7;Marcus
> Shawcroft'; 'Ramana Radhakrishnan'; 'Richard Earnshaw'
> Subject: RE: [PATCH] [aarch64] Implemented reciprocal square root (rsqrt)
> estimation in -ffast-math
>
> Hi,
>
> I missed your email and noticed it this week.
>
> What does column 2
Benedikt Huber'; gcc-patches@gcc.gnu.org; 'Marcus
> Shawcroft'; 'Ramana Radhakrishnan'; 'Richard Earnshaw'
> Subject: RE: [PATCH] [aarch64] Implemented reciprocal square root (rsqrt)
> estimation in -ffast-math
>
> I ran a simple test on A57 rev. 0, looping
omsich
> > Cc: James Greenhalgh; Kumar, Venkataramanan; Benedikt Huber; gcc-
> > patc...@gcc.gnu.org; Marcus Shawcroft; Ramana Radhakrishnan; Richard
> > Earnshaw
> > Subject: Re: [PATCH] [aarch64] Implemented reciprocal square root
> > (rsqrt) estimation in -ffast-math
Sent: Monday, June 29, 2015 3:47
> To: Kumar, Venkataramanan
> Cc: pins...@gmail.com; Benedikt Huber; gcc-patches@gcc.gnu.org
> Subject: Re: [PATCH] [aarch64] Implemented reciprocal square root (rsqrt)
> estimation in -ffast-math
>
> Kumar,
>
> This does not come unexpected
lgh
> Cc: Kumar, Venkataramanan; pins...@gmail.com; Benedikt Huber; gcc-
> patc...@gcc.gnu.org; Marcus Shawcroft; Ramana Radhakrishnan; Richard Earnshaw
> Subject: Re: [PATCH] [aarch64] Implemented reciprocal square root (rsqrt)
> estimation in -ffast-math
>
> James,
>
> On 29 Jun
akrishnan; Richard
> Earnshaw
> Subject: Re: [PATCH] [aarch64] Implemented reciprocal square root (rsqrt)
> estimation in -ffast-math
>
>
>
>
>
> > On Jun 29, 2015, at 4:44 AM, Dr. Philipp Tomsich
> wrote:
> >
> > James,
> >
> >> On 29 Jun 20
.org
> Subject: Re: [PATCH] [aarch64] Implemented reciprocal square root (rsqrt)
> estimation in -ffast-math
>
> >
> > Benedikt , I have ICE for 444.namd with your patch, not sure if something
> wrong in my local tree.
>
> Venkat, now I could reproduce it.
> Strangely
>
> Benedikt , I have ICE for 444.namd with your patch, not sure if something
> wrong in my local tree.
Venkat, now I could reproduce it.
Strangely it does not happen with -flto.
I will try to find out the reason for that.
Thank you for the catch,
Benedikt
signature.asc
Description: Message
-Original Message-
>>>> From: Dr. Philipp Tomsich [mailto:philipp.toms...@theobroma-systems.com]
>>>> Sent: Monday, June 29, 2015 2:17 PM
>>>> To: Kumar, Venkataramanan
>>>> Cc: pins...@gmail.com; Benedikt Huber; gcc-patches@gcc.gnu.org
>>>> Subj
> Hmm, Reducing the iterations to "1 step for float" and "2 steps for double"
>
> I got VE (miscompares) on following benchmarks
> 416.gamess
> 453.povray
> 454.calculix
> 459.GemsFDTD
>
> Benedikt , I have ICE for 444.namd with your patch, not sure if something
> wrong in my local tree.
I co
t: Monday, June 29, 2015 2:17 PM
>>> To: Kumar, Venkataramanan
>>> Cc: pins...@gmail.com; Benedikt Huber; gcc-patches@gcc.gnu.org
>>> Subject: Re: [PATCH] [aarch64] Implemented reciprocal square root (rsqrt)
>>> estimation in -ffast-math
>>>
>>>
..@gmail.com; Benedikt Huber; gcc-patches@gcc.gnu.org
> > Subject: Re: [PATCH] [aarch64] Implemented reciprocal square root (rsqrt)
> > estimation in -ffast-math
> >
> > Kumar,
> >
> > This does not come unexpected, as the initial estimation and each iteratio
ree.
