OpenMP Support in Sun Studio Compilers and Tools

• Compiler directives,
• Runtime library routines, and
• Environment variables

• In June 2003, Sun Microsystems announced a world-record for the SPEC OMPL2001 suite (peak performance) on a Sun Fire 15K server configured with 72 UltraSPARC III Cu processors.  The Sun Fire 15K server was the first server to break the 200,000 mark with a score of 213,466.

• In February 2004, Sun Microsystems established a new world record on the SPEC OMPL2001 suite (peak performance) on a Sun Fire E25K server configured with 72 UltraSPARC IV processors  The Sun Fire E25K system set a record SPEC OMPL2001 peak performance score of 316,182.

• In March 2005, Sun Microsystems announced new world record SPEC OMPM2001 results in the two- and four-thread categories. The peak result of 12,434 on the Sun Fire V40z server in a four CPU configuration outperformed the scores reported by other commercially available compilers by up to 43 percent.

 
Figure 6: Scaling of OMPL2001 (Base) on Sun Fire 6800


Figure 7: Scaling of OMPL2001 (Base) on Sun Fire 15K

• New OpenMP features.  Sun continues to track changes in the OpenMP Specification and play an active part in its evolution.
  
• OpenMP-specific optimizations for improved performance. These include compiler optimizations, such as removal of redundant barriers, as well as optimizations in the runtime library for reducing the overhead of parallelization.
  
• Enhanced tools support.  Sun continues to invest in tools that aid the programmer in writing, debugging, and analyzing the performance of OpenMP programs.  These tools include enhanced automatic scoping for OpenMP programs, data race detection, and interactive tools to assist programmers in parallelizing their applications.
  
• Architectural support.  Sun continues to enhance the performance of its OpenMP implementation.  Work in this area includes improving performance on Non-Uniform Memory Access (NUMA) machines and on Chip Multi-threading (CMT) architectures.

Fortran – PARALLEL Directive Example:

       PROGRAM HELLO
            


       USE OMP_LIB
            


       INTEGER TID
            


       CALL OMP_SET_DYNAMIC (.FALSE.)
            


       CALL OMP_SET_NUM_THREADS (10)
            


!$OMP PARALLEL PRIVATE (TID)
            


! Obtain thread ID.
            


       TID = OMP_GET_THREAD_NUM()
            


! Print thread ID.
            


       PRINT *, 'Hello World from thread = ', TID
            


!$OMP END PARALLEL
            


       END
            


          

C/C++ – PARALLEL Directive Example:

#include <stdio.h>
            


#include <omp.h>
            


int main(void)
            


{
            


  int tid; omp_set_dynamic(0);
            


  omp_set_num_threads(10);
            


#pragma omp parallel private(tid)
            


  {
            


/* Obtain thread ID. */
            


    tid = omp_get_thread_num();
            


/* Print thread ID. */
            


    printf ("Hello World from thread = %d\n", tid);
            


  }
            


}
            


          

Fortran – DO Directive Example:

       PROGRAM VECTOR_ADD
            


       USE OMP_LIB
            


       PARAMETER (N=100)
            


       INTEGER N, I
            


       REAL A(N), B(N), C(N)
            


       CALL OMP_SET_DYNAMIC (.FALSE.)
            


       CALL OMP_SET_NUM_THREADS (20)
            


! Initialize arrays A and B.
            


       DO I = 1, N
            


         A(I) = I * 1.0
            


         B(I) = I * 2.0
            


       ENDDO
            


! Compute values of array C in parallel.
            


!$OMP PARALLEL SHARED(A, B, C), PRIVATE(I)
            


!$OMP DO
            


       DO I = 1, N
            


         C(I) = A(I) + B(I)
            


       ENDDO
            


!$OMP END PARALLEL
            


       PRINT *, C(10)
            


       END
            


          

C/C++ – For Directive Example:

#include <stdio.h>
            


#include <omp.h>
            


#define N 100
            


int main(void)
            


{
            


  float a[N], b[N], c[N];
            


  int i;
            


  omp_set_dynamic(0);
            


  omp_set_num_threads(20);
            


/* Initialize arrays a and b. */
            


  for (i = 0; i < N; i++)
            


    {
            


      a[i] = i * 1.0;
            


      b[i] = i * 2.0;
            


    }
            


/* Compute values of array c in parallel. */
            


#pragma omp parallel shared(a, b, c) private(i)
            


  {
            


#pragma omp for
            


    for (i = 0; i < N; i++)
            


      c[i] = a[i] + b[i];
            


  }
            


  printf ("%f\n", c[10]);
            


}
            


          

Fortran – SECTIONS Directive Example:

       PROGRAM SECTIONS
            


       USE OMP_LIB
            


       INTEGER SQUARE
            


       INTEGER X, Y, Z, XS, YS, ZS
            


       CALL OMP_SET_DYNAMIC (.FALSE.)
            


       CALL OMP_SET_NUM_THREADS (3)
            


       X = 2
            


       Y = 3
            


       Z = 5
            


!$OMP PARALLEL
            


!$OMP SECTIONS
            


!$OMP SECTION
            


       XS = SQUARE(X)
            


       PRINT *, "ID = ", OMP_GET_THREAD_NUM(), "XS =", XS
            


!$OMP SECTION
            


       YS = SQUARE(Y)
            


       PRINT *, "ID = ", OMP_GET_THREAD_NUM(), "YS =", YS
            


!$OMP SECTION
            


       ZS = SQUARE(Z)
            


       PRINT *, "ID = ", OMP_GET_THREAD_NUM(), "ZS =", ZS
            


!$OMP END SECTIONS
            


!$OMP END PARALLEL
            


       END
            


       INTEGER FUNCTION SQUARE(N)
            


       INTEGER N
            


       SQUARE = N*N
            


       END
            


          

C/C++ – SECTIONS Directive Example:

#include <stdio.h>
            


#include <omp.h>
            


int square(int n);
            


int main(void)
            


{
            


  int x, y, z, xs, ys, zs;
            


  omp_set_dynamic(0);
            


  omp_set_num_threads(3);
            


  x = 2;
            


  y = 3;
            


  z = 5;
            


#pragma omp parallel
            


  {
            


#pragma omp sections
            


    {
            


#pragma omp section
            


      {
            


         xs = square(x);
            


        printf ("id = %d, xs = %d\n", omp_get_thread_num(), xs);
            


      }
            


#pragma omp section
            


      {
            


        ys = square(y);
            


        printf ("id = %d, ys = %d\n", omp_get_thread_num(), ys);
            


      }
            


#pragma omp section
            


      {
            


        zs = square(z);
            


        printf ("id = %d, zs = %d\n", omp_get_thread_num(), zs);
            


      }
            


    }
            


  }
            


}
            


int square(int n)
            


{
            


return n*n;
            


}