arXiv subjects

Saman Amarasinghe

Publications and source records attributed to Saman Amarasinghe.

At least 19 recordsLinked to original sources

arXiv2026

SPAC: Automating FPGA-based Network Switches with Protocol Adaptive Customization

With network requirements diverging across emerging applications, latency-critical services demand minimal logic delay, while hyperscale training and collectives require sustained line-rate throughput for synchronized bulk transfers. This divergence creates an urgent need for custom network switches tailored to specialized protocols and application-specific traffic patterns. This paper presents SPAC (Switch and Protocol Adaptive Customization), a novel approach that automates the generation of FPGA-based network switches co-optimized for custom protocols and application-specific traffic patterns. SPAC introduces a unified workflow with a domain-specific language (DSL) for protocol-architecture co-design, a library of modular HLS-based adaptive switch components, and a trace-aware Design Space Exploration (DSE) engine. By providing a multi-fidelity simulation stack, SPAC enables rapid identification of Pareto-optimal designs prior to deployment. We demonstrate the efficacy of the domain-specific adaptation of SPAC across a spectrum of real-world scenarios, spanning from latency-sensitive sensor and HFT networks to hyperscale datacenter fabrics. Experimental results show that by tailoring the micro-architecture and protocol to the specific workload, SPAC-generated designs reduce LUT and BRAM usage by 55% and 53%, respectively. Compared to fixed-architecture counterparts, SPAC delivers latency reductions ranging from 7.8% to 38.4% across various tasks while maintaining adequate resource consumption and packet drop rate.

cs.NI↗

arXiv2026

Backwards Data-Flow Analysis using Prophecy Variables in the BuildIt System

Many program transformations and optimizations require information about the future behavior of the program. A standard way to obtain this information is to build an intermediate program representation, then use a backwards program analysis to propagate relevant information against the flow of control back to the transformation/optimization site. We instead propose to use prophecy variables, which predict information about the future execution of the program, to enable such transformations and optimizations. We implement prophecy variables in BuildIt, a lightweight domain specific language implementation system. BuildIt uses staged compilation to implement high performance domain specific languages embedded within a standard general purpose programming language (C++). The BuildIt first phase uses standard C++ program execution to generate optimized C, C++, and CUDA second phase code. This approach enables BuildIt to eliminate programming language implementation components such as parsers and intermediate representations, delivering a dramatic decrease in the engineering effort required to implement domain specific languages. The combination of prophecy variables and repeated forward program execution enables BuildIt to extend this approach to include transformations and optimizations that require information about the future execution of the program without backwards analyses and without the engineering overhead associated with implementing these analyses. We formalize the use of prophecy variables for this purpose, discuss the implementation of prophecy variables and repeated execution in BuildIt, and present experimental results for BuildIt computations that benefit from optimizations enabled by the information that prophecy variables provide.

cs.PL↗

arXiv2025

Modular GPU Programming with Typed Perspectives

To achieve peak performance on modern GPUs, one must balance two frames of mind: issuing instructions to individual threads to control their behavior, while simultaneously tracking the convergence of many threads acting in concert to perform collective operations like Tensor Core instructions. The tension between these two mindsets makes modular programming error prone. Functions that encapsulate collective operations, despite being called per-thread, must be executed cooperatively by groups of threads. In this work, we introduce Prism, a new GPU language that restores modularity while still giving programmers the low-level control over collective operations necessary for high performance. Our core idea is typed perspectives, which materialize, at the type level, the granularity at which the programmer is controlling the behavior of threads. We describe the design of Prism, implement a compiler for it, and lay its theoretical foundations in a core calculus called Bundl. We implement state-of-the-art GPU kernels in Prism and find that it offers programmers the safety guarantees needed to confidently write modular code without sacrificing performance.