> >
> > Regards,
> > Venkat.
> >
> >> -Original Message-
> >> From: pins...@gmail.com [mailto:pins...@gmail.com]
> >> Sent: Sunday, June 28, 2015 8:35 PM
> >> To: Kumar, Venkataramanan
> >> Cc: Dr. Philipp Tomsich; Benedikt Hub
> Andrew
>>
>>
>>>
>>> Regards,
>>> Venkat.
>>>
>>>> -Original Message-
>>>> From: gcc-patches-ow...@gcc.gnu.org [mailto:gcc-patches-
>>>> ow...@gcc.gnu.org] On Behalf Of Dr. Philipp Tomsich
>>>
hes-
> >> ow...@gcc.gnu.org] On Behalf Of Dr. Philipp Tomsich
> >> Sent: Thursday, June 25, 2015 9:13 PM
> >> To: Kumar, Venkataramanan
> >> Cc: Benedikt Huber; pins...@gmail.com; gcc-patches@gcc.gnu.org
> >> Subject: Re: [PATCH] [aarch64] Implemented reci
r; pins...@gmail.com; gcc-patches@gcc.gnu.org
>> Subject: Re: [PATCH] [aarch64] Implemented reciprocal square root (rsqrt)
>> estimation in -ffast-math
>>
>> Kumar,
>>
>> what is the relative gain that you see on Cortex-A57?
>>
>> Thanks,
>&g
On Thu, Jun 25, 2015 at 1:24 AM, Ramana Radhakrishnan
wrote:
> Benedikt,
>
> On 25/06/15 08:01, pins...@gmail.com wrote:
>>
>>
>>
>>
>>
>>> On Jun 18, 2015, at 5:04 AM, Benedikt Huber
>>> wrote:
>>>
>>> arch64 offers the instructions frsqrte and frsqrts, for rsqrt estimation
>>> and
>>> a Newton-
ataramanan
> Cc: Benedikt Huber; pins...@gmail.com; gcc-patches@gcc.gnu.org
> Subject: Re: [PATCH] [aarch64] Implemented reciprocal square root (rsqrt)
> estimation in -ffast-math
>
> Kumar,
>
> what is the relative gain that you see on Cortex-A57?
>
> Thanks,
> Ph
.gnu.org; philipp.toms...@theobroma-systems.com
>> Subject: Re: [PATCH] [aarch64] Implemented reciprocal square root (rsqrt)
>> estimation in -ffast-math
>>
>> Andrew,
>>
>>> This is NOT a win on thunderX at least for single precision because you have
>> to
Sent: Thursday, June 25, 2015 4:09 PM
> To: pins...@gmail.com
> Cc: gcc-patches@gcc.gnu.org; philipp.toms...@theobroma-systems.com
> Subject: Re: [PATCH] [aarch64] Implemented reciprocal square root (rsqrt)
> estimation in -ffast-math
>
> Andrew,
>
> > This is NOT a win
Hi,
On Thu, 25 Jun 2015, Benedikt Huber wrote:
> > This is NOT a win on thunderX at least for single precision because
> > you have to do the divide and sqrt in the same time as it takes 5
> > multiples (estimate and step are multiplies in the thunderX pipeline).
> > Doubles is 10 multiplies
ch
>> Sent: Wednesday, June 24, 2015 15:08
>> To: Evandro Menezes
>> Cc: Benedikt Huber; gcc-patches@gcc.gnu.org
>> Subject: Re: [PATCH] [aarch64] Implemented reciprocal square root (rsqrt)
>> estimation in -ffast-math
>>
>> Evandro,
>>
>> Sh
Andrew,
> This is NOT a win on thunderX at least for single precision because you have
> to do the divide and sqrt in the same time as it takes 5 multiples (estimate
> and step are multiplies in the thunderX pipeline). Doubles is 10 multiplies
> which is just the same as what the patch does (b
Benedikt,
On 25/06/15 08:01, pins...@gmail.com wrote:
On Jun 18, 2015, at 5:04 AM, Benedikt Huber
wrote:
arch64 offers the instructions frsqrte and frsqrts, for rsqrt estimation and
a Newton-Raphson step, respectively.
