Searcharxiv⌕ Search

arXiv subjects

Jiya Su

Publications and source records attributed to Jiya Su.

4 recordsLinked to original sources

Accelerating Direct Sparse Solvers with Graph Computing Accelerators

Solving large sparse linear systems by Gaussian elimination is a challenging computational task due to the introduction of non-zero elements, or fill-in. Practitioners use heuristics such as the nested dissection reordering algorithm to try to reduce fill-in. In practice, reordering codes do not achieve the same parallel scaling as factorization, nor can they exploit AVX instructions or GPUs. Thus, reordering can be the primary runtime bottleneck in large-scale computer-aided engineering applications. We consider the use of a novel accelerator, the UpDown system, to accelerate the METIS multilevel nested dissection reordering algorithm. The UpDown system is designed for a broad class of graph computing and irregular algorithms. We report results for small-scale UpDown systems that will be available commercially in 2027, using validated simulation and FPGA emulation platforms. Our findings indicate that small UpDown systems can speed up METIS by two-orders of magnitude versus a single CPU. Compared to ParMETIS on hundreds of MPI ranks, we anticipate the same small UpDown systems offer speedups of 4 - 7, providing the potential to significantly speed finite element simulations

cs.DC↗

Fine-Grained Parallel Graph Algorithms Can Be Both Fast and Scalable

Making graph algorithms fast and scalable on traditional architectures and GPUs often involves breaking them into large, coarse-grained computational blocks that access similar regions of memory. We show that graph algorithms, which have tremendous vertex- and edge-level parallelism, can be scaled as fine-grained programs on suitable architectures. Specifically, we investigate graph algorithms on the UpDown architecture and show how this many-threaded, cache-less architecture enables simple, fine-grained parallel graph algorithms to be both fast and scalable. Single-node UpDown performance is 28x (geomean) over an H200 GPU, and that same program scales to 1000's of nodes. We evaluate the system three ways: simulation, analytical projection models, and selected validation studies at scale (simulation of 16,384 UpDown nodes, using 256 supercomputer nodes). These results show the UpDown system can achieve 680K giga-traversed edges per second (GTEPS) for PageRank and 989K GTEPS BFS, exceeding prior results significantly.

cs.DC↗

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.

cs.AR↗

PIMMiner: A High-performance PIM Architecture-aware Graph Mining Framework

Graph mining applications, such as subgraph pattern matching and mining, are widely used in real-world domains such as bioinformatics, social network analysis, and computer vision. Such applications are considered a new class of data-intensive applications that generate massive irregular computation workloads and memory accesses, which degrade the performance significantly. Leveraging emerging hardware, such as process-in-memory (PIM) technology, could potentially accelerate such applications. In this paper, we propose PIMMiner, a high-performance PIM architecture graph mining framework. We first identify that current PIM architecture cannot be fully utilized by graph mining applications. Next, we propose a set of optimizations and interfaces that enhance the locality, and internal bandwidth utilization and reduce remote bank accesses and load imbalance through cohesive algorithm and architecture co-designs. We compare PIMMiner with several state-of-the-art graph mining frameworks and show that PIMMiner is able to outperform all of them significantly.

cs.AR↗