Nicolas Pitre writes:
> On Thu, 26 Nov 2015, Måns Rullgård wrote:
>
>> Russell King - ARM Linux writes:
>>
>> > On Thu, Nov 26, 2015 at 12:50:08AM +, Måns Rullgård wrote:
>> >> If not calling the function saves an I-cache miss, the benefit can be
>> >> substantial. No, I have no proof of
Nicolas Pitre writes:
> On Thu, 26 Nov 2015, Måns Rullgård wrote:
>
>> Russell King - ARM Linux writes:
>>
>> > On Thu, Nov 26, 2015 at 12:50:08AM +, Måns Rullgård wrote:
>> >> If not calling the function saves an I-cache miss, the benefit can be
On Thu, 26 Nov 2015, Måns Rullgård wrote:
> Russell King - ARM Linux writes:
>
> > On Thu, Nov 26, 2015 at 12:50:08AM +, Måns Rullgård wrote:
> >> If not calling the function saves an I-cache miss, the benefit can be
> >> substantial. No, I have no proof of this being a problem, but it's
>
Russell King - ARM Linux writes:
> On Thu, Nov 26, 2015 at 12:50:08AM +, Måns Rullgård wrote:
>> If not calling the function saves an I-cache miss, the benefit can be
>> substantial. No, I have no proof of this being a problem, but it's
>> something that could happen.
>
> That's a
On Thu, Nov 26, 2015 at 12:50:08AM +, Måns Rullgård wrote:
> If not calling the function saves an I-cache miss, the benefit can be
> substantial. No, I have no proof of this being a problem, but it's
> something that could happen.
That's a simplistic view of modern CPUs.
As I've already
Nicolas Pitre writes:
> On Thu, 26 Nov 2015, Måns Rullgård wrote:
>
>> Nicolas Pitre writes:
>>
>> > 3) In fact I was wondering if the overhead of the branch and back is
>> >really significant compared to the non trivial cost of a idiv
>> >instruction and all the complex
On Thu, 26 Nov 2015, Måns Rullgård wrote:
> Nicolas Pitre writes:
>
> > On Wed, 25 Nov 2015, Stephen Boyd wrote:
> >
> >> The ARM compiler inserts calls to __aeabi_uidiv() and
> >> __aeabi_idiv() when it needs to perform division on signed and
> >> unsigned integers. If a processor has support
On Wed, Nov 25, 2015 at 01:51:04PM -0800, Stephen Boyd wrote:
> diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h
> index 85e374f873ac..48c77d422a0d 100644
> --- a/arch/arm/include/asm/cputype.h
> +++ b/arch/arm/include/asm/cputype.h
> @@ -250,8 +250,14 @@ static inline
Nicolas Pitre writes:
> On Wed, 25 Nov 2015, Stephen Boyd wrote:
>
>> The ARM compiler inserts calls to __aeabi_uidiv() and
>> __aeabi_idiv() when it needs to perform division on signed and
>> unsigned integers. If a processor has support for the udiv and
>> sdiv division instructions the calls
On Wed, Nov 25, 2015 at 06:09:13PM -0500, Nicolas Pitre wrote:
> 3) In fact I was wondering if the overhead of the branch and back is
>really significant compared to the non trivial cost of a idiv
>instruction and all the complex infrastructure required to patch
>those branches
On Wed, 25 Nov 2015, Stephen Boyd wrote:
> The ARM compiler inserts calls to __aeabi_uidiv() and
> __aeabi_idiv() when it needs to perform division on signed and
> unsigned integers. If a processor has support for the udiv and
> sdiv division instructions the calls to these support routines
> can
The ARM compiler inserts calls to __aeabi_uidiv() and
__aeabi_idiv() when it needs to perform division on signed and
unsigned integers. If a processor has support for the udiv and
sdiv division instructions the calls to these support routines
can be replaced with those instructions. Now that
On Wed, Nov 25, 2015 at 01:51:04PM -0800, Stephen Boyd wrote:
> diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h
> index 85e374f873ac..48c77d422a0d 100644
> --- a/arch/arm/include/asm/cputype.h
> +++ b/arch/arm/include/asm/cputype.h
> @@ -250,8 +250,14 @@ static inline
On Wed, Nov 25, 2015 at 06:09:13PM -0500, Nicolas Pitre wrote:
> 3) In fact I was wondering if the overhead of the branch and back is
>really significant compared to the non trivial cost of a idiv
>instruction and all the complex infrastructure required to patch
>those branches
On Thu, 26 Nov 2015, Måns Rullgård wrote:
> Nicolas Pitre writes:
>
> > On Wed, 25 Nov 2015, Stephen Boyd wrote:
> >
> >> The ARM compiler inserts calls to __aeabi_uidiv() and
> >> __aeabi_idiv() when it needs to perform division on signed and
> >> unsigned integers. If a
Nicolas Pitre writes:
> On Thu, 26 Nov 2015, Måns Rullgård wrote:
>
>> Nicolas Pitre writes:
>>
>> > 3) In fact I was wondering if the overhead of the branch and back is
>> >really significant compared to the non trivial cost of a idiv
>> >
On Wed, 25 Nov 2015, Stephen Boyd wrote:
> The ARM compiler inserts calls to __aeabi_uidiv() and
> __aeabi_idiv() when it needs to perform division on signed and
> unsigned integers. If a processor has support for the udiv and
> sdiv division instructions the calls to these support routines
> can
Nicolas Pitre writes:
> On Wed, 25 Nov 2015, Stephen Boyd wrote:
>
>> The ARM compiler inserts calls to __aeabi_uidiv() and
>> __aeabi_idiv() when it needs to perform division on signed and
>> unsigned integers. If a processor has support for the udiv and
>> sdiv division
Russell King - ARM Linux writes:
> On Thu, Nov 26, 2015 at 12:50:08AM +, Måns Rullgård wrote:
>> If not calling the function saves an I-cache miss, the benefit can be
>> substantial. No, I have no proof of this being a problem, but it's
>> something that could
On Thu, Nov 26, 2015 at 12:50:08AM +, Måns Rullgård wrote:
> If not calling the function saves an I-cache miss, the benefit can be
> substantial. No, I have no proof of this being a problem, but it's
> something that could happen.
That's a simplistic view of modern CPUs.
As I've already
The ARM compiler inserts calls to __aeabi_uidiv() and
__aeabi_idiv() when it needs to perform division on signed and
unsigned integers. If a processor has support for the udiv and
sdiv division instructions the calls to these support routines
can be replaced with those instructions. Now that
On Thu, 26 Nov 2015, Måns Rullgård wrote:
> Russell King - ARM Linux writes:
>
> > On Thu, Nov 26, 2015 at 12:50:08AM +, Måns Rullgård wrote:
> >> If not calling the function saves an I-cache miss, the benefit can be
> >> substantial. No, I have no proof of this
22 matches
Mail list logo