Просмтор этого файла доступен только зарегистрированным пользователям. Но у нас супер быстрая регистрация: достаточно только электронной почты!

Текст из файла (страница 17)

where:

If *AxisPtr = 0, the size of the object (product of sizes of all dimensions) is returned.

If the pointer *ObjectRefPtr is not a pointer to any of the mentioned above objects, then the function returns zero.

The function locsiz_ is similar to the function getsiz_, but it returns the local size of dimension *AxisPtr (or the local size of the object), i.e. the size of the object part, mapped on the current processor. If the object is a processor system, then the values, returned by the functions getsiz_ and locsiz_ are the same.

Note, that a local size of the object, having no a local part on the current processor, is equal to zero.

17.3. Requesting if object is distributed array.

long tstda_ (ObjectRef *ObjectRefPtr);

The function tstda_ allowes to determine whether the object, specified by the pointer *ObjectRefPtr, is a distributed array.

The following values are returned:

0 - the object is not a distributed array;

1 - the object is a distributed array;

2 - the object is a fully replicated distributed array.

17.4. Requesting size of distributed array element.

long getlen_ (long ArrayHeader[]);

ArrayHeader - header of the distributed array.

The function getlen_ returns the size in bytes of element of specified distributed array in bytes.

17.5. Deleting object.

long delobj_(ObjectRef *ObjectRefPtr);

*ObjectRefPtr - pointer to the deleted object.

It is possible to use the followings as an object:

• distributed array (in that case the pointer is the first word of the header of the array);

• the representation of the abstract machine;

• the processor system;

• map of abstract machine representation;

• map of distributed array;

• reduction;

• reduction group;

• shadow edge group.

Note, that non-static object can be deleted by the function delobj_ only in the case, if it was created in the current program block.

The function returns zero.

17.6. Requesting whether current processor is I/O processor.

long tstio_(void);

The function returns 1 if the current processor is the I/O processor, and returns zero in another case.

17.7. Sending memory areas of I/O processor.

The function srmem_ sends the memory areas of the I/O processor to another processors. During this operation the I/O processor sends the data, and the other processors receive the data. The number of the parameters in the arrays LenghtArray and StartAddrArray has to be equal to *MemoryCountPtr. The length of the each sent area has not to exceed the maximum of the positive integer (LengthArray[i] (unsigned int)-1 >> 1).

The function returns zero.

To receive an address acceptable for the function srmem_, Run-Time Library has the function:

AddrType dvmadr_(void *VarPtr) ,

This function is intended for usage in Fortran.

The following functions can be also used for Fortran variables of different types:

These functions are similar to the function dvmadr_ (in the function getach_ VarPtr is the address of text string, and StrLength is its size, formed by Fortran compiler.

The functions srmem_ and dvmadr_ (getai_, getal_, getaf_, getad_, getac_, getach_) can be used for implementation of input/output operations).

18. Using Run-Time Library in Fortran language.

To coordinate allocation of the arrays in the memory, (along the columns in the Fortran , and along the rows in the C) inverse order of specifying the array indexes (in comparison with the order in the C ) is required. In addition, in this document it is supposed that the initial array index value is equal to zero, that is conformed to the C language. In the Fortran language this index is equal to 1.

The type of the returned values is a four-bytes field (the exception is the «long» , DVMFILE* and DVMHANDLE* types). For these types it is allowable only assignment operations and the using as a parameters in the calls of the functions and subroutines. In the Fortran language the base type «long» has to be associated with integer type, which has equivalent memory representation (the particular type depends on the C and Fortran language implementations).

19. Example of program using Run-Time Library functions.

The usage of main functions of Run-Time Library is shown on the example of numerical solution of two-dimensional Laplas equation in specified rectangular area with specified boundary conditions (Dirixle task).

Three-point approximation of partial derivatives of the equation (1) on squared grid using five-point pattern

(i-1,j) , (i+1,j) , (i,j) , (i,j-1) , (i,j+1)

gives differential equation ("cross" scheme), reduced to the equation

u_i,j = (u_i+1,j + u_i-1,j + u_i,j+1 + u_i,j-1)/4 (i,j=1, ... ,k-2) (2),

where:

The value of the grid function

u_0,j , u_k-1,j , u_i,0 , u_i,k-1 (i,j=0, ... ,k-1)

is determined by boundary conditions.

