The 46th Annual IEEE/ACM International Symposium on Microarchitecture, 2013

Final MICRO-46 Program

Sunday, December 8, 2013

18:30-20:30: Conference Registration and Welcome Reception [Conference Center Ballroom]

Monday, December 9, 2013

7:30-18:30: Conference Registration [Conference Center Foyer]

7:30-8:30: Breakfast [Conference Center]

8:30-9:00: Welcome and Opening Remarks by General and Program Chairs [Conference Center Ballroom]

Message from the General Chair
Matthew Farrens, UC Davis
Message from the Program Chair
Christos Kozyrakis, Stanford

9:00-10:00: Keynote I [Conference Center Ballroom]
Session Chair: Christos Kozyrakis

Bryan Black, Senior Fellow, AMD
Die Stacking is Happening
Presentation: PDF

10:00-10:30: Break

10:30-12:00: Lightning Session [Conference Center Ballroom]
Session Chair: Tom Conte

12:00-13:30: Lunch [Conference Center]

13:30-15:00: Session 1A - Approximate Computing [Conference Center Ballroom]
Session Chair: Boris Grot

Quality-Programmable Vector Processors for Approximate Computing
Swagath Venkataramani, Vinay K. Chippa (Purdue University), Srimat T. Chakradhar (NEC Laboratories America), Kaushik Roy, and Anand Raghunathan (Purdue University)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540710
SAGE: Self-Tuning Approximation for Graphics Engines
Mehrzad Samadi, Janghaeng Lee, Davoud Jamshidi (University of Michigan), Amir Hormati (Google), and Scott Mahlke (University of Michigan)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540711
Approximate Storage in Solid-State Memories
Adrian Sampson, Jacob Nelson (University of Washington), Karin Strauss (Microsoft Research and University of Washington), and Luis Ceze (University of Washington)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540712

13:30-15:00: Session 1B - Energy Optimizations [Alpha Gamm Rho Room]
Session Chair: Pradip Bose

MLP-Aware Dynamic Instruction Window Resizing for Adaptively Exploiting Both ILP and MLP
Yuya Kora, Kyohei Yamaguchi, and Hideki Ando (Nagoya University)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540713
TLC: A Tag-less Cache Design for Reducing Dynamic First Level Cache Energy
Andreas Sembrant, Erik Hagersten, and David Black-Schaffer (Uppsala University)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540714
Decoupled Compressed Cache: Exploiting Spatial Locality for Energy-Optimized Compressed Caching
Somayeh Sardashti and David A. Wood (University of Wisconsin-Madison)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540715

15:00-15:30: Break

15:30-17:30: Session 2A - Power-Efficient GPUs [Conference Center Ballroom]
Session Chair: Nuwan Jayasena

Exploiting GPU Peak-power and Performance Tradeoffs through Reduced Effective Pipeline Latencies
Syed Zohaib Gilani (Lahore University of Management Sciences), Nam Sung Kim (University of Wisconsin-Madison), and Michael Schulte (Advanced Micro Devices)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540716
A Locality-Aware Memory Hierarchy for Energy-Efficient GPU Architectures
Minsoo Rhu, Michael Sullivan, Jingwen Leng, and Mattan Erez (The University of Texas at Austin)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540717
Divergence-Aware Warp Scheduling
Timothy G. Rogers (University of British Columbia), Mike O'Connor (NVIDIA Research / University of Texas at Austin), and Tor M. Aamodt (University of British Columbia)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540718
Warped Gates: Gating Aware Scheduling and Power Gating for GPGPUs
Mohammad Abdel-Majeed, Daniel Wong, and Murali Annavaram (University of Southern California)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540719

15:30-17:30: Session 2B - Resilience [Alpha Gamma Rho Room]
Session Chair: Milos Prvulovic

Virtually Aged Sampling DMR: Unifying Circuit Failure Detection and Circuit Failure Prediction
Raghuraman Balasubramanian and Karthikeyan Sankaralingam (University Of Wisconsin-Madison)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540720
Use It Or Lose It: Wear-out and Lifetime in Future Chip Multiprocessors
Hyungjun Kim (Texas A&M University), Arseniy Vitkovskiy (Cyprus University of Technology), Paul V. Gratz (Texas A&M University), and Vassos Soteriou (Cyprus University of Technology)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540721
uDIREC: Unified Diagnosis and Reconfiguration for Frugal Bypass of NoC faults
Ritesh Parikh and Valeria Bertacco (University of Michigan Ann Arbor)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540722
Implicit Storing and Redundant Encoding of Attribute Information in Error Correction Codes
Yiannakis Sazeides (University of Cyprus), Emre Ozer (ARM), Danny Kershaw (NXP), Panagiota Nikolaou, Marios Kleanthous (University of Cyprus), and Jaume Abella (BSC)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540723

18:00-20:00: MICRO Business Meeting [Conference Center Ballroom]

20:00-??:??: Shootout Session [Conference Center Ballroom]

Tuesday, December 10, 2013

7:30-18:30: Conference Registration [Conference Center Foyer]

7:30-8:30: Breakfast [Conference Center]

