http://www.ece.cmu.edu/~calcm/ 2009-11-20T06:16:50-05:00 http://www.ece.cmu.edu/~calcm/ http://www.ece.cmu.edu/~calcm/lib/images/favicon.ico text/html 2009-02-22T10:58:48-05:00 http://www.ece.cmu.edu/~calcm/doku.php?id=contacts&rev=1235318328&do=diff Co-Directors * James C. Hoe * Todd Mowry Spring 2009 Seminar Czar * Eric Chung Faculty * Students * Projects * Seminars * Reports * Contacts text/html 2009-07-22T17:07:37-05:00 http://www.ece.cmu.edu/~calcm/doku.php?id=faculty&rev=1248296857&do=diff Franz Franchetti www Phillip B. Gibbons www Seth Goldstein www James C. Hoe www Ken Mai www Diana Marculescu www Ravishankar Mosur www Onur Mutlu www Todd Mowry www Markus Pueschel www text/html 2009-08-24T17:44:21-05:00 http://www.ece.cmu.edu/~calcm/doku.php?id=geyser&rev=1251150261&do=diff * On August 24, 2009, the CMU's orientation tent penetrated the water main underground. This is what happened when they pulled the tent spike out: * Youtube videos: * <http://www.youtube.com/watch?v=G3quBPSFsQs> * <http://www.youtube.com/watch?v=hIsCbTvAEUw> text/html 2009-09-05T14:27:12-05:00 http://www.ece.cmu.edu/~calcm/doku.php?id=home&rev=1252175232&do=diff Welcome to CALCM CALCM (pronounced “calcium”) brings together all faculty, staff, and students interested in computer architecture research and education at Carnegie Mellon. To navigate use the menu on the left. Announcements * Weekly Seminar Series - Tuesdays at 4:00 p.m. in HH D-210 * CALCM Reading Group - Fridays at 4:00 p.m. in HH A-306 text/html 2009-09-05T10:52:14-05:00 http://www.ece.cmu.edu/~calcm/doku.php?id=links&rev=1252162334&do=diff * Center for Silicon System Implementation * "Who's Who" in Computer Architecture * World Wide Computer Architecture * Online ACM Publications * Online IEEE Publications * CALCM Tech Reports text/html 2009-08-07T13:02:06-05:00 http://www.ece.cmu.edu/~calcm/doku.php?id=micro_tutorial_09&rev=1249664526&do=diff * Where? MICRO-42 (Westin hotel at Times Square, New York City) * When? December 12, 2009 (full-day tutorial) * Who? Academic/industrial researchers interested in full-system performance evaluation using desktop and commercial applications * Keywords: full-system simulation, multi-core and multiprocessor simulation, sampling, commercial workloads, measurement methodology text/html 2009-02-16T01:58:49-05:00 http://www.ece.cmu.edu/~calcm/doku.php?id=projects&rev=1234767529&do=diff Claytronics (Programmable Matter) www ENYAC (Energy Aware Architecture) Power dissipation has become a critical design concern in recent years, driven by the increased levels of complexity and emergence of mobile applications. Our research addresses this problem by providing architectural and software solutions for reducing the energy requirements of general purpose or embedded applications. Since what drives the power consumption of modern processors is the actual software that runs on it, … text/html 2009-02-16T02:01:22-05:00 http://www.ece.cmu.edu/~calcm/doku.php?id=reports&rev=1234767682&do=diff 2008 2008-002 REDAC: Distributed, Asynchronous Redundancy in Shared Memory Servers, Brian T. Gold, Babak Falsafi, James C. Hoe, and Ken Mai. [PDF] 2008-001 R-NUCA: Data Placement in Distributed Shared Caches, Nikos Hardavellas, Michael Ferdman, Anastasia Ailamaki and Babak Falsafi, December 2008. [PDF] text/html 2009-02-22T21:20:27-05:00 http://www.ece.cmu.edu/~calcm/doku.php?id=seminar_01_27_09&rev=1235355627&do=diff Tuesday January 27, 2009 Hamerschlag Hall D-210 4:00 pm Brian Gold Carnegie Mellon University Abstract The emergence of multi-core architectures—driven by continued technology scaling—has led to concerns about increasing soft- and hard-error rates in commodity designs. Because modern chip designs can no longer operate redundant modules in lockstep, we propose an asynchronous approach to redundant execution. In asynchronous redundancy, processor pairs independently execute an instruct… text/html 2009-02-22T21:28:08-05:00 http://www.ece.cmu.edu/~calcm/doku.php?id=seminar_02_03_09&rev=1235356088&do=diff Tuesday February 3, 2009 Hamerschlag Hall D-210 4:00 pm Sebastian Herbert Carnegie Mellon University Abstract Fine-grained dynamic voltage/frequency scaling (DVFS) is an important tool in managing the balance between power and performance in chip-multiprocessors. Although manufacturing process variations are giving rise to significant core-to-core variations in power and performance, traditional DVFS controllers are unaware of these variations. text/html 2009-02-22T21:42:17-05:00 http://www.ece.cmu.edu/~calcm/doku.php?id=seminar_02_10_09&rev=1235356937&do=diff Tuesday February 10, 2009 Hamerschlag Hall D-210 4:00 pm Mike Ferdman Carnegie Mellon University Abstract Prior research demonstrates that temporal memory streaming and related address-correlating prefetchers improve performance of servers though increased memory level