update publications

content/publication/2014chen.md

@@ -51,9 +51,6 @@ tags = []
 # Does this page require source code highlighting? (true/false)
 highlight = true
 
-# Featured image thumbnail (optional)
-image_preview = ""
-
 # Links (optional)
 url_pdf = "pdf/2014chen.pdf"
 url_preprint = ""

content/publication/2016dakkak.md

@@ -5,11 +5,23 @@ date = "2016-01-01"
 title = "WebGPU: A Scalable Online Development Platform for GPU Programming Courses"
 authors = ["Adbul Dakkak", "Carl Pearson", "Cheng Li"]
 
+# Publication type.
+# Legend:
+# 0 = Uncategorized
+# 1 = Conference paper
+# 2 = Journal article
+# 3 = Manuscript
+# 4 = Report
+# 5 = Book
+# 6 = Book section
+publication_types = ["1"]
+
 abstract = 'The popularity of computer science classes offered through Massive Open On-line Courses (MOOCs) creates both opportunities and challenges. Programming-based classes need to provide consistent development infrastructures that are both scalable and user friendly to students. The \"Heterogeneous Parallel Programming\" class offered through Coursera teaches GPU programming and encountered these problems. We developed WebGPU - an online GPU development platform - providing students with a user friendly scalable GPU computing platform throughout the course. It has been used as the CUDA, OpenACC, and OpenCL programming environment for large Coursera courses, short-running summer schools, and traditional semester-long graduate and undergraduate courses. WebGPU has since replaced our traditional development infrastructure for the GPU classes offered at UIUC. This paper presents the original, revised, and upcoming WebGPU designs that address the requirements and challenges of offering sophisticated computing resources to a large, quickly-varying number of students.'
 
 
 math = false
-publication = "*Parallel and Distributed Processing Symposium Workshops, 2016 IEEE International.* IEEE, 2016."
+publication = "In *Parallel and Distributed Processing Symposium Workshops, 2016 IEEE International.*"
+publication_short = "IN *IPDPS*"
 
 url_code = ""
 url_dataset = ""

content/publication/20170621_hidayetoglu_cem.md

@@ -5,6 +5,18 @@ date = "2017-06-21"
 title = "Scalable Parallel DBIM Solutions of Inverse-Scattering Problems"
 authors = ["Mert Hidayetoglu", "Carl Pearson",  "Levent Gurel", "Wen-mei Hwu", "Weng Cho Chew"]
 
+# Publication type.
+# Legend:
+# 0 = Uncategorized
+# 1 = Conference paper
+# 2 = Journal article
+# 3 = Manuscript
+# 4 = Report
+# 5 = Book
+# 6 = Book section
+publication_types = ["1"]
+
+
 abstract = 'We report scalable solutions of inverse-scattering problems with the distorted Born iterative method (DBIM) on large number of computing nodes. Distributing forward solutions does not scale well when the number of illuminations is not greater than the number of computing nodes. As a remedy, we distribute both forward solutions and the corresponding forward solvers to improve granularity of DBIM solutions. This paper provides a set of solutions demonstrating good scaling of the proposed parallelization strategy up to 1,024 computing nodes, employing 16,394 processing cores in total.'
 
 
@@ -18,7 +30,7 @@ url_project = ""
 url_slides = ""
 url_video = ""
 
-selected = true
+selected = false
 
 # Featured image
 # To use, add an image named `featured.jpg/png` to your page's folder. 

content/publication/20170621_hwu_cem.md

@@ -1,29 +1,79 @@
 +++
+title = "Thoughts on Massively-Parallel Heterogeneous Computing for Solving Large Problems"
+date = 2017-06-21
 draft = false
 
-date = "2017-06-21"
-title = "Thoughts on Massively-Parallel Heterogeneous Computing for Solving Large Problems"
+# Authors. Comma separated list, e.g. `["Bob Smith", "David Jones"]`.
 authors = ["Wen-mei Hwu", "Mert Hidayetoglu", "Weng Cho Chew", "Carl Pearson", "Simon Garcia de Gonzalo", "Sitao Huang", "Abdul Dakkak"]
 
