PPoPP 2018 - PPoPP 2018

Write a Blog >>

Sat 24 - Wed 28 February 2018 Vösendorf / Wien, Austria

About
Program

Papers accepted for the PPoPP 2018 conference

Accepted Papers

	Title
	A Persistent Lock-Free Queue for Non-Volatile Memory
	An Effective Fusion and Tile Size Model for Optimizing Image Processing Pipelines
	Bridging the Gap between Deep Learning and Sparse Matrix Format Selection
	Cache-Tries: Concurrent Lock-Free Hash Tries with Constant-Time Operations
	Communication-Avoiding Minimum Cuts and Connected Components
	DisCVar: Discovering Critical Variables Using Algorithmic Differentiation for Transient Faults
	Efficient Parallel Race Detection for Two-Dimensional Dags
	Efficient Shuffle Management with SCache for DAG Computing Frameworks
	Featherlight On-the-fly False-sharing Detection
	FlashR: Parallelize and Scale R for Machine Learning using SSDs
	Griffin: Uniting CPU and GPU in Web Search for Intra-Query Parallelism
	HPVM: Heterogeneous Parallel Virtual Machine
	Harnessing Epoch-based Reclamation for Efficient Range Queries
	Hierarchical Memory Management for Mutable State
	High-Performance Genomics Data Analysis Framework with In-Memory Computing
	Interval-Based Memory Reclamation
	Juggler: A Dependency-Aware Task Based Execution Framework for GPUs
	LazyGraph: Lazy Data Coherency for Replicas in Distributed Graph-Parallel Computation
	Making Pull-Based Graph Processing Performant
	Optimizing N-Dimensional, Winograd-Based Convolution for Manycore CPUs
	PAM: Parallel Augmented Maps
	Practical Concurrent Traversals in Search Trees
	Register Optimizations for Stencils on GPUs
	Safe Privatization in Transactional Memory
	SuperNeurons: Dynamic GPU Memory Management for Training Deep Neural Networks
	VerifiedFT: A Verified, High-Performance Dynamic Race Detector
	swSpTRSV: a Fast Sparse Triangular Solve with Sparse Level Tile Layout on Sunway Architectures
	vSensor: Leveraging Fixed-Workload Modules of Programs for Performance Variance Detection

Mon 26 Feb

10:20 - 11:35: PPoPP 2018 - PPoPP Session 1: Concurrent Data Structures at Europa 3
Chair(s): Xipeng Shen

10:20 - 10:45
Talk

Interval-Based Memory Reclamation

10:45 - 11:10
Talk

Harnessing Epoch-based Reclamation for Efficient Range Queries

11:10 - 11:35
Talk

A Persistent Lock-Free Queue for Non-Volatile Memory

13:15 - 14:55: PPoPP 2018 - PPoPP Session 2: Compilers and runtime systems at Europa 3
Chair(s): I-Ting Angelina Lee

13:15 - 13:40
Talk

Juggler: A Dependency-Aware Task Based Execution Framework for GPUs

13:40 - 14:05
Talk

HPVM: Heterogeneous Parallel Virtual Machine

14:05 - 14:30
Talk

Hierarchical Memory Management for Mutable State

14:30 - 14:55
Talk

SuperNeurons: Dynamic GPU Memory Management for Training Deep Neural Networks

15:15 - 16:30: PPoPP 2018 - PPoPP Session 3: Performance at Europa 3
Chair(s): Milind Chabbi

15:15 - 15:40
Talk

Bridging the Gap between Deep Learning and Sparse Matrix Format Selection

15:40 - 16:05
Talk

Optimizing N-Dimensional, Winograd-Based Convolution for Manycore CPUs

16:05 - 16:30
Talk

vSensor: Leveraging Fixed-Workload Modules of Programs for Performance Variance Detection

Tue 27 Feb

08:00 - 09:40: PPoPP 2018 - PPoPP Session 4: Best Paper Candidates at Europa 3
Chair(s): Idit Keidar

08:00 - 08:25
Talk

Cache-Tries: Concurrent Lock-Free Hash Tries with Constant-Time Operations

08:25 - 08:50
Talk

Featherlight On-the-fly False-sharing Detection

08:50 - 09:15
Talk

Register Optimizations for Stencils on GPUs

09:15 - 09:40
Talk

FlashR: Parallelize and Scale R for Machine Learning using SSDs

10:05 - 11:45: PPoPP 2018 - PPoPP Session 5: Concurrency control and fault tolerance at Europa 3
Chair(s): Walter Binder

10:05 - 10:30
Talk

DisCVar: Discovering Critical Variables Using Algorithmic Differentiation for Transient Faults

10:30 - 10:55
Talk

Practical Concurrent Traversals in Search Trees

10:55 - 11:20
Talk

Communication-Avoiding Minimum Cuts and Connected Components

11:20 - 11:45
Talk

Safe Privatization in Transactional Memory

14:50 - 16:30: PPoPP 2018 - PPoPP Session 6: Models and Libraries at Europa 3
Chair(s): Zoltan Majo

14:50 - 15:15
Talk

Making Pull-Based Graph Processing Performant

15:15 - 15:40
Talk

An Effective Fusion and Tile Size Model for Optimizing Image Processing Pipelines

15:40 - 16:05
Talk

LazyGraph: Lazy Data Coherency for Replicas in Distributed Graph-Parallel Computation

16:05 - 16:30
Talk

PAM: Parallel Augmented Maps

Wed 28 Feb

09:25 - 11:05: PPoPP 2018 - PPoPP Session 7: Parallel frameworks and applications at Europa 3
Chair(s): Bernhard Egger

09:25 - 09:50
Talk

Efficient Shuffle Management with SCache for DAG Computing Frameworks

09:50 - 10:15
Talk

High-Performance Genomics Data Analysis Framework with In-Memory Computing

10:15 - 10:40
Talk

Griffin: Uniting CPU and GPU in Web Search for Intra-Query Parallelism

10:40 - 11:05
Talk

swSpTRSV: a Fast Sparse Triangular Solve with Sparse Level Tile Layout on Sunway Architectures

11:20 - 12:10: PPoPP 2018 - PPoPP Session 8: Race Detection at Europa 3
Chair(s): Jesper Träff

11:20 - 11:45
Talk

VerifiedFT: A Verified, High-Performance Dynamic Race Detector

11:45 - 12:10
Talk

Efficient Parallel Race Detection for Two-Dimensional Dags