Sandro Rigo

César Guedes Carneiro, Lucas Alvarenga, Guido Araujo et al.

In Scientific Computing and modern Machine Learning (ML) workloads, sequences of dependent General Matrix Multiplications (GEMMs) often dominate execution time. While state-of-the-art BLAS libraries aggressively optimize individual GEMM calls, they remain constrained by the BLAS API, which requires each call to independently pack input matrices and restore outputs to a canonical memory layout. In sequential GEMMs, these constraints cause redundant packing and unpacking, wasting valuable computational resources. This paper introduces LP-GEMM, a decomposition of the GEMM kernel that enables packing-layout propagation across sequential GEMM operations. This approach eliminates unnecessary data repacking while preserving full BLAS semantic correctness at the boundaries. We evaluate LP-GEMM on x86 (AVX-512) and RISC-V (RVV 1.0) architectures across MLP-like and Attention-like workloads. Our results show average speedups of 2.25x over OpenBLAS on Intel x86 for sequential GEMMs and competitive gains relative to vendor-optimized libraries such as Intel MKL. We demonstrate the practicality of the approach beyond microbenchmarks by implementing a standalone C++ version of the Llama-3.2 inference path using exclusively BLAS-level GEMM calls. These results confirm that leveraging data layout propagation between operations can significantly boost performance.

Bruno Grisci, Gabriela Kuhn, Felipe Colombelli et al.

Nowadays, data has become an invaluable asset to entities and companies, and keeping it secure represents a major challenge. Data centers are responsible for storing data provided by software applications. Nevertheless, the number of vulnerabilities has been increasing every day. Managing such vulnerabilities is essential for building a reliable and secure network environment. Releasing patches to fix security flaws in software is a common practice to handle these vulnerabilities. However, prioritization becomes crucial for organizations with an increasing number of vulnerabilities since time and resources to fix them are usually limited. This review intends to present a survey of vulnerability ranking techniques and promote a discussion on how multi-objective optimization could benefit the management of vulnerabilities risk prioritization. The state-of-the-art approaches for risk prioritization were reviewed, intending to develop an effective model for ranking vulnerabilities in data centers. The main contribution of this work is to point out multi-objective optimization as a not commonly explored but promising strategy to prioritize vulnerabilities, enabling better time management and increasing security.

Gefersom Lima, Gabriel Ramos, Sandro Rigo et al.

The interpretation of seismic data is vital for characterizing sediments' shape in areas of geological study. In seismic interpretation, deep learning becomes useful for reducing the dependence on handcrafted facies segmentation geometry and the time required to study geological areas. This work presents a Deep Neural Network for Facies Segmentation (DNFS) to obtain state-of-the-art results for seismic facies segmentation. DNFS is trained using a combination of cross-entropy and Jaccard loss functions. Our results show that DNFS obtains highly detailed predictions for seismic facies segmentation using fewer parameters than StNet and U-Net.