but after examining my profile via gprof, I found it is giving me the same output as the CPU file. How can I confirm what processors are being used for playing my mp3 file?
Last edit: Abdullah Siddiqui 2016-11-27
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Are you sure the -D does what you think it does? Please look at the output of mpg123 --longhelp or the manpage.
Regarding the main question: The mpg123 code is not ported to GPUs. You'd need to rewrite code for OpenCL or CUDA. I am also not sure how much sense that would make, since you do not have that much data that you can work on in parallel. It might make sense to write up a decoder that works on many streams in parallel instead.
If you are looking for a typical task for a GPU, an audio decoder is just too small, IMHO.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Thank you again Mr. Orgis for your response.
I understand that decoding audio is not normally done on GPUs. I am doing it simply for experimental purposes. I want to see how much time the various functions would take to execute on the GPU and compare the numbers with the CPU values.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
I ran the following command:
mpg123 -D hw:1,3 root/Downloads/convergence_-_points_of_view/Traintoleave.mp3but after examining my profile via gprof, I found it is giving me the same output as the CPU file. How can I confirm what processors are being used for playing my mp3 file?
Last edit: Abdullah Siddiqui 2016-11-27
Are you sure the -D does what you think it does? Please look at the output of
mpg123 --longhelpor the manpage.Regarding the main question: The mpg123 code is not ported to GPUs. You'd need to rewrite code for OpenCL or CUDA. I am also not sure how much sense that would make, since you do not have that much data that you can work on in parallel. It might make sense to write up a decoder that works on many streams in parallel instead.
If you are looking for a typical task for a GPU, an audio decoder is just too small, IMHO.
Thank you again Mr. Orgis for your response.
I understand that decoding audio is not normally done on GPUs. I am doing it simply for experimental purposes. I want to see how much time the various functions would take to execute on the GPU and compare the numbers with the CPU values.