK4 kernel switch (independent from USE_CXX_KERNELS)
 ifeq ($(USE_CXX_RK4),1)
 CFILES += rungekutta4_rout_c.o
+CFILES_CUDA += rungekutta4_rout_c.o
 RK4_F90_OBJ =
 else
 RK4_F90_OBJ = rungekutta4_rout.o
@@ -164,14 +181,17 @@ $(CUDAFILES): bssn_gpu.h gpu_mem.h gpu_rhsSS_mem.h
 misc.o : zbesh.o
 
 # projects
-ABE: $(C++FILES) $(CFILES) $(F90FILES) $(F77FILES) $(AHFDOBJS)
+ABE: $(C++FILES) $(CFILES_CUDA) $(F90FILES) $(F77FILES) $(AHFDOBJS)
-	$(CLINKER) $(CXXAPPFLAGS) -o $@ $(C++FILES) $(CFILES) $(F90FILES) $(F77FILES) $(AHFDOBJS) $(LDLIBS)
+	$(CLINKER) $(CXXAPPFLAGS) -o $@ $(C++FILES) $(CFILES_CUDA) $(F90FILES) $(F77FILES) $(AHFDOBJS) $(LDLIBS) -lcudart $(CUDA_LIB_PATH)
+
+ABE_CUDA: $(C++FILES) $(CFILES_CUDA) $(F90FILES) $(F77FILES) $(AHFDOBJS)
+	$(CLINKER) $(CXXAPPFLAGS) -o $@ $(C++FILES) $(CFILES_CUDA) $(F90FILES) $(F77FILES) $(AHFDOBJS) $(LDLIBS) -lcudart $(CUDA_LIB_PATH)
 
 ABEGPU: $(C++FILES_GPU) $(CFILES) $(F90FILES) $(F77FILES) $(AHFDOBJS) $(CUDAFILES)
 	$(CLINKER) $(CXXAPPFLAGS) -o $@ $(C++FILES_GPU) $(CFILES) $(F90FILES) $(F77FILES) $(AHFDOBJS) $(CUDAFILES) $(LDLIBS)
 
 TwoPunctureABE: $(TwoPunctureFILES)
-	$(CLINKER) $(TP_OPTFLAGS) -o $@ $(TwoPunctureFILES) $(LDLIBS)
+	$(CLINKER) $(TP_OPTFLAGS) -qopenmp -o $@ $(TwoPunctureFILES) $(LDLIBS)
 
 clean:
-	rm *.o ABE ABEGPU TwoPunctureABE make.log -f
+	rm *.o ABE ABE_CUDA ABEGPU TwoPunctureABE make.log -f

AMSS_NCKU_source/makefile.inc

@@ -1,27 +1,33 @@
-## Legacy GNU/OpenMPI toolchain configuration
+## GCC version (commented out)
+## filein  = -I/usr/include -I/usr/lib/x86_64-linux-gnu/mpich/include -I/usr/lib/x86_64-linux-gnu/openmpi/lib/ -I/usr/lib/gcc/x86_64-linux-gnu/11/ -I/usr/include/c++/11/
+## filein  = -I/usr/include/ -I/usr/include/openmpi-x86_64/ -I/usr/lib/x86_64-linux-gnu/openmpi/include/ -I/usr/lib/x86_64-linux-gnu/openmpi/lib/ -I/usr/lib/gcc/x86_64-linux-gnu/11/ -I/usr/include/c++/11/
+## LDLIBS  = -L/usr/lib/x86_64-linux-gnu -L/usr/lib64 -L/usr/lib/gcc/x86_64-linux-gnu/11 -lgfortran -lmpi -lgfortran
 
-## OpenMPI wrappers are installed but may not be on PATH.
+## Intel oneAPI version with oneMKL (Optimized for performance)
-OMPI_BIN ?= /usr/lib64/openmpi/bin
+filein  = -I/usr/include/ -I${MKLROOT}/include
 
