Activity
-
Excited to share that my friends & former Meta AI colleagues, Tamara Berg and Michelle Cheung, just launched something special. HeyAio is building…
Excited to share that my friends & former Meta AI colleagues, Tamara Berg and Michelle Cheung, just launched something special. HeyAio is building…
Liked by Joseph Spisak
-
Some conversations stay with you. Varun Khare and I recently hosted a panel with Joseph Spisak (Meta, PyTorch Board) and Saurabh Tangri (Intel, ONNX…
Some conversations stay with you. Varun Khare and I recently hosted a panel with Joseph Spisak (Meta, PyTorch Board) and Saurabh Tangri (Intel, ONNX…
Liked by Joseph Spisak
-
For about ~4 years or so, we've had a dream to launch a GPU marketplace. This week it finally came true after a ton of hard work from the Lightning…
For about ~4 years or so, we've had a dream to launch a GPU marketplace. This week it finally came true after a ton of hard work from the Lightning…
Liked by Joseph Spisak
Experience & Education
-
Meta
View Joseph’s full experience
See their title, tenure and more.
or
Licenses & Certifications
Publications
-
Intel's Machine Learning Strategy
See publicationJoseph Spisak, Director, Strategy and Business Development at Intel, discusses Intel’s machine learning strategy and its impact.
-
Advancing Machine Learning to Uncover New Insights
See publicationMachine learning holds the promise of not only structuring vast amounts of data but also to create true business intelligence
-
Power Efficient MapReduce Workload Acceleration using Integrated-GPU
The 1st IEEE International Conference on Big Data Computing Service and Applications
With the pervasiveness of MapReduce - one of the most prominent programming models for data parallelism in Apache Hadoop-, many researchers and developers have spent tremendous effort attempting to boost the computational speed and energy efficiency of MapReduce-based big data processing. However, the scalable and fault-tolerant nature of MapReduce introduces additional costs in disk IO and data transfer, caused by streaming intermediate outputs to disk. In light of these issues, many…
With the pervasiveness of MapReduce - one of the most prominent programming models for data parallelism in Apache Hadoop-, many researchers and developers have spent tremendous effort attempting to boost the computational speed and energy efficiency of MapReduce-based big data processing. However, the scalable and fault-tolerant nature of MapReduce introduces additional costs in disk IO and data transfer, caused by streaming intermediate outputs to disk. In light of these issues, many interesting research projects have been initiated with the goal of improving the compute speed and power efficiency of compute-intensive cloud computing workloads, several with the addition of discrete GPUs. In this work, we present a modified MapReduce approach focused on the iterative clustering algorithms in the Apache Mahout machine learning library that leverage the acceleration potential of the Intel integrated GPU in a multi-node cluster environment. The accelerated framework shows varying levels of speed-up (≈45x for Map tasks-only, ≈4.37x for the entire K-means clustering) as evaluated using the HiBench benchmark suite. Based on various experiments and in-depth analysis, we find that utilizing the integrated GPU via OpenCL offers significant performance and power efficiency gains over the original CPU based approach. Further analysis is also done to understand the correlations between compute, IO and power efficiency. As such, our results show that embracing the integrated GPU in the Hadoop MapReduce framework represents a promising advance in adding cost and energy efficient compute parallelism to a data parallel multinode environment.
Other authors -
Honors & Awards
-
Intel’s Technology Innovation in Video Encoding and Transcoding for Media Servers and the Data Center
Frost and Sullivan
http://ww2.frost.com/news/press-releases/frost-sullivan-lauds-intels-technology-innovation-video-encoding-and-transcoding-media-servers-and-data-center/
-
Cooperative Technical Leadership Program | GE Industrial Systems
General Electric Inc.
Completed 3 rotations through engineering, marketing and manufacturing.
Languages
-
Japanese
Limited working proficiency
-
English
Native or bilingual proficiency
More activity by Joseph
-
As we head into this year's Anime NYC, I wanted to share my thoughts about this moment in manga and anime with respect to genAI. We at 2nd Set AI did…
As we head into this year's Anime NYC, I wanted to share my thoughts about this moment in manga and anime with respect to genAI. We at 2nd Set AI did…
Liked by Joseph Spisak
-
A conversation that goes beyond the cloud. In our latest podcast inspired by a live panel discussion organised by Indian Institute of Technology…
A conversation that goes beyond the cloud. In our latest podcast inspired by a live panel discussion organised by Indian Institute of Technology…
Liked by Joseph Spisak
-
In a partnership with LMArena, our team at DataTecnica LLC is happy to announce the release of BiomedArena! This platform is designed to evaluate…
In a partnership with LMArena, our team at DataTecnica LLC is happy to announce the release of BiomedArena! This platform is designed to evaluate…
Liked by Joseph Spisak
-
Get recognized for your contributions to the PyTorch ecosystem! Nominations just opened for the 2025 PyTorch Contributor Awards.
Get recognized for your contributions to the PyTorch ecosystem! Nominations just opened for the 2025 PyTorch Contributor Awards.
Liked by Joseph Spisak
-
Excited to introduce Prophet Arena — a benchmark for AI’s forecasting capabilities, with a few unique features (1) AI-human collaborations (2)…
Excited to introduce Prophet Arena — a benchmark for AI’s forecasting capabilities, with a few unique features (1) AI-human collaborations (2)…
Liked by Joseph Spisak
Other similar profiles
Explore top content on LinkedIn
Find curated posts and insights for relevant topics all in one place.
View top contentOthers named Joseph Spisak in United States
-
Joseph Spisak
Expedite Specialist at R+L Carriers
-
Joe Spisak
-
Joseph Spisak
Bartender Manager at The Greek/Level 2
-
Joseph Spisak
Aircraft Maintenance Quality Assurance Inspector
16 others named Joseph Spisak in United States are on LinkedIn
See others named Joseph Spisak