<html xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns="http://www.w3.org/TR/REC-html40"><head><meta http-equiv=Content-Type content="text/html; charset=utf-8"><meta name=Generator content="Microsoft Word 15 (filtered medium)"><style><!--
/* Font Definitions */
@font-face
        {font-family:"Cambria Math";
        panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
        {font-family:Calibri;
        panose-1:2 15 5 2 2 2 4 3 2 4;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
        {margin:0cm;
        margin-bottom:.0001pt;
        font-size:12.0pt;
        font-family:"Times New Roman",serif;}
a:link, span.MsoHyperlink
        {mso-style-priority:99;
        color:blue;
        text-decoration:underline;}
a:visited, span.MsoHyperlinkFollowed
        {mso-style-priority:99;
        color:purple;
        text-decoration:underline;}
p.MsoListParagraph, li.MsoListParagraph, div.MsoListParagraph
        {mso-style-priority:34;
        margin-top:0cm;
        margin-right:0cm;
        margin-bottom:0cm;
        margin-left:36.0pt;
        margin-bottom:.0001pt;
        font-size:12.0pt;
        font-family:"Times New Roman",serif;}
span.EmailStyle17
        {mso-style-type:personal-reply;
        font-family:"Calibri",sans-serif;
        color:#1F497D;}
.MsoChpDefault
        {mso-style-type:export-only;
        font-family:"Calibri",sans-serif;
        mso-fareast-language:EN-US;}
@page WordSection1
        {size:612.0pt 792.0pt;
        margin:72.0pt 72.0pt 72.0pt 72.0pt;}
div.WordSection1
        {page:WordSection1;}
/* List Definitions */
@list l0
        {mso-list-id:597057307;
        mso-list-type:hybrid;
        mso-list-template-ids:2103471676 201916433 201916441 201916443 201916431 201916441 201916443 201916431 201916441 201916443;}
@list l0:level1
        {mso-level-text:"%1\)";
        mso-level-tab-stop:none;
        mso-level-number-position:left;
        text-indent:-18.0pt;}
@list l0:level2
        {mso-level-number-format:alpha-lower;
        mso-level-tab-stop:none;
        mso-level-number-position:left;
        text-indent:-18.0pt;}
@list l0:level3
        {mso-level-number-format:roman-lower;
        mso-level-tab-stop:none;
        mso-level-number-position:right;
        text-indent:-9.0pt;}
@list l0:level4
        {mso-level-tab-stop:none;
        mso-level-number-position:left;
        text-indent:-18.0pt;}
@list l0:level5
        {mso-level-number-format:alpha-lower;
        mso-level-tab-stop:none;
        mso-level-number-position:left;
        text-indent:-18.0pt;}
@list l0:level6
        {mso-level-number-format:roman-lower;
        mso-level-tab-stop:none;
        mso-level-number-position:right;
        text-indent:-9.0pt;}
@list l0:level7
        {mso-level-tab-stop:none;
        mso-level-number-position:left;
        text-indent:-18.0pt;}
@list l0:level8
        {mso-level-number-format:alpha-lower;
        mso-level-tab-stop:none;
        mso-level-number-position:left;
        text-indent:-18.0pt;}
@list l0:level9
        {mso-level-number-format:roman-lower;
        mso-level-tab-stop:none;
        mso-level-number-position:right;
        text-indent:-9.0pt;}
ol
        {margin-bottom:0cm;}
ul
        {margin-bottom:0cm;}
--></style><!--[if gte mso 9]><xml>
<o:shapedefaults v:ext="edit" spidmax="1026" />
</xml><![endif]--><!--[if gte mso 9]><xml>
<o:shapelayout v:ext="edit">
<o:idmap v:ext="edit" data="1" />
</o:shapelayout></xml><![endif]--></head><body lang=EN-AU link=blue vlink=purple><div class=WordSection1><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D;mso-fareast-language:EN-US'>I am thinking that this may not be as useful as I’d hoped…<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D;mso-fareast-language:EN-US'><o:p> </o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D;mso-fareast-language:EN-US'>Short Answer:<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D;mso-fareast-language:EN-US'>I am finding new opcodes on the old system all over the place, so this is not necessarily an indication of an issue they are more like a “smell” that may or maynot indicate something is off<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D;mso-fareast-language:EN-US'><o:p> </o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D;mso-fareast-language:EN-US'>Long Answer:<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D;mso-fareast-language:EN-US'><o:p> </o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D;mso-fareast-language:EN-US'>Even if code is compile on an old system it will not necessarily run on that old system if the source code explicitly users new features e.g.