-abstract = 'In this paper, we present our view of massively-parallel heterogeneous computing for solving large scientific problems. We start by observing that computing has been the primary driver of major innovations since the beginning of the 21st century. We argue that this is the fruit of decades of progress in computing methods, technology, and systems. A high-level analysis on out-scaling and up-scaling on large supercomputers is given through a time-domain wave-scattering simulation example. The importance of heterogeneous node architectures for good up-scaling is highlighted. A case for low-complexity algorithms is made for continued scale-out towards exascale systems.'
+# Publication type.
+# Legend:
+# 0 = Uncategorized
+# 1 = Conference paper
+# 2 = Journal article
+# 3 = Manuscript
+# 4 = Report
+# 5 = Book
+# 6 = Book section
+publication_types = ["1"]
 
-math = false
-publication = "*Computing and Electromagnetics International Workshop.* IEEE, 2017."
+# Publication name and optional abbreviated version.
+publication = "In *Computing and Electromagnetics International Workshop*."
+publication_short = "In *CEM*"
 
+# Abstract and optional shortened version.
+abstract = "In this paper, we present our view of massively-parallel heterogeneous computing for solving large scientific problems. We start by observing that computing has been the primary driver of major innovations since the beginning of the 21st century. We argue that this is the fruit of decades of progress in computing methods, technology, and systems. A high-level analysis on out-scaling and up-scaling on large supercomputers is given through a time-domain wave-scattering simulation example. The importance of heterogeneous node architectures for good up-scaling is highlighted. A case for low-complexity algorithms is made for continued scale-out towards exascale systems."
+abstract_short = ""
+
+# Is this a selected publication? (true/false)
+selected = false
+
+# Projects (optional).
+#   Associate this publication with one or more of your projects.
+#   Simply enter your project's folder or file name without extension.
+#   E.g. `projects = ["deep-learning"]` references 
+#   `content/project/deep-learning/index.md`.
+#   Otherwise, set `projects = []`.
+projects = []
+
+# Slides (optional).
+#   Associate this publication with Markdown slides.
+#   Simply enter your slide deck's filename without extension.
+#   E.g. `slides = "example-slides"` references 
+#   `content/slides/example-slides.md`.
+#   Otherwise, set `slides = ""`.
+slides = "example-slides"
+
+# Tags (optional).
+#   Set `tags = []` for no tags, or use the form `tags = ["A Tag", "Another Tag"]` for one or more tags.
+tags = []
+
+# Links (optional).
+url_pdf = "pdf/20170621_hwu_cem.pdf"
+url_preprint = ""
 url_code = ""
 url_dataset = ""
-url_pdf = "pdf/20170621_hwu_cem.pdf"
 url_project = ""
 url_slides = ""
 url_video = ""
+url_poster = ""
+url_source = ""
 
-selected = true
+# Custom links (optional).
+#   Uncomment line below to enable. For multiple links, use the form `[{...}, {...}, {...}]`.
+# url_custom = [{name = "Custom Link", url = "http://example.org"}]
+
+# Digital Object Identifier (DOI)
+doi = ""
+
+# Does this page contain LaTeX math? (true/false)
+math = false
 
 # Featured image
 # To use, add an image named `featured.jpg/png` to your page's folder. 
 [image]
   # Caption (optional)
-  caption = ""
+  caption = "Image credit: [**Unsplash**](https://unsplash.com/photos/jdD8gXaTZsc)"
 
   # Focal point (optional)
   # Options: Smart, Center, TopLeft, Top, TopRight, Left, Right, BottomLeft, Bottom, BottomRight

content/publication/20170621_pearson_cem.md

@@ -18,8 +18,8 @@ authors = ["Carl Pearson", "Mert Hidayetoglu", "Wei Ren", "Weng Cho Chew", "Wen-
 publication_types = ["1"]
 
 # Publication name and optional abbreviated version.
-publication = "Computing and Electromagnetics International Workshop, IEEE 2017"
-publication_short = "CEM"
+publication = "In *Computing and Electromagnetics International Workshop, IEEE 2017*"
+publication_short = "In CEM"
 
