On Fri, Oct 10, 2014 at 12:55 AM, Steve Ellcey sell...@mips.com wrote:
On Thu, 2014-10-09 at 19:50 +, Joseph S. Myers wrote:
On Thu, 9 Oct 2014, Steve Ellcey wrote:
Do you know which pass does the simple
'(float)function((double)float_val)' demotion? Maybe that would be a
good place
On Thu, Oct 09, 2014 at 03:55:34PM -0700, Steve Ellcey wrote:
On Thu, 2014-10-09 at 19:50 +, Joseph S. Myers wrote:
On Thu, 9 Oct 2014, Steve Ellcey wrote:
Do you know which pass does the simple
'(float)function((double)float_val)' demotion? Maybe that would be a
good place to
On 2014-10-10 11:07:52 +0200, Jakub Jelinek wrote:
Though, is such optimization desirable even for fast-math?
I wonder whether fast-math has a well-defined spec, but it should be
noted that because of possible cancellations, even if the final result
is a float, it may be better to keep
On Fri, Oct 10, 2014 at 3:27 PM, Vincent Lefevre vincent+...@vinc17.org wrote:
On 2014-10-10 11:07:52 +0200, Jakub Jelinek wrote:
Though, is such optimization desirable even for fast-math?
I wonder whether fast-math has a well-defined spec, but it should be
noted that because of possible
I have a -ffast-math (missing?) optimization question. I noticed on MIPS
that if I compiled:
#include math.h
extern x;
void foo() { x = sin(log(x)); }
GCC will extend 'x' to double precision, call the double precision log and sin
functions and then truncate the result to
On Thu, Oct 9, 2014 at 11:23 AM, Steve Ellcey sell...@mips.com wrote:
I have a -ffast-math (missing?) optimization question. I noticed on MIPS
that if I compiled:
#include math.h
extern x;
void foo() { x = sin(log(x)); }
GCC will extend 'x' to double precision,
On Thu, 2014-10-09 at 11:27 -0700, Andrew Pinski wrote:
Is there a reason why GCC couldn't (under -ffast-math) call the single
precision routines for the first case?
There is no reason why it could not. The reason why it does not
currently is because there is no pass which does the
On Thu, Oct 9, 2014 at 11:32 AM, Steve Ellcey sell...@mips.com wrote:
On Thu, 2014-10-09 at 11:27 -0700, Andrew Pinski wrote:
Is there a reason why GCC couldn't (under -ffast-math) call the single
precision routines for the first case?
There is no reason why it could not. The reason why
On October 9, 2014 8:40:49 PM CEST, Andrew Pinski pins...@gmail.com wrote:
On Thu, Oct 9, 2014 at 11:32 AM, Steve Ellcey sell...@mips.com wrote:
On Thu, 2014-10-09 at 11:27 -0700, Andrew Pinski wrote:
Is there a reason why GCC couldn't (under -ffast-math) call the
single
precision routines
On Thu, 9 Oct 2014, Steve Ellcey wrote:
Do you know which pass does the simple
'(float)function((double)float_val)' demotion? Maybe that would be a
good place to extend things.
convert.c does such transformations. Maybe the transformations in there
could move to the match-and-simplify
On Thu, 2014-10-09 at 19:50 +, Joseph S. Myers wrote:
On Thu, 9 Oct 2014, Steve Ellcey wrote:
Do you know which pass does the simple
'(float)function((double)float_val)' demotion? Maybe that would be a
good place to extend things.
convert.c does such transformations. Maybe the
11 matches
Mail list logo