C5000 Ultra Low Power DSP

Browse by Tags

C5000 Ultra Low Power DSP

Welcome to the C5000 Ultra Low Power DSP Section of the TI E2E Support Community. Ask questions, share knowledge, explore ideas, and help solve problems with fellow engineers. To post a question, click on the forum tab then "New Post".

Sign In to Post
Tags
You have subscribed to this tag. To view or manage your tag subscriptions, click here.   Close
You have unsubscribed from this tag. To view or manage your tag subscriptions, click here.   Close
You are currently viewing:
DSPLib
Related Posts

  • Forum Post: DSPLib problem

    Anusha James
    Hi, I want to find autocorrelation of a large value sized array of 2000. The code is implemented using intrisics,but the code is extrememly slow.So I was trying DSPLib of C5515 in order to reduce MIPS. I used power function for this which produces a Q31 format number. And the input should be DATA datatype...
    on Oct 10, 2012

  • Forum Post: Re: aliased bins in rfft() results?

    Mark Mckeown
    Hi Brian, The format of the DATA *x array is different for the RFFT() dsplib routine. rfft(DATA *x, ushort nx, type) accepts input in the following format, where DATA *x points to an array of 16-bit signed, real numbers (no complex parts) and nx is the length of the array. x[0] = x(0)Re, x[1] = x(1)Re...
    on Dec 14, 2009

  • Forum Post: efficient 16bit/Q.15 (vector-) multiplication

    Raphael19557
    Hi, does anybody have an example of an efficient implementation of a Q.15 vector multiplication for the C55x DSP? I am thinking about something like the function "mul32" of DSPLIB, but that one is for Q31 vectors. Or is there an efficient way to use the mul32 function for Q.15 vectors...
    on Dec 23, 2009

  • Forum Post: Re: Brainstorming: Strange Behaviour of MOV and ADD

    Hyun Kim
    Dear Michael, First of all, I thank you for very detail explantion of your problem. My initial guess was interrupt caused this problem. Interrupt service rutine could mess up those pointer registers if you were not carefully managing it. But you mentioned that the interrupt was disabled and still...
    on Mar 12, 2010

  • Forum Post: Re: Brainstorming: Strange Behaviour of MOV and ADD

    Hyun Kim
    Dear Michael, Thanks for sharing your code. I looked at and found your c55.cmd file was for C5510. I changed to proper memory linker file. Then I have not seen your problems. Please try attached cmd file.
    on Mar 12, 2010

  • Forum Post: Re: Call a C-callable assembly by assembly

    TommyG
    Florian, Details on C callable assembly routines are available in the TMS320C55x Optimizing C/C++ Compiler User's Guide ( http://www-s.ti.com/sc/techlit/spru281 ), sec 6.3-6.5. To reduce latency function parameters are passed through registers rather than the stack. Regards.
    on Jun 1, 2010

  • Forum Post: Re: gsm.h Intrinsics not compatible with DSP Library dsplib.h?

    TommyG
    Steffen, The gsm.h has the following description: /* Definitions for the Basic DSP Operations defined by the European */ /* Telecommunications Standards Institute (ETSI). */ These are protocol specific. The DSPLIB are generic DSP algorithms. Both happen to have add() function defined. If you are...
    on Jun 1, 2010

  • Forum Post: Re: aliased bins in rfft() results?

    Brian Willoughby
    I am still experiencing errors in the DSPlib rfft() routine, and I am close to shipping my C5506 product! The way that the expected magnitude of a pure sine wave is shared across 1, 2, or 4 bins makes it impossible to utilize the rfft() routine. I would appreciate it if someone from Texas Instruments...
    on Jul 23, 2010

  • Forum Post: DSPLIB recip16 & ldiv16 functions

    David Rick
    I'd like to use the recip16 and ldiv16 functions in DSPLIB, but the documentation leaves much to be desired. For instance recip16() takes an input X of type Q.15 and returns two outputs, R and REXP, both of type Q.15. The documentation states that R*REXP is the "true reciprocal" of X...
    on Jul 23, 2010

