diff --git a/.gitignore b/.gitignore
new file mode 100644
index 000000000..61fbc4039
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,46 @@
+build/*
+CMakeCache.txt
+CMakeFiles/
+CTestTestfile.cmake
+DartConfiguration.tcl
+Makefile
+bin/
+cmake_install.cmake
+src/CMakeFiles/
+src/CTestTestfile.cmake
+src/Drivers/CMakeFiles/
+src/Drivers/CTestTestfile.cmake
+src/Drivers/Makefile
+src/Drivers/cmake_install.cmake
+src/Drivers/tests/CMakeFiles/
+src/Drivers/tests/CTestTestfile.cmake
+src/Drivers/tests/Makefile
+src/Drivers/tests/cmake_install.cmake
+src/Makefile
+src/Particle/tests/CMakeFiles/
+src/Particle/tests/CTestTestfile.cmake
+src/Particle/tests/Makefile
+src/Particle/tests/cmake_install.cmake
+src/QMCWaveFunctions/CMakeFiles/
+src/QMCWaveFunctions/CTestTestfile.cmake
+src/QMCWaveFunctions/Makefile
+src/QMCWaveFunctions/cmake_install.cmake
+src/QMCWaveFunctions/tests/CMakeFiles/
+src/QMCWaveFunctions/tests/CTestTestfile.cmake
+src/QMCWaveFunctions/tests/Makefile
+src/QMCWaveFunctions/tests/cmake_install.cmake
+src/Utilities/CMakeFiles/
+src/Utilities/CTestTestfile.cmake
+src/Utilities/Makefile
+src/Utilities/cmake_install.cmake
+src/Utilities/tests/CMakeFiles/
+src/Utilities/tests/CTestTestfile.cmake
+src/Utilities/tests/Makefile
+src/Utilities/tests/cmake_install.cmake
+src/cmake_install.cmake
+src/config.h CMakeCache.txt
+CMakeFiles/
+CTestTestfile.cmake
+DartConfiguration.tcl
+Makefile
+
diff --git a/Benchmark_base/plot.gp b/Benchmark_base/plot.gp
new file mode 100644
index 000000000..dd39a0a5e
--- /dev/null
+++ b/Benchmark_base/plot.gp
@@ -0,0 +1,25 @@
+set term png size 1700,700 enhanced font "Terminal,12"
+set output "plot.png"
+#set grid
+
+set datafile separator ";"
+set auto x
+
+set style data histogram
+set style fill solid border -1
+set boxwidth 0.9
+
+set xtic rotate by -44 scale 0
+set logscale y
+set multiplot layout 1, 1 rowsfirst
+
+set key left
+set ylabel "Time (s)"
+set xlabel "Running on 'Nb' mpi process and 'Nb' omp threads"
+set title "Scalability analysis of the miniQMC application with differents problems size"
+plot "scalabilite_bench211.dat" using 2:xticlabels(stringcolumn(1)) t "miniQMC+211",\
+	 "scalabilite_bench221.dat" using 2:xticlabels(stringcolumn(1)) t "miniQMC+221",\
+	 "scalabilite_bench222.dat" using 2:xticlabels(stringcolumn(1)) t "miniQMC+222",\
+	 "scalabilite_bench422.dat" using 2:xticlabels(stringcolumn(1)) t "miniQMC+422"
+	 
+
diff --git a/Benchmark_base/plot.png b/Benchmark_base/plot.png
new file mode 100644
index 000000000..da0d44a1d
Binary files /dev/null and b/Benchmark_base/plot.png differ
diff --git a/Benchmark_base/scalabilite_bench.dat b/Benchmark_base/scalabilite_bench.dat
new file mode 100644
index 000000000..98a094a98
--- /dev/null
+++ b/Benchmark_base/scalabilite_bench.dat
@@ -0,0 +1,31 @@
+1 1; 0.00
+;
+2 1; 2.16
+;
+1 2; 0.00
+;
+4 1; 2.16
+;
+1 4; 0.00
+;
+2 2; 2.15
+;
+8 1; 2.17
+;
+1 8; 0.00
+;
+2 4; 2.15
+;
+4 2; 2.16
+;
+16 1; 2.23
+;
+1 16; 0.00
+;
+2 8; 2.15
+;
+4 4; ;
+8 2; ;
+32 1; 0.14
+;
+1 32; 
\ No newline at end of file
diff --git a/Benchmark_base/scalabilite_bench211.dat b/Benchmark_base/scalabilite_bench211.dat
new file mode 100644
index 000000000..6e8639067
--- /dev/null
+++ b/Benchmark_base/scalabilite_bench211.dat
@@ -0,0 +1,40 @@
+1 1; 1.61
+1 2; 1.55
+1 4; 1.79
+1 8; 2.02
+1 16; 2.15
+1 32; 2.94
+1 48; 3.35
+2 1; 1.79
+2 2; 2.29
+2 4; 4.36
+2 8; 8.23
+2 16; 16.06
+2 24; 24.11
+3 16; 4.13
+4 1; 1.67
+4 2; 1.84
+4 4; 1.93
+4 8; 2.88
+4 12; 3.02
+6 8; 2.75
+8 1; 1.75
+8 2; 1.95
+8 4; 2.55
+8 6; 2.74
+12 4; 2.77
+16 1; 1.83
+16 2; 2.43
+16 3; 2.76
+24 2; 2.80
+32 1; 0.11
+48 1; 0.12
+
+
+
+
+
+
+
+
+
diff --git a/Benchmark_base/scalabilite_bench221.dat b/Benchmark_base/scalabilite_bench221.dat
new file mode 100644
index 000000000..c9406194e
--- /dev/null
+++ b/Benchmark_base/scalabilite_bench221.dat
@@ -0,0 +1,41 @@
+1 1; 5.03
+1 2; 5.28
+1 4; 6.32
+1 8; 6.00
+1 16; 6.38
+1 32; 10.34
+1 48; 12.62
+2 1; 5.22
+2 2; 7.68
+2 4; 15.03
+2 8; 29.63
+2 16; 59.78
+2 24; 89.99
+3 16; 14.64
+4 1; 5.17
+4 2; 5.74
+4 4; 6.01
+4 8; 9.05
+4 12; 10.70
+6 8; 10.65
+8 1; 5.42
+8 2; 5.71
+8 4; 8.48
+8 6; 10.62