 # Abstract and optional shortened version.
 abstract = "We compare multi-GPU performance of the multilevel fast multipole method (MLFMM) on two different systems: A shared-memory IBM S822LC workstation with four NVIDIA P100 GPUs, and 16 XK nodes (each is employed with a single NVIDIA K20X GPU) of the Blue Waters supercomputer. MLFMM is implemented for solving scattering problems involving two-dimensional inhomogeneous bodies. Results show that the multi-GPU implementation provides 794 and 969 times speedups on the IBM and Blue Waters systems over their corresponding sequential CPU executions, respectively, where the sequential execution on the IBM system is 1.17 times faster than on the Blue Waters System."

content/publication/20170910_hwu_bsc.md

@@ -0,0 +1,81 @@
++++
+title = "Innovative Applications and Technology Pivots - A Perfect Storm in Computing"
+date = 2017-09-10
+draft = false
+
+# Authors. Comma separated list, e.g. `["Bob Smith", "David Jones"]`.
+authors = ["Wen-mei Hwu", "Izzat El Hajj", "Simon Garcia de Gonzalo", "Carl Pearson", "Nam Sung Kim", "Deming Chen", "Jinjun Xiong", "Zehra Sura"]
+
+# Publication type.
+# Legend:
+# 0 = Uncategorized
+# 1 = Conference paper
+# 2 = Journal article
+# 3 = Manuscript
+# 4 = Report
+# 5 = Book
+# 6 = Book section
+publication_types = ["0"]
+
+# Publication name and optional abbreviated version.
+publication = "Barcelona Supercomputing Center"
+publication_short = "*BSC*"
+
+# Abstract and optional shortened version.
+abstract = ""
+abstract_short = ""
+
+# Is this a selected publication? (true/false)
+selected = false
+
+# Projects (optional).
+#   Associate this publication with one or more of your projects.
+#   Simply enter your project's folder or file name without extension.
+#   E.g. `projects = ["deep-learning"]` references 
+#   `content/project/deep-learning/index.md`.
+#   Otherwise, set `projects = []`.
+projects = []
+
+# Slides (optional).
+#   Associate this publication with Markdown slides.
+#   Simply enter your slide deck's filename without extension.
+#   E.g. `slides = "example-slides"` references 
+#   `content/slides/example-slides.md`.
+#   Otherwise, set `slides = ""`.
+slides = ""
+
+# Tags (optional).
+#   Set `tags = []` for no tags, or use the form `tags = ["A Tag", "Another Tag"]` for one or more tags.
+tags = []
+
+# Links (optional).
+url_pdf = ""
+url_preprint = ""
+url_code = ""
+url_dataset = ""
+url_project = ""
+url_slides = "pdf/20170910_hwu_bsc.pdf"
+url_video = ""
+url_poster = ""
+url_source = ""
+
+# Custom links (optional).
+#   Uncomment line below to enable. For multiple links, use the form `[{...}, {...}, {...}]`.
+# url_custom = [{name = "Custom Link", url = "http://example.org"}]
+
+# Digital Object Identifier (DOI)
+doi = ""
+
+# Does this page contain LaTeX math? (true/false)
+math = false
+
+# Featured image
+# To use, add an image named `featured.jpg/png` to your page's folder. 
+[image]
+  # Caption (optional)
+  caption = "Image credit: [**Unsplash**](https://unsplash.com/photos/jdD8gXaTZsc)"
+
+  # Focal point (optional)
+  # Options: Smart, Center, TopLeft, Top, TopRight, Left, Right, BottomLeft, Bottom, BottomRight
+  focal_point = ""
++++

