> > If I comment it out as above patch, then O3/PGO can get 16% and 12%
> > performance
> > improvement compared to O2 on x86.
> >
> > O2 O3 PGO
> > cycles 2,497,674,824 2,104,993,224 2,199,753,593
> > instructions1
On Mon, Jul 31, 2023 at 03:53:26PM +0200, Richard Biener wrote:
[snip]
> > The main difference in the compilation output about code around the
> > miss-prediction
> > branch is:
> > o In O2: predicated instruction (cmov here) is selected to eliminate above
> > branch. cmov is true better tha
On Tue, Aug 01, 2023 at 10:44:02AM +0200, Jan Hubicka wrote:
> > > If I comment it out as above patch, then O3/PGO can get 16% and 12%
> > > performance
> > > improvement compared to O2 on x86.
> > >
> > > O2 O3 PGO
> > > cycles 2,
On Mon, Jul 31, 2023 at 08:55:35PM +0800, Changbin Du wrote:
> The result (p-core, no ht, no turbo, performance mode):
>
> O2 O3 PGO
> cycles 2,581,832,749 8,638,401,568 9,394,200,585
>
>
> My guess is that you were trying to do it from the PLUGIN_ANALYZER_INIT
> hook rather than from the plugin_init function, but it's hard to be
> sure without seeing the code.
>
Thanks Dave, you are entirely right — I made the mistake of trying to
do it from PLUGIN_ANALYZER_INIT hook and not fro
The Gambit Scheme->C compiler has an option to generate more efficient
code if it knows that all tail and sibling calls in the generated C code
will be optimized. If gcc does not, however, optimize a tail or sibling
call, the generated C code may be incorrect (depending on circumstances).
So
I'm puzzled.
The fundamental rule of optimization is that it doesn't change the (defined)
semantics of the program. How is it possible to write valid C that is correct
only if some optimization is done?
In other words, if it matters whether an optimization is done or not, that
suggests to me
On Tue, 2023-08-01 at 09:57 -0400, Eric Feng wrote:
> >
> > My guess is that you were trying to do it from the
> > PLUGIN_ANALYZER_INIT
> > hook rather than from the plugin_init function, but it's hard to be
> > sure without seeing the code.
> >
>
> Thanks Dave, you are entirely right — I made t
> The Gambit Scheme->C compiler has an option to generate more efficient
> code if it knows that all tail and sibling calls in the generated C
> code will be optimized. If gcc does not, however, optimize a tail or
> sibling call, the generated C code may be incorrect (depending on
> circumstance
>> The Gambit Scheme->C compiler has an option to generate more efficient
>> code if it knows that all tail and sibling calls in the generated C
>> code will be optimized. If gcc does not, however, optimize a tail or
>> sibling call, the generated C code may be incorrect (depending on
>> circums
I sent this note after reading "Final install" and seeing the buildstat.html
hasn't had 14.x yet, indicating my success in building and installing GCC.
config.guess output:
x86_64-pc-linux-gnu
gcc -v output:
Using built-in specs.
COLLECT_GCC=gcc
COLLECT_LTO_WRAPPER=/usr/local/libexec/gcc/x86_64
I sent this note after reading "Final install" and seeing the buildstat.html
hasn't had 14.x yet, indicating my success in building and installing GCC.
config.guess output:
x86_64-pc-linux-gnu
gcc -v output:
Using built-in specs.
COLLECT_GCC=gcc
COLLECT_LTO_WRAPPER=/usr/local/libexec/gcc/x86_64
On 8/1/23 12:51 PM, Paul Koning wrote:
How is it possible to write valid C that is correct only if some optimization
is done?
Perhaps "incorrect" was the wrong word. If sibling-call optimization is
not done, then perhaps the program will blow out the stack, which would
not happen if the opt
On Tue, 2023-08-01 at 20:20 +0200, Jose E. Marchesi via Gcc wrote:
>
> > > The Gambit Scheme->C compiler has an option to generate more
> > > efficient
> > > code if it knows that all tail and sibling calls in the generated
> > > C
> > > code will be optimized. If gcc does not, however, optimize
On 8/1/23 6:08 PM, David Malcolm wrote:
Or from libgccjit. FWIW I added it to support Scheme from libgccjit;
see this patch kit:
https://gcc.gnu.org/ml/gcc-patches/2016-05/msg01287.html
Perhaps there's a case for a frontend attribute for this.
Dave
Thanks. I thought a front-end warning mi
15 matches
Mail list logo