+12 4; 10.67
+16 1; 5.61
+16 2; 8.29
+16 3; 10.66
+24 2; 10.59
+32 1; 0.10
+48 1; 0.09
+
+
+
+
+
+
+
+
+
+
diff --git a/Benchmark_base/scalabilite_bench222.dat b/Benchmark_base/scalabilite_bench222.dat
new file mode 100644
index 000000000..6b8cd2694
--- /dev/null
+++ b/Benchmark_base/scalabilite_bench222.dat
@@ -0,0 +1,34 @@
+1 1; 21.50
+1 2; 22.36
+1 4; 22.43
+1 8; 23.33
+1 16; 25.20
+1 32; 41.16
+1 48; 58.76
+2 1; 87.26
+2 2; 33.48
+2 4; 65.97
+2 8; 132.41
+2 16; 269.17
+2 24; 402.38
+3 16; 70.17
+4 1; 21.49
+4 2; 22.81
+4 4; 23.95
+4 8; 38.13
+4 12; 52.21
+6 8; 51.85
+8 1; 22.58
+8 2; 23.49
+8 4; 37.01
+8 6; 51.94
+12 4; 52.10
+16 1; 23.40
+16 2; 36.36
+16 3; 52.22
+24 2; 52.61
+32 1; 00.10
+48 1; 00.11
+
+
+
diff --git a/Benchmark_base/scalabilite_bench422.dat b/Benchmark_base/scalabilite_bench422.dat
new file mode 100644
index 000000000..d6f805206
--- /dev/null
+++ b/Benchmark_base/scalabilite_bench422.dat
@@ -0,0 +1,40 @@
+1 1; 101.33
+1 2; 101.38
+1 4; 106.76
+1 8; 112.05
+1 16; 120.38
+1 32; 210.00
+1 48; 312.79
+2 1; 103.69
+2 2; 165.27
+2 4; 336.69
+2 8; 676.17
+2 16; 1395.95
+2 24; 2059.04
+3 16; 385.52
+4 1; 100.67
+4 2; 109.86
+4 4; 116.53
+4 8; 197.72
+4 12; 290.18
+6 8; 289.73
+8 1; 110.60
+8 2; 116.01
+8 4; 189.65
+8 6; 289.75
+12 4; 288.98
+16 1; 114.77
+16 2; 193.47
+16 3; 290.29
+24 2; 290.24
+32 1; 0.15
+48 1; 0.15
+
+
+
+
+
+
+
+
+
diff --git a/Benchmarks_omp/plot.gp b/Benchmarks_omp/plot.gp
new file mode 100644
index 000000000..46198bedc
--- /dev/null
+++ b/Benchmarks_omp/plot.gp
@@ -0,0 +1,26 @@
+set term png size 1700,700 enhanced font "Terminal,12"
+set output "plot.png"
+#set grid
+
+set datafile separator ";"
+set auto x
+
+set style data histogram
+set style fill solid border -1
+set boxwidth 0.9
+
+set xtic rotate by -44 scale 0
+set logscale y
+set yrange [0.01:10000]
+set multiplot layout 1, 1 rowsfirst
+
+set key left
+set ylabel "Time (s)"
+set xlabel "Running on 'Nb' mpi process and 'Nb' omp threads"
+set title "Scalability analysis of the miniQMC application with differents problems size"
+plot "scalabilite_bench211.dat" using 2:xticlabels(stringcolumn(1)) t "miniQMC+211",\
+	 "scalabilite_bench221.dat" using 2:xticlabels(stringcolumn(1)) t "miniQMC+221",\
+	 "scalabilite_bench222.dat" using 2:xticlabels(stringcolumn(1)) t "miniQMC+222",\
+	 "scalabilite_bench422.dat" using 2:xticlabels(stringcolumn(1)) t "miniQMC+422",\
+	 
+
diff --git a/Benchmarks_omp/plot.png b/Benchmarks_omp/plot.png
new file mode 100644
index 000000000..9a05d2f70
Binary files /dev/null and b/Benchmarks_omp/plot.png differ
diff --git a/Benchmarks_omp/scalabilite_bench211.dat b/Benchmarks_omp/scalabilite_bench211.dat
new file mode 100644
index 000000000..02ca179fe
--- /dev/null
+++ b/Benchmarks_omp/scalabilite_bench211.dat
@@ -0,0 +1,37 @@
+1 1; 2.30
+1 2; 2.77
+1 4; 2.69
+1 8; 2.93
+1 16; 2.88
+1 32; 4.37
+1 48; 4.61
+2 1; 2.48
+2 2; 3.20
+2 4; 6.27
+2 8; 12.05
+2 16; 23.58
+2 24; 35.24
+3 16; 5.56
+4 1; 2.54
+4 2; 2.79
+4 4; 2.79
+4 8; 4.06
+4 12; 4.33
+6 8; 3.97
+8 1; 2.46
+8 2; 2.96
+8 4; 3.73
+8 6; 4.15
+12 4; 3.99
+16 1; 2.61
+16 2; 3.43
+16 3; 3.92
+24 2; 3.92
+32 1; 0.11
+48 1; 0.10
+;
+
+
+
+
+
diff --git a/Benchmarks_omp/scalabilite_bench221.dat b/Benchmarks_omp/scalabilite_bench221.dat
new file mode 100644
index 000000000..8140086d4
--- /dev/null
+++ b/Benchmarks_omp/scalabilite_bench221.dat
@@ -0,0 +1,40 @@
+1 1; 6.96
+1 2; 7.32
+1 4; 7.84
+1 8; 8.14
+1 16; 8.54
+1 32; 13.57
+1 48; 15.81
+2 1; 7.16
+2 2; 10.96
+2 4; 21.46
+2 8; 43.23
+2 16; 86.13
+2 24; 129.11
+3 16; 19.22
+4 1; 6.97
+4 2; 7.79
+4 4; 8.12
+4 8; 12.19
+4 12; 14.48
+6 8; 14.49
+8 1; 7.56
+8 2; 7.76
+8 4; 11.50
+8 6; 14.34
+12 4; 14.11
+16 1; 7.67
+16 2; 11.28
+16 3; 14.21
+24 2; 14.19
+32 1; 0.10
+48 1; 0.11
+;
+
+
+
+
+
+
+1
+
diff --git a/Benchmarks_omp/scalabilite_bench222.dat b/Benchmarks_omp/scalabilite_bench222.dat
new file mode 100644
index 000000000..0ab372ed4
--- /dev/null
+++ b/Benchmarks_omp/scalabilite_bench222.dat
@@ -0,0 +1,39 @@
+1 1; 27.24
+1 2; 27.87
+1 4; 29.81
+1 8; 31.50
+1 16; 32.31
+1 32; 50.39
+1 48; 68.30
+2 1; 28.44
+2 2; 45.93
+2 4; 88.90
+2 8; 179.15
+2 16; 363.14
