적수네 동네 - 1원짜리 팁? [ 게시물 수정 ]

	>> Edit article


			이름
			제목
			패스워드

클러스터링 하시나부죠?
 MPICH 사이트를 참조해보세요.
   http://www-unix.mcs.anl.gov/mpi/mpich  설정시 아키텍쳐, C컴파일러, Fotran 컴파일러 등을 지정을 해야할겁니다.
음.. 오래돼놔서 기억이 가물하네요... 
  : MPICH-1.2.3 컴파일시 다음과 같은 메시지가 나옵니다. 2.95.3으로
: 컴파일 할때는 조용하더군요. Redhat 7.2(updated) + Ximian
: 
: 
: 
: checking for correct handling of #elif... no
: *#    ******************************************************************
: *#    * Your C compiler can not properly handle the #elif preprocessor *
: *#    * directive.  Report the problem to your vendor; you may want to *
: *#    * using the GNU C compiler instead.                              *
: *#    *                                                                *
: *#    * Please file a bug report with your vendor.  If you do not get  *
: *#    * satisfaction from your vendor, we suggest that you consider    *
: *#    * gcc.                                                           *
: *#    *                                                                *
: *#    ******************************************************************
: Output from compile step was:
: In file included from /usr/include/_G_config.h:44,
:                  from /usr/include/libio.h:32,
:                  from /usr/include/stdio.h:65,
:                  from conftest.c:18:
: /usr/include/gconv.h:172: array size missing in `__data&#039;
: checking that constant folding in arrays works... yes
: checking that compiler truncates unsigned char correctly ...... no
: *#    ******************************************************************
: *#    *                YOUR C COMPILER HAS A BUG!!!!!!                 *
: *#    *                                                                *
: *#    * Your C compiler fails to properly handle truncations of data   *
: *#    * to unsigned char properly.  This should not affect MPICH but   *
: *#    * may cause errors in user programs and in some parts of the     *
: *#    * MPICH test suite.                                              *
: *#    *                                                                *
: *#    * You may find that the compiler will generate correct code      *
: *#    * a lower levels of optimization.                                *
: *#    ******************************************************************
: Output from compile step was:
: In file included from /usr/include/_G_config.h:44,
:                  from /usr/include/libio.h:32,
:                  from /usr/include/stdio.h:65,
:                  from conftest.c:1:
: 
: /usr/include/gconv.h:172: array size missing in `__data&#039;
: checking that compiler/hardware has commutative arithmetic ...... no
: *#    ******************************************************************
: *#    * YOUR C COMPILER / HARDWARE HAS NON-COMMUTATIVE ARITHMETIC!!!   *
: *#    *                                                                *
: *#    * Your C compiler believes that x*y-y*x can be different from    *
: *#    * zero.  This may be the result of inconsistent rounding in      *
: *#    * your computers hardware when multiply-add instructions are     *
: *#    * used.                                                          *
: *#    *                                                                *
: *#    * On some systems, a Multiply-Add combination whose results are  *
: *#    * different from a Multiply and an Add can cause this to happen. *
: *#    * Results on this system, if it alleges to be IEEE, will differ  *
: *#    * from IEEE systems where arithmetic is commutative.             *
: *#    *                                                                *
: *#    * At least one vendor views this behavior as a feature; if       *
: *#    * commutative arithmetic is important to you, consider using     *
: *#    * compilation options to reduce the amount of optimization or    *
: *#    * eliminate the use of Multiply-Add (this may reduce             *
: *#    * performance but will make it possible to compare computations  *
: *#    * on different systems).                                         *
: *#    *                                                                *
: *#    ******************************************************************
: Output from compile step was:
: In file included from /usr/include/_G_config.h:44,
:                  from /usr/include/libio.h:32,
:                  from /usr/include/stdio.h:65,
:                  from conftest.c:1:
: /usr/include/gconv.h:172: array size missing in `__data&#039;
: checking that compiler assigns to char correctly ...... no
: *#    ******************************************************************
: *#    *                YOUR C COMPILER HAS A BUG!!!!!!                 *
: *#    *                                                                *
: *#    * Your C compiler fails to properly handle assignments or        *
: *#    * references to char arrays properly when the most significant   *
: *#    * bit in the character bit is set.  This should not affect MPICH *
: *#    * but may cause errors in user programs and in some parts of the *
: *#    * MPICH test suite.                                              *
: *#    *                                                                *
: *#    * You may find that the compiler will generate correct code      *
: *#    * a lower levels of optimization.                                *
: *#    ******************************************************************
: Output from compile step was:
: In file included from /usr/include/_G_config.h:44,
:                  from /usr/include/libio.h:32,
:                  from /usr/include/stdio.h:65,
:                  from conftest.c:1:
: /usr/include/gconv.h:172: array size missing in `__data&#039;
: checking that compiler does not call unknown routines for long doubles... yes
: checking that compiler accepts args correctly ...... no
: *#    ******************************************************************
: *#    *             YOUR C COMPILER IS SERIOUSLY BROKEN!!!!!!          *
: *#    *                                                                *
: *#    * Your C compiler fails to accept macro definitions to strings   *
: *#    * with embedded blanks.  This often means that your compiler is  *
: *#    * improperly implemented as a shell script.  You should file a   *
: *#    * bug report and require a fix                                   *
: *#    *                                                                *
: *#    * MPICH is able to work around this bug; however, any compiler   *
: *#    * that can not handle this simple case is highly suspect.        *
: *#    *                                                                *
: *#    * You may find that the compiler is an sh script with a          *
: *#    * statement containing $*.  This is a common error; consider     *
: *#    * replacing $* with "$@".                                        *
: *#    ******************************************************************
: *#
: 
: --
: 장미가 장미라는 것은 장미인가?--피망~!