24 citations · 77 across the 28 of their papers we have counts for
31 papers
Architecting for Hardware Diversity: Meta's End-to-End Co-Design for High-Performance AI Training on AMD GPUs
Haoyu Zhang, Arshad Rahman, Adnan Aziz +55
Meta deploys a heterogeneous fleet comprising NVIDIA GPUs, AMD GPUs, and proprietary MTIA accelerators to reduce costs and mitigate vendor lock-in. However, the extensive history o…
Lindblad Multiproduct Formulas
Niall F. Robertson, Andrea D'Urbano, Anton Dekusar +11
We introduce Lindblad Multiproduct Formulas: a quantum error mitigation technique that uses two-dimensional tensor networks contracted with loop-corrected belief propagation. The q…
The Einsum-Enabled Design Space for Graph Algorithms: A BFS Case Study
Toluwanimi O. Odemuyiwa, Serban D. Porumbescu, Muhammad Osama +2
We propose a principled approach to reasoning about various graph algorithm implementations. We leverage the extended general Einsum notation (EDGE) which allows us to factor compl…
Trust but Verify: Mitigating Medical Hallucinations via Post-Hoc Adversarial Auditing and Multi-Agent Feedback Loops
Muhammad Osama, Maheera Amjad, Zartasha Mustansar +2
Large Language Models (LLMs) are increasingly deployed in healthcare settings, yet their tendency to hallucinate poses risks when clinical decisions are involved. This study examin…
Quokka#: Quantum Computing with #SAT
Jingyi Mei, Dekel Zak, Muhammad Osama +2
We present Quokka#, a versatile, open-source Python library for quantum circuit analysis. Quokka# reduces various simulation, verification, and synthesis tasks to weighted model co…
Fleet: Hierarchical Task-based Abstraction for Megakernels on Multi-Die GPUs
Sangeeta Chowdhary, Ryan Swann, Sean Siddens +7
Modern GPUs adopt chiplet-based designs with multiple private cache hierarchies, but current programming models (CUDA/HIP) expose a flat execution hierarchy that cannot express chi…
GPU-Accelerated Quantum Simulation of Stabilizer Circuits
Muhammad Osama, Dimitrios Thanos, Alfons Laarman
We introduce new parallel algorithms for efficiently simulating stabilizer (Clifford) circuits on GPUs, with a focus on data-parallel tableau evolution and scalable handling of pro…
tritonBLAS: Triton-based Analytical Approach for GEMM Kernel Parameter Selection
Ryan Swann, Muhammad Osama, Xiaohu Guo +8
We present tritonBLAS, a fast and deterministic analytical model that uses architectural parameters like the cache hierarchy, and relative code and data placement to generate perfo…
Iris: First-Class Multi-GPU Programming Experience in Triton
Muhammad Awad, Muhammad Osama, Brandon Potter
Multi-GPU programming traditionally requires developers to navigate complex trade-offs between performance and programmability. High-performance implementations typically rely on l…
HipKittens: Fast and Furious AMD Kernels
William Hu, Drew Wadsworth, Sean Siddens +6
AMD GPUs offer state-of-the-art compute and memory bandwidth; however, peak performance AMD kernels are written in raw assembly. To address the difficulty of mapping AI algorithms…
Eliminating Multi-GPU Performance Taxes: A Systems Approach to Efficient Distributed LLMs
Octavian Alexandru Trifan, Karthik Sangaiah, Muhammad Awad +5
As large language models (LLMs) continue to scale, their workloads increasingly rely on distributed execution across multiple GPUs. However, the conventional bulk synchronous paral…
Optimizing Attention on GPUs by Exploiting GPU Architectural NUMA Effects
Mansi Choudhary, Karthik Sangaiah, Sonali Singh +3
The rise of disaggregated AI GPUs has exposed a critical bottleneck in large-scale attention workloads: non-uniform memory access (NUMA). As multi-chiplet designs become the norm f…
ELMF4EggQ: Ensemble Learning with Multimodal Feature Fusion for Non-Destructive Egg Quality Assessment
Md Zahim Hassan, Md. Osama, Muhammad Ashad Kabir +2
Accurate, non-destructive assessment of egg quality is critical for ensuring food safety, maintaining product standards, and operational efficiency in commercial poultry production…
Stream-K++: Adaptive GPU GEMM Kernel Scheduling and Selection using Bloom Filters
Harisankar Sadasivan, Muhammed Emin Ozturk, Muhammad Osama +7
General matrix multiplication (GEMM) operations are the fundamental building blocks of computational domains including artificial intelligence (AI). As GPU architectures evolve and…
Seer: Predictive Runtime Kernel Selection for Irregular Problems
Ryan Swann, Muhammad Osama, Karthik Sangaiah +1
Modern GPUs are designed for regular problems and suffer from load imbalance when processing irregular data. Prior to our work, a domain expert selects the best kernel to map fine-…
The Sparsity Roofline: Understanding the Hardware Limits of Sparse Neural Networks
Cameron Shinn, Collin McCarthy, Saurav Muralidharan +2
We introduce the Sparsity Roofline, a visual performance model for evaluating sparsity in neural networks. The Sparsity Roofline jointly models network accuracy, sparsity, and theo…
A Programming Model for GPU Load Balancing
Muhammad Osama, Serban D. Porumbescu, John D. Owens
We propose a GPU fine-grained load-balancing abstraction that decouples load balancing from work processing and aims to support both static and dynamic schedules with a programmabl…
Stream-K: Work-centric Parallel Decomposition for Dense Matrix-Matrix Multiplication on the GPU
Muhammad Osama, Duane Merrill, Cris Cecka +2
We introduce Stream-K, a work-centric parallelization of matrix multiplication (GEMM) and related computations in dense linear algebra. Whereas contemporary decompositions are prim…
GPU Load Balancing
Muhammad Osama
Fine-grained workload and resource balancing is the key to high performance for regular and irregular computations on the GPUs. In this dissertation, we conduct an extensive survey…
Essentials of Parallel Graph Analytics
Muhammad Osama, Serban D. Porumbescu, John D. Owens
We identify the graph data structure, frontiers, operators, an iterative loop structure, and convergence conditions as essential components of graph analytics systems based on the…
Robust Learning in Heterogeneous Contexts
Muhammad Osama, Dave Zachariah, Petre Stoica
We consider the problem of learning from training data obtained in different contexts, where the underlying context distribution is unknown and is estimated empirically. We develop…
Robust Localization in Wireless Networks From Corrupted Signals
Muhammad Osama, Dave Zachariah, Satyam Dwivedi +1
We address the problem of timing-based localization in wireless networks, when an unknown fraction of data is corrupted by nonideal signal conditions. While timing-based techniques…
Prediction of Spatial Point Processes: Regularized Method with Out-of-Sample Guarantees
Muhammad Osama, Dave Zachariah, Petre Stoica
A spatial point process can be characterized by an intensity function which predicts the number of events that occur across space. In this paper, we develop a method to infer predi…
Learning Robust Decision Policies from Observational Data
Muhammad Osama, Dave Zachariah, Peter Stoica
We address the problem of learning a decision policy from observational data of past decisions in contexts with features and associated outcomes. The past policy maybe unknown and…