cs.PL↗

arXiv2025

Insum: Sparse GPU Kernels Simplified and Optimized with Indirect Einsums

Programming high-performance sparse GPU kernels is notoriously difficult, requiring both substantial effort and deep expertise. Sparse compilers aim to simplify this process, but existing systems fall short in two key ways. First, they are primarily designed for CPUs and rarely produce high-performance GPU code. Second, when computations involve both sparse and dense regions, these compilers often fail to optimize the dense portions effectively. In this paper, we propose a new approach for expressing sparse computations. We start from format-agnostic Einsums over sparse tensors and rewrite them into format-conscious indirect Einsums, which explicitly encode format information by mapping sparse data and metadata onto dense tensor operations through indirect indexing. To execute indirect Einsums, we introduce the Insum compiler, which generates efficient GPU code for these Einsums by lowering to the PyTorch compiler, extended to better support Tensor Core-enabled indirect Einsums. We also present two fixed-length sparse formats, GroupCOO and BlockGroupCOO, designed to fit naturally with indirect Einsums. Our approach achieves 1.14x to 3.81x speedups across a range of sparse GPU applications while reducing lines of code by 202x to 4491x compared to hand-written implementations.

cs.PL↗

arXiv2025

Eliminating Hallucination-Induced Errors in LLM Code Generation with Functional Clustering

Modern code-generation LLMs can already solve a large fraction of programming problems, yet they still hallucinate subtle bugs that make their outputs unsafe for autonomous deployment. We present functional clustering, a black-box wrapper that eliminates nearly all hallucination-induced errors while providing a tunable confidence score. The wrapper samples many candidate programs, executes each on a self-generated test suite, and clusters candidates whose I/O behavior is identical; the empirical mass of the largest cluster serves as an exact confidence estimate. A single scalar threshold on this estimate lets users trade coverage for reliability with exponential guarantees. On LiveCodeBench our verifier preserves baseline pass@1 on solvable tasks yet slashes the error rate of returned answers from ~65% to 2%, and drives it to 0% at a conservative threshold while still answering 15.6% of prompts. Manual audits show that the few residual mistakes stem from prompt misinterpretation, not random generation noise, narrowing future work to specification clarity. Because the method requires only sampling and sandbox execution, it applies unchanged to closed-source APIs and future models, offering a practical path toward dependable, autonomous code generation. Our code is available on Github (https://github.com/20ChaituR/functional-clustering).

cs.SE↗

arXiv2024

The Continuous Tensor Abstraction: Where Indices are Real

This paper introduces the continuous tensor abstraction, allowing indices to take real-number values (for example, A[3.14]). It also presents continuous tensor algebra expressions, such as C(x,y) = A(x,y) * B(x,y), where indices are defined over a continuous domain. This work expands the traditional tensor model to include continuous tensors. Our implementation supports piecewise-constant tensors, enabling infinite domains to be processed in finite time. We also introduce a new tensor format for efficient storage and a code generation technique for automatic kernel generation. For the first time, our abstraction expresses domains like computational geometry and computer graphics in the language of tensor programming. Our approach demonstrates competitive or better performance than hand-optimized kernels in leading libraries across diverse applications. Compared to hand-implemented libraries on a CPU, our compiler-based implementation achieves an average speedup of 9.20x on 2D radius search with approximately 60x fewer lines of code (LoC), 1.22x on genomic interval overlapping queries (with approximately 18x LoC saving), and 1.69x on trilinear interpolation in Neural Radiance Field (with approximately 6x LoC saving).

cs.PL↗

arXiv2024

SySTeC: A Symmetric Sparse Tensor Compiler

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. Sparse tensors, on the other hand, are mostly zero, and we can save asymptotically by processing only nonzeros. Unfortunately, specializing for both symmetry and sparsity at the same time is uniquely challenging. Optimizing for symmetry requires consideration of $n!$ transpositions of a triangular kernel, which can be complex and error prone. Considering multiple transposed iteration orders and triangular loop bounds also complicates iteration through intricate sparse tensor formats. Additionally, since each combination of symmetry and sparse tensor formats requires a specialized implementation, this leads to a combinatorial number of cases. A compiler is needed, but existing compilers cannot take advantage of both symmetry and sparsity within the same kernel. In this paper, we describe the first compiler which can automatically generate symmetry-aware code for sparse or structured tensor kernels. We introduce a taxonomy for symmetry in tensor kernels, and show how to target each kind of symmetry. Our implementation demonstrates significant speedups ranging from 1.36x for SSYMV to 30.4x for a 5-dimensional MTTKRP over the non-symmetric state of the art.