content/publication/20171108_hwu_icrc.md

@@ -0,0 +1,81 @@
++++
+title = "Rebooting the Data Access Hierarchy of Computing Systems"
+date = 2017-11-18
+draft = false
+
+# Authors. Comma separated list, e.g. `["Bob Smith", "David Jones"]`.
+authors = ["Wen-mei Hwu", "Izzat El Hajj", "Simon Garcia de Gonzalo", "Carl Pearson", "Nam Sung Kim", "Deming Chen", "Jinjun Xiong", "Zehra Sura"]
+
+# Publication type.
+# Legend:
+# 0 = Uncategorized
+# 1 = Conference paper
+# 2 = Journal article
+# 3 = Manuscript
+# 4 = Report
+# 5 = Book
+# 6 = Book section
+publication_types = ["0"]
+
+# Publication name and optional abbreviated version.
+publication = "In *Computing and Electromagnetics International Workshop*."
+publication_short = "In *CEM*"
+
+# Abstract and optional shortened version.
+abstract = "In this paper, we present our view of massively-parallel heterogeneous computing for solving large scientific problems. We start by observing that computing has been the primary driver of major innovations since the beginning of the 21st century. We argue that this is the fruit of decades of progress in computing methods, technology, and systems. A high-level analysis on out-scaling and up-scaling on large supercomputers is given through a time-domain wave-scattering simulation example. The importance of heterogeneous node architectures for good up-scaling is highlighted. A case for low-complexity algorithms is made for continued scale-out towards exascale systems."
+abstract_short = ""
+
+# Is this a selected publication? (true/false)
+selected = false
+
+# Projects (optional).
+#   Associate this publication with one or more of your projects.
+#   Simply enter your project's folder or file name without extension.
+#   E.g. `projects = ["deep-learning"]` references 
+#   `content/project/deep-learning/index.md`.
+#   Otherwise, set `projects = []`.
+projects = []
+
+# Slides (optional).
+#   Associate this publication with Markdown slides.
+#   Simply enter your slide deck's filename without extension.
+#   E.g. `slides = "example-slides"` references 
+#   `content/slides/example-slides.md`.
+#   Otherwise, set `slides = ""`.
+slides = ""
+
+# Tags (optional).
+#   Set `tags = []` for no tags, or use the form `tags = ["A Tag", "Another Tag"]` for one or more tags.
+tags = []
+
+# Links (optional).
+url_pdf = "pdf/20170621_hwu_cem.pdf"
+url_preprint = ""
+url_code = ""
+url_dataset = ""
+url_project = ""
+url_slides = ""
+url_video = ""
+url_poster = ""
+url_source = ""
+
+# Custom links (optional).
+#   Uncomment line below to enable. For multiple links, use the form `[{...}, {...}, {...}]`.
+# url_custom = [{name = "Custom Link", url = "http://example.org"}]
+
+# Digital Object Identifier (DOI)
+doi = ""
+
+# Does this page contain LaTeX math? (true/false)
+math = false
+
+# Featured image
+# To use, add an image named `featured.jpg/png` to your page's folder. 
+[image]
+  # Caption (optional)
+  caption = "Image credit: [**Unsplash**](https://unsplash.com/photos/jdD8gXaTZsc)"
+
+  # Focal point (optional)
+  # Options: Smart, Center, TopLeft, Top, TopRight, Left, Right, BottomLeft, Bottom, BottomRight
+  focal_point = ""
++++

content/publication/2017dakkak.md

@@ -9,12 +9,12 @@ authors = ["Adbul Dakkak", "Carl Pearson", "Cheng Li"]
 # Publication type.
 # Legend:
 # 0 = Uncategorized
-# 1 = Conference proceedings
-# 2 = Journal
-# 3 = Work in progress
-# 4 = Technical report
+# 1 = Conference paper
+# 2 = Journal article
+# 3 = Manuscript
+# 4 = Report
 # 5 = Book
-# 6 = Book chapter
+# 6 = Book section
 publication_types = ["1"]
 
 # Publication name and optional abbreviated version.
@@ -29,13 +29,10 @@ abstract_short = ""
 math = false
 
 # Does this page require source code highlighting? (true/false)
-highlight = true
-
-# Featured image thumbnail (optional)
-image_preview = ""
+highlight = false
 
 # Is this a selected publication? (true/false)
-selected = false
+selected = true
 
 # Links (optional)
 url_pdf = "pdf/rai-edupar2017.pdf"

content/publication/2017hidayetoglu.md

@@ -5,11 +5,21 @@ date = "2017-03-28"
 title = "Large Inverse-Scattering Solutions with DBIM on GPU-Enabled Supercomputers"
 authors = ["Mert Hidayetoglu", "Carl Pearson", "Weng Cho Chew", "Levent Gurel", "Wen-mei Hwu"]
 
