🔖 Merge branch 'master' into release

.gitignore

@@ -6,6 +6,8 @@ prof
 .vscode
 doc/html
 doc/latex
+*.d
+*.in
 *.x
 *.xlsx
 *.log

samples/compareP3DFFT++/main_compare++.cpp

@@ -260,24 +260,24 @@ int main(int argc, char *argv[]) {
     // //-------------------------------------------------------------------------
     // /** - allocate rhs and solution */
     // //-------------------------------------------------------------------------
-
-    printf("[FLUPS] topo IN glob : %d %d %d \n",topoIn->nglob(0),topoIn->nglob(1),topoIn->nglob(2));
-    printf("[FLUPS] topo IN loc : %d*%d*%d = %d (check: %d %d %d)\n",topoIn->nmem(0),topoIn->nmem(1),topoIn->nmem(2),topoIn->memsize(),topoIn->nloc(0),topoIn->nloc(1),topoIn->nloc(2));
-    printf("[FLUPS] topo OUT glob : %d %d %d \n",topoSpec->nglob(0),topoSpec->nglob(1),topoSpec->nglob(2));
-    printf("[FLUPS] topo OUT loc  : nmem: %d*%d*%d nf:%d (nloc: %d %d %d)  \n",topoSpec->nmem(0),topoSpec->nmem(1),topoSpec->nmem(2),topoSpec->nf(),topoSpec->nloc(0),topoSpec->nloc(1),topoSpec->nloc(2));
+    if(rank == 0) {
+        printf("[FLUPS] topo IN glob : %d %d %d \n",topoIn->nglob(0),topoIn->nglob(1),topoIn->nglob(2));
+        printf("[FLUPS] topo IN loc : %d*%d*%d = %d (check: %d %d %d)\n",topoIn->nmem(0),topoIn->nmem(1),topoIn->nmem(2),topoIn->memsize(),topoIn->nloc(0),topoIn->nloc(1),topoIn->nloc(2));
+        printf("[FLUPS] topo OUT glob : %d %d %d \n",topoSpec->nglob(0),topoSpec->nglob(1),topoSpec->nglob(2));
+        printf("[FLUPS] topo OUT loc  : nmem: %d*%d*%d nf:%d (nloc: %d %d %d)  \n",topoSpec->nmem(0),topoSpec->nmem(1),topoSpec->nmem(2),topoSpec->nf(),topoSpec->nloc(0),topoSpec->nloc(1),topoSpec->nloc(2));
 
 #ifndef SKIP_P3D
-    printf("[P3DFFT++] topo IN glob  : %d %d %d  \n",gdimsIN[0],gdimsIN[1],gdimsIN[2]);
-    printf("[P3DFFT++] topo IN loc   : %d %d %d (is: %d %d %d) \n",P3DnlocIN[0],P3DnlocIN[1],P3DnlocIN[2],glob_startIN[0],glob_startIN[1],glob_startIN[2]);
-    printf("[P3DFFT++] topo OUT glob : %d %d %d  \n",gdimsOUT[0],gdimsOUT[1],gdimsOUT[2]);
-    printf("[P3DFFT++] topo OUT loc  : %d %d %d (is: %d %d %d) \n",P3DnlocOUT[0],P3DnlocOUT[1],P3DnlocOUT[2],glob_startOUT[0],glob_startOUT[1],glob_startOUT[2]);
+        printf("[P3DFFT++] topo IN glob  : %d %d %d  \n",gdimsIN[0],gdimsIN[1],gdimsIN[2]);
+        printf("[P3DFFT++] topo IN loc   : %d %d %d (is: %d %d %d) \n",P3DnlocIN[0],P3DnlocIN[1],P3DnlocIN[2],glob_startIN[0],glob_startIN[1],glob_startIN[2]);
+        printf("[P3DFFT++] topo OUT glob : %d %d %d  \n",gdimsOUT[0],gdimsOUT[1],gdimsOUT[2]);
+        printf("[P3DFFT++] topo OUT loc  : %d %d %d (is: %d %d %d) \n",P3DnlocOUT[0],P3DnlocOUT[1],P3DnlocOUT[2],glob_startOUT[0],glob_startOUT[1],glob_startOUT[2]);
 #endif
 
