arXiv subjects

Fredrik Kjolstad

Publications and source records attributed to Fredrik Kjolstad.

At least 19 recordsLinked to original sources

arXiv2026

Partitioning Unstructured Sparse Tensor Algebra for Load-Balanced Parallel Execution

Sparse tensor algebra is challenging to efficiently parallelize due to the irregular, data-dependent, and potentially skewed structure of sparse computation. We propose the first partitioning algorithm that provably load balances the computation of any sparse tensor algebra expression across parallel execution units. Our algorithm generalizes parallel merging algorithms to any number of operands, and to multi-dimensional, hierarchical sparse data structures. We implement our algorithm within an existing sparse tensor algebra compilation framework to automatically generate parallel sparse tensor algebra kernels that target multi-core CPUs and GPUs. We show that our generated code is competitive with hand-implemented parallelization strategies used by vendor libraries like Intel MKL and NVIDIA cuSPARSE (geo-means of $0.73$--$3.4\times$) and \textsc{Taco} (geo-means of $1.0$--$2.4\times$), and significantly outperforms general-purpose strategies for sparse tensor expressions where specialized algorithms have not been developed (geo-means of $2.0$--$6.4\times$).

cs.PL↗

arXiv2026

Compiling Bioinformatics Recurrences

Many bioinformatics algorithms, such as sequence alignment and structure prediction, can be expressed as recurrence equations over a dynamic programming matrix. Efficient implementations of these algorithms for large-scale biological data often require changing the order in which matrix cells are calculated and pruning ineffectual regions of the matrix from consideration altogether, but these techniques typically complicate implementation. We introduce FILTR, a domain-specific language (DSL) and compiler framework for bioinformatics recurrences. FILTR keeps the core recurrence rules separate from the pruning and scheduling strategies, where pruning acts as an approximation to limit where in the DP matrix cells are computed, and scheduling determines the iteration order for how cells are explored. FILTR compiles these high-level descriptions into optimized C++ code that matches the performance of hand-tuned implementations while enabling rapid exploration of new heuristics. FILTR is competitive with hand-optimized sequence-alignment libraries, ranging from 0.95x to 30x faster across biological benchmarks.

cs.PL↗

arXiv2026

TensorBench: Benchmarking Coding Agents on a Compiler-Based Tensor Framework

Repository-level coding benchmarks face a trade-off between task difficulty and evaluation reliability: tasks that challenge frontier models often involve large codebases with incomplete test coverage, while human review does not scale. We introduce TensorBench, a benchmark of 199 feature-addition and refactoring tasks on an open-source compiler-based tensor framework that extends PyTorch with first-class support for dense and sparse tensors. Tasks cover new sparse formats, dense optimization passes, IR transformations, scheduler changes, runtime components, and high-level numerical operators. TensorBench grades each run by applying the agent's patch and running the framework's test suite, which includes the pre-existing randomized regression tests and any tests the agent adds. For feature-addition tasks, a pass means that the patched repository preserves the tested pre-existing behavior and satisfies the agent-added checks for the requested feature. We evaluate seven coding agents spanning three frontier model families and one open-weight model. Pass rates under this criterion range from $64.8\%$ for the strongest agent to $22.1\%$ for the weakest. Agents pass different subsets of tasks: pairwise Cohen's $κ$ ranges from $-0.07$ to $0.43$, with $κ= 0.05$ for the two strongest agents.

cs.CL↗

arXiv2026

Bonsai: Compiling Queries to Pruned Tree Traversals

Trees can accelerate queries that search or aggregate values over large collections. They achieve this by storing metadata that enables quick pruning (or inclusion) of subtrees when predicates on that metadata can prove that none (or all) of the data in a subtree affect the query result. Existing systems implement this pruning logic manually for each query predicate and data structure. We generalize and mechanize this class of optimization. Our method derives conditions for when subtrees can be pruned (or included wholesale), expressed in terms of the metadata available at each node. We efficiently generate these conditions using symbolic interval analysis, extended with new rules to handle geometric predicates (e.g., intersection, containment). Additionally, our compiler fuses compound queries (e.g., reductions on filters) into a single tree traversal. These techniques enable the automatic derivation of generalized single-index and dual-index tree joins that support a wide class of join predicates beyond standard equality and range predicates. The generated traversals match the behavior of expert-written code that implements query-specific traversals, and can asymptotically outperform the linear scans and nested-loop joins that existing systems fall back to when hand-written cases do not apply.