+2 24; 542.38
+3 16; 88.64
+4 1; 27.69
+4 2; 30.41
+4 4; 31.25
+4 8; 47.59
+4 12; 64.62
+6 8; 64.12
+8 1; 30.03
+8 2; 30.72
+8 4; 47.02
+8 6; 63.10
+12 4; 64.50
+16 1; 30.48
+16 2; 46.82
+16 3; 64.02
+24 2; 64.08
+32 1; 0.10
+48 1; 0.11
+;
+
+
+
+
+
+
+
diff --git a/Benchmarks_omp/scalabilite_bench422.dat b/Benchmarks_omp/scalabilite_bench422.dat
new file mode 100644
index 000000000..9dc6951b6
--- /dev/null
+++ b/Benchmarks_omp/scalabilite_bench422.dat
@@ -0,0 +1,40 @@
+1 1; 119.23
+1 2; 120.35
+1 4; 127.97
+1 8; 132.13
+1 16; 139.62
+1 32; 233.18
+1 48; 329.06
+2 1; 121.54
+2 2; 206.11
+2 4; 405.85
+2 8; 822.06
+2 16; 1667.00
+2 24; 2504.87
+3 16; 433.31
+4 1; 118.62
+4 2; 129.26
+4 4; 137.09
+4 8; 225.07
+4 12; 315.16
+6 8; 313.06
+8 1; 130.30
+8 2; 135.34
+8 4; 214.02
+8 6; 313.55
+12 4; 312.25
+16 1; 135.76
+16 2; 212.71
+16 3; 313.45
+24 2; 313.00
+32 1; 0.15
+48 1; 0.16
+;
+
+
+
+
+
+
+
+
diff --git a/bench.sh b/bench.sh
new file mode 100644
index 000000000..56585ee9d
--- /dev/null
+++ b/bench.sh
@@ -0,0 +1,4 @@
+#!/bin/bash
+./exec211.sh 48
+./exec221.sh 48
+./exec422.sh 48
diff --git a/bench_comparaison/plot.gp b/bench_comparaison/plot.gp
new file mode 100644
index 000000000..8cd4bd7a3
--- /dev/null
+++ b/bench_comparaison/plot.gp
@@ -0,0 +1,25 @@
+set term png size 1700,700 enhanced font "Terminal,12"
+set output "plot.png"
+#set grid
+
+set datafile separator ";"
+set auto x
+
+set style data histogram
+set style fill solid border -1
+set boxwidth 0.9
+
+set xtic rotate by -44 scale 0
+set logscale y
+set yrange [0.01:10000]
+set multiplot layout 1, 1 rowsfirst
+
+set key left
+set ylabel "Time (s)"
+set xlabel "Running on 'Nb' mpi process and 'Nb' omp threads"
+set title "Scalability analysis of the miniQMC application with differents problems size"
+plot "scalabilite_bench422base.dat" using 2:xticlabels(stringcolumn(1)) t "miniQMC+422+base",\
+	 "scalabilite_bench422omp.dat" using 2:xticlabels(stringcolumn(1)) t "miniQMC+422+optim"
+	
+	 
+
diff --git a/bench_comparaison/plot.png b/bench_comparaison/plot.png
new file mode 100644
index 000000000..6dec023a3
Binary files /dev/null and b/bench_comparaison/plot.png differ
diff --git a/bench_comparaison/scalabilite_bench422base.dat b/bench_comparaison/scalabilite_bench422base.dat
new file mode 100644
index 000000000..d6f805206
--- /dev/null
+++ b/bench_comparaison/scalabilite_bench422base.dat
@@ -0,0 +1,40 @@
+1 1; 101.33
+1 2; 101.38
+1 4; 106.76
+1 8; 112.05
+1 16; 120.38
+1 32; 210.00
+1 48; 312.79
+2 1; 103.69
+2 2; 165.27
+2 4; 336.69
+2 8; 676.17
+2 16; 1395.95
+2 24; 2059.04
+3 16; 385.52
+4 1; 100.67
+4 2; 109.86
+4 4; 116.53
+4 8; 197.72
+4 12; 290.18
+6 8; 289.73
+8 1; 110.60
+8 2; 116.01
+8 4; 189.65
+8 6; 289.75
+12 4; 288.98
+16 1; 114.77
+16 2; 193.47
+16 3; 290.29
+24 2; 290.24
+32 1; 0.15
+48 1; 0.15
+
+
+
+
+
+
+
+
+
diff --git a/bench_comparaison/scalabilite_bench422omp.dat b/bench_comparaison/scalabilite_bench422omp.dat
new file mode 100644
index 000000000..9dc6951b6
--- /dev/null
+++ b/bench_comparaison/scalabilite_bench422omp.dat
@@ -0,0 +1,40 @@
+1 1; 119.23
+1 2; 120.35
+1 4; 127.97
+1 8; 132.13
+1 16; 139.62
+1 32; 233.18
+1 48; 329.06
+2 1; 121.54
+2 2; 206.11
+2 4; 405.85
+2 8; 822.06
+2 16; 1667.00
+2 24; 2504.87
+3 16; 433.31
+4 1; 118.62
+4 2; 129.26
+4 4; 137.09
+4 8; 225.07
+4 12; 315.16
+6 8; 313.06
+8 1; 130.30
+8 2; 135.34
+8 4; 214.02
+8 6; 313.55
+12 4; 312.25
+16 1; 135.76
+16 2; 212.71
+16 3; 313.45
+24 2; 313.00
+32 1; 0.15
+48 1; 0.16
+;
+
+
+
+
+
+
+
+
diff --git a/benchmarks/result_base_2_1_1.txt b/benchmarks/result_base_2_1_1.txt
new file mode 100644
index 000000000..4e1cbba87
--- /dev/null
+++ b/benchmarks/result_base_2_1_1.txt
@@ -0,0 +1,66 @@
+miniqmc git branch: develop
+miniqmc git commit: 5ed650c8c390884d6a84f002be2bbfa103b7df3e
+
+Number of orbitals/splines = 384
+Tile size = 384
+Number of tiles = 1
+Number of electrons = 768
+Rmax = 1.7
+AcceptanceRatio = 0.5
+Iterations = 5
+OpenMP threads = 4
+Number of walkers per rank = 4
+
+SPO coefficients size = 196608000 bytes (187.5 MB)
+delayed update rank = 32
+Using SoA distance table, Jastrow + einspline, 
+and determinant update.
