diff --git a/Carpet/src/Comm.cc b/Carpet/src/Comm.cc
index 375b1be33..8ec6d6f09 100644
--- a/Carpet/src/Comm.cc
+++ b/Carpet/src/Comm.cc
@@ -242,12 +242,10 @@ static void ProlongateGroupBoundaries(const cGH *cctkGH,
     for (astate state = static_cast<astate>(0); state != state_done;
          state = static_cast<astate>(static_cast<int>(state) + 1)) {
       ostringstream name1;
-      name1 << "comm_state[" << timers.size() << "]"
-            << "." << tostring(state) << ".user";
+      name1 << "comm_state[" << timers.size() << "].user." << tostring(state);
       timers.push_back(new Timers::Timer(name1.str()));
       ostringstream name2;
-      name2 << "comm_state[" << timers.size() << "]"
-            << "." << tostring(state) << ".step";
+      name2 << "comm_state[" << timers.size() << "].step." << tostring(state);
       timers.push_back(new Timers::Timer(name2.str()));
     }
   }
diff --git a/CarpetLib/src/copy_3d.cc b/CarpetLib/src/copy_3d.cc
index 386b86781..cb1b4348a 100644
--- a/CarpetLib/src/copy_3d.cc
+++ b/CarpetLib/src/copy_3d.cc
@@ -116,12 +116,11 @@ void copy_3d(T const *restrict const src, ivect3 const &restrict srcpadext,
   ptrdiff_t const dstkoff = dstoff[2];
 
   // Loop over region
-  if (use_openmp) {
+  if (false and use_openmp) {
 #pragma omp parallel for collapse(3)
     for (int k = 0; k < regkext; ++k) {
       for (int j = 0; j < regjext; ++j) {
         for (int i = 0; i < regiext; ++i) {
-
           dst[DSTIND3(i, j, k)] = src[SRCIND3(i, j, k)];
         }
       }
@@ -129,8 +128,8 @@ void copy_3d(T const *restrict const src, ivect3 const &restrict srcpadext,
   } else {
     for (int k = 0; k < regkext; ++k) {
       for (int j = 0; j < regjext; ++j) {
+#pragma omp simd
         for (int i = 0; i < regiext; ++i) {
-
           dst[DSTIND3(i, j, k)] = src[SRCIND3(i, j, k)];
         }
       }
diff --git a/CarpetLib/src/copy_4d.cc b/CarpetLib/src/copy_4d.cc
index 382541e4f..84696dc0c 100644
--- a/CarpetLib/src/copy_4d.cc
+++ b/CarpetLib/src/copy_4d.cc
@@ -101,13 +101,12 @@ void copy_4d(T const *restrict const src, ivect4 const &restrict srcpadext,
   ptrdiff_t const dstloff = dstoff[3];
 
   // Loop over region
-  if (use_openmp) {
+  if (false and use_openmp) {
 #pragma omp parallel for collapse(4)
     for (int l = 0; l < reglext; ++l) {
       for (int k = 0; k < regkext; ++k) {
         for (int j = 0; j < regjext; ++j) {
           for (int i = 0; i < regiext; ++i) {
-
             dst[DSTIND4(i, j, k, l)] = src[SRCIND4(i, j, k, l)];
           }
         }
@@ -117,8 +116,8 @@ void copy_4d(T const *restrict const src, ivect4 const &restrict srcpadext,
     for (int l = 0; l < reglext; ++l) {
       for (int k = 0; k < regkext; ++k) {
         for (int j = 0; j < regjext; ++j) {
+#pragma omp simd
           for (int i = 0; i < regiext; ++i) {
-
             dst[DSTIND4(i, j, k, l)] = src[SRCIND4(i, j, k, l)];
           }
         }
diff --git a/CarpetLib/src/interpolate_3d_2tl.cc b/CarpetLib/src/interpolate_3d_2tl.cc
index 751e0062e..d51ee421a 100644
--- a/CarpetLib/src/interpolate_3d_2tl.cc
+++ b/CarpetLib/src/interpolate_3d_2tl.cc
@@ -104,11 +104,10 @@ void interpolate_3d_2tl(T const *restrict const src1, CCTK_REAL const t1,
   RT const s1fac = (t - t2) / (t1 - t2);
   RT const s2fac = (t - t1) / (t2 - t1);
 
