Example A.22.1c and A.22.1f differences

[nathanweeks]

The resulting values of the x and y arrays are different between examples A.22.1c and A.22.1f. It's probably no big deal, as the OpenMP concepts are implemented correctly, though it could result in some confusion for someone who attempts to run both programs and compare the results. The former example results in:

x[0] == 45000.0, x[1] == 45010.0, ... x[999] == 54990.0
and
y[0] == 0.0 y[1] == 2.0, ..., y[9999] == 19998.0

while the latter results in

X(1) == 55000.0, X(2) == 45010.0, X(3) == 45020.0, ..., X(1000) == 54990.0
and
Y(1) == 2.0, Y(2) == 4.0, ..., Y(10000) == 20000.0.

The Fortran version could be made consistent with the C/C++ version by changing lines 23-24 from

Code: Select all

   X(INDEX(I)) = X(INDEX(I)) + WORK1(I)
Y(I) = Y(I) + WORK2(I)


to

Code: Select all

   X(INDEX(I)) = X(INDEX(I)) + WORK1(I-1)
Y(I) = Y(I) + WORK2(I-1)


and line 35 from

Code: Select all

INDEX(I) = MOD(I, 1000) + 1


to

Code: Select all

INDEX(I) = MOD(I-1, 1000) + 1


[hhj]

Thanks Nathan for your comment. We will include your suggestion into the next release of the spec.
-Henry Jin