Re: PCI Interrupt and Acknowledgement

[Kevin Normoyle <Kevin.Normoyle@Sun.COM>]

use another OS?

Are you using some variant of Windows?

I thought people have done analyses showing worst-case 100 millisecond
interrupt latency on windows systems? (might be dated info)

interesting paper here ('99) talking about the new (at the time) Windows
Driver Model 

http://www.usenix.org/publications/library/proceedings/osdi99/full_papers/cota/c
ota_html/cota.html

Look at Table 3 "Windows 98 Interrupt and Thread Latencies"

Breaks down the contributors to latency.


Figure 5 is good too. (note the effect of an app like a virus scanner
on latencies)

references another paper from 9/98 (similar info)

ftp://download.intel.com/ial/sm/Win98Lat.pdf


I have no idea what newer windows oses provide in this area.

-kevin

> Resent-Date: Mon, 4 Feb 2002 04:34:29 -0800
> X-Authentication-Warning: electra.znyx.com: list set sender to 
pci-sig-request@znyx.com using -f
> To: <pci-sig@znyx.com>
> Subject: PCI Interrupt and Acknowledgement
> MIME-Version: 1.0
> X-Priority: 3 (Normal)
> X-MSMail-Priority: Normal
> Disposition-Notification-To: "I. Servan Uzun" <isu@btae.mam.gov.tr>
> X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2600.0000
> X-MIMETrack: Itemize by SMTP Server on rollsroyce/Znyx(Release 5.0.7 |March 
21, 2001) at 02/04/2002 04:17:47 AM, Serialize by Router on 
rollsroyce/Znyx(Release 5.0.7 |March 21, 2001) at 02/04/2002 04:17:47 AM, 
Serialize complete at 02/04/2002 04:17:47 AM
> Content-Transfer-Encoding: 7bit
> Resent-Message-ID: <hKQMJ.A.K2F.1ynX8@electra>
> Resent-From: pci-sig@znyx.com
> X-Mailing-List: <pci-sig@znyx.com> archive/latest/8575
> X-Loop: pci-sig@znyx.com
> Resent-Sender: pci-sig-request@znyx.com
> 
> Hi,
> 
> I am using Altera' s 64-bit 66MHz PCI Megacore in my project.
> I implemented an interrrupt & acknowledgement logic as follows,
> 
>     1-) When the process is completed, an interrupt signal is
> generated and fed to pci megacore function.
>     2-) When my software that is running on the computer catches the
> pci interrrupt, it sets a predefined bit of a register (in fpga) in order to
> acknowledge the interrupt.
>     3-) When I check this timing by a logic analyzer, I found that it is
> 8 microseconds between the rising edge of the interrupt signal and the
> rising edge of int-acknowledge signal. This means that it takes 8 usec
> to acknowledge the interrupt.
> 
> My question is that is this time is normal or long? Is it possible to
> shorten
> this interrupt acknowledgement time?
> 
> Thanks in advance.
> 
> - Servan
> 
> 
>