-## Wrapper compilers
+## Using sequential MKL (OpenMP disabled for better single-threaded performance)
-f90          = $(OMPI_BIN)/mpifort
+## Added -lifcore for Intel Fortran runtime and -limf for Intel math library
-f77          = $(OMPI_BIN)/mpifort
+LDLIBS  = -L${MKLROOT}/lib -lmkl_intel_lp64 -lmkl_sequential -lmkl_core -lifcore -limf -lpthread -lm -ldl -liomp5
-CXX          = $(OMPI_BIN)/mpicxx
-CC           = $(OMPI_BIN)/mpicc
-CLINKER      = $(OMPI_BIN)/mpicxx
 
-## Extra include flags are not needed when using the OpenMPI wrappers.
+## Memory allocator switch
-filein       =
+##   1 (default) : link Intel oneTBB allocator (libtbbmalloc)
+##   0           : use system default allocator (ptmalloc)
+USE_TBBMALLOC ?= 1
+TBBMALLOC_SO ?= /home/intel/oneapi/2025.3/lib/libtbbmalloc.so
+ifneq ($(wildcard $(TBBMALLOC_SO)),)
+TBBMALLOC_LIBS = -Wl,--no-as-needed $(TBBMALLOC_SO) -Wl,--as-needed
+else
+TBBMALLOC_LIBS = -Wl,--no-as-needed -ltbbmalloc -Wl,--as-needed
+endif
+ifeq ($(USE_TBBMALLOC),1)
+LDLIBS := $(TBBMALLOC_LIBS) $(LDLIBS)
+endif
 
-## BLAS/LAPACK backend:
+## PGO build mode switch (ABE only; TwoPunctureABE always uses opt flags)
-## OpenBLAS on this system provides BLAS, CBLAS and LAPACK symbols.
+##   opt        : (default) maximum performance with PGO profile-guided optimization
-BLAS_LAPACK_LIB ?= /lib64/libopenblaso.so.0
+##   instrument : PGO Phase 1 instrumentation to collect fresh profile data
-LDLIBS  = $(BLAS_LAPACK_LIB) -lgfortran -lpthread -lm -ldl
+PGO_MODE ?= opt
-
-## PGO build mode switch
-##   off        : default legacy GNU build without PGO
-##   instrument : accepted for compatibility, currently same as off
-PGO_MODE ?= off
 
 ## Interp_Points load balance profiling mode
 ##   off        : (default) no load balance instrumentation
@@ -43,13 +49,17 @@ endif
 USE_CXX_KERNELS ?= 1
 
 ## RK4 kernel implementation switch
-##   1 (default) : use C/C++ rewrite of rungekutta4_rout
+##   1 (default) : use C/C++ rewrite of rungekutta4_rout (for optimization experiments)
 ##   0           : use original Fortran rungekutta4_rout.o
 USE_CXX_RK4 ?= 1
 
-## OpenMP is only used for TwoPunctures on the legacy toolchain.
+f90          = ifx
-TP_OPENMP_FLAGS ?= -fopenmp
+f77          = ifx
+CXX          = icpx
+CC           = icx
+CLINKER      = mpiicpx
 
 Cu = nvcc
 CUDA_LIB_PATH = -L/usr/lib/cuda/lib64 -I/usr/include -I/usr/lib/cuda/include
-CUDA_APP_FLAGS = -c -g -O3 --ptxas-options=-v -Dfortran3 -Dnewc
+#CUDA_APP_FLAGS = -c -g -O3 --ptxas-options=-v -arch compute_13 -code compute_13,sm_13 -Dfortran3 -Dnewc
+CUDA_APP_FLAGS = -c -g -O3 --ptxas-options=-v -Dfortran3 -Dnewc -arch=sm_80

AMSS_NCKU_source/prolongrestrict_cell.f90

@@ -217,7 +217,6 @@
   real*8,dimension(2*ghost_width) :: X,Y,Z
   real*8, dimension(2*ghost_width,2*ghost_width) :: tmp2
   real*8, dimension(2*ghost_width) :: tmp1
-  real*8 :: ddy
   real*8,dimension(3) :: ccp
 
 #if (ghost_width == 2)
@@ -580,7 +579,7 @@
             tmp1(ghost_width-cxI(1)+cxB(1)  :ghost_width-cxI(1)+cxT(1)  ) = funf(cxB(1):cxT(1),j,k)
          endif
 