+================================== 
+Stack timer profile in seconds
+Timer                             Inclusive_time  Exclusive_time  Calls       Time_per_call
+Setup                                0.0572     0.0572              1       0.057204007
+Total                                2.3655     0.3644              1       2.365510626
+  Diffusion                          0.9438     0.0031              5       0.188756147
+    Accept move                      0.0015     0.0015           1913       0.000000782
+    Complete Updates                 0.0296     0.0000              5       0.005926068
+      Determinant::update            0.0296     0.0296             10       0.002961351
+    Current Gradient                 0.0485     0.0014           3840       0.000012624
+      Determinant::ratio             0.0464     0.0464           3840       0.000012076
+      OneBodyJastrow                 0.0004     0.0004           3840       0.000000102
+      TwoBodyJastrow                 0.0003     0.0003           3840       0.000000082
+    Kinetic Energy                   0.0090     0.0090              5       0.001805381
+      OneBodyJastrow                 0.0000     0.0000              5       0.000009225
+      TwoBodyJastrow                 0.0000     0.0000              5       0.000005901
+    Make move                        0.0826     0.0826           3840       0.000021510
+    New Gradient                     0.2125     0.0021           3840       0.000055339
+      Determinant::ratio             0.0024     0.0024           3840       0.000000613
+      Determinant::spovgl            0.1814     0.0048           3840       0.000047232
+        Single-Particle Orbitals     0.1766     0.1766           3840       0.000045983
+      OneBodyJastrow                 0.0027     0.0027           3840       0.000000692
+      TwoBodyJastrow                 0.0240     0.0240           3840       0.000006247
+    Set active                       0.0836     0.0836           3840       0.000021775
+    Update                           0.4734     0.0010           1913       0.000247448
+      Determinant::update            0.4559     0.4559           1913       0.000238301
+      OneBodyJastrow                 0.0002     0.0002           1913       0.000000106
+      TwoBodyJastrow                 0.0163     0.0163           1913       0.000008520
+  Initialization                     0.1507     0.0716              1       0.150714155
+    Determinant::inverse             0.0249     0.0249              2       0.012473029
+    Determinant::spovgl              0.0504     0.0019              2       0.025175876
+      Single-Particle Orbitals       0.0484     0.0484            768       0.000063085
+    OneBodyJastrow                   0.0005     0.0005              1       0.000466003
+    TwoBodyJastrow                   0.0033     0.0033              1       0.003317725
+  Pseudopotential                    0.9067     0.0046              5       0.181331985
+    Make move                        0.3530     0.3530          15792       0.000022355
+    Value                            0.5491     0.0062          15792       0.000034768
+      Determinant::ratio             0.0051     0.0051          15792       0.000000323
+      Determinant::spoval            0.4879     0.0040          15792       0.000030896
+        Single-Particle Orbitals     0.4839     0.4839          15792       0.000030640
+      OneBodyJastrow                 0.0052     0.0052          15792       0.000000331
+      TwoBodyJastrow                 0.0446     0.0446          15792       0.000002825
+
+========== Throughput ============ 
+
+Total throughput ( N_walkers * N_elec^3 / Total time ) = 7.65982e+08
+Diffusion throughput ( N_walkers * N_elec^3 / Diffusion time ) = 1.91987e+09
+Pseudopotential throughput ( N_walkers * N_elec^2 / Pseudopotential time ) = 2.60218e+06
+
diff --git a/exec.sh b/exec.sh
new file mode 100644
index 000000000..1ac020069
--- /dev/null
+++ b/exec.sh
@@ -0,0 +1,62 @@
+#!/bin/bash
+rm -rf scalabilite_bench.dat
+TIME_FORMAT=%R
+max_core=$1
+
+printf 'running on 1 process\n\n'
+echo -n "1 1; " >> scalabilite_bench.dat 
+OMP_NUM_THREADS=1 ~/time -p ./build/bin/miniqmc -g "2 2 2" |& grep -E "real [0-9][0-9]*\.[0-9][0-9]*" | sed "s/real //g" >> scalabilite_bench.dat
+echo ";" >> scalabilite_bench.dat
+for((i=2; i<=max_core; i=i*2))
+do
+	printf 'running on %d mpi process and 1 omp threads\n' "$i"
+	echo -n "$i 1; " >> scalabilite_bench.dat
+	OMP_NUM_THREADS=1 ~/time -p mpirun -n $i ./build/bin/miniqmc -g "2 2 2" |& grep -E "real [0-9][0-9]*\.[0-9][0-9]*" | sed "s/real //g" >> scalabilite_bench.dat
+	echo ";" >> scalabilite_bench.dat
+
+	printf 'running on 1 mpi process and %d omp threads\n' "$i"
+	echo -n "1 $i; " >> scalabilite_bench.dat
+	OMP_NUM_THREADS=$i ~/time -p ./build/bin/miniqmc -g "2 2 2" |& grep -E "real [0-9][0-9]*\.[0-9][0-9]*" | sed "s/real //g" >> scalabilite_bench.dat
+	echo ";" >> scalabilite_bench.dat
+
+	for((k=2; k<i; k=k*2))
+	do
+		div=$(($i/$k))
+		printf 'running on %d mpi process and %d omp threads\n' "$k" "$div"
+		echo -n "$k $div; " >> scalabilite_bench.dat
+		OMP_NUM_THREADS=$div ~/time -p mpirun -n $k ./build/bin/miniqmc -g "2 2 2"|& grep -E "real [0-9][0-9]*\.[0-9][0-9]*" | sed "s/real //g" >> scalabilite_bench.dat
