# Using volk

**URL:** <https://www.ruby-forum.com/t/using-volk/232407>\
**Category:** GNU Radio\
**Created:** [October 7, 2014, 9:51pm UTC](https://www.ruby-forum.com/t/using-volk/232407 "2014-10-07T21:51:05Z")\
**Posts on this page:** 5\
**Page:** 1

<div class="post-metadata">

**Author:** ![addis\_a](https://www.ruby-forum.com/letter_avatar_proxy/v4/letter/a/c4cdca/32.png) [@addis\_a](https://www.ruby-forum.com/u/addis_a)\
**Post date:** [October 7, 2014, 9:51pm UTC](https://www.ruby-forum.com/t/using-volk/232407/1 "2014-10-07T21:51:05Z")

</div>

Hello all,

I wondered about volk. I want it to compute mean to peak value of a  
complex  
array. How could I do this?  
Besides, I really need to know is there any example of using volk? The  
code  
itself, doesn’t reflect input and output parameters explicitly.

Best,  
Mostafa

---

<div class="post-metadata">

**Author:** ![mostafa\_a](https://www.ruby-forum.com/letter_avatar_proxy/v4/letter/m/5e9695/32.png) [@mostafa\_a](https://www.ruby-forum.com/u/mostafa_a)\
**Post date:** [October 8, 2014, 11:58am UTC](https://www.ruby-forum.com/t/using-volk/232407/2 "2014-10-08T11:58:00Z")

</div>

Hi Mostafa,

VOLK is but an accelerated Library of Vector Optimized Kernels.  
What you want is basically three operations:  
a) finding maximum absolute  
b) finding average absolute  
c) dividing these two values

Now, looking closer at a) and b), one notices that both require the  
samples to be converted to their magnitudes, first. And because we’re in  
the business of optimizing things, let’s just use the squared magnitude,  
because that’s faster to compute by one sqrt, usually. So this boils  
down to  
a) take mag\_squared of input (length N)  
b1) find maximum of a)  
b2) find sum of a)  
c) sqrt(b2/b1)/N

As you can see, c) is not a vector operation, and thus not a case for  
volk.  
For a) (“Complex to Mag ^ 2”) there is a GNU Radio block that uses VOLK.  
That’s the example for using VOLK that I would have recommended to read,  
anyway 🙂

In other terms: If you don’t have to write your own highly optimized  
block, don’t use VOLK directly, use the standard GNU Radio blockset.  
It’s rather optimized 😉

Now, for the maximum search b1, things are a bit more complicated.  
Searching for a maximum is not _easily_ vectorizable, because it is a  
inherently sequential operation (think of it as the first step of a  
bubble sort).  
Now, you can achieve _awesome_ performance by basically turning your  
linear search into a N-ary tree, with N being the order of parallelism  
you can achieve by using a maximum-finding SIMD instruction. But that  
requires the size of the problem to be a power of N. That just doesn’t  
fly well with the usually more “multiple of 64 bit”-typey alignment  
restrictions.  
You’re however, highly encouraged to try just that: use the existing  
volk\_32f\_x2\_max\_32f, which compares two vectors, and stores the  
element-wise maximum in a third one, to compare the first with the  
second half of your mag\_squared vector, and repeat the same with the  
first and second half of the result (and so on) until you have a single  
maximum value. That’s the comparison tree from above for the N=2 case.  
You can employ clever overlapping to use as many values twice in the  
input to virtually extend your input’s length to a power of two, and  
then just waltz on.

For b2) you can simply use the “integrate” block, which is not VOLK  
optimized (possibly because it’s a gengen template and these are _so  
much fun_ to specialize). But seeing as it is simply an accumulating for  
loop, I kind of expect your compiler to make the best of the situation.  
However, you can also use the volk\_32f\_accumulator\_s32f VOLK kernel. I  
kind of want to use that in integrate, because for my machine, the SSE  
VOLK kernel is 4 times as fast as the generic implementation, which  
nicely matches the 4-operand SSE SIMD instruction behind it.

