CS 293S, Winter 2019

Code Optimization


Tentative Schedule of lectures: This schedule is relatively fluid and will change as the quarter progresses.


WeekDateTopicNote
1
1-Oct Introduction and overview
2
6-Oct Redundancy Removal: IRs and DAG-based Methods
8-Oct Redundancy Removal: SVN & DVN HW1 out
3
13-Oct GCSE (Paper list out.)
15-Oct Guest Lecture
4
20-Oct Data Flow Analysis
22-Oct SSA (HW1 due, HW2 out.)
5
27-Oct SSA + Dead Code Elimination
29-Oct Partial Redundancy Elimination
6
3-Nov Parallelsim and data dependence (First paper review due.)
5-Nov Parallelsim and data dependence (HW3 out, HW2 due.)
7
10-Nov No class
12-Nov Student Presentations and Discusssion Suriya Dakshina Murthy (#11 Dominance-based duplication simulation (DBDS): code duplication to enable compiler optimizations); Dengxian Yang (#15 GLORE: generalized loop redundancy elimination upon LER-notation)
8
17-Nov Student Presentations and Discusssion Huake He (#9. What every scientific programmer should know about compiler optimizations?); Jacqueline Mai (#12 IDEal : Efficient and Precise Alias-Aware Dataflow Analysis)
19-Nov Student Presentations and Discusssion Shlomi Steinberg (#2 Halide: a language and compiler for optimizing parallelism, locality, and recomputation in image processing pipelines); Jeff Longo (#18 Delite: A Compiler Architecture for Performance-Oriented Embedded Domain-Specific Languages)
9
24-Nov Student Presentation and Discusssion Pengfei Xu (#3 Opentuner: An extensible framework for program autotuning); David Weinflash (#19 PolyMage: Automatic Optimization for Image Processing Pipelines)
26-Nov Holiday - no class
10
1-Dec Student Presentation and Project Discusssion (HW3 and second paper review Due.)Kaiqi Zhang  (#25. CHET: Compiler and Runtime for Homomorphic Evaluation of Tensor Programs)
3-Dec Extra Readings: SIMD and Cache Optimization
11
8-Dec Final Project Presentation