AMSS_NCKU_source/fdderivs_c.C

@@ -141,12 +141,26 @@ void fdderivs(const int ex[3],
     const int j4_hi = ex2 - 3;
     const int k4_hi = ex3 - 3;
 
+    /*
+     * Strategy A:
+     * Avoid redundant work in overlap of 2nd/4th-order regions.
+     * Only compute 2nd-order on shell points that are NOT overwritten by
+     * the 4th-order pass.
+     */
+    const int has4 = (i4_lo <= i4_hi && j4_lo <= j4_hi && k4_lo <= k4_hi);
+
     if (i2_lo <= i2_hi && j2_lo <= j2_hi && k2_lo <= k2_hi) {
         for (int k0 = k2_lo; k0 <= k2_hi; ++k0) {
             const int kF = k0 + 1;
             for (int j0 = j2_lo; j0 <= j2_hi; ++j0) {
                 const int jF = j0 + 1;
                 for (int i0 = i2_lo; i0 <= i2_hi; ++i0) {
+                    if (has4 &&
+                        i0 >= i4_lo && i0 <= i4_hi &&
+                        j0 >= j4_lo && j0 <= j4_hi &&
+                        k0 >= k4_lo && k0 <= k4_hi) {
+                        continue;
+                    }
                     const int iF = i0 + 1;
                     const size_t p = idx_ex(i0, j0, k0, ex);
 
@@ -193,7 +207,7 @@ void fdderivs(const int ex[3],
         }
     }
 
-    if (i4_lo <= i4_hi && j4_lo <= j4_hi && k4_lo <= k4_hi) {
+    if (has4) {
         for (int k0 = k4_lo; k0 <= k4_hi; ++k0) {
             const int kF = k0 + 1;
             for (int j0 = j4_lo; j0 <= j4_hi; ++j0) {