Greetings,  
Marcus

---

<div class="post-metadata">

**Author:** ![mostafa\_a](https://www.ruby-forum.com/letter_avatar_proxy/v4/letter/m/5e9695/32.png) [@mostafa\_a](https://www.ruby-forum.com/u/mostafa_a)\
**Post date:** [October 8, 2014, 3:14pm UTC](https://www.ruby-forum.com/t/using-volk/232407/3 "2014-10-08T15:14:50Z")

</div>

On Tue, Oct 7, 2014 at 3:49 PM, Mostafa A.  
[removed\_email\_address@domain.invalid](mailto:removed_email_address@domain.invalid)  
wrote:

> Hello all,
> 
> I wondered about volk. I want it to compute mean to peak value of a  
> complex array. How could I do this?  
> Besides, I really need to know is there any example of using volk? The  
> code itself, doesn’t reflect input and output parameters explicitly.
> 
> Best,  
> Mostafa

Marcus gave you a far more complete answer. Just a few words here.  
First,  
VOLK is used all over the place in GNU Radio. So look for blocks that  
use  
VOLK. Second, the name scheme of VOLK is incredibly explicit as to the  
input and output parameters. See the manual page and wiki page  
describing  
VOLK:

[http://gnuradio.org/doc/doxygen/volk\_guide.html](http://gnuradio.org/doc/doxygen/volk_guide.html)  
[http://gnuradio.org/redmine/projects/gnuradio/wiki/VOLK](http://gnuradio.org/redmine/projects/gnuradio/wiki/VOLK)

There also my talk on VOLK recorded for the IEEE Signal Processing  
Society:

> **[Nearly 50 Minutes of Volk! — Rondeau Research](http://www.trondeau.com/blog/2013/6/12/nearly-50-minutes-of-volk.html)**
>
> I want to announce that a slide show plus audio of me talking about our Volk library has been published by the IEEE Signal Processing Society here: 
> http://www.brainshark.com/SPS/vu?pi=zH8zQcV8dzAXPbz0  
> This is based on a paper and presentation...

Tom

---

<div class="post-metadata">

**Author:** ![mostafa\_a](https://www.ruby-forum.com/letter_avatar_proxy/v4/letter/m/5e9695/32.png) [@mostafa\_a](https://www.ruby-forum.com/u/mostafa_a)\
**Post date:** [October 9, 2014, 1:11pm UTC](https://www.ruby-forum.com/t/using-volk/232407/4 "2014-10-09T13:11:23Z")

</div>

Thank you so much Marcus,

I’ve learnt so much from you here 🙂  
The algorithm of finding the Max of a vector by comparing one half to  
the  
other half, is an appropriate idea! I can’t use GNURadio blocks for this  
calculation because I must do these within my own block.

Unfortunately, I’m not familiar with optimization and parallelization  
algorithm, so I just want to compute fast not necessarily as fast as  
possible 🙂

Best,  
Mostafa

On Wed, Oct 8, 2014 at 5:56 AM, Marcus M. [removed\_email\_address@domain.invalid](mailto:removed_email_address@domain.invalid)  
wrote:

> the business of optimizing things, let’s just use the squared magnitude,
> 
> can achieve by using a maximum-finding SIMD instruction. But that requires  
> on.  
> Greetings,  
> itself, doesn’t reflect input and output parameters explicitly.
> 
> * * *
> 
> Discuss-gnuradio mailing list  
> [removed\_email\_address@domain.invalid](mailto:removed_email_address@domain.invalid)  
> [Discuss-gnuradio Info Page](https://lists.gnu.org/mailman/listinfo/discuss-gnuradio)

–

* * *

Department of Electrical Engineering  
Aboureyhan Building  
MMWCL LAB  
Amirkabir University Of Technology  
Tehran  
IRAN  
Tel: +98 (919) 158-7730  
LAB: [http://ele.aut.ac.ir/~mmwcl/?page\_id=411](http://ele.aut.ac.ir/~mmwcl/?page_id=411)  
Homepage: [http://ele.aut.ac.ir/~alizadeh/](http://ele.aut.ac.ir/~alizadeh/)

* * *

---

<div class="post-metadata">

**Author:** ![mostafa\_a](https://www.ruby-forum.com/letter_avatar_proxy/v4/letter/m/5e9695/32.png) [@mostafa\_a](https://www.ruby-forum.com/u/mostafa_a)\
**Post date:** [October 9, 2014, 3:01pm UTC](https://www.ruby-forum.com/t/using-volk/232407/5 "2014-10-09T15:01:48Z")

</div>

Compilers are good, just use a linear comparison:

float \*current= input;  
float max = \*current;  
float \*end = first + length\_of\_array;  
while(current \< end){  
max = (\*current \> max) ? \*current++ : max;

🙂