README.md

# FPGA in Image Feature detection and comparison with CPU
#### Group4: Sabyasachi Mondal , Ravi Yadav
fpga for streamlining of computation intensive tasks. Like in cases where signals or images from sensors are procesed continously.

### I Have tried to implementation from scratch with no libraries in use so we can have much higher control over design. It has been sucessful and for very large images received as continous streams FPGA is 3 times as fast as CPU.

| Index | Title | Content |
| - | ------ | ------ |
| 1 | Overview | Why do we use FPGA |
| 2 | Problem background | Where can we apply our FPGA and get results |
| 3 | Objective | Our vision of the solution |
| 4 | Implementation | The Hardware architechture and HLS code constructs |
| 5 | Robert's cross | The algorithm we implemented |
| 6 | What we achieved and Caveats | (RESULTS) Success and limitations |
| 7 | Future Scope | Possible use in multiagent robot control using continous streaming |
| 8 | Tasks , Errors , References | Epilogue |

## Overview
We want to use FPGA for implementing an algorithm in hardware to perform computation more effeciently. CPU hardware is non-flexible so the code runs using the same set of registers and ALU , we cant optimize the harware as per our code. Our objective here is to harware a processing unit (something smilar to a flexible ALU using the CLBs) in the FPGA using High level code.


## Problem background
<b>*For applications like real time image processing, using CPU resource can be expensive. The reaction time may increase in applications where decisions are based on calculations. We need a dedicated hardware that can process continous stream of data coming in from sensors or camera endlessly.*</b>

<b>*FPGA should be able to process multiple streams in synchronized manner. We want to process the streams coming from an image and process them through a convolution algorithm (Robert's matrix) and then use another function to filter out bands of pixel values*</b>

## Objective

Our objective is to use enable continous data stream processing in a pipeline that runs faster using FPGA in comparison to CPU.
We try to implement a image-filter which works by taking data streams and processing them on real time, and the FPGA should work faster than CPU. *My primary objective is to adapt the FPGA logic design so that it can process multi-channel streams in synchronized manner and still be faster than CPU.*

We should be able to:

1. <b>*Remove limitations on length and size of data so the design can be adapted for real-time continous use with streaming data (ideally an really large image can be fed to our FPGA using streams)*</b>
    
2. <b>*Enable multiple data stream processing is parallel and using the strategies used in HLS for faster processing*</b>

3. <b>*FPGA should be reasonably faster than our CPU for processing streams*</b>

## Implementation Strategy
Previously we have seen the image resizer takes in the whole data DMA makes the data transfer rate much faster, but we cant process an image or stream of data that is infinitely received and has no limit on total length.

I intend to implement the following:
1. <b>*fast multichannel stream operations at a hardware level (HLS synthesis) integrated with similar software definitions and constructs in python*</b>
    
    *1.a High Level Code structure in pythonto enable parallel operation and feed data continously using DMA*
    
    *1.b CPU packs data and feed them to FPGA till the image is processed (but we can simply loop it forever for continous data)*

2. <b>*make the FPGA capable to process continous stream of data in seperate threads without interdependent variables*</b>

    *2.a Maintain same level of parallelism (multiple processing streams) in unrolled loops*

    *2.b Synchronized operation between packets of each stream which is essential for processing multiple togather.*

We try to read each row in the image as a pack of 3 streams, process it in 2 seperate block, and return the output as an array. *Since Robert's cross works on a specific 2x2 set of pixels of the image we must synchronize the stream of data coming in from our DMA such that if we read Nth packet in DMA A we must read Nth packet in DMA B and Nth packet in DMA E this is the only dependency we have on the variables so they need to wait for each other to complete the processing.*

![Schematic streaming rows and output](https://mygit.th-deg.de/sm11312/fpga_final_project/-/raw/main/HLSolution.JPG "Schematic streaming rows and output")

This would mean we can store real-time data in frames and feed them continously from our python code. The processing blocks consists of a 2x2 array each and they are the convolution weights added to our stream of data and we return the output with a pre-processing in another function.

![Convolution on streaming row](https://mygit.th-deg.de/sm11312/fpga_final_project/-/raw/main/RobertCross.JPG "Convolution on streaming row")

(DMA1 + DMA2) streams are processed in PU1 and (DMA2 + DMA3) streams in PU2. However becuase Robert's convolution algorithm needs data to be processed in a 2x2 array they must enter and get processed in Synchronized manner.

