This is the mail archive of the libc-alpha@sourceware.org mailing list for the glibc project.

Index Nav:	[Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav:	[Date Prev] [Date Next]	[Thread Prev] [Thread Next]
Other format:	[Raw text]

Re: [PATCH] Faster x^(2^m) for mpexp using __sqr

From: Andreas Jaeger <aj at suse dot com>
To: libc-alpha at sourceware dot org
Cc: Siddhesh Poyarekar <siddhesh at redhat dot com>, rsa at us dot ibm dot com
Date: Wed, 13 Feb 2013 09:05:58 +0100
Subject: Re: [PATCH] Faster x^(2^m) for mpexp using __sqr
References: <20130212074031.GA15748@spoyarek.pnq.redhat.com> <20130212143442.GJ15748@spoyarek.pnq.redhat.com>

On Tuesday, February 12, 2013 20:04:42 Siddhesh Poyarekar wrote:
> Sorry, there was a stray bit of code that I forgot to remove in the
> previous patch.  Here's the updated patch; everything else remains the
> same.


Thanks, this is fine.

I noticed that there's some other code in dbl-64 that does squaring and 
could use __sqr instead of __mul, e.g.:
sysdeps/ieee754/dbl-64/sincos32.c:  __mul(x,x,&x2,p);
sysdeps/ieee754/dbl-64/mpatan.c:    __mul(x,x,&mpsm,p);
sysdeps/ieee754/dbl-64/mpsqrt.c:    __mul(&mpu,&mpu,&mpt1,p);

Could you check whether using __sqr in those - and perhaps other cases 
helps as well?

Andreas
-- 
 Andreas Jaeger aj@{suse.com,opensuse.org} Twitter/Identica: jaegerandi
  SUSE LINUX Products GmbH, Maxfeldstr. 5, 90409 Nürnberg, Germany
   GF: Jeff Hawn,Jennifer Guild,Felix Imendörffer,HRB16746 (AG Nürnberg)
    GPG fingerprint = 93A3 365E CE47 B889 DF7F  FED1 389A 563C C272 A126

Follow-Ups:
- Re: [PATCH] Faster x^(2^m) for mpexp using __sqr
  - From: Siddhesh Poyarekar

References:
- [PATCH] Faster x^(2^m) for mpexp using __sqr
  - From: Siddhesh Poyarekar
- Re: [PATCH] Faster x^(2^m) for mpexp using __sqr
  - From: Siddhesh Poyarekar

Index Nav:	[Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav:	[Date Prev] [Date Next]	[Thread Prev] [Thread Next]