cs.MS↗

arXiv2024

Finch: Sparse and Structured Tensor Programming with Control Flow

From FORTRAN to NumPy, tensors have revolutionized how we express computation. However, tensors in these, and almost all prominent systems, can only handle dense rectilinear integer grids. Real world tensors often contain underlying structure, such as sparsity, runs of repeated values, or symmetry. Support for structured data is fragmented and incomplete. Existing frameworks limit the tensor structures and program control flow they support to better simplify the problem. In this work, we propose a new programming language, Finch, which supports both flexible control flow and diverse data structures. Finch facilitates a programming model which resolves the challenges of computing over structured tensors by combining control flow and data structures into a common representation where they can be co-optimized. Finch automatically specializes control flow to data so that performance engineers can focus on experimenting with many algorithms. Finch supports a familiar programming language of loops, statements, ifs, breaks, etc., over a wide variety of tensor structures, such as sparsity, run-length-encoding, symmetry, triangles, padding, or blocks. Finch reliably utilizes the key properties of structure, such as structural zeros, repeated values, or clustered non-zeros. We show that this leads to dramatic speedups in operations such as SpMV and SpGEMM, image processing, and graph analytics.

cs.MS↗

arXiv2024

Mechanised Hypersafety Proofs about Structured Data: Extended Version

Arrays are a fundamental abstraction to represent collections of data. It is often possible to exploit structural properties of the data stored in an array (e.g., repetition or sparsity) to develop a specialised representation optimised for space efficiency. Formally reasoning about correctness of manipulations with such structured data is challenging, as they are often composed of multiple loops with non-trivial invariants. In this work, we observe that specifications for structured data manipulations can be phrased as hypersafety properties, i.e., predicates that relate traces of $k$ programs. To turn this observation into an effective verification methodology, we developed the Logic for Graceful Tensor Manipulation (LGTM), a new Hoare-style relational separation logic for specifying and verifying computations over structured data. The key enabling idea of LGTM is that of parametrised hypersafety specifications that allow the number $k$ of the program components to depend on the program variables. We implemented LGTM as a foundational embedding into Coq, mechanising its rules, meta-theory, and the proof of soundness. Furthermore, we developed a library of domain-specific tactics that automate computer-aided hypersafety reasoning, resulting in pleasantly short proof scripts that enjoy a high degree of reuse. We argue for the effectiveness of relational reasoning about structured data in LGTM by specifying and mechanically proving correctness of 13 case studies including computations on compressed arrays and efficient operations over multiple kinds of sparse tensors.

cs.PL↗

arXiv2023

AskIt: Unified Programming Interface for Programming with Large Language Models

Large Language Models (LLMs) exhibit a unique phenomenon known as emergent abilities, demonstrating adeptness across numerous tasks, from text summarization to code generation. While these abilities open up novel avenues in software design and crafting, their incorporation presents substantial challenges. Developers face decisions regarding the use of LLMs for directly performing tasks within applications as well as for generating and executing code to accomplish these tasks. Moreover, effective prompt design becomes a critical concern, given the necessity of extracting data from natural language outputs. To address these complexities, this paper introduces AskIt, a domain-specific language (DSL) specifically designed for LLMs. AskIt simplifies LLM integration by providing a unified interface that not only allows for direct task execution using LLMs but also supports the entire cycle of code generation and execution. This dual capability is achieved through (1) type-guided output control, (2) template-based function definitions, and (3) prompt generation for both usage modes. Our evaluations underscore AskIt's effectiveness. Across 50 tasks, AskIt generated concise prompts, achieving a 16.14 % reduction in prompt length compared to benchmarks. Additionally, by enabling a seamless transition between using LLMs directly in applications and for generating code, AskIt achieved significant efficiency improvements, as observed in our GSM8K benchmark experiments. The implementations of AskIt in TypeScript and Python are available at https://github.com/katsumiok/ts-askit and https://github.com/katsumiok/pyaskit, respectively.