![CPU FPGA interconnection and data transfer](https://mygit.th-deg.de/sm11312/fpga_final_project/-/raw/main/CPU_FPGA.JPG "CPU FPGA interconnection and data transfer")

On the higher level the interaction between CPU and FPGA looks like the schematic shown above.

We use two blocks to process the streams but that doesnot mean we use one thread we basically dont wait for Nth set of data to be processed before we can start processing N+1 data. Since the convolution algorithm does not wait for processing it can start to read and process the next N+1 set of data from the stream as soon as Nth set has been read. It looks something like this due to loop unrolling and leads to parallel processing.

![Unravelling of streams in loop and parallel processing](https://mygit.th-deg.de/sm11312/fpga_final_project/-/raw/main/Parallel_process.JPG "Unravelling of streams in loop and parallel processing")

We also use the Schedule Viewer to find out the interdependent variables so that we can have higher level of loop unrolling and find out the variables that can become bottlenecks in parallel processing for example for synchronization we needto have dependency on the three variables in a single execution instant (for example when DMA A's Nth packet is read same Nth index data must be read in DMA B and DMA E) of the loop.

![The interdependent packets of data in the three input DMAs](https://mygit.th-deg.de/sm11312/fpga_final_project/-/raw/main/Schedule_Viewer.JPG "Interdependency to synchronize our image processing which can also be a bottleneck since we need to wait for other 2 DMA data to arrive.")

[The notebook for analysis of the algorithm itself and looking at its corresponding CPU implementation.](https://mygit.th-deg.de/sm11312/fpga_final_project/-/blob/main/Image_Filter_FPGA_CPU.ipynb)

[The block diagram illustrated](https://mygit.th-deg.de/sm11312/fpga_final_project/-/raw/main/Block_diagram_illustrated.jpg 'Blockdiagram')

https://mygit.th-deg.de/sm11312/fpga_final_project/-/blob/main/design_1.pdf

## Instroduction to the algorithm
<br>*The Robert's cross operation is very effective in detecting features in an image, specifically for images with more precise features*</br>

<br>*The Robert's operator is a 2x2 Matrix that can be used to find out differences in image boundaries becuase of it's weights*<br>

*It uses different weights in different pixel positions in a 2x2 cell which effectively acts like an differential operation. So places with higher differences in pixel values get pronounced in the output.*

![Introduction to Robert's cross operation](https://homepages.inf.ed.ac.uk/rbf/HIPR2/roberts.htm "Brief introduction to Robert's cross operation")

## What we achieved and the caveat :
<b>*We intended to build a architechture that can process multiple streams and process them in same parallel level and we were sucessful.*</b>

<b>*Our main goal is to ensure such a architechture runs faster in FPGA and it was reasonably fast; most importantly it can be scaled up to handle multiple streams.*</b>

<b>*CPU Average for images was at about 25s and FPGA at about 10s for 6 images for smaller images*</b>

![Speed comparison in single images](https://mygit.th-deg.de/sm11312/fpga_final_project/-/raw/main/Speed_table.JPG "Speed comparison in single images")

But the best part of the result is summarized in the following:
#### An Important observation was that for very large images (greater then 1 MB) our resizer is almost 3 times faster, thoguh its about 0.2 times fast for lower size images.

Please refer to the Jupyter notebook linked [here](https://mygit.th-deg.de/sm11312/fpga_final_project/-/blob/main/Notebook_Speed_Comparison.ipynb) which shows this result (image 2 and 3 are around 200KB rest are above 800KB)

## Future scope
*This is a new idea and has no previous references except implementaton guides. All the code and ideas were developed groundup*

<b>*The image processing can serve a stepping stone for controlling multi-agent systems. Where each streaming interface can be used for instruction input and output for each agent/bots.*</b>

*We achieved good synchronization between the input streams in terms of pixel processing. We can consider extending the filter to video with streaming, it might be possible with similar kind of streaming interface. Specially we have seen in the results that for longer streams the FPGA performance is more pronounced than CPU.*


#### Tasks
The Tasks and maximum actual time:

1. Problem statement and brainstorming for project selection : *24 hrs*
2. Design a basic model and build overlay : *6 hrs*
3. Python code adjustment and integration : *4 hrs*
4. Plan next stage of overlay design : *4 hrs*
5. Develop algorithm for FPGA using C++ : *4 hrs*
6. Optimize code and add synchronization of multiple channels : *24 hrs*
7. Implement block diagram : *4 hrs*
8. Upload code and test in IPy notebook : *3 hrs* 