8:30-10:00: Session 3A - Main Memory [Conference Center Ballroom]
Session Chair: Jung Ho Ahn

Linearly Compressed Pages: A Low-Complexity, Low-Latency Main Memory Compression Framework
Gennady Pekhimenko, Vivek Seshadri, Yoongu Kim, Hongyi Xin, Onur Mutlu (CMU), Phillip B. Gibbons, Michael A. Kozuch (Intel), and Todd C. Mowry (CMU)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540724
RowClone: Fast and Energy-Efficient In-DRAM Bulk Data Copy and Initialization
Vivek Seshadri, Yoongu Kim, Chris Fallin, Donghyuk Lee, Rachata Ausavarungnirun, Gennady Pekhimenko, Yixin Luo, Onur Mutlu (CMU), Phillip B. Gibbons, Michael A. Kozuch (Intel), and Todd C. Mowry (CMU)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540725
Quantifying the Relationship between the Power Delivery Network and Architectural Policies in a 3D-Stacked Memory Device
Manjunath Shevgoor (University of Utah), Jung-Sik Kim (Samsung), Niladrish Chatterjee, Rajeev Balasubramonian, Al Davis (University of Utah), and Aniruddha N. Udipi (ARM)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540726

8:30-10:00: Session 3B - Power Management & Interconnects [Alpha Gamma Rho Ballroom]
Session Chair: Karu Sankaraligam

Crank It Up or Dial It Down: Coordinated Multiprocessor Frequency and Folding Control
Augusto Vega, Alper Buyuktosunoglu, Heather Hanson, Pradip Bose, and Srinivasan Ramani (IBM)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540727
Wavelength Stealing: An Opportunistic Approach to Channel Sharing in Multi-chip Photonic Interconnects
Arslan Zulfiqar (University of Wisconsin - Madison), Pranay Koka, Herb Schwetman (Oracle Labs), Mikko Lipasti (University of Wisconsin - Madison), Xuezhe Zheng, and Ashok V. Krishnamoorthy (Oracle Labs)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540728
DESC: Energy-Efficient Data Exchange using Synchronized Counters
Mahdi Nazm Bojnordi and Engin Ipek (University of Rochester)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540729

10:00-10:30: Break

10:30-12:00: Session 4A - Prefetching [Conference Center Ballroom]
Session Chair: Simha Sethumadhavan

Linearizing Irregular Memory Accesses for Improved Correlated Prefetching
Akanksha Jain and Calvin Lin (University of Texas at Austin)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540730
RDIP: Return-address-stack Directed Instruction Prefetching
Aasheesh Kolli (University of Michigan), Ali Saidi (ARM), and Thomas Wenisch (University of Michigan)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540731
SHIFT: Shared History Instruction Fetch for Lean-Core Server Processors
Cansu Kaynak (EPFL), Boris Grot (University of Edinburgh), and Babak Falsafi (EPFL)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540732

10:30-12:00: Session 4B - Cache Management [Alpha Gamma Rho Room]
Session Chair: Daniel Sanchez

Insertion and Promotion for Tree-Based PseudoLRU Last-Level Caches
Daniel A. Jimenez (Texas A&M)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540733
Imbalanced Cache Partitioning for Balanced Data-Parallel Programs
Abhisek Pan and Vijay S. Pai (Purdue University)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540734
The Reuse Cache: Downsizing the Shared Last-Level Cache
Jorge Albericio (University of Toronto), Pablo Ibáñez, Víctor Viñals (University of Zaragoza), and José M. Llabería (UPC Barcelona Tech)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540735

12:00-13:00: Lunch [Conference Center]

13:00-14:00: Bob Rau Award Presentation [Conference Center Ballroom]

Bob Rau Award Presentation - Speech by Kemal Ebcioğlu
Introduction to Bob Rau Award, by Bill Mangione-Smith
Presentation: PDF

14:00-15:00: Poster Session [Conference Center]
Session Chair: Christina Delimitrou

15:00-15:30: Break

15:30-17:00: Session 5A - Programming, Compilation, and Provisioning [Conference Center Ballroom]
Session Chair: Jason Mars

Enabling Datacenter Servers to Scale Out Economically and Sustainably
Chao Li, Yang Hu, Ruijin Zhou, Ming Liu (University of Florida), Longjun Liu (Xi'an Jiaotong University, China), Jingling Yuan (Wuhan University of Technology, China), and Tao Li (University of Florida)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540736
Efficient Multiprogramming for Multicores with SCAF
Timothy Creech, Aparna Kotha, and Rajeev Barua (University of Maryland, College Park)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540737
Allocating Rotating Registers by Scheduling
Hongbo Rong, Hyunchul Park, Cheng Wang, and Youfeng Wu (Intel Labs)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540738

15:30-17:00: Session 5B - Coherence & Memory Management [Alpha Gamma Rho Room]
Session Chair: Satish Narayanasamy

Multi-Grain Coherence Directory
Jason Zebchuk (University of Toronto), Babak Falsafi (EPFL), and Andreas Moshovos (University of Toronto)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540739
BulkCommit: Scalable and Fast Commit of Atomic Blocks in a Lazy Multiprocessor Environment
Xuehai Qian (University of California, Berkeley), Benjamin Sahelics (Universidad de Valladolid, Spain), Josep Torrellas (University of Illinois, Urbana-Champaign), and Depei Qian (Beihang University)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540740
Large-Reach Memory Management Unit Caches
Abhishek Bhattacharjee (Rutgers University)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540741

18:30-22:30: Conference Excursion and Banquet - California State Railroad Museum

Buses depart to the Railroad Museum from the Conference Center approximately every 10 minutes from 18:00 to 19:00; buses return to the hotel approximately every 15 minutes between 21:30 and 23:00.