There are ARMv8 implementations where this is faster than using fdiv
> On Jun 18, 2015, at 5:04 AM, Benedikt Huber
> wrote:
>
> arch64 offers the instructions frsqrte and frsqrts, for rsqrt estimation and
> a Newton-Raphson step, respectively.
> There are ARMv8 implementations where this is faster than using fdiv and
> rsqrt.
> It runs three steps for double
nu.org
> >> [mailto:gcc-patches-ow...@gcc.gnu.org]
> > On
> >> Behalf Of Benedikt Huber
> >> Sent: Thursday, June 18, 2015 7:04
> >> To: gcc-patches@gcc.gnu.org
> >> Cc: benedikt.hu...@theobroma-systems.com;
> philipp.tomsich@theobroma-
> >&g
t the series is always for all data types and on
> >>>> all processors. It would be useful to allow each AArch64 processor
> >>>> to enable this or not depending on the data type. BTW, do you have
> >>>> some tests showing the speed up?
> >>>>
er [mailto:benedikt.hu...@theobroma-systems.com]
>> Sent: Wednesday, June 24, 2015 12:11
>> To: Dr. Philipp Tomsich
>> Cc: Evandro Menezes; gcc-patches@gcc.gnu.org
>> Subject: Re: [PATCH] [aarch64] Implemented reciprocal square root (rsqrt)
>> estimation in -ffast-math
>>
ms.com]
> Sent: Wednesday, June 24, 2015 12:11
> To: Dr. Philipp Tomsich
> Cc: Evandro Menezes; gcc-patches@gcc.gnu.org
> Subject: Re: [PATCH] [aarch64] Implemented reciprocal square root (rsqrt)
> estimation in -ffast-math
>
> Evandro,
>
> Yes, we also have the 1/x approx
gcc.gnu.org [mailto:gcc-patches-ow...@gcc.gnu.org]
>> On
>>> Behalf Of Benedikt Huber
>>> Sent: Thursday, June 18, 2015 7:04
>>> To: gcc-patches@gcc.gnu.org
>>> Cc: benedikt.hu...@theobroma-systems.com; philipp.tomsich@theobroma-
>>> systems.com
>&
;
>> -Original Message-
>> From: gcc-patches-ow...@gcc.gnu.org [mailto:gcc-patches-ow...@gcc.gnu.org]
> On
>> Behalf Of Benedikt Huber
>> Sent: Thursday, June 18, 2015 7:04
>> To: gcc-patches@gcc.gnu.org
>> Cc: benedikt.hu...@theobroma-systems.com; philipp.tom
8, 2015 7:04
> To: gcc-patches@gcc.gnu.org
> Cc: benedikt.hu...@theobroma-systems.com; philipp.tomsich@theobroma-
> systems.com
> Subject: [PATCH] [aarch64] Implemented reciprocal square root (rsqrt)
> estimation in -ffast-math
>
> arch64 offers the instructions frsqrte and
cc.gnu.org
> Cc: benedikt.hu...@theobroma-systems.com;
> philipp.toms...@theobroma-systems.com
> Subject: [PATCH] [aarch64] Implemented reciprocal square root (rsqrt)
> estimation in -ffast-math
>
> arch64 offers the instructions frsqrte and frsqrts, for rsqrt estimation and a
&g
arch64 offers the instructions frsqrte and frsqrts, for rsqrt estimation and
a Newton-Raphson step, respectively.
There are ARMv8 implementations where this is faster than using fdiv and rsqrt.
It runs three steps for double and two steps for float to achieve the needed
precision.
There is one ca
34 matches
Mail list logo
