1

Bolt: Fast Inference for Random Forests
Random forests use ensembles of decision trees to boost accuracy for machine learning tasks. However, large ensembles slow down …
Eduardo Romero, Christopher Stewart, Angela Li, Kyle C. Hale, Nathaniel Morris
Cite DOI ACM
Isolating Functions at the Hardware Limit with Virtines
An important class of applications, including programs that leverage third-party libraries, programs that use user-defined functions in …
Nicholas C. Wanninger, Joshua J. Bowden, Kirtankumar Shetty, Ayush Garg, Kyle C. Hale
Cite DOI ACM arXiv PDF Code Reproducible Artifact
Extremely Fine-grained Parallelism via Scalable Concurrent Queues on Modern Many-core Architectures
Enabling efficient fine-grained task parallelism is a significant challenge for hardware platforms with increasingly many cores. …
Poornima Nookala, Peter Dinda, Kyle C. Hale, Kyle Chard, Ioan Raicu
Cite DOI IEEE PDF
The Case for an Interwoven Parallel Hardware/Software Stack
The layered structure of the system software stacks we use today allows for separation of concerns and increases portability. However, …
Kyle C. Hale, Simone Campanoni, Nikos Hardavellas, Peter A. Dinda
Cite DOI IEEE PDF
Coalescent Computing
As computational infrastructure extends to the edge, it will increasingly offer the same fine-grained resource provisioning mechanisms …
Kyle C. Hale
Cite DOI ACM arXiv
Memory Mapping and Parallelizing Random Forests for Speed and Cache Efficiency
Memory mapping enhances decision tree implementations by enabling constant-time statistical inference, and is particularly effective …
Eduardo Romero-Gainza, Christopher Stewart, Angela Li, Kyle C. Hale, Nathaniel Morris
Cite DOI ACM Talk
Playing Fetch with CAT: Composing Cache Partitioning and Prefetching for Task-Based Query Processing
Software prefetching and hardware-based cache allocation techniques (CAT) have been successfully applied in main-memory database …
Qitian Zeng, Kyle C. Hale, Boris Glavic
Cite DOI ACM PDF
Paths to OpenMP in the Kernel
OpenMP implementations make increasing demands on the kernel. We take the next step and consider bringing OpenMP into the kernel. Our …
Jiacheng Ma, Wenyi Wang, Aaron Nelson, Michael Cuevas, Brian Homerding, Conghao Liu, Zhen Huang, Simone Campanoni, Kyle C. Hale, Peter Dinda
Cite DOI DOI PDF
Task Parallel Assembly Language for Uncompromising Parallelism
Achieving parallel performance and scalability involves making compromises between parallel and sequential computation. If not …
Mike Rainey, Ryan R. Newton, Kyle C. Hale, Nikos Hardavellas, Simone Campanoni, Peter Dinda, Umut A. Acar
Cite DOI ACM PDF Website Code
Modeling Speedup in Multi-OS Environments
For workloads that place strenuous demands on system software, novel operating system designs like unikernels, library OSes, and hybrid …
Brian Tauro, Conghao Liu, Kyle C. Hale
Cite DOI IEEE PDF