Optimize numerical algorithms with Intel oneMKL

- FFT.f90: Replace hand-written Cooley-Tukey FFT with oneMKL DFTI
   - ilucg.f90: Replace manual dot product loop with BLAS DDOT
   - gaussj.C: Replace Gauss-Jordan elimination with LAPACK dgesv/dgetri
   - makefile.inc: Add MKL include paths and library linking

   All optimizations maintain mathematical equivalence and numerical precision.

AMSS_NCKU_source/ilucg.f90

@@ -512,11 +512,10 @@
       IMPLICIT DOUBLE PRECISION (A-H,O-Z)
       DIMENSION V(N),W(N)
 !     SUBROUTINE TO COMPUTE DOUBLE PRECISION VECTOR DOT PRODUCT.
+!     Optimized using Intel oneMKL BLAS ddot
+!     Mathematical equivalence: DGVV = sum_{i=1}^{N} V(i)*W(i)
 
-      SUM = 0.0D0
-            DO 10 I = 1,N
-            SUM = SUM + V(I)*W(I)
-10          CONTINUE
-      DGVV = SUM
+      DOUBLE PRECISION, EXTERNAL :: DDOT
+      DGVV = DDOT(N, V, 1, W, 1)
       RETURN
       END