26,098 papers · page 41 of 1,305
High-performance micro-kernels must fully exploit today’s diverse and specialized hardware to deliver peak performance to deep neural networks (DNNs). While higher-level optimizations for DNNs are offered by numerous compilers (e.g., MLIR, TVM, OpenXLA), performance-critical micr…
To take full advantage of a specific hardware target, performance engineers need to gain control on compilers in order to leverage their domain knowledge about the program and hardware. Yet, modern compilers are poorly controlled, usually by configuring a sequence of coarse-grain…
Tensor compilers play a critical role in optimizing deep neural networks (DNNs), with memory performance emerging as a key bottleneck in code generation for DNN models. Existing tensor compilers are constrained by inefficient auto-tuning algorithms. They either must deploy coarse…
Accurate static profile prediction is crucial for achieving optimal program performance in the absence of dynamic profiles. However, existing static profiling methods struggle to fully exploit the complex structure of the compiler’s intermediate representation and fail to effecti…
Dynamic programming (DP) is a fundamental algorithmic strategy that decomposes large problems into manageable subproblems. It is a cornerstone of many important computational methods in diverse fields, especially in the field of computational genomics, where it is used for sequen…
Determining the optimal sequence of compiler optimization passes is challenging due to the extensive and intricate search space. Traditional auto-tuning techniques, such as iterative compilation and machine learning methods, are often limited by high computational costs and diffi…
Symmetric and sparse tensors arise naturally in many domains including linear algebra, statistics, physics, chemistry, and graph theory. Symmetric tensors are equal to their transposes, so in the n-dimensional case we can save up to a factor of n! by avoiding redundant operations…
In a memory-managed programming language, programmers allocate memory by creating new objects, but programmers never free memory. A garbage collector (GC) periodically reclaims memory used by unreachable objects. As an optimization based on escape analysis, some memory can be fre…
Pattern matching based on Regular Expressions (REs) is a pervasive and challenging computational kernel used in several applications to identify critical information in a data stream. Due to the sequential data dependency of REs and the increasing data volume growth, hardware acc…
Vectorization is a powerful optimization technique that significantly boosts the performance of high performance computing applications operating on large data arrays. Despite decades of research on auto-vectorization, compilers frequently miss opportunities to vectorize code. On…
Quantum simulation plays a critical role in advancing our understanding and development of quantum algorithms, quantum computing hardware, and quantum information science. Despite the availability of various quantum circuit simulators, they often face challenges in terms of maint…
The same computations are often expressed differently across software projects and programming languages. In particular, how computations involving loops are expressed varies due to the many possibilities to permute and compose loops. Since each variant may have unique performanc…
Recently, AlphaDev has shown significant advances in the synthesis of branchless sorting kernels for arrays of lengths 3 to 5. In this paper, we propose an enumerative search technique based on A* search and present novel optimality-preserving heuristics and non-optimality-prese…
Supervised machine learning techniques have shown promising results in code analysis and optimization problems. However, a learning-based solution can be brittle because minor changes in hardware or application workloads – such as facing a new CPU architecture or code pattern – m…
Convolution is the most time consuming computation kernel in Convolutional Neural Network (CNN) applications and the majority of Graph Neural Network (GNN) applications. To achieve good convolution performance, current NN libraries such as cuDNN usually transform the naive convol…
MLIR’s ability to optimize programs at multiple levels of abstraction is key to enabling domain-specific optimizing compilers. However, expressing optimizations remains tedious. Optimizations can interact in unexpected ways, making it hard to unleash full performance. Equality sa…
The increasing vulnerability of microprocessors due to frequent silicon faults greatly exacerbates the risks of silent data corruption. Existing software-based schemes to detect these suffer from high power and performance overhead. State-of-the-art hardware fault-tolerance techn…
Fully homomorphic encryption (FHE) and zero-knowledge proofs (ZKPs) are emerging as solutions for data security in distributed environments. However, the widespread adoption of these encryption techniques is hindered by their significant computational overhead, primarily resultin…
Fully Homomorphic Encryption (FHE), particularly the CKKS scheme, enables computation on encrypted data, facilitating secure task offloading to untrusted servers. CKKS allows packing multiple complex values into a single ciphertext, crucial for fixed-point arithmetic in machine l…
We introduce VEGA, an AI-driven system aimed at easing the development of compiler backends for new targets. Our approach involves categorizing functions from existing backends into function groups, each comprising various target-specific implementations of a standard compiler in…