<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>ColdFire/68K Microcontrollers and ProcessorsのトピックRe: MCF52259 -- errata?  Address fetch speculation?</title>
    <link>https://community.nxp.com/t5/ColdFire-68K-Microcontrollers/MCF52259-errata-Address-fetch-speculation/m-p/148617#M3625</link>
    <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;DIV&gt;&lt;/DIV&gt;&lt;DIV&gt;I'm not really sure the absence in the 52223/52235 reference manual means anything, since both the 52223 and 52235 errata's say:&lt;/DIV&gt;&lt;DIV&gt;&amp;nbsp;&lt;/DIV&gt;&lt;BLOCKQUOTE&gt;&lt;DIV&gt;Use FLASHBAR[6] to enable or disable the address speculation mechanisms of the flash controller. The default configuration (FLASHBAR[6] = 0) enables the address speculation. If FLASHBAR[6] equals 1, address speculation is disabled. Core performance may be degraded from 4% – 9%, depending heavily on application code.&lt;/DIV&gt;&lt;/BLOCKQUOTE&gt;&lt;DIV&gt;So you actually have to *set* a reserved bit in this case, and the stationery startup code does just that.&lt;/DIV&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
    <pubDate>Tue, 03 Feb 2009 21:21:13 GMT</pubDate>
    <dc:creator>RichTestardi</dc:creator>
    <dc:date>2009-02-03T21:21:13Z</dc:date>
    <item>
      <title>MCF52259 -- errata?  Address fetch speculation?</title>
      <link>https://community.nxp.com/t5/ColdFire-68K-Microcontrollers/MCF52259-errata-Address-fetch-speculation/m-p/148615#M3623</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;DIV&gt; &lt;/DIV&gt;&lt;DIV&gt;Hi all,&lt;/DIV&gt;&lt;DIV&gt;&amp;nbsp;&lt;/DIV&gt;&lt;DIV&gt;I noticed in the 52259 stationery that flash address speculation is still disabled in FLASHBAR bit 6.&lt;/DIV&gt;&lt;DIV&gt;&amp;nbsp;&lt;/DIV&gt;&lt;DIV&gt;However, I was unable to find any errata that might indicate this is broken, like in the 52221 or 52233.&lt;/DIV&gt;&lt;DIV&gt;&amp;nbsp;&lt;/DIV&gt;&lt;DIV&gt;&lt;STRONG&gt;Does anyone know if it is safe to turn it on?&lt;/STRONG&gt;&lt;/DIV&gt;&lt;DIV&gt;&amp;nbsp;&lt;/DIV&gt;&lt;DIV&gt;It sure seems to work, and gives an instant 9% performance improvement for my application, on top of the 5% that seems intrinsic in the 52259 already!&lt;/DIV&gt;&lt;DIV&gt;&amp;nbsp;&lt;/DIV&gt;&lt;DIV&gt;(With it turned on, 52221's and 52233's can't even boot my application.)&lt;/DIV&gt;&lt;DIV&gt;&amp;nbsp;&lt;/DIV&gt;&lt;DIV&gt;-- Rich&lt;/DIV&gt;&lt;DIV&gt;&amp;nbsp;&lt;/DIV&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Tue, 03 Feb 2009 12:27:47 GMT</pubDate>
      <guid>https://community.nxp.com/t5/ColdFire-68K-Microcontrollers/MCF52259-errata-Address-fetch-speculation/m-p/148615#M3623</guid>
      <dc:creator>RichTestardi</dc:creator>
      <dc:date>2009-02-03T12:27:47Z</dc:date>
    </item>
    <item>
      <title>Re: MCF52259 -- errata?  Address fetch speculation?</title>
      <link>https://community.nxp.com/t5/ColdFire-68K-Microcontrollers/MCF52259-errata-Address-fetch-speculation/m-p/148616#M3624</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;DIV&gt;&lt;/DIV&gt;Hi Rich,&lt;BR /&gt;&lt;BR /&gt;If the AFS bit still in the Reference Manual, I guess it works, because there's no AFS anymore in the MCF52235RM/MCR52223RM (bit 7-6 reserved, should be cleared).&amp;nbsp; This feature seems to be discarded on kirin2 devices. I don't seen any kirin3 device errata for the moment.&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;Emmanuel&lt;BR /&gt;&lt;DIV&gt;&lt;/DIV&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Tue, 03 Feb 2009 15:57:17 GMT</pubDate>