-// Loop over region
-#pragma omp parallel
+  // Loop over region
+  // #pragma omp parallel
   CCTK_LOOP3(interpolate_3d_2tl, i, j, k, 0, 0, 0, regiext, regjext, regkext,
              dstipadext, dstjpadext, dstkpadext) {
-
     dst[DSTIND3(i, j, k)] =
         +s1fac * src1[SRCIND3(i, j, k)] + s2fac * src2[SRCIND3(i, j, k)];
   }
diff --git a/CarpetLib/src/interpolate_3d_3tl.cc b/CarpetLib/src/interpolate_3d_3tl.cc
index 5bda88448..74fb33cab 100644
--- a/CarpetLib/src/interpolate_3d_3tl.cc
+++ b/CarpetLib/src/interpolate_3d_3tl.cc
@@ -107,11 +107,10 @@ void interpolate_3d_3tl(T const *restrict const src1, CCTK_REAL const t1,
   RT const s2fac = (t - t1) * (t - t3) / ((t2 - t1) * (t2 - t3));
   RT const s3fac = (t - t1) * (t - t2) / ((t3 - t1) * (t3 - t2));
 
-// Loop over region
-#pragma omp parallel
+  // Loop over region
+  // #pragma omp parallel
   CCTK_LOOP3(interpolate_3d_3tl, i, j, k, 0, 0, 0, regiext, regjext, regkext,
              dstipadext, dstjpadext, dstkpadext) {
-
     dst[DSTIND3(i, j, k)] = +s1fac * src1[SRCIND3(i, j, k)] +
                             s2fac * src2[SRCIND3(i, j, k)] +
                             s3fac * src3[SRCIND3(i, j, k)];
diff --git a/CarpetLib/src/interpolate_3d_4tl.cc b/CarpetLib/src/interpolate_3d_4tl.cc
index 69f02e464..fa4517067 100644
--- a/CarpetLib/src/interpolate_3d_4tl.cc
+++ b/CarpetLib/src/interpolate_3d_4tl.cc
@@ -115,11 +115,10 @@ void interpolate_3d_4tl(T const *restrict const src1, CCTK_REAL const t1,
   RT const s4fac =
       (t - t1) * (t - t2) * (t - t3) / ((t4 - t1) * (t4 - t2) * (t4 - t3));
 
-// Loop over region
-#pragma omp parallel
+  // Loop over region
+  // #pragma omp parallel
   CCTK_LOOP3(interpolate_3d_4tl, i, j, k, 0, 0, 0, regiext, regjext, regkext,
              dstipadext, dstjpadext, dstkpadext) {
-
     dst[DSTIND3(i, j, k)] =
         +s1fac * src1[SRCIND3(i, j, k)] + s2fac * src2[SRCIND3(i, j, k)] +
         s3fac * src3[SRCIND3(i, j, k)] + s4fac * src4[SRCIND3(i, j, k)];
diff --git a/CarpetLib/src/interpolate_3d_5tl.cc b/CarpetLib/src/interpolate_3d_5tl.cc
index b999e72e5..f2fc4ae3b 100644
--- a/CarpetLib/src/interpolate_3d_5tl.cc
+++ b/CarpetLib/src/interpolate_3d_5tl.cc
@@ -120,11 +120,10 @@ void interpolate_3d_5tl(T const *restrict const src1, CCTK_REAL const t1,
   RT const s5fac = (t - t1) * (t - t2) * (t - t3) * (t - t4) /
                    ((t5 - t1) * (t5 - t2) * (t5 - t3) * (t5 - t4));
 
