W06.1.5 Near-Memory Hardware Acceleration of Sparse Workloads

Dear DATE community,

We, the DATE Sponsors Committee (DSC) and the DATE Executive Committee (DEC), are deeply shocked and saddened by the tragedy currently unfolding in Ukraine, and we would like to express our full solidarity with all the people and families affected by the war.

Our thoughts also go out to everyone in Ukraine and Russia, whether they are directly or indirectly affected by the events, and we extend our deep sympathy.

We condemn Russia’s military action in Ukraine, which violates international law. And we call on the different governments to take immediate action to protect everyone in that country, particularly including its civilian population and people affiliated with its universities.

Now more than ever, our DATE community must promote our societal values (justice, freedom, respect, community, and responsibility) and confront this situation collectively and peacefully to end this nonsense war.

DATE Sponsors and Executive Committees.

Kindly note that all times on the virtual conference platform are displayed in the user's time zone.

The time zone for all times mentioned at the DATE website is CET – Central Europe Time (UTC+1).

W06.1.5 Near-Memory Hardware Acceleration of Sparse Workloads

Start

14:45

End

15:15

Speaker

Zhiru Zhang, Cornell University, United States

Sparse linear algebra operations are widely used in numerous application domains such as graph processing, machine learning, and scientific computing. These operations are typically more challenging to accelerate due to low operational intensity and irregular data access patterns.

This talk presents our recent investigation into near-memory hardware acceleration for sparse processing. Specifically, I will discuss the importance of co-designing the sparse storage format and accelerator architecture to maximize the bandwidth utilization and compute occupancy. As a case study, I will introduce GraphLily, a graph linear algebra overlay for accelerating graph processing on HBM-equipped FPGAs. GraphLily supports a rich set of graph algorithms by adopting the GraphBLAS programming interface, which formulates graph algorithms as sparse linear algebra operations.