*** Important note: The course moves to Fishbach 505 ***
Course Topics
The students will present two papers each week, according to the schedule listed below.
Course Duties
Each student must present two papers during the semester (note that the date/time for presenting each paper is set).
NEW: Following some questions of the presentation layout and content, here is an example presentation about the
Q100 Database Architecture from one of my students. Note that the large number of slides is due to animations, but the actual content is equivalent to a presentation with 25-30 slides.
Use the following link to select a paper to present: https://doodle.com/poll/itku7wv4vs2bvphr
Note that selecting a date also means selecting the paper scheduled for that date as listed below.
In your presentations, make sure you address the following points:
1. What is the problem that the paper addresses?
2. According to the authors, what is the new insight that the paper contributes?
3. How does the paper addresses the problem at hand?
4. What are the results?
You presentations should also convey your critique of the paper:
1. Is the problem important?
2. Are the insights significantly novel?
3. Is the methodology sound?
4. Are the results substantial?
Talk Schedule
(you can download each paper using its link, provided you are using the Technion network)
Date and time |
Speaker |
Title |
Paper Venue |
06/11/2018 |
Yoav Etsion |
Introduction |
|
13/11/2018, 14:30 |
|
Applied Machine Learning at Facebook: A Datacenter Infrastructure Perspective |
HPCA 2018 |
13/11/2018, 15:30 |
|
Are Coherence Protocol States vulnerable to Information Leakage? |
HPCA 2018 |
20/11/2018, 14:30 |
|
Amdahl’s Law in the Datacenter Era: A Market for Fair Processor Allocation |
HPCA 2018 |
20/11/2018, 15:30 |
|
Lost in Abstraction: Pitfalls of Analyzing GPUs at the Intermediate Language Level |
HPCA 2018 |
27/11/2018, 14:30 |
|
D-ORAM: Path-ORAM Delegation for Low Execution Interference on Cloud Servers with Untrusted Memory |
HPCA 2018 |
27/11/2018, 15:30 |
|
Darwin: A Genomics Co-processor provides up to 15,000X acceleration on long read assembly |
ASPLOS 2018 |
04/12/2018 |
|
Hannukkah |
|
11/12/2018, 14:30 |
|
Reducing Data Transfer Energy by Exploiting Similarity within a Data Transaction |
HPCA 2018 |
11/12/2018, 15:30 |
|
Devirtualizing virtual memory for heterogeneous systems |
ASPLOS 2018 |
18/12/2018, 14:30 |
|
Wonderland: A Novel Abstraction-Based Out-Of-Core Graph Processing System |
ASPLOS 2018 |
18/12/2018, 15:30 |
|
Liquid Silicon: A Reconfigurable Memory-Oriented Computing Fabric with Scalable Multi-Context Support |
ASPLOS 2018 |
25/12/2018, 14:30 |
|
Frightening small children and disconcerting grown-ups: Concurrency in the Linux kernel |
ASPLOS 2018 |
25/12/2018, 15:30 |
|
Google Workloads for Consumer Devices: Mitigating Data Movement Bottlenecks |
ASPLOS 2018 |
01/01/2018, 14:30 |
|
WSMeter: A Performance Evaluation Methodology for Google’s Production Warehouse-Scale Computers |
ASPLOS 2018 |
01/01/2018, 15:30 |
|
Architectural Support for Task Dependence Management with Flexible Software Scheduling |
HPCA 2018 |
08/01/2018, 14:30 |
|
In-Memory Data Parallel Processor |
ASPLOS 2018 |
08/01/2018, 15:30 |
|
Generic System Calls for GPUs |
ISCA 2018 |
15/01/2018, 14:30 |
|
Hiding Intermittent Information Leakage with Architectural Support for Blinking |
ISCA 2018 |
15/01/2018, 15:30 |
|
Space-Time Algebra: A Model for Neocortical Computation |
ISCA 2018 |
22/01/2018, 14:30 |
|
Rethinking Belady’s Algorithm to Accommodate Prefetching |
ISCA 2018 |
22/01/2018, 15:30 |
|
FireSim: FPGA-Accelerated Cycle-Exact Scale-Out System Simulation in the Public Cloud |
ISCA 2018 |