Huiyang Zhou
Raleigh, North Carolina, United States
956 followers
500+ connections
About
Huiyang Zhou received the bachelor's degree in electrical engineering from Xian Jiaotong…
Activity
-
It's my turn to be thrilled 😉😁 I am starting the Fall 25 semester as an Associate Professor with tenure and University Faculty Scholar at North…
It's my turn to be thrilled 😉😁 I am starting the Fall 25 semester as an Associate Professor with tenure and University Faculty Scholar at North…
Liked by Huiyang Zhou
-
While sending my daughter to CMU, I visited the campus for the first time, stayed in the Strip District again, and checked out the old building of…
While sending my daughter to CMU, I visited the campus for the first time, stayed in the Strip District again, and checked out the old building of…
Liked by Huiyang Zhou
-
It is an honour to receive the TCCA Young Architect Award, presented at the International Symposium on Computer Architecture (ISCA) 2024. This award…
It is an honour to receive the TCCA Young Architect Award, presented at the International Symposium on Computer Architecture (ISCA) 2024. This award…
Liked by Huiyang Zhou
Experience
Education
Licenses & Certifications
Publications
-
yaSpMV Yet Another SpMV Framework on GPUs
PPoPP'14
SpMV is a key linear algebra algorithm and has been widely used in many important application domains. As a result, numerous attempts have been made to optimize SpMV on GPUs to leverage their massive computational throughput. Although the previous work has shown impressive progress, load imbalance and high memory bandwidth remain the critical performance bottlenecks for SpMV. In this paper, we present our novel solutions to these problems. First, we devise a new SpMV format, called blocked…
SpMV is a key linear algebra algorithm and has been widely used in many important application domains. As a result, numerous attempts have been made to optimize SpMV on GPUs to leverage their massive computational throughput. Although the previous work has shown impressive progress, load imbalance and high memory bandwidth remain the critical performance bottlenecks for SpMV. In this paper, we present our novel solutions to these problems. First, we devise a new SpMV format, called blocked compressed common coordinate (BCCOO), which uses bit flags to store the row indices in a blocked common coordinate (COO) format so as to alleviate the bandwidth problem. We further improve this format by partitioning the matrix into vertical slices to enhance the cache hit rates when accessing the vector to be multiplied. Second, we revisit the segmented scan approach for SpMV to address the load imbalance problem. We propose a highly efficient matrix-based segmented sum/scan for SpMV and further improve it by eliminating global synchronization. Then, we introduce an auto-tuning framework to choose optimization parameters based on the characteristics of input sparse matrices and target hardware platforms. Our experimental results on GTX680 GPUs and GTX480 GPUs show that our proposed framework achieves significant performance improvement over the vendor tuned CUSPARSE V5.0 (up to 229% and 65% on average on GTX680 GPUs, up to 150% and 42% on average on GTX480 GPUs) and some most recently proposed schemes (e.g., up to 195% and 70% on average over clSpMV on GTX680 GPUs, up to 162% and 40% on average over clSpMV on GTX480 GPUs).