-abstract = ''
+# Publication type.
+# Legend:
+# 0 = Uncategorized
+# 1 = Conference paper
+# 2 = Journal article
+# 3 = Manuscript
+# 4 = Report
+# 5 = Book
+# 6 = Book section
+publication_types = ["1"]
 
+abstract = 'We report inverse-scattering solutions on supercomputers involving large numbers of graphics processing units (GPUs). The distorted-Born iterative method (DBIM) is employed for the iterative inversions. In each iteration, the required forward problems are distributed among computing nodes equipped with GPUs, and solved with the multilevel fast multipole algorithm. A tomographic reconstruction of a synthetic object with a linear dimension of one hundred wavelengths is obtained on 256 GPUs. The results show that DBIM obtains images approximately four times faster on GPUs, compared to parallel executions on traditional CPU-only computing nodes.'
 
 math = false
-publication = "*Applied and Computational Electromagnetics Symposium, 2017.* For the special session: Big Data Aspects"
+publication = "In *Applied and Computational Electromagnetics Symposium, 2017.* For the special session: Big Data Aspects"
 
 url_code = ""
 url_dataset = ""
@@ -18,7 +28,7 @@ url_project = ""
 url_slides = ""
 url_video = ""
 
-selected = true
+selected = false
 
 # Featured image
 # To use, add an image named `featured.jpg/png` to your page's folder. 

content/publication/20180521_hidayetoglu_ipdps.md

@@ -1,5 +1,5 @@
 +++
-title = "A Fast and Massively-Parallel Solver for Nonlinear Tomographic Image Reconstruction"
+title = "A Fast and Massively-Parallel Solver for Multiple-Scattering Tomographic Image Reconstruction"
 date = 2018-05-21
 draft = false
 
@@ -18,8 +18,8 @@ authors = ["Mert Hidayetoglu", "Carl Pearson", "Izzat El Hajj", "Levent Gurel",
 publication_types = ["1"]
 
 # Publication name and optional abbreviated version.
-publication = "2018 IEEE International Parallel and Distributed Processing Symposium"
-publication_short = "IPDPS 2018"
+publication = "In *2018 IEEE International Parallel and Distributed Processing Symposium*"
+publication_short = "In *IPDPS*"
 
 # Abstract and optional shortened version.
 abstract = "We present a massively-parallel solver for large Helmholtz-type inverse scattering problems. The solver employs the distorted Born iterative method for capturing the multiple-scattering phenomena in image reconstructions. This method requires many full-wave forward-scattering solutions in each iteration, constituting the main performance bottleneck with its high computational complexity. As a remedy, we use the multilevel fast multipole algorithm (MLFMA). The solver scales among computing nodes using a two-dimensional parallelization strategy that distributes illuminations in one dimension, and MLFMA sub-trees in the other dimension. Multi-core CPUs and GPUs are used to provide per-node speedup. We demonstrate a 76% efficiency when scaling from 64 GPUs to 4,096 GPUs. The paper provides reconstruction of a 204.8λ×204.8λ image (4M unknowns) executed on 4,096 GPUs in near-real time (almost 2 minutes). To the best of our knowledge, this is the largest full-wave inverse scattering solution to date, in terms of both image size and computational resources."

