fix benchmarking on frontier

Author: Anand Radhakrishnan

src/simulation/m_riemann_solvers.fpp

@@ -3097,7 +3097,7 @@ contains
                     #:endcall GPU_PARALLEL_LOOP
                 else
                     ! 5-EQUATION MODEL WITH HLLC
-                    #:call GPU_PARALLEL_LOOP(collapse=3, private='[T_L, T_R, idx1, idxi, vel_L_rms, vel_R_rms, pres_L, pres_R, rho_L, gamma_L, pi_inf_L, qv_L, rho_R, gamma_R, pi_inf_R, qv_R, alpha_L_sum, alpha_R_sum, E_L, E_R, MW_L, MW_R, R_gas_L, R_gas_R, Cp_L, Cp_R, Cv_L, Cv_R, Gamm_L, Gamm_R, Y_L, Y_R, H_L, H_R, rho_avg, gamma_avg, H_avg, c_L, c_R, c_avg, s_P, s_M, xi_P, xi_M, xi_L, xi_R, Ms_L, Ms_R, pres_SL, pres_SR, vel_L, vel_R, Re_L, Re_R, alpha_L, alpha_R, s_L, s_R, s_S, vel_avg_rms, pcorr, zcoef, vel_L_tmp, vel_R_tmp, Ys_L, Ys_R, Xs_L, Xs_R, Gamma_iL, Gamma_iR, Cp_iL, Cp_iR, tau_e_L, tau_e_R, xi_field_L, xi_field_R, Yi_avg,Phi_avg, h_iL, h_iR, h_avg_2, G_L, G_R]', copyin='[is1, is2, is3]')
+                    #:call GPU_PARALLEL_LOOP(collapse=3, private='[i,q, T_L, T_R, idx1, idxi, vel_L_rms, vel_R_rms, pres_L, pres_R, rho_L, gamma_L, pi_inf_L, qv_L, rho_R, gamma_R, pi_inf_R, qv_R, alpha_L_sum, alpha_R_sum, E_L, E_R, MW_L, MW_R, R_gas_L, R_gas_R, Cp_L, Cp_R, Cv_L, Cv_R, Gamm_L, Gamm_R, Y_L, Y_R, H_L, H_R, rho_avg, gamma_avg, H_avg, c_L, c_R, c_avg, s_P, s_M, xi_P, xi_M, xi_L, xi_R, Ms_L, Ms_R, pres_SL, pres_SR, vel_L, vel_R, Re_L, Re_R, alpha_L, alpha_R, s_L, s_R, s_S, vel_avg_rms, pcorr, zcoef, vel_L_tmp, vel_R_tmp, Ys_L, Ys_R, Xs_L, Xs_R, Gamma_iL, Gamma_iR, Cp_iL, Cp_iR, tau_e_L, tau_e_R, xi_field_L, xi_field_R, Yi_avg,Phi_avg, h_iL, h_iR, h_avg_2, G_L, G_R]', copyin='[is1, is2, is3]')
                         do l = is3%beg, is3%end
                             do k = is2%beg, is2%end
                                 do j = is1%beg, is1%end