Le 11/02/2021 à 15:30, Segher Boessenkool a écrit :
On Thu, Feb 11, 2021 at 03:09:43PM +0100, Christophe Leroy wrote:
Le 11/02/2021 à 12:49, Segher Boessenkool a écrit :
On Thu, Feb 11, 2021 at 07:41:52AM +, Christophe Leroy wrote:
powerpc BUG_ON() is based on using twnei or tdnei
Excerpts from Segher Boessenkool's message of February 11, 2021 9:50 pm:
> On Thu, Feb 11, 2021 at 08:04:55PM +1000, Nicholas Piggin wrote:
>> It would be nice if we could have a __builtin_trap_if that gcc would use
>> conditional traps with, (and which never assumes following code is
>>
Le 11/02/2021 à 15:30, Segher Boessenkool a écrit :
On Thu, Feb 11, 2021 at 03:09:43PM +0100, Christophe Leroy wrote:
Le 11/02/2021 à 12:49, Segher Boessenkool a écrit :
On Thu, Feb 11, 2021 at 07:41:52AM +, Christophe Leroy wrote:
powerpc BUG_ON() is based on using twnei or tdnei
On Thu, Feb 11, 2021 at 03:09:43PM +0100, Christophe Leroy wrote:
> Le 11/02/2021 à 12:49, Segher Boessenkool a écrit :
> >On Thu, Feb 11, 2021 at 07:41:52AM +, Christophe Leroy wrote:
> >>powerpc BUG_ON() is based on using twnei or tdnei instruction,
> >>which obliges gcc to format the
Le 11/02/2021 à 12:49, Segher Boessenkool a écrit :
On Thu, Feb 11, 2021 at 07:41:52AM +, Christophe Leroy wrote:
powerpc BUG_ON() is based on using twnei or tdnei instruction,
which obliges gcc to format the condition into a 0 or 1 value
in a register.
Huh? Why is that?
Will it work
On Thu, Feb 11, 2021 at 01:26:12PM +0100, Christophe Leroy wrote:
> >What PowerPC cpus implement branch folding? I know none.
>
> Extract from powerpc mpc8323 reference manual:
> — Zero-cycle branch capability (branch folding)
Yeah, this is not what is traditionally called branch folding
On Thu, Feb 11, 2021 at 08:04:55PM +1000, Nicholas Piggin wrote:
> Excerpts from Christophe Leroy's message of February 11, 2021 5:41 pm:
> > As modern powerpc implement branch folding, that's even more efficient.
Ah, it seems you mean what Arm calls branch folding. Sure, power4
already did
Le 11/02/2021 à 12:49, Segher Boessenkool a écrit :
On Thu, Feb 11, 2021 at 07:41:52AM +, Christophe Leroy wrote:
powerpc BUG_ON() is based on using twnei or tdnei instruction,
which obliges gcc to format the condition into a 0 or 1 value
in a register.
Huh? Why is that?
Will it work
On Thu, Feb 11, 2021 at 07:41:52AM +, Christophe Leroy wrote:
> powerpc BUG_ON() is based on using twnei or tdnei instruction,
> which obliges gcc to format the condition into a 0 or 1 value
> in a register.
Huh? Why is that?
Will it work better if this used __builtin_trap? Or does the
On Thu, Feb 11, 2021 at 08:04:55PM +1000, Nicholas Piggin wrote:
> It would be nice if we could have a __builtin_trap_if that gcc would use
> conditional traps with, (and which never assumes following code is
> unreachable even for constant true, so we can use it with WARN and put
> explicit
Excerpts from Christophe Leroy's message of February 11, 2021 5:41 pm:
> powerpc BUG_ON() is based on using twnei or tdnei instruction,
> which obliges gcc to format the condition into a 0 or 1 value
> in a register.
>
> By using a generic implementation, gcc will generate a branch
> to the
powerpc BUG_ON() is based on using twnei or tdnei instruction,
which obliges gcc to format the condition into a 0 or 1 value
in a register.
By using a generic implementation, gcc will generate a branch
to the unconditional trap generated by BUG().
As modern powerpc implement branch folding,
12 matches
Mail list logo