  • Forum Post: Re: EZdsp USB stick dsplib filter problem

    Mark Mckeown
    Arvid, You are correct that (2^31) - 1 represents 1.0 (or .999999... rather) in Q.31 format. The correct order of biquad coeffs is b2 b1 b0 a2 a1. iircas32.asm is incorrect when it reads that the order is a1 a2 b2 b0 b1. When working with fixed-point numbers, you need to be concerned about overflow...
    on Nov 20, 2010

  • Forum Post: Re: C5515 DSP LIB v2.40 question. How can I rebuild this library package for a newer CPU rev. 3.x and which options to choose? Using readme file do not solve the issue. Executing Blt55xx.bat file only delete the old *.lib file.

    Mark Mckeown
    Hi John, Here is how to rebuild the DSP library package for CPU rev. 3.3 with options to choose memory models 1) Copy and rename Blt55xx.bat in the dsplib_2.40.00 folder. Open with a text editor. 2) Comment out c:\ti\dosrun.bat (CCS3.3 relic). REM is the CMD line comment (remark) 3) Specify the path...
    on Dec 28, 2010

  • Forum Post: how to use the add() and the acorr() is dsplib

    habeeb siddique37664
    hi i need to add a 150 hz sine wave to my audio file and then detect it. i plan to use the add() in the dsplib for adding the 150hz sine wave fft coefficients to my audio file, but its not working. please can some one tell me how i can use the acorr() for the correlation filter to detect the 150...
    on Jan 13, 2011

  • Forum Post: correlate function breaks down

    habeeb siddique37664
    BElow is the line of code i worte to detect a 150 hz sine wave added in my audio, every time my function to detect the sine wave is called, the function breaksdown as soon as it reaches the correlate function, plz help me solve this #define BUFFSIZE 128 short temp_squelch[BUFFSIZE + 53]; //...
    on Jan 13, 2011

  • Forum Post: Re: correlate function to detect a 150 hz sine wave in my audio

    David Rick
    Hello Habeeb, The corr( ) function is part of DSPLib, and is fully documented in the TMS320C55x DSP Library Programmer's Reference. I think the idea in your example is to compare the input data to a prototype sine wave. The corr( ) function is essentially a linear projection. You will get the...
    on Jan 19, 2011

  • Forum Post: correlate function to detect a 150 hz sine wave in my audio

    habeeb siddique37664
    Hi i am trying to use the correlate function to detect a 150 hz sine wave in my audio, below is the code, i am not able to hear sound, can anyone explain me the correlate function and what is the output expected. corr(actual_input, sine150, input, buffersize, 53, raw); // corr(b,a,r,NA,NB,raw...
    on Jan 13, 2011

  • Forum Post: Re: FIR with C55xx

    Max Zhegulin
    1. Look for DSPlib, it's include different types of FIR filters. 2. Why not? But how much time takes convolution, it's another question. Max
    on Feb 3, 2011

  • Forum Post: Re: How is T3 getting trashed during CALL ?

    David Rick
    Brian, I chased a problem like this about five years ago. It was very difficult to find, but it turned out that an assembly language routine in DSPlib was not properly preserving the T3 register. T3 is (or used to be) a "save on entry" register. In C, it isn't normally stacked unless...
    on Feb 24, 2011

  • Forum Post: Re: How is T3 getting trashed during CALL ?

