Personal tools

Difference between revisions of "PULPonFPGA: Lightweight Virtual Memory Support - Multi-Level TLB"

From iis-projects

Jump to: navigation, search
Line 13: Line 13:
 
: ... Set up operation on the evaluation platform, and characterize the enhanced solution using heterogeneous benchmark applications.
 
: ... Set up operation on the evaluation platform, and characterize the enhanced solution using heterogeneous benchmark applications.
  
===Status: Available ===
+
===Status: Taken ===
: Looking for Interested Master Students
 
 
: Supervision: [[:User:Vogelpi|Pirmin Vogel]], [[:User:Schaffner|Michael Schaffner]], [[:User:Mandrea|Andrea Marongiu]]
 
: Supervision: [[:User:Vogelpi|Pirmin Vogel]], [[:User:Schaffner|Michael Schaffner]], [[:User:Mandrea|Andrea Marongiu]]
  

Revision as of 15:12, 28 September 2015

Pulp on fpga.png

Short Description

While high-end heterogeneous systems-on-chip (SoCs) are increasingly supporting heterogeneous uniform memory access (hUMA) as envisioned by the Heterogeneous System Architecture (HSA) foundation, their low-power counterparts targeting the embedded domain still lack basic features like virtual memory support for accelerators. As opposed to simply passing virtual address pointers, explicit data management involving copies is needed to share data between host processor and accelerators which hampers programmability and performance.

At IIS, we use an evaluation platform based on the Xilinx Zynq-7000 SoC with PULPonFPGA implemented in the programmable logic to study the integration of programmable many-core accelerators into embedded heterogeneous SoCs. We have developed a mixed hardware/software solution to enable lightweight virtual memory support for many-core accelerators in heterogeneous embedded SoCs. Based on a content-addressable memory (CAM), efficiently managed by a kernel-level driver module running on the host, our solution features a considerably lower design complexity compared to conventional input/output memory management units (IOMMUs).

The idea of this project is to enhance our solution with a multi-level TLB and lightweight hardware support for TLB management in order to support dynamic self-updating of the TLB without frequent host interaction.

This project requires work to be done at several layers of abstraction. More precisely, you will need to:

... Evaluate the cost and benefit of different alternative RAB/TLB designs (size-complexity tradeoff).
... Implement the selected design in hardware by extending the current design.
... Extend the Linux kernel-level driver managing the RAB
... Set up operation on the evaluation platform, and characterize the enhanced solution using heterogeneous benchmark applications.

Status: Taken

Supervision: Pirmin Vogel, Michael Schaffner, Andrea Marongiu

Character

40% Theory, Algorithms and Simulation
40% VHDL, FPGA Design
20% Linux Kernel-Level Driver Development

Prerequisites

VLSI I,
VHDL/System Verilog, C
Embedded Linux experience
Experience with Linux kernel-level driver development is of advantage.

Professor

Luca Benini

Links

  • Xilinx Zynq-7000 All-Programmable SoC [1]
  • PULP [2]

↑ top