-         call polint(X,tmp1,0.d0,funf(i,j,k),ddy,2*ghost_width)
+         call polint0(X,tmp1,funf(i,j,k),2*ghost_width)
 
 ! for y direction
        elseif(sum(fg).eq.2.and.fg(2) .eq. 0.and. &
@@ -690,7 +689,7 @@
             tmp1(ghost_width-cxI(2)+cxB(2)  :ghost_width-cxI(2)+cxT(2)  ) = funf(i,cxB(2):cxT(2),k)
          endif
 
-         call polint(Y,tmp1,0.d0,funf(i,j,k),ddy,2*ghost_width)
+         call polint0(Y,tmp1,funf(i,j,k),2*ghost_width)
 
 ! for z direction
        elseif(sum(fg).eq.2.and.fg(3) .eq. 0.and. &
@@ -802,7 +801,7 @@
             tmp1(ghost_width-cxI(3)+cxB(3)  :ghost_width-cxI(3)+cxT(3)  ) = funf(i,j,cxB(3):cxT(3))
          endif
 
-         call polint(Z,tmp1,0.d0,funf(i,j,k),ddy,2*ghost_width)
+         call polint0(Z,tmp1,funf(i,j,k),2*ghost_width)
 
 #else
 

AMSS_NCKU_source/prolongrestrict_vertex.f90

@@ -217,7 +217,6 @@
   real*8,dimension(2*ghost_width) :: X,Y,Z
   real*8, dimension(2*ghost_width,2*ghost_width) :: tmp2
   real*8, dimension(2*ghost_width) :: tmp1
-  real*8 :: ddy
 
 #if (ghost_width == 2)
   real*8, parameter :: C1=-1.d0/16,C2=9.d0/16
@@ -470,7 +469,7 @@
 
          tmp1(cxB(1)+ghost_width-i+1:cxT(1)+ghost_width-i+1) = fh(cxB(1):cxT(1),j,k)
 
-         call polint(X,tmp1,0.d0,funf(i,j,k),ddy,2*ghost_width)
+         call polint0(X,tmp1,funf(i,j,k),2*ghost_width)
 
 ! for y direction
        elseif (fg(2) .eq. 0)then
@@ -529,7 +528,7 @@
 
          tmp1(cxB(2)+ghost_width-j+1:cxT(2)+ghost_width-j+1) = fh(i,cxB(2):cxT(2),k)
 
-         call polint(Y,tmp1,0.d0,funf(i,j,k),ddy,2*ghost_width)
+         call polint0(Y,tmp1,funf(i,j,k),2*ghost_width)
 
 ! for z direction
        else
@@ -588,7 +587,7 @@
 
          tmp1(cxB(3)+ghost_width-k+1:cxT(3)+ghost_width-k+1) = fh(i,j,cxB(3):cxT(3))
 
-         call polint(Z,tmp1,0.d0,funf(i,j,k),ddy,2*ghost_width)
+         call polint0(Z,tmp1,funf(i,j,k),2*ghost_width)
 
        endif
       

AMSS_NCKU_source/rungekutta4_rout_c.C

@@ -2,7 +2,6 @@
 #include <cstdio>
 #include <cstdlib>
 #include <cstddef>
-#include <complex>
 #include <immintrin.h>
 
