<?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>LPC MicrocontrollersのトピックRe: Optimisation of CMSIS constants for cortex M4</title>
    <link>https://community.nxp.com/t5/LPC-Microcontrollers/Optimisation-of-CMSIS-constants-for-cortex-M4/m-p/1458375#M48768</link>
    <description>&lt;P&gt;&lt;EM&gt;&amp;gt; Is there any way to optimize these constants or is there any code optimized fft library for this microcontroller.&lt;/EM&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;Optimize for what ?&amp;nbsp;&lt;/SPAN&gt;&lt;SPAN&gt;You can either optimize for speed, for size, or a mixture (=compromise) of both.&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;The usage of the named pre-calculated constants for FFT is a speed optimization of that algorithm.&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;You can try implementing any other FFT algorithm, if you wish. But be aware of the limitations of "float" versus "double".&lt;/SPAN&gt;&lt;/P&gt;</description>
    <pubDate>Mon, 16 May 2022 05:12:35 GMT</pubDate>
    <dc:creator>frank_m</dc:creator>
    <dc:date>2022-05-16T05:12:35Z</dc:date>
    <item>
      <title>Optimisation of CMSIS constants for cortex M4</title>
      <link>https://community.nxp.com/t5/LPC-Microcontrollers/Optimisation-of-CMSIS-constants-for-cortex-M4/m-p/1458345#M48765</link>
      <description>&lt;P&gt;Hi,&lt;/P&gt;&lt;P&gt;I am using&amp;nbsp;CMSIS library for FFT computation in LPC54607J256BD208E.&lt;/P&gt;&lt;P&gt;IDE: MCXpresso IDE v 10.3.1_2233&lt;/P&gt;&lt;P&gt;I am trying to optimize my code size to fit a bootloader along with application code.&lt;/P&gt;&lt;P&gt;On analysis of Map size, I found that cmsis fft constants take up a lot spcae.&lt;/P&gt;&lt;TABLE width="208"&gt;&lt;TBODY&gt;&lt;TR&gt;&lt;TD width="144"&gt;Constants&lt;/TD&gt;&lt;TD width="64"&gt;Size&lt;/TD&gt;&lt;/TR&gt;&lt;TR&gt;&lt;TD&gt;twiddleCoef_2048&lt;/TD&gt;&lt;TD&gt;16384&lt;/TD&gt;&lt;/TR&gt;&lt;TR&gt;&lt;TD&gt;twiddleCoef_rfft_4096&lt;/TD&gt;&lt;TD&gt;16384&lt;/TD&gt;&lt;/TR&gt;&lt;TR&gt;&lt;TD&gt;twiddleCoef_rfft_2048&lt;/TD&gt;&lt;TD&gt;8192&lt;/TD&gt;&lt;/TR&gt;&lt;TR&gt;&lt;TD&gt;twiddleCoef_1024&lt;/TD&gt;&lt;TD&gt;8192&lt;/TD&gt;&lt;/TR&gt;&lt;TR&gt;&lt;TD&gt;armBitRevIndexTable2048&lt;/TD&gt;&lt;TD&gt;7616&lt;/TD&gt;&lt;/TR&gt;&lt;TR&gt;&lt;TD&gt;twiddleCoef_512&lt;/TD&gt;&lt;TD&gt;4096&lt;/TD&gt;&lt;/TR&gt;&lt;TR&gt;&lt;TD&gt;twiddleCoef_rfft_1024&lt;/TD&gt;&lt;TD&gt;4096&lt;/TD&gt;&lt;/TR&gt;&lt;TR&gt;&lt;TD&gt;armBitRevIndexTable1024&lt;/TD&gt;&lt;TD&gt;3600&lt;/TD&gt;&lt;/TR&gt;&lt;TR&gt;&lt;TD&gt;twiddleCoef_256&lt;/TD&gt;&lt;TD&gt;2048&lt;/TD&gt;&lt;/TR&gt;&lt;TR&gt;&lt;TD&gt;twiddleCoef_rfft_512&lt;/TD&gt;&lt;TD&gt;2048&lt;/TD&gt;&lt;/TR&gt;&lt;TR&gt;&lt;TD&gt;Total&lt;/TD&gt;&lt;TD&gt;72656&lt;/TD&gt;&lt;/TR&gt;&lt;/TBODY&gt;&lt;/TABLE&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Is there any way to optimize these constants or is there any code optimized fft library for this microcontroller.&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Thanks and best regards,&lt;/P&gt;&lt;P&gt;Prasanna&lt;/P&gt;</description>
      <pubDate>Mon, 16 May 2022 04:04:25 GMT</pubDate>
      <guid>https://community.nxp.com/t5/LPC-Microcontrollers/Optimisation-of-CMSIS-constants-for-cortex-M4/m-p/1458345#M48765</guid>
      <dc:creator>prasannanaik</dc:creator>
      <dc:date>2022-05-16T04:04:25Z</dc:date>
    </item>
    <item>
      <title>Re: Optimisation of CMSIS constants for cortex M4</title>
      <link>https://community.nxp.com/t5/LPC-Microcontrollers/Optimisation-of-CMSIS-constants-for-cortex-M4/m-p/1458375#M48768</link>
      <description>&lt;P&gt;&lt;EM&gt;&amp;gt; Is there any way to optimize these constants or is there any code optimized fft library for this microcontroller.&lt;/EM&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;Optimize for what ?&amp;nbsp;&lt;/SPAN&gt;&lt;SPAN&gt;You can either optimize for speed, for size, or a mixture (=compromise) of both.&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;The usage of the named pre-calculated constants for FFT is a speed optimization of that algorithm.&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;You can try implementing any other FFT algorithm, if you wish. But be aware of the limitations of "float" versus "double".&lt;/SPAN&gt;&lt;/P&gt;</description>
      <pubDate>Mon, 16 May 2022 05:12:35 GMT</pubDate>
      <guid>https://community.nxp.com/t5/LPC-Microcontrollers/Optimisation-of-CMSIS-constants-for-cortex-M4/m-p/1458375#M48768</guid>
      <dc:creator>frank_m</dc:creator>
      <dc:date>2022-05-16T05:12:35Z</dc:date>
    </item>
  </channel>
</rss>

