UL Lecture 2 Part 2: Density estimation Literature CHACÓN, J. & DUONG, T. (2018) [C] Multivariate kernel smoothing and its application. CRC Press. Sec 2.1-2.2, 3.1 HASTIE, T...

Exercise 4 Roofline analysis of matrix–vector multiplication The goal of this exercise is to perform a roofline analysis of matrix–vector multiplication. We will look at the effect that compiler f...

PO Lecture 3 Roofline Models Exercise 2: results —-wait page4 – # Memory/node topology likwid-topology reports an ASCII version of diagrams like this. Exercise 3: results Conclusions...

CV Lecture 4 Image segmentation The process of segmenting an image into parts or fragments and assigning a label to each of those Three are the basic types of image segmentation I...

Why and How do we characterise an image The holy grail of computer vision is to develop algorithms that extract sufficient information from an image This would let us transmit an image betwee...

作业回顾 Sum reduction benchmark (Exercise 1) SIMD: 4 plateaus scalar: 3 plateaus Performance peak Variability This is due to CPU Boosting. Question SIMD code does not achieve theoretical ...

Part 1: Basics of multivariate analysis First: What is learning? Learning means finding probability distributions to model data $Y$. 概率分布对数据建模 We will see many examples of ...

Monday week 6 ADVANCED STATISTICS AND MACHINE LEARNING FOUNDATIONS Introduction What is the goal? Make rational inferences and decisions from data. Inference about unknown quantity $U$ giv...

Exercise 2 Memory bandwidth in the memory hierarchy The goal of this exercise is to determine the memory bandwidth as a function of the amount of data we are moving on the Hamilton cores. As don...

Excercise 1 PreviousLecture 1 Notes NextFirst_draft_of_a_report_on_the_EDVAC.pdf Benchmarking with likwid-bench We’re going to look at the throughput of a very simple piece of code float reduc...