From: Paul Colin Gloster <Colin_Paul_Gloster@ACM.org>
Subject: Re: Numerical calculations: Why not use fixed point types for everything?
Date: Fri, 25 Jan 2013 12:09:05 +0000 (UTC)
Date: 2013-01-25T12:09:05+00:00 [thread overview]
Message-ID: <kdtsl0$83d$1@dont-email.me> (raw)
In-Reply-To: kdcfdq$bfu$1@munin.nbi.dk
On 2013-01-18, Randy Brukardt <randy@rrsoftware.com> sent:
|-----------------------------------------------------------------------------|
|""Adam Beneschan" <adam@irvine.com> wrote in message |
|news:7aeff757-a038-45e0-93d6-bd1d6e02093e@googlegroups.com... |
|... |
|>What I mean is that some processors (including the Pentium) have |
|>instructions |
|>to perform mathematical operations like trig functions, square-root, etc., |
|>on |
|>floating-point numbers, and special hardware to do the computation. |
| |
|We're talking Ada here, and in at least some cases (i.e. Intel processors), |
|at least, those instructions aren't accurate enough to meet the requirements |
|of Annex G for those mathematical operations. So it's unlikely that your |
|compiler would use them (unless of course Annex G isn't supported at all, in |
|which case you have no idea what the math actually does)." |
|-----------------------------------------------------------------------------|
During a VHDL-standardization meeting, David Bishop mentioned that a
widespread, non-VHDL supposed implementation of a mathematical
function was very wrong even within the supposedly supported bitwidth.
|-----------------------------------------------------------------------------|
|"So I find this to be a red herring: most Ada software uses only software |
|trig functions and the like. [. . .] |
| |
|[. . .]" |
|-----------------------------------------------------------------------------|
Recent hardware lacks 128-bit floating-point support regardless of
language. For example, from
HTTP://software.Intel.com/en-us/forums/topic/304052?wapkw=quadruple
:
#####################################################################
#"[. . .] #
# #
# TimP (Intel) #
#Tue, 11/27/2007 - 05:51 #
# #
#ifort real*16 (113 bits precision) is implemented on Xeon CPUs by #
#functions which combine x87 operations, so the performance is quite#
#low [. . .] #
# #
#[. . .]" #
#####################################################################
Similarly from
WWW.PGroup.com/userforum/viewtopic.php?t=127&highlight=double+emulation
:
!-----------------------------------------------------------------------!
!"[. . .] !
! !
!mkcolg !
! !
! !
! !
!Joined: 30 Jun 2004 !
!Posts: 4616 !
!Location: The Portland Group Inc. !
!PostPosted: Tue Dec 14, 2004 2:03 pm Post subject: Reply with quote!
!Hello, !
! !
! !
!At this time we don't plan on supporting REAL*16. This is due to the !
!lack of hardware support and the extreme performance penalty of !
!software emulation. Of course, if we see more demand then we'll !
!reconsider. !
! !
!Thanks, !
!Mat !
! !
![. . .]" !
!-----------------------------------------------------------------------!
Similarly from
HTTP://StackOverflow.com/questions/2799684/x86-64-long-double-precision
:
|__________________________________________________________________|
|"[. . .] |
| |
|x86-64 precision is the same as regular x86. Extended double is 80|
|bits, using the x87 ISA, with 6 padding bytes added. There is no |
|128-bit FP hardware. |
| |
|[. . .] |
| |
|answered May 10 '10 at 0:16 |
|Potatoswatter |
|[. . .] |
| |
|[. . .]" |
|__________________________________________________________________|
next prev parent reply other threads:[~2013-01-25 12:09 UTC|newest]
Thread overview: 47+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-01-17 10:33 Numerical calculations: Why not use fixed point types for everything? Ada novice
2013-01-17 14:40 ` Nasser M. Abbasi
2013-01-17 16:16 ` Adam Beneschan
2013-01-17 17:00 ` Georg Bauhaus
2013-01-17 16:25 ` Adam Beneschan
2013-01-18 9:17 ` Ada novice
2013-01-18 17:24 ` J-P. Rosen
2013-01-18 17:52 ` Jeffrey Carter
2013-01-18 18:15 ` Dennis Lee Bieber
2013-01-18 18:59 ` Adam Beneschan
2013-01-19 4:41 ` Dennis Lee Bieber
2013-01-19 6:26 ` Jeffrey Carter
2013-01-19 14:14 ` Robert A Duff
2013-01-25 12:16 ` Paul Colin Gloster
2013-01-24 10:55 ` Ada novice
2013-01-24 11:47 ` Simon Wright
2013-01-24 14:21 ` Ada novice
2013-01-20 0:05 ` Robin Vowels
2013-01-18 23:06 ` Robin Vowels
2013-01-18 19:09 ` Adam Beneschan
2013-01-18 21:39 ` Randy Brukardt
2013-01-19 7:02 ` Ada novice
2013-01-25 12:09 ` Paul Colin Gloster [this message]
2013-01-25 12:23 ` Paul Colin Gloster
2013-01-28 9:09 ` Ada novice
2013-02-01 10:53 ` Ada novice
2013-02-01 15:01 ` Shark8
2013-02-02 18:55 ` Ada novice
2013-02-03 4:05 ` Shark8
2013-02-04 6:23 ` Ada novice
2013-02-04 6:43 ` Niklas Holsti
2013-02-04 7:27 ` Ada novice
2013-02-04 9:37 ` Niklas Holsti
2013-02-04 10:09 ` Ada novice
2013-02-04 14:24 ` Niklas Holsti
2013-02-04 16:44 ` Jeffrey Carter
2013-02-04 21:12 ` Niklas Holsti
2013-02-04 17:31 ` Robert A Duff
2013-02-04 21:20 ` Niklas Holsti
2013-02-02 21:08 ` Nasser M. Abbasi
2013-02-04 6:17 ` Ada novice
2013-02-05 2:27 ` Randy Brukardt
2013-02-06 7:11 ` Ada novice
2013-02-07 6:03 ` Randy Brukardt
2013-02-07 8:43 ` Shark8
2013-02-08 3:17 ` Randy Brukardt
2013-02-08 6:20 ` Ada novice
replies disabled
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox