Personal tools

Difference between pages "LAPACK/BLAS for FPGA" and "Active-Set QP Solver on FPGA"

From iis-projects

(Difference between pages)
Jump to: navigation, search
m (Prerequisites)
 
m (Short Description)
 
Line 2: Line 2:
  
 
==Short Description==
 
==Short Description==
The master thesis will be carry on in collaboration with [http://www.abb.ch/cawp/abbzh254/ec72bb280fd24d47c1256b5700522f3a.aspx ABB CHCRC] and will focus on the acceleration of specific LAPACK/BLAS kernels on FPGA.
+
The master thesis will be carry on in collaboration with [http://www.abb.ch/cawp/abbzh254/ec72bb280fd24d47c1256b5700522f3a.aspx ABB CHCRC] and will focus on the implementation of an Active-Set quadratic program (QP) solver accelerator on FPGA.
  
The LAPACK and BLAS libraries have been developed decades ago to perform standard linear algebra operations in an efficient and reliable way. Aim of this thesis is to identify a subset of these routines that are naturally suited to be executed on an FPGA. Out of this subset, a few simple operations are to be implemented on an FPGA, while the implementation is generic enough to take into account actual problem data size as well as resource constraints imposed by the actual FPGA hardware.
+
QP problems arise in various embedded optimization applications such as model predictive control or constrained least-square fitting. Various solution algorithms have been proposed and implemented on CPUs (some of them also on FPGAs), each of them exhibiting specific advantages and drawbacks. Active-set methods are frequently used on CPUs for solving QPs efficiently, but their use on FPGAs is considered challenging as they rely on more involved linear algebra operations such as matrix factorizations. Aim of this thesis project is to investigate the potential of implementing an active-set method for FPGAs and to identify/adapt an existing scheme to be implemented in hardware.
  
 
===Status: Available ===
 
===Status: Available ===
 
: Looking for Interested Students
 
: Looking for Interested Students
: Type: Master- or Semester Thesis
+
: Type: Master Thesis
 
: Supervisors: [[:User:Barandre|Andrea Bartolini]], [[:User:schaffner|Michael Schaffner]]
 
: Supervisors: [[:User:Barandre|Andrea Bartolini]], [[:User:schaffner|Michael Schaffner]]
  
 
===Prerequisites===
 
===Prerequisites===
: VLSI I, VLSI II
+
: VLSI I, VLSI II, Control Systems
 
: Matlab, C++, VHDL or System Verilog
 
: Matlab, C++, VHDL or System Verilog
  
Line 43: Line 43:
  
  
[[Category:Hot]] [[Category:Digital]] [[Category:Master Thesis]] [[Category:Available]] [[Category:Accelerator]] [[Category:FPGA]] [[Category:SBB CHCRC]] [[Category:Model Predictive Controller]] [[Category:least-square fitting]]
+
[[Category:Hot]] [[Category:Digital]] [[Category:Master Thesis]] [[Category:Available]] [[Category:Accelerator]] [[Category:FPGA]] [[Category:SBB CHCRC]] [[Category:Model Predictive Controller]]

Revision as of 12:31, 12 January 2015

TeaserAbb.png

Short Description

The master thesis will be carry on in collaboration with ABB CHCRC and will focus on the implementation of an Active-Set quadratic program (QP) solver accelerator on FPGA.

QP problems arise in various embedded optimization applications such as model predictive control or constrained least-square fitting. Various solution algorithms have been proposed and implemented on CPUs (some of them also on FPGAs), each of them exhibiting specific advantages and drawbacks. Active-set methods are frequently used on CPUs for solving QPs efficiently, but their use on FPGAs is considered challenging as they rely on more involved linear algebra operations such as matrix factorizations. Aim of this thesis project is to investigate the potential of implementing an active-set method for FPGAs and to identify/adapt an existing scheme to be implemented in hardware.

Status: Available

Looking for Interested Students
Type: Master Thesis
Supervisors: Andrea Bartolini, Michael Schaffner

Prerequisites

VLSI I, VLSI II, Control Systems
Matlab, C++, VHDL or System Verilog

Character

20% Theory
60% Implementation
20% Testing

Professor

Luca Benini

↑ top

Detailed Task Description

Goals

Practical Details

Results