-
-    printf("I am going to allocate FLUPS: %d (inside FLUPS: %d)\n",FLUmemsizeIN,FLUmemsizeOUT);
+        printf("I am going to allocate FLUPS: %d (inside FLUPS: %d)\n",FLUmemsizeIN,FLUmemsizeOUT);
 #ifndef SKIP_P3D    
-    printf("                        P3D: %d (out %d C) \n",P3DmemsizeIN,P3DmemsizeOUT);
+        printf("                        P3D: %d (out %d C) \n",P3DmemsizeIN,P3DmemsizeOUT);
 #endif
+    }
 
 
     double *rhsFLU   = (double *)fftw_malloc(sizeof(double) * FLUmemsizeIN);

samples/compareP3DFFT++/run/zenobe_weakscaling_a2a.sh

@@ -9,7 +9,7 @@ VER=a2a
 EXE=flups_vs_p3dfft++_${VER}
 
 ######### WEAK -> increase the number of CPU and the size
-SCRATCH=/SCRATCH/acad/examples/dcaprace/flupsVSp3dfft3_weak_$VER
+SCRATCH=/SCRATCH/acad/examples/dcaprace/flupsVSp3dfft3_weak_${VER}_V3
 
 # clean the validation dir
 # rm -rf ${SCRATCH}
@@ -38,18 +38,22 @@ cd $SCRATCH
 # qsub -q large -v EXE=${EXE},MY_NY=32,MY_NZ=32,LX=8,LY=8,LZ=16,MY_SIZE=64,MY_NTH=1, -l select=256:ncpus=4:mem=10500mb:mpiprocs=4:ompthreads=1 ./zenobe_kernel.sh
 
 #####################   size = 128^3/proc  #################################
-# cpu = 64
+## CANNOT DO cpu=96,192,384... due to P3D !
+
+# cpu = 128 (-> actually allocating 144)
 # same on large
-qsub -q large -v EXE=${EXE},MY_NY=8,MY_NZ=16,LX=4,LY=4,LZ=8,MY_SIZE=128,MY_NTH=1, -l select=32:ncpus=4:mem=10500mb:mpiprocs=4:ompthreads=1 ./zenobe_kernel.sh
+qsub -q large -v EXE=${EXE},MY_NY=8,MY_NZ=16,LX=4,LY=4,LZ=8,MY_SIZE=128,MY_NTH=1, -l select=6:ncpus=24:mem=63000mb:mpiprocs=24:ompthreads=1 ./zenobe_kernel.sh
 
-# cpu = 256
-qsub -q large -v EXE=${EXE},MY_NY=16,MY_NZ=16,LX=4,LY=8,LZ=8,MY_SIZE=128,MY_NTH=1, -l select=64:ncpus=4:mem=10500mb:mpiprocs=4:ompthreads=1 ./zenobe_kernel.sh
+# cpu = 256 (->264)
+qsub -q large -v EXE=${EXE},MY_NY=16,MY_NZ=16,LX=4,LY=8,LZ=8,MY_SIZE=128,MY_NTH=1, -l select=11:ncpus=24:mem=63000mb:mpiprocs=24:ompthreads=1 ./zenobe_kernel.sh
 
-# cpu = 512
-qsub -q large -v EXE=${EXE},MY_NY=16,MY_NZ=32,LX=8,LY=8,LZ=8,MY_SIZE=128,MY_NTH=1, -l select=128:ncpus=4:mem=10500mb:mpiprocs=4:ompthreads=1 ./zenobe_kernel.sh
+# cpu = 512 (->528)
+qsub -q large -v EXE=${EXE},MY_NY=16,MY_NZ=32,LX=8,LY=8,LZ=8,MY_SIZE=128,MY_NTH=1, -l select=22:ncpus=24:mem=63000mb:mpiprocs=24:ompthreads=1 ./zenobe_kernel.sh
 
-# cpu = 1024
-qsub -q large -v EXE=${EXE},MY_NY=32,MY_NZ=32,LX=8,LY=8,LZ=16,MY_SIZE=128,MY_NTH=1, -l select=256:ncpus=4:mem=10500mb:mpiprocs=4:ompthreads=1 ./zenobe_kernel.sh
+# cpu = 1024 (->1032)
+qsub -q large -v EXE=${EXE},MY_NY=32,MY_NZ=32,LX=8,LY=8,LZ=16,MY_SIZE=128,MY_NTH=1, -l select=43:ncpus=24:mem=63000mb:mpiprocs=24:ompthreads=1 ./zenobe_kernel.sh
 