<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D;mso-fareast-language:EN-US'>http://www.codeproject.com/Articles/874396/Crunching-Numbers-with-AVX-and-AVX<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D;mso-fareast-language:EN-US'>]$ gcc -mavx -o hello_avx hello_avx.c<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D;mso-fareast-language:EN-US'>]$ ./hello_avx<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D;mso-fareast-language:EN-US'>Illegal instruction<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D;mso-fareast-language:EN-US'><o:p> </o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D;mso-fareast-language:EN-US'>Yes – opcodes.sh will find the issue…<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D;mso-fareast-language:EN-US'>]$ objdump -D -M intel hello_avx | ~/opcode.sh -s AVX -m 2<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D;mso-fareast-language:EN-US'>  40058d:       c5 fa 10 45 a0          vmovss xmm0,DWORD PTR [rbp-0x60]<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D;mso-fareast-language:EN-US'>  400598:       c4 e3 79 21 95 ec fe    vinsertps xmm2,xmm0,DWORD PTR [rbp-0x114],0x10<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D;mso-fareast-language:EN-US'><o:p> </o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D;mso-fareast-language:EN-US'>However there are lots of system libraries on the old system that have new opcodes…<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D;mso-fareast-language:EN-US'><o:p> </o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D;mso-fareast-language:EN-US'>objdump -D -M intel /usr/lib64/libfreetype.so.6  | ~/opcode.sh -s AVX<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D;mso-fareast-language:EN-US'>  3d51800aa6:   f3 c5 09 67 2a          repz vpackuswb xmm13,xmm14,XMMWORD PTR [rdx]<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D;mso-fareast-language:EN-US'>  3d5180b691:   c5 a9 51 3d 00 00 00    vsqrtpd xmm7,XMMWORD PTR [rip+0x7000000]        # 3d5880b699 <_end+0x6d6efe9><o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D;mso-fareast-language:EN-US'>  3d5180b6a9:   c5 a9 51 3d 00 00 00    vsqrtpd xmm7,XMMWORD PTR [rip+0x7000000]        # 3d5880b6b1 <_end+0x6d6f001><o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D;mso-fareast-language:EN-US'>  3d5180b6c1:   c5 a9 51 3d 00 00 00    vsqrtpd xmm7,XMMWORD PTR [rip+0x7000000]        # 3d5880b6c9 <_end+0x6d6f019><o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D;mso-fareast-language:EN-US'>  3d5180b6f1:   c5 a9 51 3d 00 00 00    vsqrtpd xmm7,XMMWORD PTR [rip+0x7000000]        # 3d5880b6f9 <_end+0x6d6f049><o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D;mso-fareast-language:EN-US'><o:p> </o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D;mso-fareast-language:EN-US'>So I am guessing that things like freetype are built to support multiple architectures and contain opcodes that never get hit.<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D;mso-fareast-language:EN-US'><o:p> </o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D;mso-fareast-language:EN-US'>Interestingly dmesg has more info on the issue so that might be a better avenue for alerts of software not running correctly…<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D;mso-fareast-language:EN-US'><o:p> </o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D;mso-fareast-language:EN-US'>dmesg<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D;mso-fareast-language:EN-US'>hello_avx[11258] trap invalid opcode ip:40058d sp:7fffca0f34c0 error:0 in hello_avx[400000+1000]<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D;mso-fareast-language:EN-US'><o:p> </o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D;mso-fareast-language:EN-US'>Cheers,<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D;mso-fareast-language:EN-US'><o:p> </o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D;mso-fareast-language:EN-US'>Paul<o:p></o:p></span></p><p class=MsoNormal><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D;mso-fareast-language:EN-US'><o:p> </o:p></span></p><p class=MsoNormal><b><span lang=EN-US style='font-size:11.0pt;font-family:"Calibri",sans-serif'>From:</span></b><span lang=EN-US style='font-size:11.0pt;font-family:"Calibri",sans-serif'> Peter St. John [mailto:peter.st.john@gmail.com] <br><b>Sent:</b> Friday, 6 May 2016 9:46 AM<br><b>To:</b> Paul McIntosh <paul.mcintosh@monash.edu><br><b>Subject:</b> Re: [Beowulf] Detecting binaries that are limited to an architecture?<o:p></o:p></span></p><p class=MsoNormal><o:p> </o:p></p><div><p class=MsoNormal>If you ran the compiler (for your current target architecture) on the assembler (from decompiling the binaries you want to port) you'd get error messages, but I've never done that myself<o:p></o:p></p><div><p class=MsoNormal>Peter<o:p></o:p></p></div></div><div><p class=MsoNormal><o:p> </o:p></p><div><p class=MsoNormal>On Thu, May 5, 2016 at 6:39 PM, Paul McIntosh <<a href="mailto:paul.mcintosh@monash.edu" target="_blank">paul.mcintosh@monash.edu</a>> wrote:<o:p></o:p></p><blockquote style='border:none;border-left:solid #CCCCCC 1.0pt;padding:0cm 0cm 0cm 6.0pt;margin-left:4.8pt;margin-right:0cm'><div><div><p class=MsoNormal style='mso-margin-top-alt:auto;mso-margin-bottom-alt:auto'><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D'>Yes – tried that and it gets the opcodes but then I am back to the issue of not knowing which opcodes are related to which architecture. My current train of though is finding something in the gcc install that works out generating the opcodes for an architecture and see if it can be used to reverse them.