Comparative (Computer) Architectures

Module Description: https://www.cl.cam.ac.uk/teaching/1819/CompArch/

Worksheet: https://www.cl.cam.ac.uk/teaching/1819/CompArch/cam-only/supervision-work.pdf

Supervision-1 (Amdahl's Law, ISA Design, Branch Prediction, Pipeline Hazards)

• Lecture: 1, 2, 3, 4
• Homework: 1.1, 2.{2, 3, 11}, 3.4, 4.{3,7}, Exam.y2017p7q6{a,b}, Exam.y2016p8q3a
• Design Challenge: http://bit.ly/2EIBVKm
• Additional Materials:
  • Tse-Yu Yeh and Yale N. Patt. 1991. Two-level adaptive training branch prediction. In Proceedings of the 24th annual international symposium on Microarchitecture (MICRO 24). ACM, New York, NY, USA, 51-61. DOI=http://dx.doi.org/10.1145/123465.123475
  • J. E. Smith and G. S. Sohi, "The microarchitecture of superscalar processors," in Proceedings of the IEEE, vol. 83, no. 12, pp. 1609-1624, Dec 1995. URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=476078&isnumber=10194
  • R. E. Kessler, "The Alpha 21264 microprocessor," in IEEE Micro, vol. 19, no. 2, pp. 24-36, Mar/Apr 1999. URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=755465&isnumber=16354
  • Thomas Ball and James R. Larus. 1993. Branch prediction for free. In Proceedings of the ACM SIGPLAN 1993 conference on Programming language design and implementation (PLDI '93), Robert Cartwright (Ed.). ACM, New York, NY, USA, 300-313. DOI=http://dx.doi.org/10.1145/155090.155119
  • W. W. L. Fung, I. Sham, G. Yuan and T. M. Aamodt, "Dynamic Warp Formation and Scheduling for Efficient GPU Control Flow," 40th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO 2007), Chicago, IL, 2007, pp. 407-420. URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=4408272&isnumber=4408232
  • Combining Branch Predictors - http://www.hpl.hp.com/techreports/Compaq-DEC/WRL-TN-36.pdf
  • Dynamic Branch Predictions with Perceptrons: https://www.cs.utexas.edu/~lin/papers/hpca01.pdf

Supervision-2 (ILP, Superscalar, VLIW, Software Pipelining, Speculative Compilation)

• Lecture: 5, 6, 7, 8
• Homework: 5.{3, 6}, 7.{2, 4}, 8.{2, 3, 4}, Exam.y2016p8q3b, Exam.y2011p8q3{b,d}
• Design Challenge: http://bit.ly/2EIWsLz
• Additional Materials:
  • Tomasulo's Algorithm Simulator: http://nathantypanski.github.io/tomasulo-simulator/
  • R. E. Kessler, "The Alpha 21264 microprocessor," in IEEE Micro, vol. 19, no. 2, pp. 24-36, Mar/Apr 1999. URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=755465&isnumber=16354
  • Hwu et al., "The Superblock: An effective technique for VLIW and superscalar compilation" Journal of Supercomputing 1993, URL: https://safari.ethz.ch/architecture/fall2017/lib/exe/fetch.php?media=10.1007_2fbf01205185.pdf
  • ARM Cortex A72 Microarchitecture Overview: http://www.tomshardware.com/reviews/arm-cortex-a72-architecture,4424.html#p2
  • ARM Cortex A73 Microarchitecture Overview: https://www.anandtech.com/show/10347/arm-cortex-a73-artemis-unveiled/2

Supervision-3 (Memory, Cache, Interconnects)

• Lecture: 9, 10, 11, 12
• Homework: 9.{2,3,4}, 11.2, 12.{4,5,7,11}, y2017p8q3{a,c}
• Design Challenge 1: Re-attempt the design challenge from Supervision-2: http://bit.ly/2EIWsLz
• Design Challenge 2: (No New Problem)
• Additional Materials:
  • N.P. Jouppi, “Improving Direct-Mapped Cache Performance by the Addition of a Small Fully-Associative Cache and Prefetch Buffers,” ISCA 1990
  • A. Seznec, “A Case for Two-Way Skewed-Associative Caches,” ISCA 1993
  • D. Kroft, “Lockup-Free Instruction Fetch/Prefetch Cache Organization," ISCA 1981
  • Cache Blocking: https://devblogs.nvidia.com/cutlass-linear-algebra-cuda/

Supervision-4 (Coherency, Consistency, TLP, SIMD|T, Vector Processors, Accelerators, DSA)

• Lecture: 13, 14, 15, 1, 2
• Homework: 14.{2,3,5}, 15.2, y2013p8q3{c,d}, y2006p8q1, y2011p7q4.d
• Design Challenge: (No New Problem)
• Additional Materials:
  • http://wiki.expertiza.ncsu.edu/index.php/CSC/ECE_506_Spring_2012/8a_cj

Foundations of Machine Learning

Supervision-1 (Is learning feasible, Training vs Testing)

• Homework: QP{1,3,4,6,8}, Exam:y2014p9q11{a,b,e}, Exam:y2013p8q13a, Exam:y2012p8q13d
• Additional Materials:
  • Hoeffding's Inequality: http://cs229.stanford.edu/extra-notes/hoeffding.pdf
  • Chernoff’s Bound: http://nowak.ece.wisc.edu/SLT07/lecture7.pdf

Supervision-2 (Theory of Generalisation, VC Dimension, Bias-Variance Trade off )

• Homework: QP{1,3,4,6,8}, Exam:y2014p9q11{a,b,e}, Exam:y2013p8q13a, Exam:y2012p8q13d
• Additional Materials:
  • Vapnik–Chervonenkis dimension: https://en.wikipedia.org/wiki/Vapnik%E2%80%93Chervonenkis_dimension
  • Growth Function: https://en.wikipedia.org/wiki/Growth_function

Supervision-3 (Linear Model, Neural Network, Over-fitting, Regularisation)

• Homework: QP{1,3,4,6,8}, Exam:y2014p9q11{a,b,e}, Exam:y2013p8q13a, Exam:y2012p8q13d
• Additional Materials: https://medium.com/greyatom/what-is-underfitting-and-overfitting-in-machine-learning-and-how-to-deal-with-it-6803a989c76

Supervision-4 (Support Vector Machine, Kernel Method, Radial Basis Function)

• Homework: QP{1,3,4,6,8}, Exam:y2014p9q11{a,b,e}, Exam:y2013p8q13a, Exam:y2012p8q13d
• Additional Materials: https://towardsdatascience.com/radial-basis-functions-neural-networks-all-we-need-to-know-9a88cc053448

Supervision-5 (SVD, PCA, Variational Autoencoder, Dimensionality Reduction)

• Homework: QP{1,3,4,6,8}, Exam:y2014p9q11{a,b,e}, Exam:y2013p8q13a, Exam:y2012p8q13d
• Additional Materials: A tutorial on PCA/SVD: https://arxiv.org/abs/1404.1100
• PCA vs Autoencoder: https://towardsdatascience.com/pca-vs-autoencoders-1ba08362f450