Related papers: Optimal Software Pipelining using an SMT-Solver

The input data pipeline is an essential component of each machine learning (ML) training job. It is responsible for reading massive amounts of training data, processing batches of samples using complex transformations, and loading them onto…

Language Model Programs, i.e. sophisticated pipelines of modular language model (LM) calls, are increasingly advancing NLP tasks, but they require crafting prompts that are jointly effective for all modules. We study prompt optimization for…

This paper explores reoptimization techniques for solving sequences of similar mixed integer programs (MIPs) more effectively. Traditionally, these MIPs are solved independently, without capitalizing on information from previously solved…

Software technology has high impact on the global economy as in many sectors of contemporary society. As a product enabling the most varied daily activities, the software product has to be produced reflecting high quality. Software quality…

Optimizing Pandas programs is a challenging problem. Existing systems and compiler-based approaches offer reliability but are either heavyweight or support only a limited set of optimizations. Conversely, using LLMs in a per-program…

While model serving has unlocked unprecedented capabilities, the high cost of serving large-scale models continues to be a significant barrier to widespread accessibility and rapid innovation. Compiler optimizations have long driven…

Hyperparameter tuning of multi-stage pipelines introduces a significant computational burden. Motivated by the observation that work can be reused across pipelines if the intermediate computations are the same, we propose a pipeline-aware…

Besides training, mathematical optimization is also used in deep learning to model and solve formulations over trained neural networks for purposes such as verification, compression, and optimization with learned constraints. However,…

Split learning (SL) has been recently proposed as a way to enable resource-constrained devices to train multi-parameter neural networks (NNs) and participate in federated learning (FL). In a nutshell, SL splits the NN model into parts, and…

Computer architectures become more and more complex. It requires more effort to develop techniques that improve the programs of performance and allow to exploit material resources efficiently. As a result, many transformations are applied…

Obtaining optimal data transfer performance is of utmost importance to today's data-intensive distributed applications and wide-area data replication services. Doing so necessitates effectively utilizing available network bandwidth and…

There is increasing interest in applying verification tools to programs that have bitvector operations. SMT solvers, which serve as a foundation for these tools, have thus increased support for bitvector reasoning through bit-blasting and…

As the field of data science continues to grow, there will be an ever-increasing demand for tools that make machine learning accessible to non-experts. In this paper, we introduce the concept of tree-based pipeline optimization for…

Frontier models increasingly adopt Mixture-of-Experts (MoE) architectures to achieve large-model performance at reduced cost. However, training MoE models on HPC platforms is hindered by large memory footprints, frequent large-scale…

Translation is important for cross-language communication, and many efforts have been made to improve its accuracy. However, less investment is conducted in aligning translations with human preferences, such as translation tones or styles.…

The rapid rise in demand for training large neural network architectures has brought into focus the need for partitioning strategies, for example by using data, model, or pipeline parallelism. Implementing these methods is increasingly…

Transformer-based models for time series forecasting (TSF) have attracted significant attention in recent years due to their effectiveness and versatility. However, these models often require extensive hyperparameter optimization (HPO) to…

Mixed-integer linear programming (MILP) has been a fundamental problem in combinatorial optimization. Conventional MILP solving mainly relies on carefully designed heuristics embedded in the branch-and-bound framework. Driven by the strong…

Logical reasoning about program data often requires dealing with heap structures as well as scalar data types. Recent advances in Satisfiability Modular Theory (SMT) already offer efficient procedures for dealing with scalars, yet they lack…

To usher in the next round of client AI innovation, there is an urgent need to enable efficient, lossless inference of high-accuracy large language models (LLMs) and vision language models (VLMs), jointly referred to as xLMs, on client…