cs.PL↗

arXiv2026

Decoupling Data Layouts from Bounding Volume Hierarchies

Bounding volume hierarchies are ubiquitous acceleration structures in graphics, scientific computing, and data analytics. Their performance depends critically on data layout choices that affect cache utilization, memory bandwidth, and vectorization -- increasingly dominant factors in modern computing. Yet, in most programming systems, these layout choices are hopelessly entangled with the traversal logic. This entanglement prevents developers from independently optimizing data layouts and algorithms across different contexts, perpetuating a false dichotomy between performance and portability. We introduce Scion, a domain-specific language and compiler for specifying the data layouts of bounding volume hierarchies independent of tree traversal algorithms. We show that Scion can express a broad spectrum of layout optimizations used in high-performance computing while remaining architecture-agnostic. We demonstrate empirically that Pareto-optimal layouts (along performance and memory footprint axes) vary across algorithms, architectures, and workload characteristics. Through systematic design exploration, we also identify a novel ray tracing layout that combines optimization techniques from prior work, achieving Pareto-optimality across diverse architectures and scenes.

cs.PL↗

arXiv2026

FuseFlow: A Fusion-Centric Compilation Framework for Sparse Deep Learning on Streaming Dataflow

As deep learning models scale, sparse computation and specialized dataflow hardware have emerged as powerful solutions to address efficiency. We propose FuseFlow, a compiler that converts sparse machine learning models written in PyTorch to fused sparse dataflow graphs for reconfigurable dataflow architectures (RDAs). FuseFlow is the first compiler to support general cross-expression fusion of sparse operations. In addition to fusion across kernels (expressions), FuseFlow also supports optimizations like parallelization, dataflow ordering, and sparsity blocking. It targets a cycle-accurate dataflow simulator for microarchitectural analysis of fusion strategies. We use FuseFlow for design-space exploration across four real-world machine learning applications with sparsity, showing that full fusion (entire cross-expression fusion across all computation in an end-to-end model) is not always optimal for sparse models-fusion granularity depends on the model itself. FuseFlow also provides a heuristic to identify and prune suboptimal configurations. Using Fuseflow, we achieve performance improvements, including a ~2.7x speedup over an unfused baseline for GPT-3 with BigBird block-sparse attention.

cs.LG↗

arXiv2025

Optimal Software Pipelining and Warp Specialization for Tensor Core GPUs

GPU architectures have continued to grow in complexity, with recent incarnations introducing increasingly powerful fixed-function units for matrix multiplication and data movement to accompany highly parallel general-purpose cores. To fully leverage these machines, software must use sophisticated schedules that maximally utilize all hardware resources. Since realizing such schedules is complex, both programmers and compilers routinely employ program transformations, such as software pipelining (SWP) and warp specialization (WS), to do so in practice. However, determining how best to use SWP and WS in combination is a challenging problem that is currently handled through a mix of brittle compilation heuristics and fallible human intuition, with little insight into the space of solutions. To remedy this situation, we introduce a novel formulation of SWP and WS as a joint optimization problem that can be solved holistically by off-the-shelf constraint solvers. We reify our approach in Twill, the first system that automatically derives optimal SWP and WS schedules for a large class of iterative programs. Twill is heuristic-free, easily extensible to new GPU architectures, and guaranteed to produce optimal schedules. We show that Twill can rediscover, and thereby prove optimal, the SWP and WS schedules manually developed by experts for Flash Attention on both the NVIDIA Hopper and Blackwell GPU architectures.