+# cpu = 2048 (->2064)
+qsub -q large -v EXE=${EXE},MY_NY=32,MY_NZ=64,LX=8,LY=16,LZ=16,MY_SIZE=128,MY_NTH=1, -l select=86:ncpus=24:mem=63000mb:mpiprocs=24:ompthreads=1 ./zenobe_kernel.sh
 
 #end of file

samples/compareP3DFFT++/run/zenobe_weakscaling_nb.sh

@@ -9,7 +9,7 @@ VER=nb
 EXE=flups_vs_p3dfft++_${VER}
 
 ######### WEAK -> increase the number of CPU and the size
-SCRATCH=/SCRATCH/acad/examples/dcaprace/flupsVSp3dfft3_weak_$VER
+SCRATCH=/SCRATCH/acad/examples/dcaprace/flupsVSp3dfft3_weak_${VER}_V3
 
 # clean the validation dir
 # rm -rf ${SCRATCH}
@@ -38,18 +38,22 @@ cd $SCRATCH
 # qsub -q large -v EXE=${EXE},MY_NY=32,MY_NZ=32,LX=8,LY=8,LZ=16,MY_SIZE=64,MY_NTH=1, -l select=256:ncpus=4:mem=10500mb:mpiprocs=4:ompthreads=1 ./zenobe_kernel.sh
 
 #####################   size = 128^3/proc  #################################
-# cpu = 64
+## CANNOT DO cpu=96,192,384... due to P3D !
+
+# cpu = 128 (-> actually allocating 144)
 # same on large
-qsub -q large -v EXE=${EXE},MY_NY=8,MY_NZ=16,LX=4,LY=4,LZ=8,MY_SIZE=128,MY_NTH=1, -l select=32:ncpus=4:mem=10500mb:mpiprocs=4:ompthreads=1 ./zenobe_kernel.sh
+qsub -q large -v EXE=${EXE},MY_NY=8,MY_NZ=16,LX=4,LY=4,LZ=8,MY_SIZE=128,MY_NTH=1, -l select=6:ncpus=24:mem=63000mb:mpiprocs=24:ompthreads=1 ./zenobe_kernel.sh
 
-# cpu = 256
-qsub -q large -v EXE=${EXE},MY_NY=16,MY_NZ=16,LX=4,LY=8,LZ=8,MY_SIZE=128,MY_NTH=1, -l select=64:ncpus=4:mem=10500mb:mpiprocs=4:ompthreads=1 ./zenobe_kernel.sh
+# cpu = 256 (->264)
+qsub -q large -v EXE=${EXE},MY_NY=16,MY_NZ=16,LX=4,LY=8,LZ=8,MY_SIZE=128,MY_NTH=1, -l select=11:ncpus=24:mem=63000mb:mpiprocs=24:ompthreads=1 ./zenobe_kernel.sh
 
-# cpu = 512
-qsub -q large -v EXE=${EXE},MY_NY=16,MY_NZ=32,LX=8,LY=8,LZ=8,MY_SIZE=128,MY_NTH=1, -l select=128:ncpus=4:mem=10500mb:mpiprocs=4:ompthreads=1 ./zenobe_kernel.sh
+# cpu = 512 (->528)
+qsub -q large -v EXE=${EXE},MY_NY=16,MY_NZ=32,LX=8,LY=8,LZ=8,MY_SIZE=128,MY_NTH=1, -l select=22:ncpus=24:mem=63000mb:mpiprocs=24:ompthreads=1 ./zenobe_kernel.sh
 
-# cpu = 1024
-qsub -q large -v EXE=${EXE},MY_NY=32,MY_NZ=32,LX=8,LY=8,LZ=16,MY_SIZE=128,MY_NTH=1, -l select=256:ncpus=4:mem=10500mb:mpiprocs=4:ompthreads=1 ./zenobe_kernel.sh
+# cpu = 1024 (->1032)
+qsub -q large -v EXE=${EXE},MY_NY=32,MY_NZ=32,LX=8,LY=8,LZ=16,MY_SIZE=128,MY_NTH=1, -l select=43:ncpus=24:mem=63000mb:mpiprocs=24:ompthreads=1 ./zenobe_kernel.sh
 
+# cpu = 2048 (->2064)
+qsub -q large -v EXE=${EXE},MY_NY=32,MY_NZ=64,LX=8,LY=16,LZ=16,MY_SIZE=128,MY_NTH=1, -l select=86:ncpus=24:mem=63000mb:mpiprocs=24:ompthreads=1 ./zenobe_kernel.sh
 
 #end of file