Speed of a computer language can mean two things. Seconds from run command to
result depends on the quality of the language implementation. Months from
hiring to publication depends on the quality of the language design. Which of
these matters most depends on context.
Date:Thu, 8 May 2014
Can it be parallelized? That is how you reduce run-time. One of the tests
matrix-matrix multiplication has been successfully speeded up by using GPUs.
CUDA is the language used for this, which is a derivative of C. To be fair you
only see the benefit for really large matrices, smaller ones
Le 09/05/2014 15:36, Adam Ralph a écrit :
Can it be parallelized? That is how you reduce run-time. One of the
tests matrix-matrix multiplication has been successfully speeded up by
using GPUs. CUDA is the language used for this, which is a derivative
of C. To be fair you only see the benefit
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Hi Pascal,
I would think that a good programmer can often optimise better for a
specific problem than a general purpose library would. For example I
implemented a peak search for diffraction images which is about an
order of magnitude faster than
http://arstechnica.com/science/2014/05/scientific-computings-future-can-any-coding-language-top-a-1950s-behemoth/
Scientific computing's future: Can any coding language top a 1950s
behemoth?
Cutting-edge research still universally involves Fortran; a trio of
challengers wants in.
---