 namespace {
@@ -118,62 +117,6 @@ inline void rk4_stage3(std::size_t n,
 
 extern "C" {
 
-void f_rungekutta4_scalar(double &dT, double &f0, double &f1, double &f_rhs, int &RK4) {
-    constexpr double F1o6 = 1.0 / 6.0;
-    constexpr double HLF = 0.5;
-    constexpr double TWO = 2.0;
-
-    switch (RK4) {
-    case 0:
-        f1 = f0 + HLF * dT * f_rhs;
-        break;
-    case 1:
-        f_rhs = f_rhs + TWO * f1;
-        f1 = f0 + HLF * dT * f1;
-        break;
-    case 2:
-        f_rhs = f_rhs + TWO * f1;
-        f1 = f0 + dT * f1;
-        break;
-    case 3:
-        f1 = f0 + F1o6 * dT * (f1 + f_rhs);
-        break;
-    default:
-        std::fprintf(stderr, "rungekutta4_scalar_c: invalid RK4 stage %d\n", RK4);
-        std::abort();
-    }
-}
-
-void rungekutta4_cplxscalar_(double &dT,
-                             std::complex<double> &f0,
-                             std::complex<double> &f1,
-                             std::complex<double> &f_rhs,
-                             int &RK4) {
-    constexpr double F1o6 = 1.0 / 6.0;
-    constexpr double HLF = 0.5;
-    constexpr double TWO = 2.0;
-
-    switch (RK4) {
-    case 0:
-        f1 = f0 + HLF * dT * f_rhs;
-        break;
-    case 1:
-        f_rhs = f_rhs + TWO * f1;
-        f1 = f0 + HLF * dT * f1;
-        break;
-    case 2:
-        f_rhs = f_rhs + TWO * f1;
-        f1 = f0 + dT * f1;
-        break;
-    case 3:
-        f1 = f0 + F1o6 * dT * (f1 + f_rhs);
-        break;
-    default:
-        std::fprintf(stderr, "rungekutta4_cplxscalar_c: invalid RK4 stage %d\n", RK4);
-        std::abort();
-    }
-}
-
 int f_rungekutta4_rout(int *ex, double &dT,
                        double *f0, double *f1, double *f_rhs,
                        int &RK4) {

AMSS_NCKU_source/surface_integral.h

@@ -36,11 +36,6 @@ private:
 
 	double *nx_g, *ny_g, *nz_g; // global list of unit normals
 	int myrank, cpusize;
-	int wave_cache_spinw, wave_cache_maxl, wave_cache_modes;
-	double *wave_theta_pos, *wave_theta_neg;
-	double *wave_phi_cos, *wave_phi_sin;
-	void clear_wave_cache();
-	void build_wave_cache(int spinw, int maxl);
 
 public:
 	surface_integral(int iSymmetry);
@@ -87,29 +82,13 @@ public:
 					   var *Axx, var *Axy, var *Axz, var *Ayy, var *Ayz, var *Azz,
 					   var *Gmx, var *Gmy, var *Gmz,
 					   var *Sfx_rhs, var *Sfy_rhs, var *Sfz_rhs,
-					   double *Rout, monitor *Monitor, bool refresh_mass_fields = true);
+					   double *Rout, monitor *Monitor);
 	void surf_MassPAng(double rex, int lev, ShellPatch *GH, var *chi, var *trK,
 					   var *gxx, var *gxy, var *gxz, var *gyy, var *gyz, var *gzz,
 					   var *Axx, var *Axy, var *Axz, var *Ayy, var *Ayz, var *Azz,
 					   var *Gmx, var *Gmy, var *Gmz,
 					   var *Sfx_rhs, var *Sfy_rhs, var *Sfz_rhs,
-					   double *Rout, monitor *Monitor, bool refresh_mass_fields = true);
+					   double *Rout, monitor *Monitor);
-	void surf_WaveMassPAng(double rex, int lev, cgh *GH,
-					   var *Rpsi4, var *Ipsi4, int spinw, int maxl, int NN, double *RP, double *IP,
-					   var *chi, var *trK,
-					   var *gxx, var *gxy, var *gxz, var *gyy, var *gyz, var *gzz,
-					   var *Axx, var *Axy, var *Axz, var *Ayy, var *Ayz, var *Azz,
-					   var *Gmx, var *Gmy, var *Gmz,
-					   var *Sfx_rhs, var *Sfy_rhs, var *Sfz_rhs,
-					   double *Rout, monitor *Monitor, bool refresh_mass_fields = true);
-	void surf_WaveMassPAng(double rex, int lev, ShellPatch *GH,
-					   var *Rpsi4, var *Ipsi4, int spinw, int maxl, int NN, double *RP, double *IP,
-					   var *chi, var *trK,
-					   var *gxx, var *gxy, var *gxz, var *gyy, var *gyz, var *gzz,
-					   var *Axx, var *Axy, var *Axz, var *Ayy, var *Ayz, var *Azz,
-					   var *Gmx, var *Gmy, var *Gmz,
-					   var *Sfx_rhs, var *Sfy_rhs, var *Sfz_rhs,
-					   double *Rout, monitor *Monitor, bool refresh_mass_fields = true);
 	void surf_Wave(double rex, cgh *GH, ShellPatch *SH,
 				   var *chi, var *trK,
 				   var *gxx, var *gxy, var *gxz, var *gyy, var *gyz, var *gzz,
@@ -136,7 +115,7 @@ public:
 					   var *Axx, var *Axy, var *Axz, var *Ayy, var *Ayz, var *Azz,
 					   var *Gmx, var *Gmy, var *Gmz,
 					   var *Sfx_rhs, var *Sfy_rhs, var *Sfz_rhs, // temparay memory for mass^i
-					   double *Rout, monitor *Monitor, MPI_Comm Comm_here, bool refresh_mass_fields = true);
+					   double *Rout, monitor *Monitor, MPI_Comm Comm_here);
 	void surf_Wave(double rex, int lev, cgh *GH, var *Rpsi4, var *Ipsi4,
 				   int spinw, int maxl, int NN, double *RP, double *IP,
 				   monitor *Monitor, MPI_Comm Comm_here);

