Merge pull request #1022 from su2code/feature_simd_numerics

Vectorized (SIMD) Numerical Schemes

Author: pcarruscag

Common/include/CConfig.hpp

@@ -43,8 +43,8 @@
 #include <map>
 #include <assert.h>
 
-#include "./option_structure.hpp"
-#include "./toolboxes/C2DContainer.hpp"
+#include "option_structure.hpp"
+#include "containers/container_decorators.hpp"
 
 #ifdef HAVE_CGNS
 #include "cgnslib.h"
@@ -419,6 +419,7 @@ class CConfig {
   su2double *RK_Alpha_Step;                 /*!< \brief Runge-Kutta beta coefficients. */
 
   unsigned short nQuasiNewtonSamples;  /*!< \brief Number of samples used in quasi-Newton solution methods. */
+  bool UseVectorization;       /*!< \brief Whether to use vectorized numerics schemes. */
 
   unsigned short nMGLevels;    /*!< \brief Number of multigrid levels (coarse levels). */
   unsigned short nCFL;         /*!< \brief Number of CFL, one for each multigrid level. */
@@ -591,10 +592,10 @@ class CConfig {
   *Kappa_AdjFlow,                  /*!< \brief Numerical dissipation coefficients for the adjoint flow equations. */
   *Kappa_Heat;                     /*!< \brief Numerical dissipation coefficients for the (fvm) heat equation. */
   su2double* FFD_Axis;          /*!< \brief Numerical dissipation coefficients for the adjoint equations. */
-  su2double Kappa_1st_AdjFlow,  /*!< \brief JST 1st order dissipation coefficient for adjoint flow equations (coarse multigrid levels). */
+  su2double Kappa_1st_AdjFlow,  /*!< \brief Lax 1st order dissipation coefficient for adjoint flow equations (coarse multigrid levels). */
   Kappa_2nd_AdjFlow,            /*!< \brief JST 2nd order dissipation coefficient for adjoint flow equations. */
   Kappa_4th_AdjFlow,            /*!< \brief JST 4th order dissipation coefficient for adjoint flow equations. */
-  Kappa_1st_Flow,           /*!< \brief JST 1st order dissipation coefficient for flow equations (coarse multigrid levels). */
+  Kappa_1st_Flow,           /*!< \brief Lax 1st order dissipation coefficient for flow equations (coarse multigrid levels). */
   Kappa_2nd_Flow,           /*!< \brief JST 2nd order dissipation coefficient for flow equations. */
   Kappa_4th_Flow,           /*!< \brief JST 4th order dissipation coefficient for flow equations. */
   Kappa_2nd_Heat,           /*!< \brief 2nd order dissipation coefficient for heat equation. */
@@ -1164,7 +1165,7 @@ class CConfig {
   ionization;                               /*!< \brief Flag for determining if free electron gas is in the mixture. */
   string GasModel,                          /*!< \brief Gas Model. */
   *Wall_Catalytic;                          /*!< \brief Pointer to catalytic walls. */
-  
+
   /*!
    * \brief Set the default values of config options not set in the config file using another config object.
    * \param config - Config object to use the default values from.
@@ -4114,6 +4115,11 @@ class CConfig {
    */
   unsigned short GetnQuasiNewtonSamples(void) const { return nQuasiNewtonSamples; }
 
+  /*!
+   * \brief Get whether to use vectorized numerics (if available).
+   */
+  bool GetUseVectorization(void) const { return UseVectorization; }
+
   /*!
    * \brief Get the relaxation coefficient of the linear solver for the implicit formulation.
    * \return relaxation coefficient of the linear solver for the implicit formulation.
@@ -4509,7 +4515,7 @@ class CConfig {
    *       during the computation.
    * \return Kind of center convective numerical scheme for the flow equations.
    */
-  unsigned short GetKind_Centered_Flow(void) const { return Kind_Centered_Flow; }
+  ENUM_CENTERED GetKind_Centered_Flow(void) const { return static_cast<ENUM_CENTERED>(Kind_Centered_Flow); }
 
   /*!
    * \brief Get the kind of center convective numerical scheme for the plasma equations.