    Brian Willoughby
    Thanks, Peter. I just found the problem. This is a serious bug in unpack.asm, rendering the routine useless in any environment with interrupts. Basically, the code should be: MOV pair(T2), dbl(*SP(#1)) With the Stack Pointer offset of #0, as in the original code, T2 is written within the safe area...
    on Mar 1, 2011

  • Forum Post: Bugs in sqrt_16() sqrtv.asm, and non-optimal performance

    Brian Willoughby
    There is an off-by-one error in the sqrt_16() routine of dsplib for all output values, e.g., sqrt(0) = 0x0001 (0.000030517578125), instead of the expected 0. In addition, the code is not taking full advantage of the C55x instruction set, and thus its memory, stack, and CPU usage are higher than necessary...
    on Mar 1, 2011

  • Forum Post: Re: Noise Cancellation Headphone

    Max Zhegulin
    Hi Vinod, For your DSP algorithm implementation on C55xx Dsplib will be very usefully. http://focus.ti.com/docs/toolsw/folders/print/sprc100.html Max
    on Mar 12, 2011

  • Forum Post: TMS320C55x DSP Library - Huge Memory Model Compatible?

    Jack Bolton
    Hi all, I am trying to build a modified version of the TMS320C5505 Audio Filter which uses a couple of the DSPLIB functions (RFFT32, RIFFT32) . However the build fails when trying to link, giving me the error message: "<cbrev32.obj> specifies a large memory model which is not compatible...
    on Apr 15, 2011

  • Forum Post: Re: EZdsp USB stick dsplib filter problem

    Frederico
    Hi, I´m trying to implent a 60Hz digital notch filter with iircas32.asm filter.I have had the same problem . Did someone solve the issue? My coeficients are: b0 = 0.99920134248799 b1 = 1.98953370312275 b2 = 0.99920134248799 a0 = 1 a1 = 1.98953370312275 a2 = 0.998402684975981...
    on Apr 18, 2011

  • Forum Post: Re: EZdsp USB stick dsplib filter problem

    Frederico
    Hi, I normalized the coefficients and the filter not works properly! I have thinking about and I suppose the problem happens because I can´t to normalize a0 coefficient which is 1 because I can´t put the on the dBuffer vector the coefficient a0. The normalized coefficients are shown...
    on Apr 18, 2011

  • Forum Post: DSPLib Rfft Example Project

    Jack Bolton
    Hi all, I have been trying to code an audio noise reduction routine using DSPLib 2.4 on the eZDSP TMS320C5505 stick, however I came across some problems using the rfft and rifft functions, as they did not behave as I expected them to. I then went right back to basics to try and understand how they...
    on Apr 19, 2011

  • Forum Post: Rfft Example Project in DSPLib 2.40 does not work when built?

    Jack Bolton
    Hi all, I am having trouble using rfft so I decided to try and compile and run the example project included in the "Examples" folder. It is a legacy project, which I added to my workspace by right clicking on the "C/C++ Projects" pane and clicking import. I then tried to build...
    on Apr 28, 2011
12

All content and materials on this site are provided "as is". TI and its respective suppliers and providers of content make no representations about the suitability of these materials for any purpose and disclaim all warranties and conditions with regard to these materials, including but not limited to all implied warranties and conditions of merchantability, fitness for a particular purpose, title and non-infringement of any third party intellectual property right. TI and its respective suppliers and providers of content make no representations about the suitability of these materials for any purpose and disclaim all warranties and conditions with respect to these materials. No license, either express or implied, by estoppel or otherwise, is granted by TI. Use of the information on this site may require a license from a third party, or a license from TI.

Content on this site may contain or be subject to specific guidelines or limitations on use. All postings and use of the content on this site are subject to the Terms of Use of the site; third parties using this content agree to abide by any limitations or guidelines and to comply with the Terms of Use of this site. TI, its suppliers and providers of content reserve the right to make corrections, deletions, modifications, enhancements, improvements and other changes to the content and materials, its products, programs and services at any time or to move or discontinue any content, products, programs, or services without notice.

TI Worldwide | Contact Us | my.TI Login | Site Map | Corporate Citizenship | mobile m.ti.com (Mobile Version)

TI is a global semiconductor design and manufacturing company. Innovate with 100,000+ analog ICs and
embedded processors, along with software, tools and the industry’s largest sales/support staff.

© Copyright 1995-2013 Texas Instruments Incorporated. All rights reserved.
Trademarks | Privacy Policy | Terms of Use