From owner-hpff-interpret Thu Feb 13 02:56:36 1997 Received: (from daemon@localhost) by cs.rice.edu (8.8.5/8.7.1) id CAA15524 for hpff-interpret-out; Thu, 13 Feb 1997 02:56:36 -0600 (CST) Received: from TYO9.gate.nec.co.jp (TYO9.gate.nec.co.jp [203.180.98.35]) by cs.rice.edu (8.8.5/8.7.1) with ESMTP id CAA15519 for ; Thu, 13 Feb 1997 02:56:30 -0600 (CST) Received: from mailsv.nec.co.jp ([133.200.254.203]) by TYO9.gate.nec.co.jp (8.8.5+2.7Wbeta5/3.4Wb-NEC-TYO9) with ESMTP id RAA04784 for ; Thu, 13 Feb 1997 17:56:27 +0900 (JST) Received: from mailsv.bs1.fc.nec.co.jp (venus.d2.bs1.fc.nec.co.jp [133.203.2.164]) by mailsv.nec.co.jp (8.8.5+2.7Wbeta5/3.4W-97020710) with ESMTP id RAA12068 for ; Thu, 13 Feb 1997 17:56:21 +0900 (JST) Received: from c1mail.lang1.bs1.fc.nec.co.jp by mailsv.bs1.fc.nec.co.jp (8.7.3+2.6Wbeta5/6.4JAIN) id RAA02082; Thu, 13 Feb 1997 17:55:34 +0900 (JST) Received: from c1mpc.lang1.bs1.fc.nec.co.jp by c1mail.lang1.bs1.fc.nec.co.jp (8.8.4+2.7Wbeta4/6.4J.6) id RAA00518; Thu, 13 Feb 1997 17:57:33 +0900 (JST) Received: by c1mpc.lang1.bs1.fc.nec.co.jp (5.67+1.6W/6.4J.6) id AA02477; Thu, 13 Feb 97 17:57:58 JST Date: Thu, 13 Feb 97 17:57:58 JST From: hayashi@lang1.bs1.fc.nec.co.jp (Yasuharu Hayashi) Message-Id: <9702130857.AA02477@c1mpc.lang1.bs1.fc.nec.co.jp> To: hpff-interpret@cs.rice.edu Subject: hpff-interpret: About the remapping of a dummy in the subprogram. Sender: owner-hpff-interpret Precedence: bulk --------------------------------------------------------------------------- hpff-interpret@cs.rice.edu is a mailing list for corrections, clarifications, and interpretations related to High Performance Fortran. Instructions for adding or deleting yourself from this list appear at the bottom of this message. --------------------------------------------------------------------------- Dear HPFF: I have two questions about the remapping of the dummy argument whose associated actual argument has the DYNAMIC attribute. High Performance Fortran Language Specification Version2.0 on p.149,l.1 says; The effect of any redistribution of the dummy after the procedure returns to the caller is dependent on the attribute of the actual argument. If the actual argument associated with the dummy has also been declared DYNAMIC, then any explicit remapping of the dummy is visible in the caller after the procedure returns. EXAMPLE1: PROGRAM SAMPLE1 INTERFACE SUBROUTINE SUB(B) REAL B(10) !HPF$ PROCESSORS P(2) !HPF$ DYNAMIC,DISTRIBUTE (BLOCK) ONTO P :: B ENDSUBROUTINE ENDINTERFACE REAL A(10),B(10) !HPF$ PROCESSORS P(2) !HPF$ DYNAMIC,ALIGN (I) WITH B(I) :: A !HPF$ DYNAMIC,DISTRIBUTE (BLOCK) ONTO P :: B : CALL SUB(B) : END SUBROUTINE SUB(B) REAL B(10) !HPF$ PROCESSORS P(2) !HPF$ DYNAMIC,DISTRIBUTE (BLOCK) ONTO P :: B : !HPF$ REDISTRIBUTE (CYCLIC) ONTO P :: B RETURN END In EXAMPLE1, when the subroutine SUB returns and the caller resumes execution, the array A is remapped to maintain the alignment with the array B because the distribution of B was changed in the subroutine SUB. Is it true? EXAMPLE2; PROGRAM SAMPLE2 INTERFACE SUBROUTINE SUB2(A,B) REAL A(10),B(10) !HPF$ PROCESSORS P(2) !HPF$ DISTRIBUTE (BLOCK) ONTO P :: A,B !HPF$ DYNAMIC :: A ENDSUBROUTINE ENDINTERFACE REAL A(10),B(10) !HPF$ PROCESSORS P(2) !HPF$ DYNAMIC,ALIGN (I) WITH B(I) :: A !HPF$ DYNAMIC,DISTRIBUTE (BLOCK) ONTO P :: B : CALL SUB2(A,B) : END SUBROUTINE SUB2(A,B) REAL A(10),B(10) !HPF$ PROCESSORS P(2) !HPF$ DISTRIBUTE (BLOCK) ONTO P :: A,B !HPF$ DYNAMIC :: A : !HPF$ REDISTRIBUTE (CYCLIC) ONTO P :: A RETURN END In EXAMPLE2, the REDISTRIBUTE directive to A in the subroutine SUB2 is not HPF conforming because it is impossible to maintain both the alignment of the array A with the array B and the remapping of the array A in the subroutine SUB2 when the subroutine SUB2 returns and the caller resumes execution. Is it true? Thanks, Yasuharu Hayashi ------------------------------------------------------------------- # Yasuharu Hayashi # NEC Corporation # hayashi@lang1.bs1.fc.nec.co.jp ------------------------------------------------------------------- --------------------------------------------------------------------------- To (un)subscribe to this list, send mail to hpff-interpret-request@cs.rice.edu. Leave the subject line blank, and in the body put the line (un)subscribe ---------------------------------------------------------------------------