-// Loop over region
-#pragma omp parallel
+  // Loop over region
+  // #pragma omp parallel
   CCTK_LOOP3(interpolate_3d_5tl, i, j, k, 0, 0, 0, regiext, regjext, regkext,
              dstipadext, dstjpadext, dstkpadext) {
-
     dst[DSTIND3(i, j, k)] =
         +s1fac * src1[SRCIND3(i, j, k)] + s2fac * src2[SRCIND3(i, j, k)] +
         s3fac * src3[SRCIND3(i, j, k)] + s4fac * src4[SRCIND3(i, j, k)] +
diff --git a/CarpetLib/src/interpolate_eno_3d_3tl.cc b/CarpetLib/src/interpolate_eno_3d_3tl.cc
index cdb8f6204..d9a676b66 100644
--- a/CarpetLib/src/interpolate_eno_3d_3tl.cc
+++ b/CarpetLib/src/interpolate_eno_3d_3tl.cc
@@ -129,15 +129,14 @@ void interpolate_eno_3d_3tl(
   bool const use_12 = t >= min(t1, t2) - eps and t <= max(t1, t2) + eps;
   bool const use_23 = t >= min(t2, t3) - eps and t <= max(t2, t3) + eps;
   assert(use_12 or use_23);
-// TODO: Instead of use_12, calculate 3 coefficents that perform
-// the desired 2-point interpolation, which would avoid the if
-// statement in the loop, simplifying the code.
+  // TODO: Instead of use_12, calculate 3 coefficents that perform
+  // the desired 2-point interpolation, which would avoid the if
+  // statement in the loop, simplifying the code.
 
-// Loop over region
-#pragma omp parallel
+  // Loop over region
+  // #pragma omp parallel
   CCTK_LOOP3(interpolate_end_3d_3tl, i, j, k, 0, 0, 0, regiext, regjext,
              regkext, srcipadext, srcjpadext, srckpadext) {
-
     T const s1 = src1[SRCIND3(i, j, k)];
     T const s2 = src2[SRCIND3(i, j, k)];
     T const s3 = src3[SRCIND3(i, j, k)];
diff --git a/CarpetLib/src/prolongate_3d_cc_eno_rf2.cc b/CarpetLib/src/prolongate_3d_cc_eno_rf2.cc
index e7f8c2cd1..765425f39 100644
--- a/CarpetLib/src/prolongate_3d_cc_eno_rf2.cc
+++ b/CarpetLib/src/prolongate_3d_cc_eno_rf2.cc
@@ -1289,8 +1289,8 @@ void prolongate_3d_cc_eno_rf2(
 
   } else { // use_loopcontrol_in_operators
 
-// Loop over fine region
-#pragma omp parallel
+    // Loop over fine region
+    // #pragma omp parallel
     CCTK_LOOP3(prolongate_3d_cc_eno_rf2, i, j, k, 0, 0, 0, regiext, regjext,
                regkext, dstipadext, dstjpadext, dstkpadext) {
       const ptrdiff_t is = (srcioff + i) / 2;
diff --git a/CarpetLib/src/prolongate_3d_dgfe_rf2.cc b/CarpetLib/src/prolongate_3d_dgfe_rf2.cc
index e3eea4558..dbb522bdd 100644
--- a/CarpetLib/src/prolongate_3d_dgfe_rf2.cc
+++ b/CarpetLib/src/prolongate_3d_dgfe_rf2.cc
@@ -135,7 +135,7 @@ void prolongate_3d_dgfe_rf2(
 
     // Loop over fine region
     ptrdiff_t const i = 0;
-#pragma omp parallel for collapse(2)
+    // #pragma omp parallel for collapse(2)
     // Zwicky's Intel compiler 11.1 ices on ptrdiff_t
     for (/*ptrdiff_t*/ int k = 0; k < regkext; k += 2 * (ORDER + 1)) {
       for (/*ptrdiff_t*/ int j = 0; j < regjext; j += 2 * (ORDER + 1)) {
@@ -171,7 +171,7 @@ void prolongate_3d_dgfe_rf2(
 
     // Loop over fine region
     ptrdiff_t const j = 0;
-#pragma omp parallel for collapse(2)
+    // #pragma omp parallel for collapse(2)
     // Zwicky's Intel compiler 11.1 ices on ptrdiff_t
     for (/*ptrdiff_t*/ int k = 0; k < regkext; k += 2 * (ORDER + 1)) {
       for (/*ptrdiff_t*/ int i = 0; i < regiext; i += 2 * (ORDER + 1)) {
@@ -207,7 +207,7 @@ void prolongate_3d_dgfe_rf2(
 