+		echo ";" >> scalabilite_bench.dat
+
+	done
+	printf "\n"
+	if((i==max_core))
+	then
+		exit 0
+	fi
+done
+
+printf 'running on %d mpi process and 1 omp threads\n' "$max_core"
+echo -n "$max_core 1; " >> scalabilite_bench.dat
+OMP_NUM_THREADS=1 ~/time -p mpirun -n $max_core ./build/bin/miniqmc -g "2 2 2"|& grep -E "real [0-9][0-9]*\.[0-9][0-9]*" | sed "s/real //g" >> scalabilite_bench.dat
+echo ";" >> scalabilite_bench.dat
+
+printf 'running on 1 mpi process and %d omp threads\n' "$max_core"
+echo -n "1 $max_core; " >> scalabilite_bench.dat
+OMP_NUM_THREADS=$max_core ~/time -p ./build/bin/miniqmc -g "2 2 2"|& grep -E "real [0-9][0-9]*\.[0-9][0-9]*" | sed "s/real //g" >> scalabilite_bench.dat
+echo ";" >> scalabilite_bench.dat
+
+for((k=2; k<=max_core; k=k*2))
+do
+	div=$(($max_core/$k))
+	if((div == 1 && k!= max_core)); then break; fi
+	printf 'running on %d mpi process and %d omp threads\n' "$k" "$div"
+	echo -n "$k $div; " >> scalabilite_bench.dat
+	OMP_NUM_THREADS=$div ~/time -p mpirun -n $k ./build/bin/miniqmc -g "2 2 2"|& grep -E "real [0-9][0-9]*\.[0-9][0-9]*" | sed "s/real //g" >> scalabilite_bench.dat
+	echo ";" >> scalabilite_bench.dat
+
+	printf 'running on %d mpi process and %d omp threads\n' "$div" "$k"
+	echo -n "$div $k; " >> scalabilite_bench.dat
+	OMP_NUM_THREADS=$k ~/time -p mpirun -n $div ./build/bin/miniqmc -g "2 2 2"|& grep -E "real [0-9][0-9]*\.[0-9][0-9]*" | sed "s/real //g" >> scalabilite_bench.dat
+	echo ";" >> scalabilite_bench.dat
+done
+printf "\n"
diff --git a/exec211.sh b/exec211.sh
new file mode 100644
index 000000000..ea4cb2db2
--- /dev/null
+++ b/exec211.sh
@@ -0,0 +1,62 @@
+#!/bin/bash
+rm -rf scalabilite_bench211.dat
+TIME_FORMAT=%R
+max_core=$1
+
+printf 'running on 1 process\n\n'
+echo -n "1 1; " >> scalabilite_bench211.dat 
+OMP_NUM_THREADS=1 ~/time -p ./build/bin/miniqmc -g "2 1 1" |& grep -E "real [0-9][0-9]*\.[0-9][0-9]*" | sed "s/real //g" >> scalabilite_bench211.dat
+echo ";" >> scalabilite_bench211.dat
+for((i=2; i<=max_core; i=i*2))
+do
+	printf 'running on %d mpi process and 1 omp threads\n' "$i"
+	echo -n "$i 1; " >> scalabilite_bench211.dat
+	OMP_NUM_THREADS=1 ~/time -p mpirun -n $i ./build/bin/miniqmc -g "2 1 1" |& grep -E "real [0-9][0-9]*\.[0-9][0-9]*" | sed "s/real //g" >> scalabilite_bench211.dat
+	echo ";" >> scalabilite_bench211.dat
+
+	printf 'running on 1 mpi process and %d omp threads\n' "$i"
+	echo -n "1 $i; " >> scalabilite_bench211.dat
+	OMP_NUM_THREADS=$i ~/time -p ./build/bin/miniqmc -g "2 1 1" |& grep -E "real [0-9][0-9]*\.[0-9][0-9]*" | sed "s/real //g" >> scalabilite_bench211.dat
+	echo ";" >> scalabilite_bench211.dat
+
+	for((k=2; k<i; k=k*2))
+	do
+		div=$(($i/$k))
+		printf 'running on %d mpi process and %d omp threads\n' "$k" "$div"
+		echo -n "$k $div; " >> scalabilite_bench211.dat
+		OMP_NUM_THREADS=$div ~/time -p mpirun -n $k ./build/bin/miniqmc -g "2 1 1"|& grep -E "real [0-9][0-9]*\.[0-9][0-9]*" | sed "s/real //g" >> scalabilite_bench211.dat
+		echo ";" >> scalabilite_bench211.dat
+
+	done
+	printf "\n"
+	if((i==max_core))
+	then
+		exit 0
+	fi
+done
+
+printf 'running on %d mpi process and 1 omp threads\n' "$max_core"
+echo -n "$max_core 1; " >> scalabilite_bench211.dat
+OMP_NUM_THREADS=1 ~/time -p mpirun -n $max_core ./build/bin/miniqmc -g "2 1 1"|& grep -E "real [0-9][0-9]*\.[0-9][0-9]*" | sed "s/real //g" >> scalabilite_bench211.dat
+echo ";" >> scalabilite_bench211.dat
+
+printf 'running on 1 mpi process and %d omp threads\n' "$max_core"
+echo -n "1 $max_core; " >> scalabilite_bench211.dat
+OMP_NUM_THREADS=$max_core ~/time -p ./build/bin/miniqmc -g "2 1 1"|& grep -E "real [0-9][0-9]*\.[0-9][0-9]*" | sed "s/real //g" >> scalabilite_bench211.dat
+echo ";" >> scalabilite_bench211.dat
+
+for((k=2; k<=max_core; k=k*2))
+do
+	div=$(($max_core/$k))
+	if((div == 1 && k!= max_core)); then break; fi
+	printf 'running on %d mpi process and %d omp threads\n' "$k" "$div"
+	echo -n "$k $div; " >> scalabilite_bench211.dat
+	OMP_NUM_THREADS=$div ~/time -p mpirun -n $k ./build/bin/miniqmc -g "2 1 1"|& grep -E "real [0-9][0-9]*\.[0-9][0-9]*" | sed "s/real //g" >> scalabilite_bench211.dat
+	echo ";" >> scalabilite_bench211.dat
+
+	printf 'running on %d mpi process and %d omp threads\n' "$div" "$k"
+	echo -n "$div $k; " >> scalabilite_bench211.dat
+	OMP_NUM_THREADS=$k ~/time -p mpirun -n $div ./build/bin/miniqmc -g "2 1 1"|& grep -E "real [0-9][0-9]*\.[0-9][0-9]*" | sed "s/real //g" >> scalabilite_bench211.dat
+	echo ";" >> scalabilite_bench211.dat
+done
+printf "\n"
diff --git a/exec221.sh b/exec221.sh
new file mode 100644
index 000000000..2d0ddd7a1
--- /dev/null
+++ b/exec221.sh
@@ -0,0 +1,62 @@
+#!/bin/bash
+rm -rf scalabilite_bench221.dat
+TIME_FORMAT=%R
+max_core=$1
+
+printf 'running on 1 process\n\n'
+echo -n "1 1; " >> scalabilite_bench221.dat 
+OMP_NUM_THREADS=1 ~/time -p ./build/bin/miniqmc -g "2 2 1" |& grep -E "real [0-9][0-9]*\.[0-9][0-9]*" | sed "s/real //g" >> scalabilite_bench221.dat
+echo ";" >> scalabilite_bench221.dat
+for((i=2; i<=max_core; i=i*2))
+do
+	printf 'running on %d mpi process and 1 omp threads\n' "$i"
+	echo -n "$i 1; " >> scalabilite_bench221.dat
+	OMP_NUM_THREADS=1 ~/time -p mpirun -n $i ./build/bin/miniqmc -g "2 2 1" |& grep -E "real [0-9][0-9]*\.[0-9][0-9]*" | sed "s/real //g" >> scalabilite_bench221.dat