content/publication/20180625_pearson_ms.md

@@ -0,0 +1,60 @@
++++
+title = "Heterogeneous Application and System Modeling"
+date = 2018-06-25
+draft = false
+
+# Authors. Comma separated list, e.g. `["Bob Smith", "David Jones"]`.
+authors = ["Carl Pearson"]
+
+# Publication type.
+# Legend:
+# 0 = Uncategorized
+# 1 = Conference paper
+# 2 = Journal article
+# 3 = Manuscript
+# 4 = Report
+# 5 = Book
+# 6 = Book section
+publication_types = ["3"]
+
+# Publication name and optional abbreviated version.
+publication = "M.S. Thesis"
+publication_short = ""
+
+# Abstract and optional shortened version.
+abstract = "With the end of Dennard scaling, high-performance computing increasingly relies on heterogeneous systems with specialized hardware to improve application performance. This trend has driven up the complexity of high-performance software development, as developers must manage multiple programming systems and develop system-tuned code to utilize specialized hardware. In addition, it has exacerbated existing challenges of data placement as the specialized hardware often has local memories to fuel its computational demands. In addition to using appropriate software resources to target application computation at the best hardware for the job, application developers now must manage data movement and placement within their application, which also must be specifically tuned to the target system. Instead of relying on the application developer to have specialized knowledge of system characteristics and specialized expertise in multiple programming systems, this work proposes a heterogeneous system communication library that automatically chooses data location and data movement for high-performance application development and execution on heterogeneous systems. This work presents the foundational components of that library: a systematic approach for characterization of system communication links and application communication demands."
+abstract_short = ""
+
+# Does this page contain LaTeX math? (true/false)
+math = false
+
+# Does this page require source code highlighting? (true/false)
+highlight = false
+
+# Featured image thumbnail (optional)
+image_preview = ""
+
+# Is this a selected publication? (true/false)
+selected = true
+
+# Links (optional)
+url_pdf = "pdf/20180625_pearson_ms.pdf"
+url_preprint = ""
+url_code = ""
+url_dataset = ""
+url_project = ""
+url_slides = ""
+url_video = ""
+url_poster = ""
+url_source = ""
+
+# Featured image
+# To use, add an image named `featured.jpg/png` to your page's folder. 
+[image]
+  # Caption (optional)
+  caption = ""
+
+  # Focal point (optional)
+  # Options: Smart, Center, TopLeft, Top, TopRight, Left, Right, BottomLeft, Bottom, BottomRight
+  focal_point = ""
++++

content/publication/20180628_pearson_iwoph.md

@@ -9,12 +9,12 @@ authors = ["Carl Pearson", "I-Hsin Chung", "Zehra Sura", "Jinjun Xiong", "Wen-Me
 # Publication type.
 # Legend:
 # 0 = Uncategorized
-# 1 = Conference proceedings
-# 2 = Journal
-# 3 = Work in progress
-# 4 = Technical report
+# 1 = Conference paper
+# 2 = Journal article
+# 3 = Manuscript
+# 4 = Report
 # 5 = Book
-# 6 = Book chapter
+# 6 = Book section
 publication_types = ["1"]
 
 # Publication name and optional abbreviated version.
@@ -57,5 +57,4 @@ url_source = ""
   # Focal point (optional)
   # Options: Smart, Center, TopLeft, Top, TopRight, Left, Right, BottomLeft, Bottom, BottomRight
   focal_point = ""
-
 +++

content/publication/20180919_pearson_arxiv.md

@@ -0,0 +1,60 @@
++++
+title = "SCOPE: C3SR Systems Characterization and Benchmarking Framework"
+date = 2018-09-18
+draft = false
+
+# Authors. Comma separated list, e.g. `["Bob Smith", "David Jones"]`.
+authors = ["Carl Pearson", "Abdul Dakkak", "Cheng Li", "Sarah Hashash", "Jinjun Xiong", "Wen-Mei Hwu"]
+
+# Publication type.
+# Legend:
+# 0 = Uncategorized
+# 1 = Conference paper
+# 2 = Journal article
+# 3 = Manuscript
+# 4 = Report
+# 5 = Book
+# 6 = Book section
+publication_types = ["4"]
+
+# Publication name and optional abbreviated version.
+publication = "arXiv preprint"
+publication_short = "arXiv preprint"
+
+# Abstract and optional shortened version.
+abstract = "This report presents the design of the Scope infrastructure for extensible and portable benchmarking. Improvements in high-performance computing systems rely on coordination across different levels of system abstraction. Developing and defining accurate performance measurements is necessary at all levels of the system hierarchy, and should be as accessible as possible to developers with different backgrounds. The Scope project aims to lower the barrier to entry for developing performance benchmarks by providing a software architecture that allows benchmarks to be developed independently, by providing useful C/C++ abstractions and utilities, and by providing a Python package for generating publication-quality plots of resulting measurements."
+abstract_short = ""
+
+# Does this page contain LaTeX math? (true/false)
+math = false
+
+# Does this page require source code highlighting? (true/false)
+highlight = false
+
+# Featured image thumbnail (optional)
+image_preview = ""
+
+# Is this a selected publication? (true/false)
+selected = false
+
+# Links (optional)
+url_pdf = "pdf/20180918_pearson_arxiv.pdf"
+url_preprint = ""
+url_code = ""
+url_dataset = ""
+url_project = ""
+url_slides = ""
+url_video = ""
+url_poster = ""
+url_source = ""
+
+# Featured image
+# To use, add an image named `featured.jpg/png` to your page's folder. 
+[image]
+  # Caption (optional)
+  caption = ""
+
+  # Focal point (optional)
+  # Options: Smart, Center, TopLeft, Top, TopRight, Left, Right, BottomLeft, Bottom, BottomRight
+  focal_point = ""
++++

