PROGRAM MATMUL_TIME
C
      INTEGER I, J, K
      INTEGER SIZE, NTIMES, M, N, P
      PARAMETER (SIZE=2000)
      PARAMETER (M=SIZE,N=SIZE,P=SIZE)
      PARAMETER (NTIMES=1)
      REAL*8 A, B, C, AROW
      DIMENSION A(M,N), B(N,P), C(N,P), AROW(N)
C
      INTEGER L
      REAL WALLTIME, MFLOPS
      INTEGER HZ, CLOCK0, CLOCK1, CLOCK2
      REAL*8 OMP_GET_WTIME
      REAL*8 TIME0, TIME1, TIME2
C
      DO I = 1, M
      DO J = 1, N
         A(I,J) = 1.0
      ENDDO
      ENDDO
      DO I = 1, N
      DO J = 1, P
         B(I,J) = 1.0
      ENDDO
      ENDDO
C
      TIME0 = OMP_GET_WTIME()

      DO L = 1, NTIMES
!$OMP PARALLEL
!$OMP DO
         DO J = 1, P
            DO I = 1, M
               C(I,J) = 0.0
            ENDDO
         ENDDO
         DO I = 1, M
!$OMP DO
            DO II = 1, N
               AROW(II) = A(I,II)
            ENDDO
!$OMP DO
            DO J = 1, P
               DO K = 1, N
                  C(I,J) = C(I,J) + AROW(K) * B(K,J)
               ENDDO
            ENDDO
         ENDDO
!$OMP END PARALLEL
         CALL DUMMY(C)
      ENDDO
      TIME1 = OMP_GET_WTIME()
      DO I = 1, NTIMES
         CALL DUMMY(C)
      ENDDO
      TIME2 = OMP_GET_WTIME()
C
      WALLTIME = ((TIME1 - TIME0) - (TIME2 - TIME1)) / REAL(NTIMES)
      MFLOPS = (M*P*(2.0*N-1.0)) / (WALLTIME * 1.0E+06)
      PRINT *, WALLTIME, TIME0, TIME1, TIME2
C
      PRINT *, "M =",M,", N =",N,", P =",P
      PRINT *, "MFLOPS = ", MFLOPS
      PRINT *, "C(1,1) = ", C(1,1)
C
      END
C
      SUBROUTINE DUMMY(C)
      REAL*8 C
      RETURN
      END