diff options
author | Andreas Baumann <abaumann@yahoo.com> | 2009-02-21 22:22:00 +0100 |
---|---|---|
committer | Andreas Baumann <abaumann@yahoo.com> | 2009-02-21 22:22:00 +0100 |
commit | bdb2a7d1d2ba1ea54782475c134b1e3018f80db4 (patch) | |
tree | 4cbc39a06a2a8e7f3c1ac5813493397426d44a84 /docs/port | |
parent | 625dccff9867b97e0de3230e86a3d3bd45d361df (diff) | |
download | wolfbones-bdb2a7d1d2ba1ea54782475c134b1e3018f80db4.tar.gz wolfbones-bdb2a7d1d2ba1ea54782475c134b1e3018f80db4.tar.bz2 |
added documentation for iic
Diffstat (limited to 'docs/port')
-rw-r--r-- | docs/port/icc_vec0_remarks.txt | 167 |
1 files changed, 167 insertions, 0 deletions
diff --git a/docs/port/icc_vec0_remarks.txt b/docs/port/icc_vec0_remarks.txt new file mode 100644 index 0000000..d9f5b2d --- /dev/null +++ b/docs/port/icc_vec0_remarks.txt @@ -0,0 +1,167 @@ + #[1]PDF version [2]alternate + +Re: BLOCK WAS VECTORIZED. + __________________________________________________________________ + + * From: Steve Lionel <[3]steve.lionel@xxxxxxxxxxxxx> + * Date: Sat, 20 Sep 2008 14:22:31 GMT + __________________________________________________________________ + + Fatemeh wrote: + + Dear all + when I compile my code I see the following lines: + main-goodformat2.f90(71): (col. 7) remark: BLOCK WAS VECTORIZED. + main-goodformat2.f90(71): (col. 7) remark: BLOCK WAS VECTORIZED. + main-goodformat2.f90(82): (col. 8) remark: BLOCK WAS VECTORIZED. + main-goodformat2.f90(82): (col. 8) remark: BLOCK WAS VECTORIZED. + main-goodformat2.f90(143): (col. 7) remark: BLOCK WAS VECTORIZED. + main-goodformat2.f90(144): (col. 7) remark: BLOCK WAS VECTORIZED. + main-goodformat2.f90(144): (col. 7) remark: BLOCK WAS VECTORIZED. + main-goodformat2.f90(147): (col. 7) remark: BLOCK WAS VECTORIZED. + Can these lines cause error in the result? + + No - they are optimization information messages from the compiler + letting you know that it figured out it could use vector instructions + to perform as many as four operations in one instruction. That they + appear by default is somewhat historical. + You are using the Intel compiler, which has offered vectorization for + many years, but in the past you had to explicitly specify an option to + request use of the vector instructions. As of version 10 on x64, and + the upcoming version 11 on IA-32, the compiler assumes it is ok to + generate SSE2 instructions which have been supported since the Pentium + 4. All x64 processors and all Intel-based Mac processors support SSE2, + for IA-32 the compiler has a switch to restrict it to generic "Pentium" + instructions (-mia32 on Linux, /arch:ia32 on Windows.) + I can understand your surprise at seeing messages like this when the + normal course of events is no messages unless there is an error. I + expect we'll see more questions such as yours in the future and I'll + suggest to the product team that we turn off the vectorization messages + by default. If you want to turn them off, use -vec-report0 on Linux and + Mac, and /Qvec-report0 on Windows. + -- + Steve Lionel + Developer Products Division + Intel Corporation + Nashua, NH + For email address, replace "invalid" with "com" + User communities for Intel Software Development Products + [4]http://softwareforums.intel.com/ + Intel Fortran Support + [5]http://support.intel.com/support/performancetools/fortran + My Fortran blog + [6]http://www.intel.com/software/drfortran + . + __________________________________________________________________ + + * Follow-Ups: + + [7]Re: BLOCK WAS VECTORIZED. + o From: glen herrmannsfeldt + + * References: + + [8]BLOCK WAS VECTORIZED. + o From: Fatemeh + + * Prev by Date: [9]Re: Praise for Gfortran (finally) + * Next by Date: [10]Re: Praise for Gfortran (finally) + * Previous by thread: [11]BLOCK WAS VECTORIZED. + * Next by thread: [12]Re: BLOCK WAS VECTORIZED. + * Index(es): + + [13]Date + + [14]Thread + __________________________________________________________________ + +Relevant Pages + + * [15]Re: Force SMS Client reinstall / repair remotely + ... When I was refering to the sms actions, I