cs.PL↗

arXiv2022

Looplets: A Language For Structured Coiteration

Real world arrays often contain underlying structure, such as sparsity, runs of repeated values, or symmetry. Specializing for structure yields significant speedups. But automatically generating efficient code for structured data is challenging, especially when arrays with different structure interact. We show how to abstract over array structures so that the compiler can generate code to coiterate over any combination of them. Our technique enables new array formats (such as 1DVBL for irregular clustered sparsity), new iteration strategies (such as galloping intersections), and new operations over structured data (such as concatenation or convolution).

cs.PL↗

arXiv2021

Dynamic Sparse Tensor Algebra Compilation

This paper shows how to generate efficient tensor algebra code that compute on dynamic sparse tensors, which have sparsity structures that evolve over time. We propose a language for precisely specifying recursive, pointer-based data structures, and we show how this language can express a wide range of dynamic data structures that support efficient modification, such as linked lists, binary search trees, and B-trees. We then describe how, given high-level specifications of such data structures, a compiler can generate code to efficiently iterate over and compute with dynamic sparse tensors that are stored in the aforementioned data structures. Furthermore, we define an abstract interface that captures how nonzeros can be inserted into dynamic data structures, and we show how this abstraction guides a compiler to emit efficient code that store the results of sparse tensor algebra computations in dynamic data structures. We evaluate our technique and find that it generates efficient dynamic sparse tensor algebra kernels. Code that our technique emits to compute the main kernel of the PageRank algorithm is 1.05$\times$ as fast as Aspen, a state-of-the-art dynamic graph processing framework. Furthermore, our technique outperforms PAM, a parallel ordered (key-value) maps library, by 7.40$\times$ when used to implement element-wise addition of a dynamic sparse matrix to a static sparse matrix.

cs.MS↗

arXiv2021

An Asymptotic Cost Model for Autoscheduling Sparse Tensor Programs

While loop reordering and fusion can make big impacts on the constant-factor performance of dense tensor programs, the effects on sparse tensor programs are asymptotic, often leading to orders of magnitude performance differences in practice. Sparse tensors also introduce a choice of compressed storage formats that can have asymptotic effects. Research into sparse tensor compilers has led to simplified languages that express these tradeoffs, but the user is expected to provide a schedule that makes the decisions. This is challenging because schedulers must anticipate the interaction between sparse formats, loop structure, potential sparsity patterns, and the compiler itself. Automating this decision making process stands to finally make sparse tensor compilers accessible to end users. We present, to the best of our knowledge, the first automatic asymptotic scheduler for sparse tensor programs. We provide an approach to abstractly represent the asymptotic cost of schedules and to choose between them. We narrow down the search space to a manageably small "Pareto frontier" of asymptotically undominated kernels. We test our approach by compiling these kernels with the TACO sparse tensor compiler and comparing them with those generated with the default TACO schedules. Our results show that our approach reduces the scheduling space by orders of magnitude and that the generated kernels perform asymptotically better than those generated using the default schedules.

cs.MS↗

arXiv2021

An Attempt to Generate Code for Symmetric Tensor Computations

This document describes an attempt to develop a compiler-based approach for computations with symmetric tensors. Given a computation and the symmetries of its input tensors, we derive formulas for random access under a storage scheme that eliminates redundancies; construct intermediate representations to describe the loop structure; and translate this information, using the taco tensor algebra compiler, into code. While we achieve a framework for reasoning about a fairly general class of symmetric computations, the resulting code is not performant when the symmetries are misaligned.