     // Loop over fine region
     ptrdiff_t const k = 0;
-#pragma omp parallel for collapse(2)
+    // #pragma omp parallel for collapse(2)
     // Zwicky's Intel compiler 11.1 ices on ptrdiff_t
     for (/*ptrdiff_t*/ int j = 0; j < regjext; j += 2 * (ORDER + 1)) {
       for (/*ptrdiff_t*/ int i = 0; i < regiext; i += 2 * (ORDER + 1)) {
@@ -239,8 +239,8 @@ void prolongate_3d_dgfe_rf2(
     int const srcstr[3] = {srcdi, srcdj, srcdk};
     int const dststr[3] = {dstdi, dstdj, dstdk};
 
-// Loop over fine region
-#pragma omp parallel for collapse(3)
+    // Loop over fine region
+    // #pragma omp parallel for collapse(3)
     // Zwicky's Intel compiler 11.1 ices on ptrdiff_t
     for (/*ptrdiff_t*/ int k = 0; k < regkext; k += 2 * (ORDER + 1)) {
       for (/*ptrdiff_t*/ int j = 0; j < regjext; j += 2 * (ORDER + 1)) {
diff --git a/CarpetLib/src/restrict_3d_cc_o3_rf2.cc b/CarpetLib/src/restrict_3d_cc_o3_rf2.cc
index 06a59e0d6..7b5434ceb 100644
--- a/CarpetLib/src/restrict_3d_cc_o3_rf2.cc
+++ b/CarpetLib/src/restrict_3d_cc_o3_rf2.cc
@@ -118,8 +118,8 @@ void restrict_3d_cc_o3_rf2(
 
   if (not use_loopcontrol_in_operators) {
 
-// Loop over coarse region
-#pragma omp parallel for collapse(3)
+    // Loop over coarse region
+    // #pragma omp parallel for collapse(3)
     for (int k = 0; k < regkext; ++k) {
       for (int j = 0; j < regjext; ++j) {
         for (int i = 0; i < regiext; ++i) {
@@ -215,8 +215,8 @@ void restrict_3d_cc_o3_rf2(
 
   } else {
 
-// Loop over coarse region
-#pragma omp parallel
+    // Loop over coarse region
+    // #pragma omp parallel
     CCTK_LOOP3(restrict_3d_cc_o3_rf2, i, j, k, 0, 0, 0, regiext, regjext,
                regkext, dstipadext, dstjpadext, dstkpadext) {
 
diff --git a/CarpetLib/src/restrict_3d_cc_o5_rf2.cc b/CarpetLib/src/restrict_3d_cc_o5_rf2.cc
index ebe339403..5c1a49122 100644
--- a/CarpetLib/src/restrict_3d_cc_o5_rf2.cc
+++ b/CarpetLib/src/restrict_3d_cc_o5_rf2.cc
@@ -167,8 +167,8 @@ void restrict_3d_cc_o5_rf2(
 
   if (not use_loopcontrol_in_operators) {
 
-// Loop over coarse region
-#pragma omp parallel for collapse(3)
+    // Loop over coarse region
+    // #pragma omp parallel for collapse(3)
     for (int k = 0; k < regkext; ++k) {
       for (int j = 0; j < regjext; ++j) {
         for (int i = 0; i < regiext; ++i) {
@@ -201,8 +201,8 @@ void restrict_3d_cc_o5_rf2(
 
   } else {
 
-// Loop over coarse region
-#pragma omp parallel
+    // Loop over coarse region
+    // #pragma omp parallel
     CCTK_LOOP3(restrict_3d_cc_o5_rf2, i, j, k, 0, 0, 0, regiext, regjext,
                regkext, dstipadext, dstjpadext, dstkpadext) {
 
diff --git a/CarpetLib/src/restrict_3d_cc_rf2.cc b/CarpetLib/src/restrict_3d_cc_rf2.cc
index 4897260b0..39fd7f142 100644
--- a/CarpetLib/src/restrict_3d_cc_rf2.cc
+++ b/CarpetLib/src/restrict_3d_cc_rf2.cc
@@ -108,8 +108,8 @@ void restrict_3d_cc_rf2(T const *restrict const src,
 