Other authors -
Time-Ordered Event Traces: A New Debugging Primitive for Concurrency Bugs
International Parallel and Distributed Processing Symposium (IPDPS-XXV)
-
Combining Local and Global History for High Performance Data Prefetching
Journal of Instruction-Level Parallelism (JILP)
-
Anomaly-Based Bug Prediction, Isolation, and Validation: An automated Approach for Software debugging
14th International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS-XIV)
-
Unified Architectural Support for Soft-Error Protection or Software-Bug Detection
International Conference on Parallel Architectures and Compilation Techniques (PACT’07)
More activity by Huiyang
-
If you know any middle school or high school students interested in learning AI and Machine Learning, consider the 1-week online summer camps: "AI…
If you know any middle school or high school students interested in learning AI and Machine Learning, consider the 1-week online summer camps: "AI…
Liked by Huiyang Zhou
-
My group, ESCAL University of California, Riverside, has two papers accepted by MICRO 2025. - SIDA: Sparse Inter-operator Dataflow Architecture with…
My group, ESCAL University of California, Riverside, has two papers accepted by MICRO 2025. - SIDA: Sparse Inter-operator Dataflow Architecture with…
Liked by Huiyang Zhou
-
I am thrilled to be starting my first day as Chair of EECS at Syracuse University College of Engineering and Computer Science. I have been blessed…
I am thrilled to be starting my first day as Chair of EECS at Syracuse University College of Engineering and Computer Science. I have been blessed…
Liked by Huiyang Zhou
-
I am excited to share our two upcoming works (to appear at MICRO-2024) on Rowhammer and Row-Press that raise the bar with a minimalist solution. (1)…
I am excited to share our two upcoming works (to appear at MICRO-2024) on Rowhammer and Row-Press that raise the bar with a minimalist solution. (1)…
Liked by Huiyang Zhou
-
🎉 On Wednesday, we celebrated Greg Byrd's 25 incredible years of dedication and service! As the former Associate Head of NC State ECE, and now the…
🎉 On Wednesday, we celebrated Greg Byrd's 25 incredible years of dedication and service! As the former Associate Head of NC State ECE, and now the…
Liked by Huiyang Zhou
-
Call for Posters for QCE 2024 Poster Submission Deadline: July 22, 2024
Call for Posters for QCE 2024 Poster Submission Deadline: July 22, 2024
Liked by Huiyang Zhou
-
Happy to share that our new paper "QuTracer: Mitigating Quantum Gate and Measurement Errors by Tracing Subsets of Qubits" has been accepted by…
Happy to share that our new paper "QuTracer: Mitigating Quantum Gate and Measurement Errors by Tracing Subsets of Qubits" has been accepted by…
Liked by Huiyang Zhou
-
It was my great honor to put together and moderate a panel on Designing Computer Systems for Sustainability for #isca2024! Many thanks to the expert…
It was my great honor to put together and moderate a panel on Designing Computer Systems for Sustainability for #isca2024! Many thanks to the expert…
Liked by Huiyang Zhou
-
Congratulations to Rahul Bera, Adithya Ranganathan and other co-authors, including my students at ETH Zürich and collaborators from Intel Labs, for…
Congratulations to Rahul Bera, Adithya Ranganathan and other co-authors, including my students at ETH Zürich and collaborators from Intel Labs, for…
Liked by Huiyang Zhou
-
IEEE Quantum Week will be held next 15-20 Sept. 9 World-Class Keynote Speakers https://lnkd.in/dmdJzDdE 36 Community-Building Workshops…
IEEE Quantum Week will be held next 15-20 Sept. 9 World-Class Keynote Speakers https://lnkd.in/dmdJzDdE 36 Community-Building Workshops…
Liked by Huiyang Zhou
-
Our chairs in their first #ISCACONF2024 day. No signs of being tired yet 😉 Augusto Vega, Esteban Mocskos.
Our chairs in their first #ISCACONF2024 day. No signs of being tired yet 😉 Augusto Vega, Esteban Mocskos.
Liked by Huiyang Zhou
-
The latest IEEE MICRO Special Issue on Hot Chips, May/June 2024 is now online, including • AMD Zen 4 and 4th gen EPYC • AMD Ryzen 7040 • Intel…
The latest IEEE MICRO Special Issue on Hot Chips, May/June 2024 is now online, including • AMD Zen 4 and 4th gen EPYC • AMD Ryzen 7040 • Intel…
Liked by Huiyang Zhou
-
I am very honored and humbled to have received the IFIP Jean-Claude Laprie (JCL) Award in Dependable Computing at DSN 2024 earlier this week, for our…
I am very honored and humbled to have received the IFIP Jean-Claude Laprie (JCL) Award in Dependable Computing at DSN 2024 earlier this week, for our…
Liked by Huiyang Zhou
-
We are delighted to announce that ACM and the IEEE Computer Society have named Wen-mei W. Hwu, a Senior Distinguished Research Scientist at NVIDIA…
We are delighted to announce that ACM and the IEEE Computer Society have named Wen-mei W. Hwu, a Senior Distinguished Research Scientist at NVIDIA…
Liked by Huiyang Zhou
-
Honored to join the Bennett Faculty Fellow family!
Honored to join the Bennett Faculty Fellow family!
Liked by Huiyang Zhou
Other similar profiles
Explore collaborative articles
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
Explore MoreOthers named Huiyang Zhou
41 others named Huiyang Zhou are on LinkedIn
See others named Huiyang Zhou