arXiv subjects

Jose M Monsalve Diaz

Publications and source records attributed to Jose M Monsalve Diaz.

3 recordsLinked to original sources

arXiv2024

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↗

arXiv2024

ComPile: A Large IR Dataset from Production Sources

Code is increasingly becoming a core data modality of modern machine learning research impacting not only the way we write code with conversational agents like OpenAI's ChatGPT, Google's Bard, or Anthropic's Claude, the way we translate code from one language into another, but also the compiler infrastructure underlying the language. While modeling approaches may vary and representations differ, the targeted tasks often remain the same within the individual classes of models. Relying solely on the ability of modern models to extract information from unstructured code does not take advantage of 70 years of programming language and compiler development by not utilizing the structure inherent to programs in the data collection. This detracts from the performance of models working over a tokenized representation of input code and precludes the use of these models in the compiler itself. To work towards the first intermediate representation (IR) based models, we fully utilize the LLVM compiler infrastructure, shared by a number of languages, to generate a 182B token dataset of LLVM IR. We generated this dataset from programming languages built on the shared LLVM infrastructure, including Rust, Swift, Julia, and C/C++, by hooking into LLVM code generation either through the language's package manager or the compiler directly to extract the dataset of intermediate representations from production grade programs. Statistical analysis proves the utility of our dataset not only for large language model training, but also for the introspection into the code generation process itself with the dataset showing great promise for machine-learned compiler components.

cs.PL↗

arXiv2022

Chiplets and the Codelet Model

Recently, hardware technology has rapidly evolved pertaining to domain-specific applications/architectures. Soon, processors may be composed of a large collection of vendor-independent IP specialized for application-specific algorithms, resulting in extreme heterogeneity. However, integrating multiple vendors within the same die is difficult. Chiplet technology is a solution that integrates multiple vendor dies within the same chip by breaking each piece into an independent block, each with a common interconnect for fast data transfer. Most prior chiplet research focuses on interconnect technology, but program execution models (PXMs) that enable programmability and performance are missing from the discussion. In chiplet architectures, a cohesive co-designed PXM can further separate the roles of the different actors, while maintaining a common abstraction for program execution. This position paper describes the need for co-designed PXMs and proposes the Codelet PXM and associated architectural features as a candidate to fill this need in extremely heterogeneous chiplet-based architectures.

cs.DC↗