      <guid>https://community.nxp.com/t5/ColdFire-68K-Microcontrollers/MCF52259-errata-Address-fetch-speculation/m-p/148616#M3624</guid>
      <dc:creator>Nouchi</dc:creator>
      <dc:date>2009-02-03T15:57:17Z</dc:date>
    </item>
    <item>
      <title>Re: MCF52259 -- errata?  Address fetch speculation?</title>
      <link>https://community.nxp.com/t5/ColdFire-68K-Microcontrollers/MCF52259-errata-Address-fetch-speculation/m-p/148617#M3625</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;DIV&gt;&lt;/DIV&gt;&lt;DIV&gt;I'm not really sure the absence in the 52223/52235 reference manual means anything, since both the 52223 and 52235 errata's say:&lt;/DIV&gt;&lt;DIV&gt;&amp;nbsp;&lt;/DIV&gt;&lt;BLOCKQUOTE&gt;&lt;DIV&gt;Use FLASHBAR[6] to enable or disable the address speculation mechanisms of the flash controller. The default configuration (FLASHBAR[6] = 0) enables the address speculation. If FLASHBAR[6] equals 1, address speculation is disabled. Core performance may be degraded from 4% – 9%, depending heavily on application code.&lt;/DIV&gt;&lt;/BLOCKQUOTE&gt;&lt;DIV&gt;So you actually have to *set* a reserved bit in this case, and the stationery startup code does just that.&lt;/DIV&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Tue, 03 Feb 2009 21:21:13 GMT</pubDate>
      <guid>https://community.nxp.com/t5/ColdFire-68K-Microcontrollers/MCF52259-errata-Address-fetch-speculation/m-p/148617#M3625</guid>
      <dc:creator>RichTestardi</dc:creator>
      <dc:date>2009-02-03T21:21:13Z</dc:date>
    </item>
    <item>
      <title>Re: MCF52259 -- errata?  Address fetch speculation?</title>
      <link>https://community.nxp.com/t5/ColdFire-68K-Microcontrollers/MCF52259-errata-Address-fetch-speculation/m-p/148618#M3626</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;Hi Rich&lt;BR /&gt;&lt;BR /&gt;I received confirmation from freescale that the "&lt;B&gt;speculaton bug has been fixed in the MCF5225X&lt;/B&gt;". This means that the workaround is no longer needed for this chip.&lt;BR /&gt;&lt;BR /&gt;Regards&lt;BR /&gt;&lt;BR /&gt;Mark&lt;BR /&gt;&lt;BR /&gt;&lt;A href="http://www.uTasker.com" rel="nofollow" target="_blank"&gt;www.uTasker.com&lt;/A&gt;&lt;BR /&gt;&lt;BR /&gt;&lt;P class="MsoNormal"&gt;&lt;SPAN lang="EN-US" style="font-size: 11pt; font-family: &amp;quot;Courier New&amp;quot;;"&gt;&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;BR /&gt;&lt;BR /&gt; &lt;DIV&gt;&lt;/DIV&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Wed, 04 Feb 2009 06:02:13 GMT</pubDate>
      <guid>https://community.nxp.com/t5/ColdFire-68K-Microcontrollers/MCF52259-errata-Address-fetch-speculation/m-p/148618#M3626</guid>
      <dc:creator>mjbcswitzerland</dc:creator>
      <dc:date>2009-02-04T06:02:13Z</dc:date>
    </item>
    <item>
      <title>Re: MCF52259 -- errata?  Address fetch speculation?</title>
      <link>https://community.nxp.com/t5/ColdFire-68K-Microcontrollers/MCF52259-errata-Address-fetch-speculation/m-p/148619#M3627</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;DIV&gt;&lt;/DIV&gt;&lt;DIV&gt;Awesome, thanks!!!&lt;/DIV&gt;&lt;DIV&gt;&amp;nbsp;&lt;/DIV&gt;&lt;DIV&gt;We broke 100,000 StickOS BASIC statements per second on the MCF52259! :smileyhappy:&lt;/DIV&gt;&lt;DIV&gt;&amp;nbsp;&lt;/DIV&gt;&lt;DIV&gt;-- Rich&lt;/DIV&gt;&lt;DIV&gt;&amp;nbsp;&lt;/DIV&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Wed, 04 Feb 2009 06:13:33 GMT</pubDate>
      <guid>https://community.nxp.com/t5/ColdFire-68K-Microcontrollers/MCF52259-errata-Address-fetch-speculation/m-p/148619#M3627</guid>
      <dc:creator>RichTestardi</dc:creator>
      <dc:date>2009-02-04T06:13:33Z</dc:date>
    </item>
  </channel>
</rss>

