On 08/07/2013 02:56 PM, Linus Torvalds wrote:
>
> Both of the biased cases *might* also want things like "save register
> state in the unlikely path so that the *likely* path doesn't have to".
> Think things like "it's a leaf function, and the likely path doesn't
> need any temporaries, but the
On 08/07/2013 02:56 PM, Linus Torvalds wrote:
Both of the biased cases *might* also want things like save register
state in the unlikely path so that the *likely* path doesn't have to.
Think things like it's a leaf function, and the likely path doesn't
need any temporaries, but the unlikely
On Wed, Aug 7, 2013 at 2:37 PM, Jason Baron wrote:
>
> ok - I can see 2 variants here as you mentioned:
>
> 1) 'Unbiased' - we want to treat both branches equally but don't want
> the load/test/jmp sequence. For things like the scheduler stats.
>
> 2) 'Biased' - where the unlikely path is moved
On 08/07/2013 04:47 PM, Linus Torvalds wrote:
> On Wed, Aug 7, 2013 at 1:19 PM, Jason Baron wrote:
>> The whole point of the thread started with wanting to move the default
>> 'disabled' branch further out-of-line.
> Yeah, but I always disagreed with that.
>
> Putting the unusual code out-of-line
On Wed, Aug 7, 2013 at 1:19 PM, Jason Baron wrote:
>
> The whole point of the thread started with wanting to move the default
> 'disabled' branch further out-of-line.
Yeah, but I always disagreed with that.
Putting the unusual code out-of-line (as in "at the end of the
function") is a good
On Wed, 2013-08-07 at 16:19 -0400, Jason Baron wrote:
> The whole point of the thread started with wanting to move the default
> 'disabled' branch further out-of-line. We could get there with better
> compiler support for the 'cold' label attribute. Thus, in theory the
> whole 2-byte jmp is just
On Wed, 2013-08-07 at 12:49 -0700, Linus Torvalds wrote:
> On Wed, Aug 7, 2013 at 12:27 PM, H. Peter Anvin wrote:
> > Well we do... both to extract relocations and to sort the exception table.
> > Perhaps we need to merge those kinds of postprocessing tools?
>
> If we can do this generically
On 08/07/2013 03:22 PM, Linus Torvalds wrote:
> On Wed, Aug 7, 2013 at 10:54 AM, Steven Rostedt wrote:
>> On another box, using a distro config, I had even better results:
>>
>> [2.352448] short jumps: 193
>> [2.355407] long jumps: 219
> .. well, another way of looking at this is to say
On Wed, Aug 7, 2013 at 12:27 PM, H. Peter Anvin wrote:
> Well we do... both to extract relocations and to sort the exception table.
> Perhaps we need to merge those kinds of postprocessing tools?
If we can do this generically and without adding 500 lines of
specialized code, my argument
Well we do... both to extract relocations and to sort the exception table.
Perhaps we need to merge those kinds of postprocessing tools?
Linus Torvalds wrote:
>On Wed, Aug 7, 2013 at 10:54 AM, Steven Rostedt
>wrote:
>>
>> On another box, using a distro config, I had even better results:
>>
>>
On Wed, Aug 7, 2013 at 10:54 AM, Steven Rostedt wrote:
>
> On another box, using a distro config, I had even better results:
>
> [2.352448] short jumps: 193
> [2.355407] long jumps: 219
.. well, another way of looking at this is to say that all of this
effort saves just 579 bytes.
Yes,
On Wed, 2013-08-07 at 13:36 -0400, Steven Rostedt wrote:
> As I said, I would post the patches that let the jmps used by jump labels
> be turn to 2 bytes where possible. These are a bit controversial due
> to the complexity of the update_jump_label code.
>
> These patches are based off of tip's
On Wed, 2013-08-07 at 13:36 -0400, Steven Rostedt wrote:
As I said, I would post the patches that let the jmps used by jump labels
be turn to 2 bytes where possible. These are a bit controversial due
to the complexity of the update_jump_label code.
These patches are based off of tip's
On Wed, Aug 7, 2013 at 10:54 AM, Steven Rostedt rost...@goodmis.org wrote:
On another box, using a distro config, I had even better results:
[2.352448] short jumps: 193
[2.355407] long jumps: 219
.. well, another way of looking at this is to say that all of this
effort saves just
Well we do... both to extract relocations and to sort the exception table.
Perhaps we need to merge those kinds of postprocessing tools?
Linus Torvalds torva...@linux-foundation.org wrote:
On Wed, Aug 7, 2013 at 10:54 AM, Steven Rostedt rost...@goodmis.org
wrote:
On another box, using a
On Wed, Aug 7, 2013 at 12:27 PM, H. Peter Anvin h...@zytor.com wrote:
Well we do... both to extract relocations and to sort the exception table.
Perhaps we need to merge those kinds of postprocessing tools?
If we can do this generically and without adding 500 lines of
specialized code, my
On 08/07/2013 03:22 PM, Linus Torvalds wrote:
On Wed, Aug 7, 2013 at 10:54 AM, Steven Rostedt rost...@goodmis.org wrote:
On another box, using a distro config, I had even better results:
[2.352448] short jumps: 193
[2.355407] long jumps: 219
.. well, another way of looking at this
On Wed, 2013-08-07 at 12:49 -0700, Linus Torvalds wrote:
On Wed, Aug 7, 2013 at 12:27 PM, H. Peter Anvin h...@zytor.com wrote:
Well we do... both to extract relocations and to sort the exception table.
Perhaps we need to merge those kinds of postprocessing tools?
If we can do this
On Wed, 2013-08-07 at 16:19 -0400, Jason Baron wrote:
The whole point of the thread started with wanting to move the default
'disabled' branch further out-of-line. We could get there with better
compiler support for the 'cold' label attribute. Thus, in theory the
whole 2-byte jmp is just an
On Wed, Aug 7, 2013 at 1:19 PM, Jason Baron jba...@akamai.com wrote:
The whole point of the thread started with wanting to move the default
'disabled' branch further out-of-line.
Yeah, but I always disagreed with that.
Putting the unusual code out-of-line (as in at the end of the
function) is
On 08/07/2013 04:47 PM, Linus Torvalds wrote:
On Wed, Aug 7, 2013 at 1:19 PM, Jason Baron jba...@akamai.com wrote:
The whole point of the thread started with wanting to move the default
'disabled' branch further out-of-line.
Yeah, but I always disagreed with that.
Putting the unusual code
On Wed, Aug 7, 2013 at 2:37 PM, Jason Baron jba...@akamai.com wrote:
ok - I can see 2 variants here as you mentioned:
1) 'Unbiased' - we want to treat both branches equally but don't want
the load/test/jmp sequence. For things like the scheduler stats.
2) 'Biased' - where the unlikely path
22 matches
Mail list logo