cs.MS↗

arXiv2021

A variational study of two-nucleon systems with lattice QCD

The low-energy spectrum and scattering of two-nucleon systems are studied with lattice quantum chromodynamics using a variational approach. A wide range of interpolating operators are used: dibaryon operators built from products of plane-wave nucleons, hexaquark operators built from six localized quarks, and quasi-local operators inspired by two-nucleon bound-state wavefunctions in low-energy effective theories. Sparsening techniques are used to compute the timeslice-to-all quark propagators required to form correlation-function matrices using products of these operators. Projection of these matrices onto irreducible representations of the cubic group, including spin-orbit coupling, is detailed. Variational methods are applied to constrain the low-energy spectra of two-nucleon systems in a single finite volume with quark masses corresponding to a pion mass of 806 MeV. Results for S- and D-wave phase shifts in the isospin singlet and triplet channels are obtained under the assumption that partial-wave mixing is negligible. Tests of interpolating-operator dependence are used to investigate the reliability of the energy spectra obtained and highlight both the strengths and weaknesses of variational methods. These studies and comparisons to previous studies using the same gauge-field ensemble demonstrate that interpolating-operator dependence can lead to significant effects on the two-nucleon energy spectra obtained using both variational and non-variational methods, including missing energy levels and other discrepancies. While this study is inconclusive regarding the presence of two-nucleon bound states at this quark mass, it provides robust upper bounds on two-nucleon energy levels that can be improved in future calculations using additional interpolating operators and is therefore a step toward reliable nuclear spectroscopy from the underlying Standard Model of particle physics.

hep-lat↗

arXiv2021

The Three Pillars of Machine Programming

In this position paper, we describe our vision of the future of machine programming through a categorical examination of three pillars of research. Those pillars are: (i) intention, (ii) invention, and(iii) adaptation. Intention emphasizes advancements in the human-to-computer and computer-to-machine-learning interfaces. Invention emphasizes the creation or refinement of algorithms or core hardware and software building blocks through machine learning (ML). Adaptation emphasizes advances in the use of ML-based constructs to autonomously evolve software.

cs.AI↗

arXiv2021

A Deep Learning Based Cost Model for Automatic Code Optimization

Enabling compilers to automatically optimize code has been a longstanding goal for the compiler community. Efficiently solving this problem requires using precise cost models. These models predict whether applying a sequence of code transformations reduces the execution time of the program. Building an analytical cost model to do so is hard in modern x86 architectures due to the complexity of the microarchitecture. In this paper, we present a novel deep learning based cost model for automatic code optimization. This model was integrated in a search method and implemented in the Tiramisu compiler to select the best code transformations. The input of the proposed model is a set of simple features representing the unoptimized code and a sequence of code transformations. The model predicts the speedup expected when the code transformations are applied. Unlike previous models, the proposed one works on full programs and does not rely on any heavy feature engineering. The proposed model has only 16% of mean absolute percentage error in predicting speedups on full programs. The proposed model enables Tiramisu to automatically find code transformations that match or are better than state-of-the-art compilers without requiring the same level of heavy feature engineering required by those compilers.

cs.PL↗

arXiv2021

Compilation Techniques for Graph Algorithms on GPUs

The performance of graph programs depends highly on the algorithm, the size and structure of the input graphs, as well as the features of the underlying hardware. No single set of optimizations or one hardware platform works well across all settings. To achieve high performance, the programmer must carefully select which set of optimizations and hardware platforms to use. The GraphIt programming language makes it easy for the programmer to write the algorithm once and optimize it for different inputs using a scheduling language. However, GraphIt currently has no support for generating high performance code for GPUs. Programmers must resort to re-implementing the entire algorithm from scratch in a low-level language with an entirely different set of abstractions and optimizations in order to achieve high performance on GPUs. We propose GG, an extension to the GraphIt compiler framework, that achieves high performance on both CPUs and GPUs using the same algorithm specification. GG significantly expands the optimization space of GPU graph processing frameworks with a novel GPU scheduling language and compiler that enables combining graph optimizations for GPUs. GG also introduces two performance optimizations, Edge-based Thread Warps CTAs load balancing (ETWC) and EdgeBlocking, to expand the optimization space for GPUs. ETWC improves load balancing by dynamically partitioning the edges of each vertex into blocks that are assigned to threads, warps, and CTAs for execution. EdgeBlocking improves the locality of the program by reordering the edges and restricting random memory accesses to fit within the L2 cache. We evaluate GG on 5 algorithms and 9 input graphs on both Pascal and Volta generation NVIDIA GPUs, and show that it achieves up to 5.11x speedup over state-of-the-art GPU graph processing frameworks, and is the fastest on 66 out of the 90 experiments.

cs.DC↗