   if (not use_loopcontrol_in_operators) {
 
-// Loop over coarse region
-#pragma omp parallel for collapse(3)
+    // Loop over coarse region
+    // #pragma omp parallel for collapse(3)
     for (int k = 0; k < regkext; ++k) {
       for (int j = 0; j < regjext; ++j) {
         for (int i = 0; i < regiext; ++i) {
@@ -131,8 +131,8 @@ void restrict_3d_cc_rf2(T const *restrict const src,
 
   } else {
 
-// Loop over coarse region
-#pragma omp parallel
+    // Loop over coarse region
+    // #pragma omp parallel
     CCTK_LOOP3(restrict_3d_cc_rf2, i, j, k, 0, 0, 0, regiext, regjext, regkext,
                dstipadext, dstjpadext, dstkpadext) {
 
diff --git a/CarpetLib/src/restrict_3d_dgfe_rf2.cc b/CarpetLib/src/restrict_3d_dgfe_rf2.cc
index 01d59b383..d79ce86f6 100644
--- a/CarpetLib/src/restrict_3d_dgfe_rf2.cc
+++ b/CarpetLib/src/restrict_3d_dgfe_rf2.cc
@@ -118,8 +118,8 @@ void restrict_3d_dgfe_rf2(
   // Ensure we traverse an integer number of elements
   assert(all(regext % (ORDER + 1) == 0));
 
-// Loop over coarse region
-#pragma omp parallel for collapse(3)
+  // Loop over coarse region
+  // #pragma omp parallel for collapse(3)
   // Zwicky's Intel compiler 11.1 ices on ptrdiff_t
   for (/*ptrdiff_t*/ int k = 0; k < regkext; k += ORDER + 1) {
     for (/*ptrdiff_t*/ int j = 0; j < regjext; j += ORDER + 1) {
diff --git a/CarpetLib/src/restrict_3d_rf2.cc b/CarpetLib/src/restrict_3d_rf2.cc
index d508b1cf2..c6bcd22f8 100644
--- a/CarpetLib/src/restrict_3d_rf2.cc
+++ b/CarpetLib/src/restrict_3d_rf2.cc
@@ -110,8 +110,8 @@ void restrict_3d_rf2(T const *restrict const src,
 
   } else {
 
-// Loop over coarse region
-#pragma omp parallel
+    // Loop over coarse region
+    // #pragma omp parallel
     CCTK_LOOP3(restrict_3d_rf2, i, j, k, 0, 0, 0, regiext, regjext, regkext,
                dstipadext, dstjpadext, dstkpadext) {
 
diff --git a/CarpetLib/src/restrict_3d_stagger011.cc b/CarpetLib/src/restrict_3d_stagger011.cc
index 510d3d0ab..5de8a3188 100644
--- a/CarpetLib/src/restrict_3d_stagger011.cc
+++ b/CarpetLib/src/restrict_3d_stagger011.cc
@@ -146,8 +146,8 @@ void restrict_3d_stagger011(
 
   } else {
 
-// Loop over coarse region
-#pragma omp parallel
+    // Loop over coarse region
+    // #pragma omp parallel
     CCTK_LOOP3(restrict_3d_stagger011, i, j, k, 0, 0, 0, regiext, regjext,
                regkext, dstipadext, dstjpadext, dstkpadext) {
 
diff --git a/CarpetLib/src/restrict_3d_stagger101.cc b/CarpetLib/src/restrict_3d_stagger101.cc
index 97aaa3b68..b02f95b9f 100644
--- a/CarpetLib/src/restrict_3d_stagger101.cc
+++ b/CarpetLib/src/restrict_3d_stagger101.cc
@@ -146,8 +146,8 @@ void restrict_3d_stagger101(
 