Common/include/CMultiGridQueue.hpp

@@ -29,7 +29,7 @@
 #pragma once
 
 #include <vector>
-#include "toolboxes/CFastFindAndEraseQueue.hpp"
+#include "containers/CFastFindAndEraseQueue.hpp"
 #include "geometry/CGeometry.hpp"
 
 using namespace std;

Common/include/basic_types/ad_structure.hpp

@@ -353,8 +353,7 @@ namespace AD{
   /*--- Base case for parameter pack expansion. ---*/
   FORCEINLINE void SetPreaccIn() {}
 
-  template<class T, class... Ts,
-           typename std::enable_if<std::is_same<T,su2double>::value,bool>::type = 0>
+  template<class T, class... Ts, su2enable_if<std::is_same<T,su2double>::value> = 0>
   FORCEINLINE void SetPreaccIn(const T& data, Ts&&... moreData) {
     if (!PreaccActive) return;
     if (data.isActive())
@@ -385,6 +384,18 @@ namespace AD{
     }
   }
 
+  template<class T>
+  FORCEINLINE void SetPreaccIn(const T& data, const int size_x, const int size_y, const int size_z) {
+    if (!PreaccActive) return;
+    for (int i = 0; i < size_x; i++) {
+      for (int j = 0; j < size_y; j++) {
+        for (int k = 0; k < size_z; k++) {
+          if (data[i][j][k].isActive()) PreaccHelper.addInput(data[i][j][k]);
+        }
+      }
+    }
+  }
+
   FORCEINLINE void StartPreacc() {
     if (globalTape.isActive() && PreaccEnabled) {
       PreaccHelper.start();
@@ -395,8 +406,7 @@ namespace AD{
   /*--- Base case for parameter pack expansion. ---*/
   FORCEINLINE void SetPreaccOut() {}
 
-  template<class T, class... Ts,
-           typename std::enable_if<std::is_same<T,su2double>::value,bool>::type = 0>
+  template<class T, class... Ts, su2enable_if<std::is_same<T,su2double>::value> = 0>
   FORCEINLINE void SetPreaccOut(T& data, Ts&&... moreData) {
     if (!PreaccActive) return;
     if (data.isActive())

Common/include/basic_types/datatype_structure.hpp

@@ -40,6 +40,17 @@
 #define FORCEINLINE inline
 #endif
 
+#if defined(__GNUC__) || defined(__clang__) || defined(__INTEL_COMPILER)
+#define NEVERINLINE inline __attribute__((noinline))
+#else
+#define NEVERINLINE inline
+#endif
+
+/*--- Convenience SFINAE typedef to conditionally
+ * enable/disable function template overloads. ---*/
+template<bool condition>
+using su2enable_if = typename std::enable_if<condition,bool>::type;
+
 /*--- Depending on the datatype defined during the configuration,
  * include the correct definition, and create the main typedef. ---*/
 
@@ -194,10 +205,10 @@ namespace SU2_TYPE {
 
   /*--- Special handling of the sprintf routine for non-primitive types. ---*/
   /*--- Pass-through for built-in types. ---*/
-  template<class T, typename std::enable_if<std::is_trivial<T>::value,bool>::type = 0>
+  template<class T, su2enable_if<std::is_trivial<T>::value> = 0>
   FORCEINLINE const T& _printGetValue(const T& val) {return val;}
   /*--- Overload for expressions of active types. ---*/
-  template<class T, typename std::enable_if<!std::is_trivial<T>::value,bool>::type = 0>
+  template<class T, su2enable_if<!std::is_trivial<T>::value> = 0>
   FORCEINLINE passivedouble _printGetValue(const T& val) { return val.getValue(); }
 
   /*!