Wednesday, December 11, 2013

7:30-12:30: Conference Registration [Conference Center Foyer]

7:30-8:30: Breakfast [Conference Center]

8:30-9:30: Keynote II [Conference Center Ballroom]
Session Chair: Matthew Farrens

Vidya Rajagopalan, VP of Processing Platforms, Xilinx
All Programmable Devices: Not just an FPGA anymore
Presentation: PDF

9:30-9:45: Break

9:45-10:45: Session 6A - GPU Memory Management [Conference Center Ballroom]
Session Chair: Vijay Janapa Reddi

Efficient Management of Last-level Caches in Graphics Processors for 3D Scene Rendering Workloads
Jayesh Gaur (Intel Corporation), Raghuram Onti Srinivasan (The Ohio State University), Sreenivas Subramoney (Intel Corporation), and Mainak Chaudhuri (Indian Institute of Technology, Kanpur)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540742
Energy Efficient GPU Transactional Memory via Space-Time Optimizations
Wilson Wai Lun Fung and Tor M. Aamodt (University of British Columbia)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540743

9:45-10:45: Session 6B - Storage Optimizations [Alpha Gamma Rho Room]
Session Chair: Engin Ipek

Kiln: Closing the Performance Gap Between Systems With and Without Persistence Support
Jishen Zhao (Pennsylvania State University), Sheng Li (Hewlett-Packard Labs), Doe Hyun Yoon (IBM Thomas J. Watson Research Center), Yuan Xie (Pennsylvania State University/AMD Research), and Norman P. Jouppi (Google)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540744
Aegis: Partitioning Data Block for Efficient Recovery of Stuck-At-Faults in Phase Change Memory
Jie Fan (Tsinghua University / Department of Computer Science and Technology), Song Jiang (Wayne State University / The ECE Department), Jiwu Shu, Youhui Zhang, and Weimin Zhen (Tsinghua University / Department of Computer Science and Technology)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540745

10:45-11:00: Break

11:00-12:30: Session 7 - Heterogeneous Computing [Conference Center Ballroom]
Session Chair: Ben Lee

Trace Based Phase Prediction For Tightly-Coupled Heterogeneous Cores
Shruti Padmanabha, Andrew Lukefahr, Reetuparna Das, and Scott Mahlke (University of Michigan)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540746
Heterogeneous System Coherence for Integrated CPU-GPU Systems
Jason Power, Arkaprava Basu (University of Wisconsin-Madison). Junli Gu, Sooraj Puthoor, Bradford M. Beckmann (AMD), Mark D. Hill (University of Wisconsin-Madison, AMD), Steven K. Reinhardt (AMD), and David A. Wood (University of Wisconsin-Madison, AMD)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540747
Meet the Walkers: Accelerating Index Traversals for In-Memory Databases
Onur Kocberber (EPFL), Boris Grot (University of Edinburgh), Javier Picorel, Babak Falsafi (EPFL), Kevin Lim (HP Labs), and Parthasarathy Ranganathan (Google)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540748

12:30-12:45: Closing Remarks & Best Paper Award [Conference Center Ballroom]

Best Paper Honorable Mention
Kiln: Closing the Performance Gap Between Systems With and Without Persistence Support

Jishen Zhao (Pennsylvania State University), Sheng Li (Hewlett-Packard Labs), Doe Hyun Yoon (IBM Thomas J. Watson Research Center), Yuan Xie (Pennsylvania State University/AMD Research), and Norman P. Jouppi (Google)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540744
Linearizing Irregular Memory Accesses for Improved Correlated Prefetching
Akanksha Jain and Calvin Lin (University of Texas at Austin)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540730
Best Paper Runner Up
Meet the Walkers: Accelerating Index Traversals for In-Memory Databases

Onur Kocberber (EPFL), Boris Grot (University of Edinburgh), Javier Picorel, Babak Falsafi (EPFL), Kevin Lim (HP Labs), and Parthasarathy Ranganathan (Google)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540748
Best Paper
SAGE: Self-Tuning Approximation for Graphics Engines

Mehrzad Samadi, Janghaeng Lee, Davoud Jamshidi (University of Michigan), Amir Hormati (Google), and Scott Mahlke (University of Michigan)
Lightning session talk: PDF, Presentation: PDF, Poster: PDF, Full Paper: DOI 10.1145/2540708.2540711

12:45-13:45: Lunch [Conference Center]