AMSS_NCKU_source/tool.h

@@ -25,9 +25,3 @@ void lopsided(const int ex[3],
               const double *f, double *f_rhs,
               const double *Sfx, const double *Sfy, const double *Sfz,
               int Symmetry, const double SoA[3]);
-
-void lopsided_kodis(const int ex[3],
-                    const double *X, const double *Y, const double *Z,
-                    const double *f, double *f_rhs,
-                    const double *Sfx, const double *Sfy, const double *Sfz,
-                    int Symmetry, const double SoA[3], double eps);

README.md

@@ -97,9 +97,7 @@ Here, we take the Ubuntu 22.04 system as an example
 
     Modify the makefile.inc file in the AMSS_NCKU_source directory and change the settings according to your computer.
 
-    The default configuration in this branch uses GNU compilers through the OpenMPI wrappers under `/usr/lib64/openmpi/bin`.
+    The settings for the Ubuntu 22.04 system do not need to be modified.
-
-    If your OpenMPI installation is in another location, update `OMPI_BIN` in `AMSS_NCKU_source/makefile.inc` or export `AMSS_OPENMPI_BIN` before running the Python launcher.
 
 1.  Enter the AMSS-NCKU Python code folder and modify the input.
 

generate_macrodef.py

@@ -144,62 +144,6 @@ def generate_macrodef_h():
     print( "#define REGLEV 0",      file=file1 )
     print(                          file=file1 )
 
