Emery Blogger

I have long been a proponent of double-blind reviewing. People suffer from expectation bias, and double-blind reviewing is a tried and true approach to combat it. I adopted double-blind reviewing when I co-chaired VEE 2010 and just recently for WoDet 3, and have decided to take a stand to sway more program committees to implement it. Join me!

When asked to serve on a PC, agree only if double-blind reviewing is used.

This approach doesn’t always work, but the fact is that most program chairs simply had not considered it and are happy to adopt it. My advisor Kathryn McKinley‘s case for double-blind and Mike Hicks‘ fantastic FAQ on the topic make excellent ammunition. I suggested it to Todd Mowry and he implemented it for ASPLOS 2011; P. Sadayappan did the same for PPoPP 2012 (I am grateful to both for their patience!)

But there has been some backsliding; double-blind reviewing is not going to be used for POPL 2013, despite the overwhelmingly positive response of the POPL 2012 committee members.

So the next time you get asked to serve on a PC, at least bring it up. Let’s help make this a standard practice across our community.

My interview today with our NPR affiliate New England Public Radio went from Zappos to broader security to a discussion of the End Times (more or less)!

http://www.nepr.net/news/umass-cyber-security-expert-examines-zappos-security-breach

We have made an alpha release of AutoMan, a platform for integrating human-based and digital computation. It allows programmers to “program with people”, which appear to the programmer to be ordinary function calls. AutoMan automatically handles details like quality control, payment, and task scheduling. It is currently implemented as a domain-specific language embedded in Scala (a language that runs on any machine with a Java Virtual Machine), and uses Amazon’s Mechanical Turk as a backend.

Visit the project page (automan-lang.org) for download information.

Technical report UMass CS TR 2011-44: Dan Barowy, Emery D. Berger, and Andrew McGregor.

Abstract:

Humans can perform many tasks with ease that remain difficult or impossible for computers. Crowdsourcing platforms like Amazon’s Mechanical Turk make it possible to harness human-based computational power on an unprecedented scale. However, their utility as a general-purpose computational platform remains limited. The lack of complete automation makes it difficult to orchestrate complex or interrelated tasks. Scheduling human workers to reduce latency costs real money, and jobs must be monitored and rescheduled when workers fail to complete their tasks. Furthermore, it is often difficult to predict the length of time and payment that should be budgeted for a given task. Finally, the results of human-based computations are not necessarily reliable, both because human skills and accuracy vary widely, and because workers have a financial incentive to minimize their effort.

This paper introduces AutoMan, the first fully automatic crowdprogramming system. AutoMan integrates human-based computations into a standard programming language as ordinary function calls, which can be intermixed freely with traditional functions. This abstraction allows AutoMan programmers to focus on their programming logic. An AutoMan program specifies a confidence level for the overall computation and a budget. TheAutoMan runtime system then transparently manages all details necessary for scheduling, pricing, and quality control. AutoMan automatically schedules human tasks for each computation until it achieves the desired confidence level; monitors, reprices, and restarts human tasks as necessary; and maximizes parallelism across human workers while staying under budget.

“-Hoard” — enabling the use of my Hoard memory allocator — is now an officially sanctioned configuration flag for SPEC CPU2006 (the industry-standard way to measure CPU performance)! See the flags in use for the Intel compiler and Open64. My opinions about benchmarking notwithstanding, I am ok with my work being a standard configuration flag .

From PBS affiliate WGBY: University of Mass. Prof. of Computer Science Emery Berger discusses cyber security and what we can do to protect our information from computer hackers.

Camera-ready versions of recent pubs from our research group:
SOSP 2011: Dthreads: Efficient and Deterministic Multithreading, Tongping Liu, Charlie Curtsinger, and Emery Berger.
OOPSLA 2011: Sheriff: Precise Detection and Automatic Mitigation of False Sharing, Tongping Liu and Emery Berger.

Sheriff: Precise Detection and Automatic Mitigation of False Sharing
Tongping Liu, Emery D. Berger, OOPSLA 2011

False sharing is an insidious problem for multithreaded programs running on multicore processors, where it can silently degrade performance and scalability. Previous tools for detecting false sharing are severely limited: they cannot distinguish false sharing from true sharing, have high false positive rates, and provide limited assistance to help programmers locate and resolve false sharing.

This paper presents two tools that attack the problem of false sharing: SHERIFF-DETECT and SHERIFF-PROTECT. Both tools leverage a framework we introduce here called SHERIFF. SHERIFF breaks out threads into separate processes, and exposes an API that allows programs to perform per-thread memory isolation and tracking on a per-page basis. We believe SHERIFF is of independent interest.

SHERIFF-DETECT finds instances of false sharing by comparing updates within the same cache lines by different threads, and uses sampling to rank them by performance impact. SHERIFF-DETECT is precise (no false positives), runs with low overhead (on average, 20%), and is accurate, pinpointing the exact objects involved in false sharing. We present a case study demonstrating SHERIFF-DETECT’s effectiveness at locating false sharing in a variety of benchmarks.

Rewriting a program to fix false sharing can be infeasible when source is unavailable, or undesirable when padding objects would unacceptably increase memory consumption or further worsen runtime performance. SHERIFF-PROTECT mitigates false sharing by adaptively isolating shared updates from different threads into separate physical addresses, effectively eliminating most of the performance impact of false sharing. We show that SHERIFF-PROTECT can improve performance for programs with catastrophic false sharing by up to 9x, without programmer intervention.

If you have an iPad, and (like me) you’d like to be able to take handwritten notes on it, there is finally a decent stylus that does the job: the AluPen. It’s chunky and a little weird, with a round rubber tip that looks like half of a tiny racquetball, but it works great (unlike every other iPad stylus I have tried). Wired has a nice review. I bought mine on Amazon; it’s available in a wide range of colors, but I like the gold for its retro pencil look. I am using it in combination with NoteTaker HD, an app by Dan Bricklin of VisiCalc fame, though other note taking apps with a magnified writing area would be fine.

I like my MacBook Air (my hands are soaking in it right now), but the speakers suck. I have never been able to get much volume out of them. Until now.

One of the winners of the MacWorld awards this year was Boom, a “volume booster” for your Mac. Works like a charm! It easily doubles the volume of the speakers, making it practical to use the Air to watch, say, The Daily Show, without having to don earphones. Well worth the $5 to crank your Mac up to 11.