diff --git a/org/qmckl_ao.org b/org/qmckl_ao.org
index 258ce00..320364a 100644
--- a/org/qmckl_ao.org
+++ b/org/qmckl_ao.org
@@ -5795,7 +5795,7 @@ qmckl_compute_ao_value_hpc_gaussian (const qmckl_context context,
     }
 
 #ifdef HAVE_OPENMP
-#pragma omp for
+#pragma omp for schedule(guided) 
 #endif
     for (int64_t ipoint=0 ; ipoint < point_num ; ++ipoint) {
 
@@ -5948,7 +5948,6 @@ IVDEP
 #ifdef HAVE_OPENMP
 #pragma omp simd
 #endif
-IVDEP
               for (int il=0 ; il<3 ; ++il) {
                 ao_value_1[il] =  poly_vgl_1[il] * s1 * f[il];
               }
@@ -5957,7 +5956,6 @@ IVDEP
 #ifdef HAVE_OPENMP
 #pragma omp simd
 #endif
-IVDEP
               for (int il=0 ; il<6 ; ++il) {
                 ao_value_1[il] =  poly_vgl_1[il] * s1 * f[il];
               }
@@ -5966,7 +5964,6 @@ IVDEP
 #ifdef HAVE_OPENMP
 #pragma omp simd
 #endif
-IVDEP
               for (int il=0 ; il<n ; ++il) {
                 ao_value_1[il] =  poly_vgl_1[il] * s1 * f[il];
               }
@@ -6718,7 +6715,6 @@ qmckl_compute_ao_vgl_hpc_gaussian (
 #ifdef HAVE_OPENMP
 #pragma omp simd
 #endif
-IVDEP
           for (int j=0 ; j<8 ; ++j) {
             ce_mat[i][j] = 0.;
           }
@@ -6730,7 +6726,6 @@ IVDEP
 #ifdef HAVE_OPENMP
 #pragma omp simd
 #endif
-IVDEP
             for (int j=0 ; j<8 ; ++j) {
               ce_mat[i][j] = ce_mat[i][j] + v[l] * exp_mat[k][j];
             }
@@ -6819,7 +6814,6 @@ IVDEP
 #ifdef HAVE_OPENMP
 #pragma omp simd
 #endif
-IVDEP
               for (int il=0 ; il<3 ; ++il) {
                 ao_vgl_1[il] =  poly_vgl_1[il] * s1 * f[il];
                 ao_vgl_2[il] = (poly_vgl_2[il] * s1 + poly_vgl_1[il] * s2) * f[il];
@@ -6835,7 +6829,6 @@ IVDEP
 #ifdef HAVE_OPENMP
 #pragma omp simd
 #endif
-IVDEP
               for (int il=0 ; il<6 ; ++il) {
                 ao_vgl_1[il] =  poly_vgl_1[il] * s1 * f[il];
                 ao_vgl_2[il] = (poly_vgl_2[il] * s1 + poly_vgl_1[il] * s2) * f[il];
@@ -6851,7 +6844,6 @@ IVDEP
 #ifdef HAVE_OPENMP
 #pragma omp simd
 #endif
-IVDEP
               for (int il=0 ; il<n ; ++il) {
                 ao_vgl_1[il] =  poly_vgl_1[il] * s1 * f[il];
                 ao_vgl_2[il] = (poly_vgl_2[il] * s1 + poly_vgl_1[il] * s2) * f[il];
diff --git a/org/qmckl_mo.org b/org/qmckl_mo.org
index efb2179..fafef30 100644
--- a/org/qmckl_mo.org
+++ b/org/qmckl_mo.org
@@ -1304,7 +1304,6 @@ qmckl_compute_mo_basis_mo_value_hpc_sp (const qmckl_context context,
 #ifdef HAVE_OPENMP
 #pragma omp simd
 #endif
-  IVDEP
     for (int64_t i=0 ; i<mo_num*ao_num ; ++i) {
       coefficient_t_sp[i] = (float) coefficient_t[i];
     }
@@ -1361,7 +1360,6 @@ qmckl_compute_mo_basis_mo_value_hpc_sp (const qmckl_context context,
 #ifdef HAVE_OPENMP
 #pragma omp simd
 #endif
-        IVDEP
           for (int64_t i=0 ; i<mo_num ; ++i) {
             vgl_sp[i] = vgl_sp[i] +
                          ck1[i] * a11 + ck2[i] * a21 + ck3[i] * a31 + ck4[i] * a41 +
@@ -1376,7 +1374,6 @@ qmckl_compute_mo_basis_mo_value_hpc_sp (const qmckl_context context,
 #ifdef HAVE_OPENMP
 #pragma omp simd
 #endif
-        IVDEP
           for (int64_t i=0 ; i<mo_num ; ++i) {
             vgl_sp[i] = vgl_sp[i] + ck[i] * a1;
           }
@@ -1385,7 +1382,6 @@ qmckl_compute_mo_basis_mo_value_hpc_sp (const qmckl_context context,
 #ifdef HAVE_OPENMP
 #pragma omp simd
 #endif
-      IVDEP
       for (int64_t i=0 ; i<mo_num ; ++i) {
         vgl1[i] = (double) vgl_sp[i];