+	echo ";" >> scalabilite_bench221.dat
+
+	printf 'running on 1 mpi process and %d omp threads\n' "$i"
+	echo -n "1 $i; " >> scalabilite_bench221.dat
+	OMP_NUM_THREADS=$i ~/time -p ./build/bin/miniqmc -g "2 2 1" |& grep -E "real [0-9][0-9]*\.[0-9][0-9]*" | sed "s/real //g" >> scalabilite_bench221.dat
+	echo ";" >> scalabilite_bench221.dat
+
+	for((k=2; k<i; k=k*2))
+	do
+		div=$(($i/$k))
+		printf 'running on %d mpi process and %d omp threads\n' "$k" "$div"
+		echo -n "$k $div; " >> scalabilite_bench221.dat
+		OMP_NUM_THREADS=$div ~/time -p mpirun -n $k ./build/bin/miniqmc -g "2 2 1"|& grep -E "real [0-9][0-9]*\.[0-9][0-9]*" | sed "s/real //g" >> scalabilite_bench221.dat
+		echo ";" >> scalabilite_bench221.dat
+
+	done
+	printf "\n"
+	if((i==max_core))
+	then
+		exit 0
+	fi
+done
+
+printf 'running on %d mpi process and 1 omp threads\n' "$max_core"
+echo -n "$max_core 1; " >> scalabilite_bench221.dat
+OMP_NUM_THREADS=1 ~/time -p mpirun -n $max_core ./build/bin/miniqmc -g "2 2 1"|& grep -E "real [0-9][0-9]*\.[0-9][0-9]*" | sed "s/real //g" >> scalabilite_bench221.dat
+echo ";" >> scalabilite_bench221.dat
+
+printf 'running on 1 mpi process and %d omp threads\n' "$max_core"
+echo -n "1 $max_core; " >> scalabilite_bench221.dat
+OMP_NUM_THREADS=$max_core ~/time -p ./build/bin/miniqmc -g "2 2 1"|& grep -E "real [0-9][0-9]*\.[0-9][0-9]*" | sed "s/real //g" >> scalabilite_bench221.dat
+echo ";" >> scalabilite_bench221.dat
+
+for((k=2; k<=max_core; k=k*2))
+do
+	div=$(($max_core/$k))
+	if((div == 1 && k!= max_core)); then break; fi
+	printf 'running on %d mpi process and %d omp threads\n' "$k" "$div"
+	echo -n "$k $div; " >> scalabilite_bench221.dat
+	OMP_NUM_THREADS=$div ~/time -p mpirun -n $k ./build/bin/miniqmc -g "2 2 1"|& grep -E "real [0-9][0-9]*\.[0-9][0-9]*" | sed "s/real //g" >> scalabilite_bench221.dat
+	echo ";" >> scalabilite_bench221.dat
+
+	printf 'running on %d mpi process and %d omp threads\n' "$div" "$k"
+	echo -n "$div $k; " >> scalabilite_bench221.dat
+	OMP_NUM_THREADS=$k ~/time -p mpirun -n $div ./build/bin/miniqmc -g "2 2 1"|& grep -E "real [0-9][0-9]*\.[0-9][0-9]*" | sed "s/real //g" >> scalabilite_bench221.dat
+	echo ";" >> scalabilite_bench221.dat
+done
+printf "\n"
diff --git a/exec222.sh b/exec222.sh
new file mode 100644
index 000000000..1e772f577
--- /dev/null
+++ b/exec222.sh
@@ -0,0 +1,62 @@
+#!/bin/bash
+rm -rf scalabilite_bench222.dat
+TIME_FORMAT=%R
+max_core=$1
+
+printf 'running on 1 process\n\n'
+echo -n "1 1; " >> scalabilite_bench222.dat 
+OMP_NUM_THREADS=1 ~/time -p ./build/bin/miniqmc -g "2 2 2" |& grep -E "real [0-9][0-9]*\.[0-9][0-9]*" | sed "s/real //g" >> scalabilite_bench222.dat
+echo ";" >> scalabilite_bench222.dat
+for((i=2; i<=max_core; i=i*2))
+do
+	printf 'running on %d mpi process and 1 omp threads\n' "$i"
+	echo -n "$i 1; " >> scalabilite_bench222.dat
+	OMP_NUM_THREADS=1 ~/time -p mpirun -n $i ./build/bin/miniqmc -g "2 2 2" |& grep -E "real [0-9][0-9]*\.[0-9][0-9]*" | sed "s/real //g" >> scalabilite_bench222.dat
+	echo ";" >> scalabilite_bench222.dat
+
+	printf 'running on 1 mpi process and %d omp threads\n' "$i"
+	echo -n "1 $i; " >> scalabilite_bench222.dat
+	OMP_NUM_THREADS=$i ~/time -p ./build/bin/miniqmc -g "2 2 2" |& grep -E "real [0-9][0-9]*\.[0-9][0-9]*" | sed "s/real //g" >> scalabilite_bench222.dat
+	echo ";" >> scalabilite_bench222.dat
+
+	for((k=2; k<i; k=k*2))
+	do
+		div=$(($i/$k))
+		printf 'running on %d mpi process and %d omp threads\n' "$k" "$div"
+		echo -n "$k $div; " >> scalabilite_bench222.dat
+		OMP_NUM_THREADS=$div ~/time -p mpirun -n $k ./build/bin/miniqmc -g "2 2 2"|& grep -E "real [0-9][0-9]*\.[0-9][0-9]*" | sed "s/real //g" >> scalabilite_bench222.dat
+		echo ";" >> scalabilite_bench222.dat
+
+	done
+	printf "\n"
+	if((i==max_core))
+	then
+		exit 0
+	fi
+done
+
+printf 'running on %d mpi process and 1 omp threads\n' "$max_core"
+echo -n "$max_core 1; " >> scalabilite_bench222.dat
+OMP_NUM_THREADS=1 ~/time -p mpirun -n $max_core ./build/bin/miniqmc -g "2 2 2"|& grep -E "real [0-9][0-9]*\.[0-9][0-9]*" | sed "s/real //g" >> scalabilite_bench222.dat
+echo ";" >> scalabilite_bench222.dat
+
+printf 'running on 1 mpi process and %d omp threads\n' "$max_core"
+echo -n "1 $max_core; " >> scalabilite_bench222.dat
+OMP_NUM_THREADS=$max_core ~/time -p ./build/bin/miniqmc -g "2 2 2"|& grep -E "real [0-9][0-9]*\.[0-9][0-9]*" | sed "s/real //g" >> scalabilite_bench222.dat
+echo ";" >> scalabilite_bench222.dat
+
+for((k=2; k<=max_core; k=k*2))
+do
+	div=$(($max_core/$k))
+	if((div == 1 && k!= max_core)); then break; fi
+	printf 'running on %d mpi process and %d omp threads\n' "$k" "$div"
+	echo -n "$k $div; " >> scalabilite_bench222.dat
+	OMP_NUM_THREADS=$div ~/time -p mpirun -n $k ./build/bin/miniqmc -g "2 2 2"|& grep -E "real [0-9][0-9]*\.[0-9][0-9]*" | sed "s/real //g" >> scalabilite_bench222.dat
+	echo ";" >> scalabilite_bench222.dat
+
+	printf 'running on %d mpi process and %d omp threads\n' "$div" "$k"
+	echo -n "$div $k; " >> scalabilite_bench222.dat
+	OMP_NUM_THREADS=$k ~/time -p mpirun -n $div ./build/bin/miniqmc -g "2 2 2"|& grep -E "real [0-9][0-9]*\.[0-9][0-9]*" | sed "s/real //g" >> scalabilite_bench222.dat
+	echo ";" >> scalabilite_bench222.dat