-    # Define fine-grained timing/debug macros.
-    # All of them default to OFF so production builds do not pay profiling overhead.
-
-    fine_timing = getattr(input_data, "Fine_Timing",
-                  getattr(input_data, "Finegrained_Timing", "no"))
-    kernel_fine_timing = getattr(input_data, "Kernel_Fine_Timing",
-                          getattr(input_data, "BSSN_Kernel_Fine_Timing", "no"))
-    stdin_abort_poll = getattr(input_data, "Enable_Stdin_Abort_Poll",
-                       getattr(input_data, "Stdin_Abort_Poll", "no"))
-    timing_report_every = max(1, int(getattr(
-        input_data, "Timing_Every_Steps",
-        getattr(input_data, "Timing_Report_Every", 1))))
-    timing_top_hotspots = max(1, int(getattr(
-        input_data, "Timing_Top_Hotspots", 8)))
-
-    if ( fine_timing == "yes" ):
-        print( "#define BSSN_FINE_TIMING 1", file=file1 )
-        print(                               file=file1 )
-    elif ( fine_timing == "no" ):
-        print( "#define BSSN_FINE_TIMING 0", file=file1 )
-        print(                               file=file1 )
-    else:
-        print( "Fine_Timing setting error!!!" )
-        print()
-        print( "# Fine_Timing setting error!!!", file=file1 )
-        print(                                   file=file1 )
-
-    print( f"#define BSSN_FINE_TIMING_EVERY {timing_report_every}", file=file1 )
-    print(                                                          file=file1 )
-    print( f"#define BSSN_FINE_TIMING_TOPN {timing_top_hotspots}",  file=file1 )
-    print(                                                          file=file1 )
-
-    if ( kernel_fine_timing == "yes" ):
-        print( "#define BSSN_KERNEL_FINE_TIMING 1", file=file1 )
-        print(                                      file=file1 )
-    elif ( kernel_fine_timing == "no" ):
-        print( "#define BSSN_KERNEL_FINE_TIMING 0", file=file1 )
-        print(                                      file=file1 )
-    else:
-        print( "Kernel_Fine_Timing setting error!!!" )
-        print()
-        print( "# Kernel_Fine_Timing setting error!!!", file=file1 )
-        print(                                          file=file1 )
-
-    if ( stdin_abort_poll == "yes" ):
-        print( "#define BSSN_ENABLE_STDIN_ABORT_POLL 1", file=file1 )
-        print(                                           file=file1 )
-    elif ( stdin_abort_poll == "no" ):
-        print( "#define BSSN_ENABLE_STDIN_ABORT_POLL 0", file=file1 )
-        print(                                           file=file1 )
-    else:
-        print( "Enable_Stdin_Abort_Poll setting error!!!" )
-        print()
-        print( "# Enable_Stdin_Abort_Poll setting error!!!", file=file1 )
-        print(                                               file=file1 )
-
     # Define macro USE_GPU
     # use GPU or not
     
@@ -280,21 +224,6 @@ def generate_macrodef_h():
     print( "//     0: for every level;",                                                 file=file1 ) 
     print( "//     1: for all",                                                          file=file1 )
     print( "//",                                                                         file=file1 )
-    print( "// define BSSN_FINE_TIMING",                                                 file=file1 )
-    print( "//     enable fine-grained per-timestep timing monitor",                     file=file1 )
-    print( "//",                                                                         file=file1 )
-    print( "// define BSSN_FINE_TIMING_EVERY",                                           file=file1 )
-    print( "//     report timing every N coarse timesteps",                              file=file1 )
-    print( "//",                                                                         file=file1 )
-    print( "// define BSSN_FINE_TIMING_TOPN",                                            file=file1 )
-    print( "//     number of hottest timing buckets shown in stdout",                    file=file1 )
-    print( "//",                                                                         file=file1 )
-    print( "// define BSSN_KERNEL_FINE_TIMING",                                          file=file1 )
-    print( "//     enable split timing inside compute_rhs_bssn",                         file=file1 )
-    print( "//",                                                                         file=file1 )
-    print( "// define BSSN_ENABLE_STDIN_ABORT_POLL",                                     file=file1 )
-    print( "//     poll stdin and broadcast abort flag every coarse step",               file=file1 )
-    print( "//",                                                                         file=file1 )
     print( "// define USE_GPU",                                                          file=file1 )
     print( "//     use gpu or not",                                                      file=file1 )
     print( "//",                                                                         file=file1 )

makefile_and_run.py

@@ -9,7 +9,6 @@
 
 
 import AMSS_NCKU_Input as input_data
-import os
 import subprocess
 import time
 
@@ -53,8 +52,6 @@ NUMACTL_CPU_BIND = get_last_n_cores_per_socket(n=32)
 
 ## Build parallelism: match the number of bound cores
 BUILD_JOBS = 64
-OPENMPI_BIN = os.environ.get("AMSS_OPENMPI_BIN", "/usr/lib64/openmpi/bin")
-MPI_RUNNER = os.path.join(OPENMPI_BIN, "mpirun")
 
 
 ##################################################################
@@ -73,7 +70,7 @@ def makefile_ABE():
 