content/publication/20180925_mailthody_hpec.md

@@ -0,0 +1,60 @@
++++
+title = "Collaborative (CPU+ GPU) Algorithms for Triangle Counting and Truss Decomposition"
+date = 2018-09-25
+draft = false
+
+# Authors. Comma separated list, e.g. `["Bob Smith", "David Jones"]`.
+authors = ["Vikram S. Mailthody", "Ketan Date", "Zaid Qureshi", "Carl Pearson", "Rakesh Nagi", "Jinjun Xiong", "Wen-Mei Hwu"]
+
+# Publication type.
+# Legend:
+# 0 = Uncategorized
+# 1 = Conference paper
+# 2 = Journal article
+# 3 = Manuscript
+# 4 = Report
+# 5 = Book
+# 6 = Book section
+publication_types = ["1"]
+
+# Publication name and optional abbreviated version.
+publication = "In *2018 IEEE High Performance extreme Computing Conference*"
+publication_short = "In *HPEC*"
+
+# Abstract and optional shortened version.
+abstract = 'In this paper, we present an update to our previous submission  from  Graph  Challenge  2017.  This  work  describes and evaluates new software algorithm optimizations undertaken for our 2018 year submission on Collaborative CPU+GPU Algorithms for Triangle Counting and Truss Decomposition. First, we describe four major optimizations for the triangle counting which improved performance by up to 117x over our prior submission. Additionally,  we  show  that  our triangle-counting  algorithm  is on average 151.7x faster than NVIDIA’s NVGraph library (max 476x)  for  SNAP  datasets.  Second,  we  propose  a  novel  parallel k-truss  decomposition  algorithm  that  is  time-efficient  and  is  up to 13.9x faster than our previous submission. Third, we evaluate the  effect  of  generational  hardware  improvements  between  the IBM  “Minsky”  (POWER8,  P100,  NVLink  1.0)  and  “Newell” (POWER9,  V100,  NVLink  2.0)  platforms.  Lastly,  the  software optimizations presented in this work and the hardware improvements  in  the  Newell  platform  enable  analytics  and  discovery  on large graphs  with millions of nodes  and billions of edges  in less than a minute. In sum, the new algorithmic implementations are significantly  faster  and  can  handle  much  larger  “big”  graphs.'
+abstract_short = ""
+
+# Does this page contain LaTeX math? (true/false)
+math = false
+
+# Does this page require source code highlighting? (true/false)
+highlight = false
+
+# Featured image thumbnail (optional)
+image_preview = ""
+
+# Is this a selected publication? (true/false)
+selected = true
+
+# Links (optional)
+url_pdf = "pdf/20180925_mailthody_iwoph.pdf"
+url_preprint = ""
+url_code = ""
+url_dataset = ""
+url_project = ""
+url_slides = ""
+url_video = ""
+url_poster = ""
+url_source = ""
+
+# Featured image
+# To use, add an image named `featured.jpg/png` to your page's folder. 
+[image]
+  # Caption (optional)
+  caption = ""
+
+  # Focal point (optional)
+  # Options: Smart, Center, TopLeft, Top, TopRight, Left, Right, BottomLeft, Bottom, BottomRight
+  focal_point = ""
++++