TheMatt
Joined: 06 Jul 2009 Posts: 263 Location: Greenbelt, MD
|
Posted: Fri Oct 23, 2009 10:02 am Post subject: |
|
|
| mkcolg wrote: | Hi Matt,
I asked Craig about the BLAS inlining issue you mentioned but he says he didn't perform any. Can you give more details?
Thanks,
Mat |
Well, it was BLAS-type, quoth the article:
| Quote: | ...and two BLAS-type subroutine calls that we manually inlined: | Code: | do k = kts, kte
call vsrec( tvec1(its), den(its,k), ite-its+1 )
do i = its, ite
tvec1(i) = tvec1(i) * den0
enddo
call vssqrt( denfac(its,k), tvec1(its), ite-its+1 )
enddo |
Routine vsrec computes the reciprocal of each vector element, and vssqrt computes the square root, so this is equivalent to: | Code: | do k = kts, kte
do i = its, ite
denfac(i,k) = den0 / den(i,k)
enddo
enddo |
|
It just looked to my eye that the sqrt call never made it into the code snippet in the article: | Code: | | denfac(i,k) = sqrt(den0 / den(i,k)) |
|
|