</span><o:p></o:p></p><p class=MsoNormal style='mso-margin-top-alt:auto;mso-margin-bottom-alt:auto'><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D'> </span><o:p></o:p></p><p class=MsoNormal style='mso-margin-top-alt:auto;mso-margin-bottom-alt:auto'><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D'>Paul</span><o:p></o:p></p><p class=MsoNormal style='mso-margin-top-alt:auto;mso-margin-bottom-alt:auto'><span style='font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D'> </span><o:p></o:p></p><p class=MsoNormal style='mso-margin-top-alt:auto;mso-margin-bottom-alt:auto'><b><span lang=EN-US style='font-size:11.0pt;font-family:"Calibri",sans-serif'>From:</span></b><span lang=EN-US style='font-size:11.0pt;font-family:"Calibri",sans-serif'> Peter St. John [mailto:<a href="mailto:peter.st.john@gmail.com" target="_blank">peter.st.john@gmail.com</a>] <br><b>Sent:</b> Friday, 6 May 2016 7:23 AM<br><b>To:</b> Paul McIntosh <<a href="mailto:paul.mcintosh@monash.edu" target="_blank">paul.mcintosh@monash.edu</a>><br><b>Cc:</b> Beowulf List <<a href="mailto:beowulf@beowulf.org" target="_blank">beowulf@beowulf.org</a>><br><b>Subject:</b> Re: [Beowulf] Detecting binaries that are limited to an architecture?</span><o:p></o:p></p><div><div><p class=MsoNormal style='mso-margin-top-alt:auto;mso-margin-bottom-alt:auto'> <o:p></o:p></p><div><p class=MsoNormal style='mso-margin-top-alt:auto;mso-margin-bottom-alt:auto'>You might run it through a decompiler; then you'd be looking at the assembler at least.<o:p></o:p></p><div><p class=MsoNormal style='mso-margin-top-alt:auto;mso-margin-bottom-alt:auto'>Peter<o:p></o:p></p></div></div><div><p class=MsoNormal style='mso-margin-top-alt:auto;mso-margin-bottom-alt:auto'> <o:p></o:p></p><div><p class=MsoNormal style='mso-margin-top-alt:auto;mso-margin-bottom-alt:auto'>On Thu, May 5, 2016 at 4:51 PM, Paul McIntosh <<a href="mailto:paul.mcintosh@monash.edu" target="_blank">paul.mcintosh@monash.edu</a>> wrote:<o:p></o:p></p><blockquote style='border:none;border-left:solid #CCCCCC 1.0pt;padding:0cm 0cm 0cm 6.0pt;margin-left:4.8pt;margin-top:5.0pt;margin-right:0cm;margin-bottom:5.0pt'><p class=MsoNormal style='mso-margin-top-alt:auto;mso-margin-bottom-alt:auto'>All,<br><br>I am wondering if there is an easy way to detect if a binary makes use of<br>opcodes which are not available on a specific architecture?<br><br>We have /usr/local mounted across nodes with some Intel Xeon X5650<br>(Westmere) and some E5-2670 (SandyBridge). Some code spits out "Illegal<br>Instruction" when run on the old nodes and it appears to be due to hitting<br>shared libraries compiled on the newer nodes. We are going to have a similar<br>situation on the newer clusters also.<br><br>I have been putting together a test suite for our software stack and would<br>like to add the ability to sanity check binaries for such errors. I thought<br>there would be easy way to do this by looking at the opcodes (objdump) and<br>comparing them to what the architecture provides. However this requires<br>knowing all the opcodes from Intel manuals for a chip.<br><br>I have be playing with opcode.sh<br>(<a href="https://gist.github.com/rindeal/72af275f05d44e10ebca" target="_blank">https://gist.github.com/rindeal/72af275f05d44e10ebca</a>) which looks promising<br>but will need a bit of manual work to get it to do what I want (and still<br>may be incomplete/inaccurate).<br><br>Has anyone done this? Know of a way to easily get a computer readable list<br>of opcodes per cpu (note /proc/cpuinfo flags just shows features not<br>opecodes)?<br><br>Cheers,<br><br>Paul<br>--<br>Dr Paul McIntosh<br>  Senior HPC Consultant, Technical Lead,<br>    Multi-modal Australian ScienceS Imaging and Visualisation Environment<br>(<a href="http://www.massive.org.au" target="_blank">www.massive.org.au</a>)<br>       Monash University, Ph: 9902 0439 Mob: 0434 524935<br><br><br><br>_______________________________________________<br>Beowulf mailing list, <a href="mailto:Beowulf@beowulf.org" target="_blank">Beowulf@beowulf.org</a> sponsored by Penguin Computing<br>To change your subscription (digest mode or unsubscribe) visit <a href="http://www.beowulf.org/mailman/listinfo/beowulf" target="_blank">http://www.beowulf.org/mailman/listinfo/beowulf</a><o:p></o:p></p></blockquote></div><p class=MsoNormal style='mso-margin-top-alt:auto;mso-margin-bottom-alt:auto'> <o:p></o:p></p></div></div></div></div></div></blockquote></div><p class=MsoNormal><o:p> </o:p></p></div></div></body></html>