   } else {
 
-// Loop over coarse region
-#pragma omp parallel
+    // Loop over coarse region
+    // #pragma omp parallel
     CCTK_LOOP3(restrict_3d_stagger101, i, j, k, 0, 0, 0, regiext, regjext,
                regkext, dstipadext, dstjpadext, dstkpadext) {
 
diff --git a/CarpetLib/src/restrict_3d_stagger110.cc b/CarpetLib/src/restrict_3d_stagger110.cc
index 1912e4295..3ae4f9385 100644
--- a/CarpetLib/src/restrict_3d_stagger110.cc
+++ b/CarpetLib/src/restrict_3d_stagger110.cc
@@ -145,8 +145,8 @@ void restrict_3d_stagger110(
 
   } else {
 
-// Loop over coarse region
-#pragma omp parallel
+    // Loop over coarse region
+    // #pragma omp parallel
     CCTK_LOOP3(restrict_3d_stagger110, i, j, k, 0, 0, 0, regiext, regjext,
                regkext, dstipadext, dstjpadext, dstkpadext) {
       dst[DSTIND3(i, j, k)] = typeprops<T>::fromreal(0);
diff --git a/CarpetLib/src/restrict_3d_stagger111.cc b/CarpetLib/src/restrict_3d_stagger111.cc
index 081e6c74f..af2075082 100644
--- a/CarpetLib/src/restrict_3d_stagger111.cc
+++ b/CarpetLib/src/restrict_3d_stagger111.cc
@@ -137,8 +137,8 @@ void restrict_3d_stagger111(
 
   } else {
 
-// Loop over coarse region
-#pragma omp parallel
+    // Loop over coarse region
+    // #pragma omp parallel
     CCTK_LOOP3(restrict_3d_stagger111, i, j, k, 0, 0, 0, regiext, regjext,
                regkext, dstipadext, dstjpadext, dstkpadext) {
       dst[DSTIND3(i, j, k)] = typeprops<T>::fromreal(0);
diff --git a/CarpetLib/src/restrict_3d_vc_rf2.cc b/CarpetLib/src/restrict_3d_vc_rf2.cc
index a8b80dd4c..fa371ca02 100644
--- a/CarpetLib/src/restrict_3d_vc_rf2.cc
+++ b/CarpetLib/src/restrict_3d_vc_rf2.cc
@@ -211,8 +211,8 @@ void restrict_3d_vc_rf2(T const *restrict const src,
 
   if (not use_loopcontrol_in_operators) {
 
-// Loop over coarse region
-#pragma omp parallel for collapse(3)
+    // Loop over coarse region
+    // #pragma omp parallel for collapse(3)
     for (int k = 0; k < regkext; ++k) {
       for (int j = 0; j < regjext; ++j) {
         for (int i = 0; i < regiext; ++i) {
@@ -240,8 +240,8 @@ void restrict_3d_vc_rf2(T const *restrict const src,
 
   } else {
 
-// Loop over coarse region
-#pragma omp parallel
+    // Loop over coarse region
+    // #pragma omp parallel
     CCTK_LOOP3(restrict_3d_vc_rf2, i, j, k, 0, 0, 0, regiext, regjext, regkext,
                dstipadext, dstjpadext, dstkpadext) {
 #ifdef CARPET_DEBUG
diff --git a/CarpetLib/src/restrict_4d_rf2.cc b/CarpetLib/src/restrict_4d_rf2.cc
index 74b256fae..0f8ab6878 100644
--- a/CarpetLib/src/restrict_4d_rf2.cc
+++ b/CarpetLib/src/restrict_4d_rf2.cc
@@ -101,13 +101,13 @@ void restrict_4d_rf2(T const *restrict const src,
   ptrdiff_t const dstkoff = dstoff[2];
   ptrdiff_t const dstloff = dstoff[3];
 
-// Loop over coarse region
-#pragma omp parallel for collapse(4)
+  // Loop over coarse region
+  // #pragma omp parallel for collapse(4)
   for (int l = 0; l < reglext; ++l) {
     for (int k = 0; k < regkext; ++k) {
       for (int j = 0; j < regjext; ++j) {
+#pragma omp simd
         for (int i = 0; i < regiext; ++i) {
-
           dst[DSTIND4(i, j, k, l)] = src[SRCIND4(2 * i, 2 * j, 2 * k, 2 * l)];
         }
       }