parallelism. Unfortunately, these prefetchers require large on-chip meta-data storage. In this talk, I will describe the requirements for storing predictor meta-data for temporal memory streaming in off-chip memory whi… text/html 2009-02-22T21:44:51-05:00 http://www.ece.cmu.edu/~calcm/doku.php?id=seminar_02_17_09&rev=1235357091&do=diff Tuesday February 17, 2009 Hamerschlag Hall D-210 4:00 pm Peter Klemperer Carnegie Mellon University Abstract The widespread availability of low-cost, general-purpose computing has led to increased automation and communication within critical infrastructure such as the electrical power grid. Introducing computing hardware into the systems that perform the work of maintaining critical infrastructure presents many new questions about assuring security against malicious attackers and sabo… text/html 2009-02-22T23:42:46-05:00 http://www.ece.cmu.edu/~calcm/doku.php?id=seminar_02_24_09&rev=1235364166&do=diff Tuesday February 24, 2009 Hamerschlag Hall D-210 4:00 pm Wei Yu Carnegie Mellon University Abstract The goal of stereo vision is to reconstruct disparity map from a stereo image pair. Most existing stereo algorithms can be classified into either local or global approaches. Generally speaking, local algorithms are computationally less expensive, while global algorithms produce a higher quality disparity map. Recent research shows that local approaches based on carefully designed cost ag… text/html 2009-02-26T01:57:22-05:00 http://www.ece.cmu.edu/~calcm/doku.php?id=seminar_03_03_09&rev=1235631442&do=diff Tuesday March 3, 2009 Hamerschlag Hall D-210 4:00 pm Evangelos Vlachos Carnegie Mellon University Abstract As multicore processors become more prevalent, application performance increasingly depends upon parallel execution through multithreading. Software lifeguards, which are online tools for monitoring software correctness, are an invaluable part of the application writing process. However, most existing lifeguards focus on single-threaded applications and can be difficult to paral… text/html 2009-03-10T23:03:15-05:00 http://www.ece.cmu.edu/~calcm/doku.php?id=seminar_03_17_09&rev=1236740595&do=diff Tuesday March 17, 2009 Hamerschlag Hall D-210 4:00 pm José Martínez Cornell University Abstract As industry rides the transistor density growth in multicore processors by providing more and more cores, these will exert increasing levels of pressure on shared system resources. Efficient resource management becomes critical to obtaining high utilization, and eliminating potential bandwidth, latency, and cost barriers in multicore systems. Unfortunately, current hardware policies for mi… text/html 2009-03-23T21:59:38-05:00 http://www.ece.cmu.edu/~calcm/doku.php?id=seminar_03_31_09&rev=1237859978&do=diff Tuesday March 31, 2009 Hamerschlag Hall D-210 4:00 pm Ippokratis Pandis Carnegie Mellon University Abstract Database storage managers have long been able to efficiently handle multiple concurrent requests. Until recently, however, a computer contained only a few single-core CPUs, and therefore only a few transactions could simultaneously access the storage manager's internal structures. This allowed storage managers to use non-scalable approaches without any penalty. With the arrival… text/html 2009-03-23T22:03:36-05:00 http://www.ece.cmu.edu/~calcm/doku.php?id=seminar_04_07_09&rev=1237860216&do=diff Tuesday April 7, 2009 CIC Building 1201 4:00 pm Mark D. Hill University of Wisconsin-Madison Abstract Over the last several decades computer architects have been phenomenally successful turning the transistor bounty provided by Moore's Law into chips with ever increasing single-threaded performance. During many of these successful years, however, many researchers paid scant attention to multiprocessor work. Now as vendors turn to multicore chips, researchers are reacting with more pa… text/html 2009-04-09T15:36:13-05:00 http://www.ece.cmu.edu/~calcm/doku.php?id=seminar_04_14_09&rev=1239305773&do=diff Tuesday April 14, 2009 Location TBD 4:00 pm Prof. Bianca Schroeder University of Toronto Abstract Errors in dynamic random access memory (DRAM) are a common form of hardware failure in modern compute clusters. Failures are costly both in terms of hardware replacement costs and service disruption. While a large body of work exists on DRAM in laboratory conditions, little has been reported on real DRAM failures in large production clusters. In this talk, we analyze measurements of memo… text/html 2009-05-05T21:38:28-05:00 http://www.ece.cmu.edu/~calcm/doku.php?id=seminar_04_28_09&rev=1241573908&do=diff Tuesday April 21, 2009 Location: HH D-210 4:00 pm David Koes Carnegie Mellon University, School of Computer Science Abstract Register allocation is a fundamental part of any optimizing compiler. Effectively managing the limited register resources of the constrained architectures commonly