#### Resources used and Future project topics

##### Resources used
0. Images: https://serc.carleton.edu/earth_analysis/image_analysis/introduction/day_4_part_2.html
1. Image segmentation : https://theailearner.com/2020/11/29/image-segmentation-with-watershed-algorithm/
2. Operation with stream: https://www.xilinx.com/html_docs/xilinx2020_2/vitis_doc/hls_stream_library.html#ivv1539734234667__ad398476
3. Stream Interface : https://www.xilinx.com/html_docs/xilinx2020_2/vitis_doc/managing_interface_synthesis.html#ariaid-title32
3. Specialized Constructs : https://www.xilinx.com/html_docs/xilinx2020_2/vitis_doc/special_graph_constructs.html?hl=template
4. Vitis Examples : https://github.com/Xilinx/Vitis_Accel_Examples/blob/master/cpp_kernels/README.md
5. Running Accelerator : https://pynq.readthedocs.io/en/v2.6.1/pynq_alveo.html#running-accelerators
6. Pragma Interfaces : https://www.xilinx.com/html_docs/xilinx2017_4/sdaccel_doc/jit1504034365862.html
7. AXI4 : https://ch.mathworks.com/help/hdlcoder/ug/getting-started-with-axi4-stream-interface-in-zynq-workflow.html
8. Interface of Streaming : https://www.xilinx.com/html_docs/xilinx2020_2/vitis_doc/managing_interface_synthesis.html#ariaid-title34
9. Database in FPGA : https://dspace.mit.edu/bitstream/handle/1721.1/91829/894228451-MIT.pdf, https://www.xilinx.com/publications/events/developer-forum/2018-frankfurt/accelerating-databases-with-fpgas.pdf, https://www.xilinx.com/html_docs/xilinx2020_2/vitis_doc/vitis_hls_process.html#djn1584047476918
10. Muxed Stream : https://liu.diva-portal.org/smash/get/diva2:1057270/FULLTEXT01.pdf
11. RAW,WAR,WAW.. : https://www.xilinx.com/html_docs/xilinx2020_2/vitis_doc/vitis_hls_optimization_techniques.html#wen1539734225565__aa1299615
12: Loop Pipelining Roll Unroll : https://www.xilinx.com/html_docs/xilinx2020_2/vitis_doc/vitis_hls_optimization_techniques.html#kcq1539734224846


### Errors Logs and Issues encountered
The input pins (listed below) are either not connected or do not have a source port, and they don't have a tie-off specified. These pins are tied-off to all 0's to avoid error in Implementation flow.
Please check your design and connect them as needed: 
/color_filter/ap_start
When ap_Ctrl = None not specified in design

Cant find custom IP in Vivado : add IP zip path, open IP Integrator view, from IP configure window manually add the IP

Cant connect hls::stream<> type object in IP : Note: The hls::stream class should always be passed between functions as a C++ reference argument. For example, &my_stream.
IMPORTANT: The hls::stream class is only used in C++ designs. Array of streams is not supported.

Non-Blocking write not-allowed in Non-FIFO Interfaces like axis instead try using FIFO m_axi

DMA size must be lesser than 16383 so we cant feed very large datasets directly to a single DMA.

WARNING: [HLS 200-786] Detected dataflow-on-top in function  'color_filter' (../project_3/color_filter.cpp:45)  with default interface mode 'ap_ctrl_hs'. Overlapped execution of successive kernel calls will not happen unless interface mode 'ap_ctrl_chain' is used (or 'ap_ctrl_none' for a purely data-driven design).
Resolution: For help on HLS 200-786 see www.xilinx.com/cgi-bin/docs/rdoc?v=2020.2;t=hls+guidance;d=200-786.html

DMA Stuck and not reponding, [fixed thanks to Lauri's Blog](https://lauri.võsandi.com/hdl/zynq/xilinx-dma.html) and [problems other's faced](https://forums.xilinx.com/t5/Processor-System-Design-and-AXI/Why-AXI-DMA-starts-acquiring-data-during-configuration/td-p/766605) and more [problems](https://forums.xilinx.com/t5/AXI-Infrastructure-Archive/tkeep-signal-in-AXI-DMA-and-tstrb-3-0-in-Custom-AXI-Stream-IP/td-p/921850)