736 papers · page 2 of 37
Over the years, many frameworks and optimization techniques have been proposed to accelerate graph neural networks (GNNs). In contrast to the optimizations explored in these systems, we observe that different matrix re-associations of GNN computations lead to novel input-sensitiv…
CUDA’s programming model, exposing massive parallelism via fine-grained scalar threads, has become the de facto standard for GPU computing. Concurrently, NPUs are emerging as highly efficient accelerators, but their architecture is fundamentally different, relying on coarse-grain…
The increasing complexity and diversity of hardware accelerators in modern computing systems demand flexible, low-overhead program analysis tools. We present PASTA, a low-overhead and modular Program AnalysiS Tool Framework for Accelerators. PASTA abstracts over low-level profili…
Binary analysis plays a critical role in software comprehension and security analysis, especially when source code is unavailable or difficult to analyze. Lifting binaries to LLVM IR enables reuse of the rich LLVM toolchain for downstream binary analyses. However, existing binary…
Generalized Matrix Chains (GMCs) are products of matrices where each matrix carries features (e.g., general, symmetric, triangular, positive-definite) and is optionally transposed and/or inverted. GMCs are commonly evaluated via sequences of calls to BLAS and LAPACK kernels. When…
Recent GPUs integrate specialized hardware for low-precision arithmetic (e.g., FP16, INT8), offering substantial speedups for tensor operations. However, existing methods typically rely on coarse, operator-level trial-and-error tuning, which restricts the performance–accuracy tra…
Data collections provide a powerful abstraction to organize data, simplifying development and maintenance. Choosing an implementation for each collection is a critical decision, with performance, memory and energy tradeoffs that need to be balanced for each use case. Specialized …
Transformer-based language models power many cloud services, but inference on sensitive data raises confidentiality concerns. Fully Homomorphic Encryption (FHE) enables computation on encrypted inputs while preserving privacy, but at high computational cost, making Transformers d…
Baseline JIT compilers need to compile early and as fast as possible, while still performing optimizations. One powerful technique to write fast baseline JIT compilers is abstract interpretation. Several implementations of this technique exist in practice, implementing in a singl…
Efficient inference on large language models (LLMs) has become a popular topic in both academia and industry. Roughly speaking, LLMs consist of a collection of weight matrices, and generative inference on these models essentially computes a sequence of matrix-vector products and …
Python exhibits inferior performance relative to traditional high performance computing (HPC) languages such as C, C++, and Fortran. This performance gap is largely due to Python’s interpreted nature and the Global Interpreter Lock (GIL), which restricts multithreading efficiency…
Automated fuzz testing is now standard practice, yet key blind spots persist. Coverage-guided fuzzers typically rely on edge coverage as a lightweight proxy for program behavior. However, this metric captures path variations only weakly: it cannot differentiate executions that fo…
Dynamic-shape DNNs are widely used in applications such as variable-resolution image processing and language modeling with variable-length sequences. Existing DL (Deep-Learning) compilers apply rule-based rewriting to either transform a subgraph into a fixed variant at compile ti…
Floating-point numbers are finite-precision approximations to real numbers and are ubiquitous in computer applications in nearly every field. Selecting the right floating-point representation that balances performance and numerical accuracy is a difficult task – one that has beco…
Hardware instruction fusion combines multiple architectural instructions into a single operation, improving performance by freeing up resources. While fusion typically involves consecutive instructions, there are proposals to fuse non-consecutive instructions to maximize potentia…
Binary diffing is the problem of determining whether two binary programs originate from the same source code. Binary diffing tools are used to identify malware, plagiarism, or code theft. Many instances of binary diffing assume an adversarial setting, where a malicious actor tran…
Fast machine code generation is especially important for fast start-up in just-in-time compilation, where the compilation time is part of the end-to-end latency. However, widely used compiler frameworks like LLVM do not prioritize fast compilation and require an extra IR translat…
We present PolyUFC, an MLIR based compilation flow for uncore frequency capping that combines (performance and power) roofline analyses and polyhedral compilation-based static analysis for characterization of affine programs. We introduce a parametric mathematical model that link…
Fault-tolerance is the future of quantum computing, ensuring error-corrected quantum computation that can be used for practical applications. Resource requirements for fault-tolerant quantum computing (FTQC) are daunting, and hence, compilation techniques must be designed to ensu…
Task classification is the challenge of determining whether two binary programs perform the same task. This problem is essential in scenarios such as malware identification, plagiarism detection, and redundancy elimination. Classification can be performed statically or dynamicall…