Pyxis: An Open-Source Performance Dataset of Sparse Accelerators
This provides a resource for researchers in accelerator, architecture, and related fields, though it is incremental as it compiles existing data rather than introducing new methods.
The paper tackles the challenge of designing accelerators for sparse applications by presenting Pyxis, an open-source performance dataset that collects accelerator designs and real execution statistics, currently containing 73.8K instances.
Specialized accelerators provide gains of performance and efficiency in specific domains of applications. Sparse data structures or/and representations exist in a wide range of applications. However, it is challenging to design accelerators for sparse applications because no architecture or performance-level analytic models are able to fully capture the spectrum of the sparse data. Accelerator researchers rely on real execution to get precise feedback for their designs. In this work, we present PYXIS, a performance dataset for specialized accelerators on sparse data. PYXIS collects accelerator designs and real execution performance statistics. Currently, there are 73.8 K instances in PYXIS. PYXIS is open-source, and we are constantly growing PYXIS with new accelerator designs and performance statistics. PYXIS can benefit researchers in the fields of accelerator, architecture, performance, algorithm, and many related topics.