found in embedded systems is essential in order to maximize code quality. In this talk I deconstruct the register allocation problem into distinct components: coalescing, spilling, move insertion, … text/html 2009-05-05T21:42:14-05:00 http://www.ece.cmu.edu/~calcm/doku.php?id=seminar_05_05_09&rev=1241574134&do=diff Tuesday May 5, 2009 Location: HH D-210 4:00 pm Qian Yu Carnegie Mellon University, Electrical & Computer Engineering Abstract The growing disparity of speed between CPU and off-chip memory makes memory latency an inevitable bottleneck in computer performance. This problem becomes more severe for highly data intensive applications, which are becoming prevalent. Although access/execution decoupled architectures in prior research allow the CPU to tolerate long access latencies, the actu… text/html 2009-10-25T23:44:58-05:00 http://www.ece.cmu.edu/~calcm/doku.php?id=seminar_09_15_09&rev=1256528698&do=diff Tuesday Sep. 15, 2009 Hamerschlag Hall D-210 4:00 pm Yoongu Kim Carnegie Mellon University Abstract The large disparity between CPU and memory speed, known as the “memory wall”, is one of the most severe performance bottlenecks in computer systems. In modern multicore archi-tectures, this problem is further exacerbated as cores must compete among themselves for access to memory. Therefore, a scheduling algo-rithm is employed by the memory controller to resolve this contention in a way… text/html 2009-10-25T23:45:14-05:00 http://www.ece.cmu.edu/~calcm/doku.php?id=seminar_09_29_09&rev=1256528714&do=diff Tuesday Sep. 29, 2009 Hamerschlag Hall D-210 4:00 pm Marek Telgarsky Carnegie Mellon University Abstract State of the art code generators, including ATLAS, Flame, FFTW and SPIRAL, rely on search to fit algorithm to hardware. The reasons for this are partially historical and partially practical. Prior to vector units and multi-cores in the general computing realm, algorithm optimization occurred primarily in the domain of the memory hierarchy. Opti-mizing for the memory hierarchy was … text/html 2009-10-25T23:56:41-05:00 http://www.ece.cmu.edu/~calcm/doku.php?id=seminar_10_06_09&rev=1256529401&do=diff Tuesday Oct. 6, 2009 Hamerschlag Hall D-210 4:00 pm Janani Mukundan Cornell University Abstract Chip Multiprocessors (CMPs) represent an at-tractive approach for sustaining scalable performance improvement in the billion-transistor era. Although the prime target of CMPs is highly parallel codes, many of the software products being written are still single-threaded applications, and even many parallel codes still contain nontrivial sequential sections. This poses a difficult design trad… text/html 2009-10-25T23:55:59-05:00 http://www.ece.cmu.edu/~calcm/doku.php?id=seminar_10_13_09&rev=1256529359&do=diff Tuesday Oct. 13, 2009 Hamerschlag Hall D-210 4:00 pm Vas Chellappa Carnegie Mellon University Abstract High-performance discrete Fourier transform (DFT) libraries are an important requirement on many computing platforms. The complexity of manually writing and tuning DFT libraries to target architectures is the motivation for the Spiral project, which can automatically generate platform-adapted libraries. text/html 2009-10-26T00:16:44-05:00 http://www.ece.cmu.edu/~calcm/doku.php?id=seminar_10_20_09&rev=1256530604&do=diff Tuesday Oct. 20, 2009 Hamerschlag Hall D-210 4:00 pm Ippokratis Pandis Carnegie Mellon University Abstract While hardware technology has undergone major advancements over the past decade, transaction processing systems have remained largely unchanged. The number of cores on a chip grows exponentially, following Moore's Law, allowing for an ever-increasing number of transactions to execute in parallel. As the number of concurrently-executing transactions increases, contended critical se… text/html 2009-10-26T16:05:21-05:00 http://www.ece.cmu.edu/~calcm/doku.php?id=seminars&rev=1256587521&do=diff The CALCM seminar series is a weekly meeting of faculty and students with broad interests in Computer Architecture, and is open to all. The seminar is an excellent medium for CALCM students/faculty to present their recent research results and/or practice conference presentations, for students to polish their presentation skills and present external results from recent conferences, and for outside speakers to tell us about their work. text/html 2009-07-07T16:20:14-05:00 http://www.ece.cmu.edu/~calcm/doku.php?id=students&rev=1246998014&do=diff Current Students * Tibi Chelcea * Eric Chung * Frederic de Mesmay * Mike Ferdman * Siddharth Garg * Brian Gold * Nikos Hardavellas * James Hendricks * Sebastian Herbert * Ryan Johnson * David Koes * Jangwoo Kim * Peter F. Klemperer * Peter Milder * Mahim Mishra * Eriko Nurvitadhi * Efstratios Papadomanolakis * Michael Papamichael * Olatunji Ruwase * Minglong Shao * Stephen Somogyi * Phillip Stanley-Marbell * Theodoros Strigkos * Girish Venkatarama…