quick question on BLAS

From: Shubao Liu <shubao.liu@xxxxxxxxx>
Date: Mon, 6 Apr 2009 19:56:43 -0700 (PDT)

In BLAS there is asum function for computing the sum of absolute
values in a vector.
Now I want to compute the sum of values in the vector (instead of
absolute values).
Is there corresponding function in BLAS? If not, why? And how should I
do it to get optimized speed (instead of literally iterating through
every value)?

Thanks.
Shubao
.

Follow-Ups:
- Re: quick question on BLAS
  - From: highegg
- Re: quick question on BLAS
  - From: Nicolas Bonneel

Prev by Date: New mathematics / physical sciences positions at http://jobs.phds.org, Apr 06, 2009
Next by Date: Re: quick question on BLAS
Previous by thread: New mathematics / physical sciences positions at http://jobs.phds.org, Apr 06, 2009
Next by thread: Re: quick question on BLAS
Index(es):
- Date
- Thread

Relevant Pages

Re: quick question on BLAS
... Now I want to compute the sum of values in the vector (instead of ... absolute values). ... Is there corresponding function in BLAS? ... In Fortran, ...
(sci.math.num-analysis)
Re: quick question on BLAS
... Now I want to compute the sum of values in the vector (instead of ... absolute values). ... Is there corresponding function in BLAS? ... for incy: ...
(sci.math.num-analysis)
Re: quick question on BLAS
... absolute values). ... Is there corresponding function in BLAS? ... There didn't seem to be a similar reason to provide a "sum" ... this is provided now in Fortran. ...
(sci.math.num-analysis)
Re: Calculating Standard Deviation
... sum of all the residuals squared. ... Because you want the standard deviation, not the mean absolute deviation. ... Squares have much nicer properties than absolute values. ...
(sci.math.num-analysis)
Re: Calculating Standard Deviation
... sum of all the residuals squared. ... Because you want the standard deviation, not the mean absolute deviation. ...
(sci.math.num-analysis)