+done
+printf "\n"
diff --git a/exec422.sh b/exec422.sh
new file mode 100644
index 000000000..0d77c5668
--- /dev/null
+++ b/exec422.sh
@@ -0,0 +1,62 @@
+#!/bin/bash
+rm -rf scalabilite_bench422.dat
+TIME_FORMAT=%R
+max_core=$1
+
+printf 'running on 1 process\n\n'
+echo -n "1 1; " >> scalabilite_bench422.dat 
+OMP_NUM_THREADS=1 ~/time -p ./build/bin/miniqmc -g "4 2 2" |& grep -E "real [0-9][0-9]*\.[0-9][0-9]*" | sed "s/real //g" >> scalabilite_bench422.dat
+echo ";" >> scalabilite_bench422.dat
+for((i=2; i<=max_core; i=i*2))
+do
+	printf 'running on %d mpi process and 1 omp threads\n' "$i"
+	echo -n "$i 1; " >> scalabilite_bench422.dat
+	OMP_NUM_THREADS=1 ~/time -p mpirun -n $i ./build/bin/miniqmc -g "4 2 2" |& grep -E "real [0-9][0-9]*\.[0-9][0-9]*" | sed "s/real //g" >> scalabilite_bench422.dat
+	echo ";" >> scalabilite_bench422.dat
+
+	printf 'running on 1 mpi process and %d omp threads\n' "$i"
+	echo -n "1 $i; " >> scalabilite_bench422.dat
+	OMP_NUM_THREADS=$i ~/time -p ./build/bin/miniqmc -g "4 2 2" |& grep -E "real [0-9][0-9]*\.[0-9][0-9]*" | sed "s/real //g" >> scalabilite_bench422.dat
+	echo ";" >> scalabilite_bench422.dat
+
+	for((k=2; k<i; k=k*2))
+	do
+		div=$(($i/$k))
+		printf 'running on %d mpi process and %d omp threads\n' "$k" "$div"
+		echo -n "$k $div; " >> scalabilite_bench422.dat
+		OMP_NUM_THREADS=$div ~/time -p mpirun -n $k ./build/bin/miniqmc -g "4 2 2"|& grep -E "real [0-9][0-9]*\.[0-9][0-9]*" | sed "s/real //g" >> scalabilite_bench422.dat
+		echo ";" >> scalabilite_bench422.dat
+
+	done
+	printf "\n"
+	if((i==max_core))
+	then
+		exit 0
+	fi
+done
+
+printf 'running on %d mpi process and 1 omp threads\n' "$max_core"
+echo -n "$max_core 1; " >> scalabilite_bench422.dat
+OMP_NUM_THREADS=1 ~/time -p mpirun -n $max_core ./build/bin/miniqmc -g "4 2 2"|& grep -E "real [0-9][0-9]*\.[0-9][0-9]*" | sed "s/real //g" >> scalabilite_bench422.dat
+echo ";" >> scalabilite_bench422.dat
+
+printf 'running on 1 mpi process and %d omp threads\n' "$max_core"
+echo -n "1 $max_core; " >> scalabilite_bench422.dat
+OMP_NUM_THREADS=$max_core ~/time -p ./build/bin/miniqmc -g "4 2 2"|& grep -E "real [0-9][0-9]*\.[0-9][0-9]*" | sed "s/real //g" >> scalabilite_bench422.dat
+echo ";" >> scalabilite_bench422.dat
+
+for((k=2; k<=max_core; k=k*2))
+do
+	div=$(($max_core/$k))
+	if((div == 1 && k!= max_core)); then break; fi
+	printf 'running on %d mpi process and %d omp threads\n' "$k" "$div"
+	echo -n "$k $div; " >> scalabilite_bench422.dat
+	OMP_NUM_THREADS=$div ~/time -p mpirun -n $k ./build/bin/miniqmc -g "4 2 2"|& grep -E "real [0-9][0-9]*\.[0-9][0-9]*" | sed "s/real //g" >> scalabilite_bench422.dat
+	echo ";" >> scalabilite_bench422.dat
+
+	printf 'running on %d mpi process and %d omp threads\n' "$div" "$k"
+	echo -n "$div $k; " >> scalabilite_bench422.dat
+	OMP_NUM_THREADS=$k ~/time -p mpirun -n $div ./build/bin/miniqmc -g "4 2 2"|& grep -E "real [0-9][0-9]*\.[0-9][0-9]*" | sed "s/real //g" >> scalabilite_bench422.dat
+	echo ";" >> scalabilite_bench422.dat
+done
+printf "\n"
diff --git a/notes_perf.md b/notes_perf.md
new file mode 100644
index 000000000..201496b5b
--- /dev/null
+++ b/notes_perf.md
@@ -0,0 +1,7 @@
+# Optimisation
+## ajout de flags de compilation
+```bash
+	cmake  -DCMAKE_BUILD_TYPE=None -DCMAKE_CXX_COMPILER=mpicxx CMAKE_CXX_FLAGS="-Ofast -march=native -finline-functions -funroll-loops -ftree-loop-vectorize -ftree-vectorize" ..  
+
+```
+Expliquer les flags
\ No newline at end of file
diff --git a/plot.png b/plot.png
new file mode 100644
index 000000000..da0d44a1d
Binary files /dev/null and b/plot.png differ
diff --git a/src/Numerics/Spline2/MultiBspline.hpp b/src/Numerics/Spline2/MultiBspline.hpp
index d687d2fad..25cc5f5cf 100644
--- a/src/Numerics/Spline2/MultiBspline.hpp
+++ b/src/Numerics/Spline2/MultiBspline.hpp
@@ -48,6 +48,7 @@ inline void evaluate_v(const typename bspline_traits<T, 3>::SplineType* restrict
   ASSUME_ALIGNED(vals);
   std::fill(vals, vals + num_splines, zero);
 
+
   for (size_t i = 0; i < 4; i++)
     for (size_t j = 0; j < 4; j++)
     {
@@ -55,10 +56,25 @@ inline void evaluate_v(const typename bspline_traits<T, 3>::SplineType* restrict
       const T* restrict coefs = spline_m->coefs + ((ix + i) * xs + (iy + j) * ys + iz * zs);
       ASSUME_ALIGNED(coefs);
       //#pragma omp simd
-      for (size_t n = 0; n < num_splines; n++)
+      /*for (size_t n = 0; n < num_splines; n++)
         vals[n] += pre00 *
             (c[0] * coefs[n] + c[1] * coefs[n + zs] + c[2] * coefs[n + 2 * zs] +
-             c[3] * coefs[n + 3 * zs]);
+             c[3] * coefs[n + 3 * zs]);*/
+      // déroulage de boucle par 4 element 
+
+      #pragma omp parallel for simd aligned(coefs:64)
+       for (size_t n = 0; n < num_splines-(num_splines%4); n+=4)
+        {
+          vals[n+0] += pre00 * (c[0] * coefs[n] + c[1] * coefs[n + zs] + c[2] * coefs[n + 2 * zs] + c[3] * coefs[n + 3 * zs]);
+          vals[n+1] += pre00 * (c[0] * coefs[n+1] + c[1] * coefs[(n+1) + zs] + c[2] * coefs[(n+1) + 2 * zs] + c[3] * coefs[(n+1) + 3 * zs]);
+          vals[n+2] += pre00 * (c[0] * coefs[n+2] + c[1] * coefs[(n+2) + zs] + c[2] * coefs[(n+2) + 2 * zs] + c[3] * coefs[(n+2) + 3 * zs]);
+          vals[n+3] += pre00 * (c[0] * coefs[n+3] + c[1] * coefs[(n+3) + zs] + c[2] * coefs[(n+3) + 2 * zs] + c[3] * coefs[(n+3) + 3 * zs]);
