Yanjing Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yanjing Li has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Andrew A. Chien
University of Chicago
2 shared publications - Andronicus Rajasukumar
University of Chicago
2 shared publications - Henry Hoffmann
University of Chicago
2 shared publications - Jianru Ding
University of Chicago
2 shared publications - Marziyeh Nourian
University of Chicago
2 shared publications - Tianshuo Su
University of Chicago
2 shared publications
Latest Publications
- 1 November 2025
- Published by Springer Nature
- p. 78-95
Efficiently Exploiting Irregular Parallelism Using Keys at Scale
- 1 November 2025
- Published by Springer Nature
- p. 78-95
Efficiently Exploiting Irregular Parallelism Using Keys at Scale
- Open Access
UpDown: Programmable fine-grained Events for Scalable Performance on Irregular Applications
Applications with irregular data structures, data-dependent control flows and fine-grained data transfers (e.g., real-world graph computations) perform poorly on cache-based systems. We propose the UpDown accelerator that supports fine-grained execution with novel architecture mechanisms - lightweight threading, event-driven scheduling, efficient ultra-short threads, and split-transaction DRAM access with software-controlled synchronization. These hardware primitives support software programmable events, enabling high performance on diverse data structures and algorithms. UpDown also supports scalable performance; hardware replication enables programs to scale up performance. Evaluation results show UpDown's flexibility and scalability enable it to outperform CPUs on graph mining and analytics computations by up to 116-195x geomean speedup and more than 4x speedup over prior accelerators. We show that UpDown generates high memory parallelism (~4.6x over CPU) required for memory intensive graph computations. We present measurements that attribute the performance of UpDown (23x architectural advantage) to its individual architectural mechanisms. Finally, we also analyze the area and power cost of UpDown's mechanisms for software programmability.
Open AccessUpDown: Programmable fine-grained Events for Scalable Performance on Irregular Applications
Applications with irregular data structures, data-dependent control flows and fine-grained data transfers (e.g., real-world graph computations) perform poorly on cache-based systems. We propose the UpDown accelerator that supports fine-grained execution with novel architecture mechanisms - lightweight threading, event-driven scheduling, efficient ultra-short threads, and split-transaction DRAM access with software-controlled synchronization. These hardware primitives support software programmable events, enabling high performance on diverse data structures and algorithms. UpDown also supports scalable performance; hardware replication enables programs to scale up performance. Evaluation results show UpDown's flexibility and scalability enable it to outperform CPUs on graph mining and analytics computations by up to 116-195x geomean speedup and more than 4x speedup over prior accelerators. We show that UpDown generates high memory parallelism (~4.6x over CPU) required for memory intensive graph computations. We present measurements that attribute the performance of UpDown (23x architectural advantage) to its individual architectural mechanisms. Finally, we also analyze the area and power cost of UpDown's mechanisms for software programmability.
- Open Access
YFlows: Systematic Dataflow Exploration and Code Generation for Efficient Neural Network Inference using SIMD Architectures on CPUs
We address the challenges associated with deploying neural networks on CPUs, with a particular focus on minimizing inference time while maintaining accuracy. Our novel approach is to use the dataflow (i.e., computation order) of a neural network to explore data reuse opportunities using heuristic-guided analysis and a code generation framework, which enables exploration of various Single Instruction, Multiple Data (SIMD) implementations to achieve optimized neural network execution. Our results demonstrate that the dataflow that keeps outputs in SIMD registers while also maximizing both input and weight reuse consistently yields the best performance for a wide variety of inference workloads, achieving up to 3x speedup for 8-bit neural networks, and up to 4.8x speedup for binary neural networks, respectively, over the optimized implementations of neural networks today.
Open AccessYFlows: Systematic Dataflow Exploration and Code Generation for Efficient Neural Network Inference using SIMD Architectures on CPUs
We address the challenges associated with deploying neural networks on CPUs, with a particular focus on minimizing inference time while maintaining accuracy. Our novel approach is to use the dataflow (i.e., computation order) of a neural network to explore data reuse opportunities using heuristic-guided analysis and a code generation framework, which enables exploration of various Single Instruction, Multiple Data (SIMD) implementations to achieve optimized neural network execution. Our results demonstrate that the dataflow that keeps outputs in SIMD registers while also maximizing both input and weight reuse consistently yields the best performance for a wide variety of inference workloads, achieving up to 3x speedup for 8-bit neural networks, and up to 4.8x speedup for binary neural networks, respectively, over the optimized implementations of neural networks today.