     ## Build command with CPU binding to nohz_full cores
     if (input_data.GPU_Calculation == "no"):
-        makefile_command  = f"{NUMACTL_CPU_BIND} make -j{BUILD_JOBS} INTERP_LB_MODE=off ABE"
+        makefile_command  = f"{NUMACTL_CPU_BIND} make -j{BUILD_JOBS} INTERP_LB_MODE=optimize ABE"
     elif (input_data.GPU_Calculation == "yes"):
         makefile_command  = f"{NUMACTL_CPU_BIND} make -j{BUILD_JOBS} ABEGPU"
     else:
@@ -150,11 +147,11 @@ def run_ABE():
     ## Define the command to run; cast other values to strings as needed
     
     if (input_data.GPU_Calculation == "no"):
-        mpi_command         = NUMACTL_CPU_BIND + " " + MPI_RUNNER + " -np " + str(input_data.MPI_processes) + " ./ABE"
+        mpi_command         = NUMACTL_CPU_BIND + " mpirun -np " + str(input_data.MPI_processes) + " ./ABE"
         #mpi_command         = " mpirun -np " + str(input_data.MPI_processes) + " ./ABE"
         mpi_command_outfile = "ABE_out.log"
     elif (input_data.GPU_Calculation == "yes"):
-        mpi_command         = NUMACTL_CPU_BIND + " " + MPI_RUNNER + " -np " + str(input_data.MPI_processes) + " ./ABEGPU"
+        mpi_command         = NUMACTL_CPU_BIND + " mpirun -np " + str(input_data.MPI_processes) + " ./ABEGPU"
         mpi_command_outfile = "ABEGPU_out.log"
  