+        }
+      for (size_t n = num_splines-(num_splines%4); n< num_splines; n++)
+      {
+          vals[n] += pre00 * (c[0] * coefs[n] + c[1] * coefs[n + zs] + c[2] * coefs[n + 2 * zs] + c[3] * coefs[n + 3 * zs]);
+      }
+
     }
 }
 
@@ -121,7 +137,10 @@ evaluate_vgl(const typename bspline_traits<T, 3>::SplineType* restrict spline_m,
       ASSUME_ALIGNED(coefs3zs);
 
 #pragma noprefetch
-#pragma omp simd
+#pragma omp parallel 
+
+{
+    #pragma omp for simd
       for (int n = 0; n < num_splines; n++)
       {
         const T coefsv    = coefs[n];
@@ -150,7 +169,7 @@ evaluate_vgl(const typename bspline_traits<T, 3>::SplineType* restrict spline_m,
   const T dyInv2 = dyInv * dyInv;
   const T dzInv2 = dzInv * dzInv;
 
-#pragma omp simd
+#pragma omp for simd
   for (int n = 0; n < num_splines; n++)
   {
     gx[n] *= dxInv;
@@ -160,6 +179,7 @@ evaluate_vgl(const typename bspline_traits<T, 3>::SplineType* restrict spline_m,
   }
 }
 
+}
 template<typename T>
 inline void
 evaluate_vgh(const typename bspline_traits<T, 3>::SplineType* restrict spline_m, T x, T y, T z,
@@ -229,7 +249,8 @@ evaluate_vgh(const typename bspline_traits<T, 3>::SplineType* restrict spline_m,
       const T pre02 = a[i] * d2b[j];
 
       const int iSplitPoint = num_splines;
-#pragma omp simd
+
+#pragma omp parallel for simd
       for (int n = 0; n < iSplitPoint; n++)
       {
         T coefsv    = coefs[n];
@@ -264,7 +285,7 @@ evaluate_vgh(const typename bspline_traits<T, 3>::SplineType* restrict spline_m,
   const T dxz   = dxInv * dzInv;
   const T dyz   = dyInv * dzInv;
 
-#pragma omp simd
+#pragma omp parallel for simd
   for (int n = 0; n < num_splines; n++)
   {
     gx[n] *= dxInv;
diff --git a/src/Particle/Lattice/ParticleBConds.h b/src/Particle/Lattice/ParticleBConds.h
index 36961880e..57a21c22d 100644
--- a/src/Particle/Lattice/ParticleBConds.h
+++ b/src/Particle/Lattice/ParticleBConds.h
@@ -82,6 +82,8 @@ struct DTD_BConds
   {
     const int n = dr.size();
     const T cone(1);
+
+    #pragma omp simd
     for (int i = 0; i < n; ++i)
     {
       r[i]    = std::sqrt(apply_bc(dr[i]));
diff --git a/src/QMCWaveFunctions/Jastrow/TwoBodyJastrow.h b/src/QMCWaveFunctions/Jastrow/TwoBodyJastrow.h
index 17bd48e9e..03b426238 100644
--- a/src/QMCWaveFunctions/Jastrow/TwoBodyJastrow.h
+++ b/src/QMCWaveFunctions/Jastrow/TwoBodyJastrow.h
@@ -122,6 +122,7 @@ struct TwoBodyJastrow : public WaveFunctionComponent
   {
     valT curUat(0);
     const int igt = P.GroupID[iat] * NumGroups;
+    #pragma simd
     for (int jg = 0; jg < NumGroups; ++jg)
     {
       const FuncType& f2(*F[igt + jg]);
@@ -148,8 +149,9 @@ struct TwoBodyJastrow : public WaveFunctionComponent
     for (int idim = 0; idim < OHMMS_DIM; ++idim)
     {
       const valT* restrict dX = displ.data(idim);
-      valT s                  = valT();
+      valT s = valT();
 
+    #pragma omp simd reduction(+ : s)
       for (int jat = 0; jat < N; ++jat)
         s += du[jat] * dX[jat];
       grad[idim] = s;
@@ -263,6 +265,9 @@ inline void TwoBodyJastrow<FT>::computeU3(const ParticleSet& P,
   std::fill_n(d2u, jelmax, czero);
 
   const int igt = P.GroupID[iat] * NumGroups;
+
+  #pragma omp simd 
+
   for (int jg = 0; jg < NumGroups; ++jg)
   {
     const FuncType& f2(*F[igt + jg]);
@@ -319,6 +324,8 @@ void TwoBodyJastrow<FT>::acceptMove(ParticleSet& P, int iat)
   const auto& new_dr    = d_table->Temp_dr;
   const auto& old_dr    = d_table->Displacements[iat];
   constexpr valT lapfac = OHMMS_DIM - RealType(1);
+  
+  #pragma omp simd 
   for (int jat = 0; jat < N; jat++)
   {
     const valT du   = cur_u[jat] - old_u[jat];
@@ -337,6 +344,8 @@ void TwoBodyJastrow<FT>::acceptMove(ParticleSet& P, int iat)
     const valT* restrict old_du_pt = old_du.data();
     valT* restrict save_g          = dUat.data(idim);
     valT cur_g                     = cur_dUat[idim];
+
+    #pragma omp simd 
     for (int jat = 0; jat < N; jat++)
     {
       const valT newg = cur_du_pt[jat] * new_dX[jat];
@@ -376,6 +385,8 @@ void TwoBodyJastrow<FT>::recompute(ParticleSet& P)
       {
         const valT* restrict dX = displ.data(idim);
         valT s                  = valT();
+
+         #pragma omp simd reduction(+ : s)
         for (int jat = 0; jat < iat; ++jat)
           s += du[jat] * dX[jat];
         grad[idim] = s;
@@ -383,15 +394,20 @@ void TwoBodyJastrow<FT>::recompute(ParticleSet& P)
       dUat(iat)  = grad;
       d2Uat[iat] = -lap;
       // add the contribution from the upper triangle
+
+      #pragma omp simd 
       for (int jat = 0; jat < iat; jat++)
       {
         Uat[jat] += u[jat];
         d2Uat[jat] -= d2u[jat] + lapfac * du[jat];
       }
+
       for (int idim = 0; idim < OHMMS_DIM; ++idim)
       {
         valT* restrict save_g   = dUat.data(idim);
         const valT* restrict dX = displ.data(idim);
+
+        #pragma omp simd
         for (int jat = 0; jat < iat; jat++)
           save_g[jat] -= du[jat] * dX[jat];
       }
@@ -418,6 +434,8 @@ void TwoBodyJastrow<FT>::evaluateGL(ParticleSet& P,
   if (fromscratch)
     recompute(P);
   LogValue = valT(0);
+
+   #pragma omp simd reduction(+ : LogValue)
   for (int iat = 0; iat < N; ++iat)
   {
     LogValue += Uat[iat];