In the programs below (Fortran and C) the solution of the equation (1) is seached by formulas (2) using method of sequential approximations. The iterational proccess is completed if maximal diviation of the grid function u_i,j on all knots for to sequential iterations will become less, then a value of variable maxeps. The solution is searched as function u_i,j = 1 + i + j. on the square[0:7, 0:7]. The boundary conditions are zero.

PROGRAM IN FORTRAM LANGUAGE

program cross

integer linit, lexit,getam, getps, crtamv, distr, crtda, align,

+ crtpl, dvmadr, mappl, endpl, exfrst, imlast, dopl,

+ tstio, crtrg, crtred, insred, strtrd, waitrd,

+ crtshg, inssh, strtsh, waitsh, delrg, delshg

real bptr(1)

integer dvm

integer amref, psref, mvref, plref, rgref, redref, shgref

integer amdim(2), disaxs(2), dispar(2)

integer shwdth(2), axis(2), coeff(2), const(2)

integer lvaddr(2), iiniti(2), ilasti(2), istep(2)

integer oiniti(2), olasti(2), ostep(2)

C A number of grid points by each dimension and

C max. number of iterations.

parameter (k = 8, itmax = 20)

real eps, maxeps

C Array header with previous values of the grid function

integer ahdr(3)

C Array header with next values of the grid function

integer bhdr(3)

maxeps = 0.5e-7

C Run-Time Library initialisation

dvm = linit (0)

C Creating abstract machine representation

C and mapping it onto processor subsystem

amref = getam ()

psref = getps (amref)

amdim(1) = k

amdim(2) = k

mvref = crtamv (amref, 2, amdim,0)

disaxs(1) = 1

disaxs(2) = 2

dispar(1) = 0

dispar(2) = 0

dvm = distr (mvref, psref, 2, disaxs, dispar)

C Creating and mapping arrays

C with the values of the grid function

shwdth(1) = 1

shwdth(2) = 1

dvm = crtda (ahdr, bptr, 2, 4, amdim, 0, 0, shwdth, shwdth)

dvm = crtda (bhdr, bptr, 2, 4, amdim, 0, 0, shwdth, shwdth)

axis(1) = 1

axis(2) = 2

coeff(1) = 1

coeff(2) = 1

const(1) = 0

const(2) = 0

dvm = align (ahdr, mvref, axis, coeff, const)

dvm = align (bhdr, mvref, axis, coeff, const)

C Parallel loop of initializing arrays

C with values of the grid function

C (parallel loop with the base array ahdr).

plref = crtpl (2)

lvaddr(1) = dvmadr (j)

lvaddr(2) = dvmadr (i)

iiniti(1) = 0

iiniti(2) = 0

ilasti(1) = k - 1

ilasti(2) = k - 1

istep(1) = 1

istep(2) = 1

dvm = mappl (plref, ahdr, axis, coeff, const, lvaddr,

+ iiniti, ilasti, istep, oiniti, olasti, ostep)

99999 if (dopl (plref) .eq. 0) goto 99998

do 1 j = oiniti(1), olasti(1), ostep(1)

do 1 i = oiniti(2), olasti(2), ostep(2)

bptr( ahdr(3) + 1 + i + ahdr(2) * j ) = 0.

bptr( bhdr(3) + 1 + i + bhdr(2) * j ) = 1. + i + j

1 continue

goto 99999

99998 dvm = endpl (plref)

C Creating reduction variable and reduction group

C to calculate maximal deviation of the grid function for

C two sequential iterations.

redref = crtred ( 3, eps, 3, 1, 0, 0, 0)

rgref = crtrg (0, 0)

dvm = insred (rgref, redref)

C Creating shadow edge group for renewing shadow edges

shgref = crtshg (0)

dvm = inssh (shgref, ahdr, shwdth, shwdth, 0)

C MAIN ITERATION LOOP

do 2 it = 1,itmax

C Parallel loop to calculate maximal deviation

C of the grid function in variable eps

C (parallel loop with base array ahdr).

plref = crtpl (2)

iiniti(1) = 1

iiniti(2) = 1

ilasti(1) = k - 2

ilasti(2) = k - 2

dvm = mappl (plref, ahdr, axis, coeff, const, lvaddr,

+ iiniti, ilasti, istep, oiniti, olasti, ostep)

eps = 0.

99997 if (dopl (plref) .eq. 0) goto 99996

Характеристики

Список файлов учебной работы