(j3.2006) What do typical processors do?

[Van Snyder]

On Wed, 2017-07-19 at 19:53 +0200, Toon Moene wrote:
> The *real* question is, though:
> 
> Why doesn't transpose(<something complex>) *mean*
> conjg(transpose(<it>)) 
> ? I can't imagine someone wanting anything else ...
> [ I wasn't a member yet when this was argued about for Fortran 90 ]

DOT_PRODUCT assumes conjugate for its first argument when the arguments
are complex.  MATMUL doesn't.  TRANSPOSE could have an optional logical
CONJG argument.  Like *GEMM, MATMUL could have extra optional arguments
to specify whether to transpose and/or conjugate either argument.