was meaning inside + the control ... item: Remark ... item: Get Registry Key Value ... + item: Compiler Variable End ... + (microsoft.public.sms.admin) + * [16]Re: Making a program quicker tips... + ... "Chris Mantoulidis" wrote in message ... compiler, a different + version of the same compiler, a different platform, ... And re your + remark in your original post about using 'if': ... + (comp.lang.cpp) + * [17]Re: A fast way to get snapshot from matlab + ... No remark about my problem? ... If you lie to the compiler, it + will get its revenge. ... -- Henry Spencer ... + (comp.soft-sys.matlab) + * [18]Re: Why is Firefox such a beast?? + ... instructions for use embedded in it. ... sign is a "remark" and + is ignored by the program. ... # If you want to present a special + hostname in error messages, ... tag is visible_hostname. ... + (Fedora) + * [19]Re: FizzBuzz (#126) + ... Not intended to be rude, but is just a little remark on how + much you ... should follow instructions when working. ... the + ability of the programmer, but it's important if you want to know + ... + (comp.lang.ruby) + __________________________________________________________________ + + We are proud to have [20]Web Hosting and Rack Housing from 9 Net Avenue + Deutschland. + (10) + + [21]derkeiler.com + + * [22]Security + * [23]UNIX + * [24]Linux + * [25]Coding + * [26]Usenet + + * [27]Archive + * [28]About + * [29]Privacy + * [30]Search + * [31]Imprint + + Path: [32]coding.derkeiler.com > [33]Archive > [34]Fortran + > [35]comp.lang.fortran > [36]2008-09 [37] Print as PDF [38] RSS + Feed + + [39]Quantcast + +References + + 1. http://coding.derkeiler.com/pdf/Archive/Fortran/comp.lang.fortran/2008-09/msg00427.pdf + 2. http://coding.derkeiler.com/Archive/Fortran/comp.lang.fortran/rss.xml + 3. mailto:steve.lionel@DOMAIN.HIDDEN + 4. http://softwareforums.intel.com/ + 5. http://support.intel.com/support/performancetools/fortran + 6. http://www.intel.com/software/drfortran + 7. http://coding.derkeiler.com/Archive/Fortran/comp.lang.fortran/2008-09/msg00429.html + 8. http://coding.derkeiler.com/Archive/Fortran/comp.lang.fortran/2008-09/msg00425.html + 9. http://coding.derkeiler.com/Archive/Fortran/comp.lang.fortran/2008-09/msg00426.html + 10. http://coding.derkeiler.com/Archive/Fortran/comp.lang.fortran/2008-09/msg00428.html + 11. http://coding.derkeiler.com/Archive/Fortran/comp.lang.fortran/2008-09/msg00425.html + 12. http://coding.derkeiler.com/Archive/Fortran/comp.lang.fortran/2008-09/msg00429.html + 13. http://coding.derkeiler.com/Archive/Fortran/comp.lang.fortran/2008-09/maillist.html#00427 + 14. http://coding.derkeiler.com/Archive/Fortran/comp.lang.fortran/2008-09/threads.html#00427 + 15. http://www.tech-archive.net/Archive/SMS/microsoft.public.sms.admin/2006-06/msg00171.html + 16. http://coding.derkeiler.com/Archive/C_CPP/comp.lang.cpp/2004-02/1388.html + 17. http://newsgroups.derkeiler.com/Archive/Comp/comp.soft-sys.matlab/2007-06/msg03775.html + 18. http://linux.derkeiler.com/Mailing-Lists/Fedora/2008-10/msg00677.html + 19. http://newsgroups.derkeiler.com/Archive/Comp/comp.lang.ruby/2007-06/msg00457.html + 20. http://www.9na.de/ + 21. http://coding.derkeiler.com/ + 22. http://www.derkeiler.com/ + 23. http://unix.derkeiler.com/ + 24. http://linux.derkeiler.com/ + 25. http://coding.derkeiler.com/ + 26. http://newsgroups.derkeiler.com/ + 27. http://coding.derkeiler.com/Archive/ + 28. http://www.derkeiler.com/about/ + 29. http://coding.derkeiler.com/privacy/ + 30. http://coding.derkeiler.com/search/ + 31. http://www.derkeiler.com/about/imprint + 32. http://coding.derkeiler.com/ + 33. http://coding.derkeiler.com/Archive/ + 34. http://coding.derkeiler.com/Archive/Fortran/ + 35. http://coding.derkeiler.com/Archive/Fortran/comp.lang.fortran/ + 36. http://coding.derkeiler.com/Archive/Fortran/comp.lang.fortran/2008-09/ + 37. http://coding.derkeiler.com/pdf/Archive/Fortran/comp.lang.fortran/2008-09/msg00427.pdf + 38. http://coding.derkeiler.com/Archive/Fortran/comp.lang.fortran/rss.xml + 39. http://www.quantcast.com/p-abMz3F92T4IJ2 |