       }
@@ -1485,7 +1481,6 @@ qmckl_compute_mo_basis_mo_value_hpc (const qmckl_context context,
 #ifdef HAVE_OPENMP
 #pragma omp simd
 #endif
-        IVDEP
           for (int64_t i=0 ; i<mo_num ; ++i) {
             vgl1[i] = vgl1[i] +
                        ck1[i] * a11 + ck2[i] * a21 + ck3[i] * a31 + ck4[i] * a41 +
@@ -1500,7 +1495,6 @@ qmckl_compute_mo_basis_mo_value_hpc (const qmckl_context context,
 #ifdef HAVE_OPENMP
 #pragma omp simd
 #endif
-        IVDEP
           for (int64_t i=0 ; i<mo_num ; ++i) {
             vgl1[i] = vgl1[i] + ck[i] * a1;
           }
@@ -2041,7 +2035,6 @@ qmckl_compute_mo_basis_mo_vgl_hpc (const qmckl_context context,
 #ifdef HAVE_OPENMP
 #pragma omp simd
 #endif
-IVDEP
       for (int64_t i=0 ; i<mo_num ; ++i) {
         vgl1[i] = vgl1[i] + ck1[i] * a11 + ck2[i] * a21 + ck3[i] * a31 + ck4[i] * a41;
         vgl2[i] = vgl2[i] + ck1[i] * a12 + ck2[i] * a22 + ck3[i] * a32 + ck4[i] * a42;
@@ -2062,7 +2055,6 @@ IVDEP
 #ifdef HAVE_OPENMP
   #pragma omp simd
 #endif
-IVDEP
       for (int64_t i=0 ; i<mo_num ; ++i) {
         vgl1[i] = vgl1[i] + ck[i] * a1;
         vgl2[i] = vgl2[i] + ck[i] * a2;
@@ -2123,7 +2115,6 @@ qmckl_compute_mo_basis_mo_vgl_hpc_sp (const qmckl_context context,
 #ifdef HAVE_OPENMP
 #pragma omp simd
 #endif
-  IVDEP
     for (int64_t i=0 ; i<mo_num*ao_num ; ++i) {
       coefficient_t_sp[i] = (float) coefficient_t[i];
     }
@@ -2222,7 +2213,6 @@ qmckl_compute_mo_basis_mo_vgl_hpc_sp (const qmckl_context context,
 #ifdef HAVE_OPENMP
 #pragma omp simd
 #endif
-        IVDEP
           for (int64_t i=0 ; i<mo_num ; ++i) {
             vgl_sp1[i] = vgl_sp1[i] + ck1[i] * a11 + ck2[i] * a21 + ck3[i] * a31 + ck4[i] * a41;
             vgl_sp2[i] = vgl_sp2[i] + ck1[i] * a12 + ck2[i] * a22 + ck3[i] * a32 + ck4[i] * a42;
@@ -2243,7 +2233,6 @@ qmckl_compute_mo_basis_mo_vgl_hpc_sp (const qmckl_context context,
 #ifdef HAVE_OPENMP
 #pragma omp simd
 #endif
-        IVDEP
           for (int64_t i=0 ; i<mo_num ; ++i) {
             vgl_sp1[i] = vgl_sp1[i] + ck[i] * a1;
             vgl_sp2[i] = vgl_sp2[i] + ck[i] * a2;
@@ -2255,7 +2244,6 @@ qmckl_compute_mo_basis_mo_vgl_hpc_sp (const qmckl_context context,
 #ifdef HAVE_OPENMP
 #pragma omp simd
 #endif
-      IVDEP
       for (int64_t i=0 ; i<mo_num ; ++i) {
         vgl1[i] = (double) vgl_sp1[i];
         vgl2[i] = (double) vgl_sp2[i];
@@ -2586,7 +2574,6 @@ qmckl_compute_mo_basis_mo_value_cusp_hpc (const qmckl_context context,
 #ifdef HAVE_OPENMP
 #pragma omp simd
 #endif
-IVDEP
       for (int64_t i=0 ; i<mo_num ; ++i) {
         vgl1[i] = vgl1[i] + ck1[i] * a11 + ck2[i] * a21 + ck3[i] * a31 + ck4[i] * a41;
       }
@@ -2599,7 +2586,6 @@ IVDEP
 #ifdef HAVE_OPENMP
 #pragma omp simd
 #endif
-IVDEP
       for (int64_t i=0 ; i<mo_num ; ++i) {
         vgl1[i] = vgl1[i] + ck[i] * a1;
       }
@@ -3011,7 +2997,6 @@ qmckl_compute_mo_basis_mo_vgl_cusp_hpc (const qmckl_context context,
 #ifdef HAVE_OPENMP
 #pragma omp simd
 #endif
-IVDEP
       for (int64_t i=0 ; i<mo_num ; ++i) {
         vgl1[i] = vgl1[i] + ck1[i] * a11 + ck2[i] * a21 + ck3[i] * a31 + ck4[i] * a41;
         vgl2[i] = vgl2[i] + ck1[i] * a12 + ck2[i] * a22 + ck3[i] * a32 + ck4[i] * a42;
@@ -3032,7 +3017,6 @@ IVDEP
 #ifdef HAVE_OPENMP
   #pragma omp simd
 #endif
-IVDEP
       for (int64_t i=0 ; i<mo_num ; ++i) {
         vgl1[i] = vgl1[i] + ck[i] * a1;
         vgl2[i] = vgl2[i] + ck[i] * a2;