     ## Execute the MPI command and stream output

pgo_profile/PGO_Profile_Analysis.md

@@ -0,0 +1,97 @@
+# AMSS-NCKU PGO Profile Analysis Report
+
+## 1. Profiling Environment
+
+| Item | Value |
+|------|-------|
+| Compiler | Intel oneAPI DPC++/C++ 2025.3.0 (icpx/ifx) |
+| Instrumentation Flag | `-fprofile-instr-generate` |
+| Optimization Level (instrumented) | `-O2 -xHost -fma` |
+| MPI Processes | 1 (single process to avoid MPI+instrumentation deadlock) |
+| Profile File | `default_9725750769337483397_0.profraw` (327 KB) |
+| Merged Profile | `default.profdata` (394 KB) |
+| llvm-profdata | `/home/intel/oneapi/compiler/2025.3/bin/compiler/llvm-profdata` |
+
+## 2. Reduced Simulation Parameters (for profiling run)
+
+| Parameter | Production Value | Profiling Value |
+|-----------|-----------------|-----------------|
+| MPI_processes | 64 | 1 |
+| grid_level | 9 | 4 |
+| static_grid_level | 5 | 3 |
+| static_grid_number | 96 | 24 |
+| moving_grid_number | 48 | 16 |
+| largest_box_xyz_max | 320^3 | 160^3 |
+| Final_Evolution_Time | 1000.0 | 10.0 |
+| Evolution_Step_Number | 10,000,000 | 1,000 |
+| Detector_Number | 12 | 2 |
+
+## 3. Profile Summary
+
+| Metric | Value |
+|--------|-------|
+| Total instrumented functions | 1,392 |
+| Functions with non-zero counts | 117 (8.4%) |
+| Functions with zero counts | 1,275 (91.6%) |
+| Maximum function entry count | 386,459,248 |
+| Maximum internal block count | 370,477,680 |
+| Total block count | 4,198,023,118 |
+
+## 4. Top 20 Hotspot Functions
+
+| Rank | Total Count | Max Block Count | Function | Category |
+|------|------------|-----------------|----------|----------|
+| 1 | 1,241,601,732 | 370,477,680 | `polint_` | Interpolation |
+| 2 | 755,994,435 | 230,156,640 | `prolong3_` | Grid prolongation |
+| 3 | 667,964,095 | 3,697,792 | `compute_rhs_bssn_` | BSSN RHS evolution |
+| 4 | 539,736,051 | 386,459,248 | `symmetry_bd_` | Symmetry boundary |
+| 5 | 277,310,808 | 53,170,728 | `lopsided_` | Lopsided FD stencil |
+| 6 | 155,534,488 | 94,535,040 | `decide3d_` | 3D grid decision |
+| 7 | 119,267,712 | 19,266,048 | `rungekutta4_rout_` | RK4 time integrator |
+| 8 | 91,574,616 | 48,824,160 | `kodis_` | Kreiss-Oliger dissipation |
+| 9 | 67,555,389 | 43,243,680 | `fderivs_` | Finite differences |
+| 10 | 55,296,000 | 42,246,144 | `misc::fact(int)` | Factorial utility |
+| 11 | 43,191,071 | 27,663,328 | `fdderivs_` | 2nd-order FD derivatives |
+| 12 | 36,233,965 | 22,429,440 | `restrict3_` | Grid restriction |
+| 13 | 24,698,512 | 17,231,520 | `polin3_` | Polynomial interpolation |
+| 14 | 22,962,942 | 20,968,768 | `copy_` | Data copy |
+| 15 | 20,135,696 | 17,259,168 | `Ansorg::barycentric(...)` | Spectral interpolation |
+| 16 | 14,650,224 | 7,224,768 | `Ansorg::barycentric_omega(...)` | Spectral weights |
+| 17 | 13,242,296 | 2,871,920 | `global_interp_` | Global interpolation |
+| 18 | 12,672,000 | 7,734,528 | `sommerfeld_rout_` | Sommerfeld boundary |
+| 19 | 6,872,832 | 1,880,064 | `sommerfeld_routbam_` | Sommerfeld boundary (BAM) |
+| 20 | 5,709,900 | 2,809,632 | `l2normhelper_` | L2 norm computation |
+
+## 5. Hotspot Category Breakdown
+
+Top 20 functions account for ~98% of total execution counts:
+
+| Category | Functions | Combined Count | Share |
+|----------|-----------|---------------|-------|
+| Interpolation / Prolongation / Restriction | polint_, prolong3_, restrict3_, polin3_, global_interp_, Ansorg::* | ~2,093M | ~50% |
+| BSSN RHS + FD stencils | compute_rhs_bssn_, lopsided_, fderivs_, fdderivs_ | ~1,056M | ~25% |
+| Boundary conditions | symmetry_bd_, sommerfeld_rout_, sommerfeld_routbam_ | ~559M | ~13% |
+| Time integration | rungekutta4_rout_ | ~119M | ~3% |
+| Dissipation | kodis_ | ~92M | ~2% |
+| Utilities | misc::fact, decide3d_, copy_, l2normhelper_ | ~256M | ~6% |
+
+## 6. Conclusions
+
+1. **Profile data is valid**: 1,392 functions instrumented, 117 exercised with ~4.2 billion total counts.
+2. **Hotspot concentration is high**: Top 5 functions alone account for ~76% of all counts, which is ideal for PGO — the compiler has strong branch/layout optimization targets.
+3. **Fortran numerical kernels dominate**: `polint_`, `prolong3_`, `compute_rhs_bssn_`, `symmetry_bd_`, `lopsided_` are all Fortran routines in the inner evolution loop. PGO will optimize their branch prediction and basic block layout.
+4. **91.6% of functions have zero counts**: These are code paths for unused features (GPU, BSSN-EScalar, BSSN-EM, Z4C, etc.). PGO will deprioritize them, improving instruction cache utilization.
+5. **Profile is representative**: Despite the reduced grid size, the code path coverage matches production — the same kernels (RHS, prolongation, restriction, boundary) are exercised. PGO branch probabilities from this profile will transfer well to full-scale runs.
+
+## 7. PGO Phase 2 Usage
+
+To apply the profile, use the following flags in `makefile.inc`:
+
+```makefile
+CXXAPPFLAGS = -O3 -xHost -fp-model fast=2 -fma -ipo \
+              -fprofile-instr-use=/home/amss/AMSS-NCKU/pgo_profile/default.profdata \
+              -Dfortran3 -Dnewc -I${MKLROOT}/include
+f90appflags = -O3 -xHost -fp-model fast=2 -fma -ipo \
+              -fprofile-instr-use=/home/amss/AMSS-NCKU/pgo_profile/default.profdata \
+              -align array64byte -fpp -I${MKLROOT}/include
+```