diff --git a/components/homme/src/share/cxx/HybridVCoord.hpp b/components/homme/src/share/cxx/HybridVCoord.hpp
index b96237acc04c..7b3712640c4d 100644
--- a/components/homme/src/share/cxx/HybridVCoord.hpp
+++ b/components/homme/src/share/cxx/HybridVCoord.hpp
@@ -107,11 +107,11 @@ class HybridVCoord
 
       auto dp_ij = Homme::subview(dp,igp,jgp);
 
-      ColumnOps::column_reduction<NUM_PHYSICAL_LEV>(kv,dp_ij,ps(igp,jgp));
-      kv.team_barrier();
+      Real ps_val = 0;
+      ColumnOps::column_reduction<NUM_PHYSICAL_LEV>(kv,dp_ij,ps_val);
 
       Kokkos::single(Kokkos::PerThread(kv.team),[&](){
-        ps(igp,jgp) += hybrid_ai0*ps0;
+        ps(igp,jgp) = ps_val + hybrid_ai0*ps0;
       });
     });
     kv.team_barrier();
diff --git a/components/homme/src/theta-l_kokkos/cxx/CaarFunctorImpl.hpp b/components/homme/src/theta-l_kokkos/cxx/CaarFunctorImpl.hpp
index 38f9dc8573d8..fbb97a25b94e 100644
--- a/components/homme/src/theta-l_kokkos/cxx/CaarFunctorImpl.hpp
+++ b/components/homme/src/theta-l_kokkos/cxx/CaarFunctorImpl.hpp
@@ -343,8 +343,6 @@ struct CaarFunctorImpl {
 
     set_rk_stage_data(data);
 
-    profiling_resume();
-
     GPTLstart("caar compute");
     int nerr;
     Kokkos::parallel_reduce("caar loop pre-boundary exchange", m_policy_pre, *this, nerr);
@@ -367,7 +365,6 @@ struct CaarFunctorImpl {
 
     limiter.run(data.np1);
 
-    profiling_pause();
   }
 
   KOKKOS_INLINE_FUNCTION
@@ -550,20 +547,14 @@ struct CaarFunctorImpl {
       Kokkos::single(Kokkos::PerThread(kv.team),[&]() {
         pi_i(0)[0] = m_hvcoord.ps0*m_hvcoord.hybrid_ai0;
       });
-      kv.team_barrier();
 
       ColumnOps::column_scan_mid_to_int<true>(kv,dp,pi_i);
 
       ColumnOps::compute_midpoint_values(kv,pi_i,pi);
 
-      // Barrier so that the buffer shared by pi_i and omega_i is free for
-      // omega_i to use.
-      kv.team_barrier();
-
       Kokkos::single(Kokkos::PerThread(kv.team),[&]() {
         omega_i(0)[0] = 0.0;
       });
-      kv.team_barrier();
 
       ColumnOps::column_scan_mid_to_int<true>(kv,div_vdp,omega_i);
       // Average omega_i to midpoints, and change sign, since later
@@ -1225,7 +1216,6 @@ struct CaarFunctorImpl {
         ColumnOps::compute_midpoint_values(kv,prod_x,mgrad_x);
         ColumnOps::compute_midpoint_values(kv,prod_y,mgrad_y);
       }
-      kv.team_barrier();
 
       // Apply pgrad_correction: mgrad += cp*T0*(grad(log(exner))-grad(exner)/exner) (if applicable)
       if (m_pgrad_correction) {
@@ -1244,7 +1234,6 @@ struct CaarFunctorImpl {
           mgrad_y(ilev) += cp*T0*(grad_tmp_i_y(ilev) - grad_exner_i_y(ilev)/exner_i(ilev));
         });
       }
-      kv.team_barrier();
 
       // Compute KE. Also, add fcor to vort
       auto u  = Homme::subview(m_state.m_v,kv.ie,m_data.n0,0,igp,jgp);
diff --git a/components/homme/src/theta-l_kokkos/cxx/LimiterFunctor.hpp b/components/homme/src/theta-l_kokkos/cxx/LimiterFunctor.hpp
index 7914c0a60e3a..f36966a4bca5 100644
--- a/components/homme/src/theta-l_kokkos/cxx/LimiterFunctor.hpp
+++ b/components/homme/src/theta-l_kokkos/cxx/LimiterFunctor.hpp
@@ -99,15 +99,11 @@ struct LimiterFunctor {
 
   void run (const int& tl)
   {
-    profiling_resume();
-
     GPTLstart("caar limiter");
     m_np1 = tl;
     Kokkos::parallel_for("caar loop dp3d limiter", m_policy_dp3d_lim, *this);
     Kokkos::fence();
     GPTLstop("caar limiter");
-
-    profiling_pause();
   }
 
   KOKKOS_INLINE_FUNCTION
@@ -130,8 +126,6 @@ struct LimiterFunctor {
         diff(ilev) = (dp(ilev) - m_dp3d_thresh*dp0(ilev))*spheremp;
       });
 
-      kv.team_barrier();
-
       Real min_diff = Kokkos::reduction_identity<Real>::min();
       auto diff_as_real = Homme::viewAsReal(diff);
       auto dp_as_real   = Homme::viewAsReal(dp);
@@ -168,8 +162,6 @@ struct LimiterFunctor {
           });
         }
 
-        kv.team_barrier();
-
         // This loop must be done over physical levels, unless we implement
         // masks, like it has been done in the E3SM/scream project
         Real mass_new = 0.0;
@@ -193,7 +185,7 @@ struct LimiterFunctor {
           dp(ilev) = diff(ilev)/spheremp + m_dp3d_thresh*dp0(ilev);
           vtheta_dp(ilev) *= dp(ilev);
         });
-      } //end of min_diff < 0
+      } // end of min_diff < 0
 
       Kokkos::parallel_for(Kokkos::ThreadVectorRange(kv.team,NUM_LEV),
                            [&](const int ilev) {