IIT Madras · Engineering

Mapping Signal Processing Algorithms to Architectures

Prof. Nitin Chandrachoodan · 105 free video lectures

105 video lectures. Topics: Introduction: Objectives and Pre-requisites; Review of digital logic; Timing and Power in digital circuits; Implementation Costs and Metrics; Example: Audio processing; Example: AlexNet; Architecture cost components; Examples of Architectures; Multi-objective…

▶ Play on Open Lecture HallCourse page ↗

Lectures

  1. Introduction: Objectives and Pre-requisites
  2. Review of digital logic
  3. Timing and Power in digital circuits
  4. Implementation Costs and Metrics
  5. Example: Audio processing
  6. Example: AlexNet
  7. Architecture cost components
  8. Examples of Architectures
  9. Multi-objective Optimization
  10. Number representation
  11. Scientific notation and Floating point
  12. Basic FIR filter
  13. Serial FIR filter architectures
  14. Simple programmable architecture
  15. Block diagrams and SFGs
  16. Dataflow Graphs
  17. Iteration period
  18. FIR filter iteration period
  19. IIR filter iteration period
  20. Computation Model
  21. Constraint analysis for IPB computation
  22. Motivational examples for IPB
  23. General IPB computation
  24. Sample period calculation
  25. Parallel architecture
  26. Odd-even register reuse
  27. Power consumption
  28. Pipelining
  29. Pipelining FIR filter
  30. Time-invariant systems
  31. Valid pipelining examples
  32. Feedforward cutsets
  33. Balanced pipeline
  34. Retiming basic concept
  35. Example and uses of retiming
  36. Resource sharing: adder example
  37. Changing iteration period
  38. Hardware assumptions and constraint analysis
  39. Mathematical formulation
  40. Examples with formulation
  41. Example: Biquad filter
  42. Hardware architecture
  43. Review biquad folding sets
  44. Complete biquad hardware
  45. DEMO: FFT in Vivado HLS
  46. DEMO: FFT synthesis
  47. Obtaining a folding schedule
  48. ASAP schedule
  49. Utilization Efficiency
  50. ALAP schedule
  51. Iteration period bound and scheduling
  52. Retiming for scheduling
  53. Blocked schedules
  54. Overlapped schedules
  55. Improved blocked schedule
  56. Allocation, Binding and Scheduling
  57. DEMO: Analyze FFT implementation
  58. DEMO: FFT interface
  59. Scheduling: problem formulation
  60. Example: differential equation solver
  61. Heuristic approaches to scheduling
  62. Mathematical formulation
  63. ILP formulation
  64. List scheduling
  65. Hardware model
  66. Force Directed Scheduling
  67. DEMO: HLS on FFT
  68. DEMO: FFT Simulation and Optimization
  69. DEMO: CPU interfacing
  70. Software Compilation
  71. Optimization Examples
  72. Loop optimizations 1
  73. Loop optimizations 2
  74. Loop optimizations 3
  75. Software pipelining 1
  76. Software pipelining 2
  77. FFT Optimization
  78. Demo: Vivado setup
  79. Background: CPUs and FPGAs
  80. Demo: Vivado HLS FFT IP Export
  81. Demo: Vivado ILA and VIO on hardware
  82. Demo: FFT on FPGA board
  83. Demo: Simulating SoC and SDK
  84. Background: Understanding ELF files
  85. On-chip communication basics
  86. Many-to-Many communication
  87. AXI bus handshaking
  88. AXI bus (contd)
  89. Demo: Microblaze processor on FPGA
  90. Demo: Performance counter AXI peripheral
  91. Demo: HW accelerator for FPGA
  92. DMA and arbitration
  93. Network-on-chip basics
  94. NoC - topologies and metrics
  95. NoC - routing
  96. NoC - switching and flow control
  97. Systolic Arrays - Background
  98. Systolic Arrays - Examples
  99. CORDIC algorithm
  100. Parallel implementation of FIR filters
  101. Unfolding Transformation
  102. Lookahead Transformation
  103. Introduction to GPUs and Matrix multiplication
  104. Live Session 09-08-2019
  105. Live Session 27-08-2019

From NPTEL (IITs and IISc) · CC BY-NC-SA. More from IIT Madras.

Open Lecture Hall is free, with no ads and no sign-up. It is not run by or connected to any university; the lectures are the universities' own free recordings, played from where they host them. About & rights