cs.PL↗

arXiv2025

Cyclotron: Compilation of Recurrences to Distributed and Systolic Architectures

We present Cyclotron, a framework and compiler for using recurrence equations to express streaming dataflow algorithms, which then get portably compiled to distributed topologies of interlinked processors. Our framework provides an input language of recurrences over logical tensors, which then gets lowered into an intermediate language of recurrences over logical iteration spaces, and finally into programs of send, receive, and computation operations specific to each individual processor. In Cyclotron's IR, programs are optimized such that external memory interactions are confined to the boundaries of the iteration space. Within inner iteration spaces, all data accesses become local: data accesses target values residing in local fast memory or on neighboring processing units, avoiding costly memory movement. We provide a scheduling language allowing users to define how data gets streamed and broadcasted between processors, enabling pipelined execution of computation kernels over distributed topologies of processing elements. We demonstrate the portability of our approach by compiling our IR to a reconfigurable simulator of systolic arrays and chiplet style distributed hardware, as well as to distributed-memory CPU clusters. In the simulated reconfigurable setting, we use our compiler for hardware design space exploration in which link costs and latencies can be specified. In the distributed CPU setting, we show how to use recurrences and our scheduling language to express various matrix multiplication routines (Cannon, SUMMA, PUMMA, weight stationary) and solvers (Triangular solve and Cholesky). For matrix multiplication and the triangular solve, we generate distributed implementations competitive with ScaLAPACK.

cs.PL↗

arXiv2025

On the Duality of Task and Actor Programming Models

Programming models for distributed and heterogeneous machines are rapidly growing in popularity to meet the demands of modern workloads. Task and actor models are common choices that offer different trade-offs between development productivity and achieved performance. Task-based models offer better productivity and composition of software, whereas actor-based models routinely deliver better peak performance due to lower overheads. While task-based and actor-based models appear to be different superficially, we demonstrate these programming models are duals of each other. Importantly, we show that this duality extends beyond functionality to performance, and elucidate techniques that let task-based systems deliver performance competitive with actor-based systems without compromising productivity. We apply these techniques to both Realm, an explicitly parallel task-based runtime, as well as Legion, an implicitly parallel task-based runtime. We show these techniques reduce Realm's overheads by between 1.7-5.3x, coming within a factor of two of the overheads imposed by heavily optimized actor-based systems like Charm++ and MPI. We further show that our techniques enable between 1.3-5.0x improved strong scaling of unmodified Legion applications.

cs.PL↗

arXiv2025

Fast Collection Operations from Indexed Stream Fusion

We present a system of efficient methods for traversing and combining associative collection data structures. A distinguishing feature of the system is that, like traditional sequential iterator libraries, it does not require specialized compiler infrastructure or staged compilation for efficiency and composability. By using a representation based on indexed streams, the library can express complex joins over input collections while using no intermediate allocations. We implement the library for the Lean, Morphic, and Rust programming languages and provide a mechanized proof of functional correctness in Lean.

cs.PL↗

arXiv2025

Ember: A Compiler for Efficient Embedding Operations on Decoupled Access-Execute Architectures

Irregular embedding lookups are a critical bottleneck in recommender models, sparse large language models, and graph learning models. In this paper, we first demonstrate that, by offloading these lookups to specialized access units, Decoupled Access-Execute (DAE) processors achieve 2.6$\times$ higher performance and 6.4$\times$ higher performance/watt than GPUs on end-to-end models. Then, we propose the Ember compiler for automatically generating optimized DAE code from PyTorch and TensorFlow. Conversely from other DAE compilers, Ember features multiple intermediate representations specifically designed for different optimization levels. In this way, Ember can implement all optimizations to match the performance of hand-written code, unlocking the full potential of DAE architectures at scale.

cs.AR↗

arXiv2025

A Compiler for Operations on Relations with Bag Semantics

We describe an abstract loop-based intermediate representation that can express fused implementations of relational algebra expressions on sets and bags (multisets). The loops are abstracted away from physical data structures thus making it easier to generate, reason about, and perform optimization like fusion on. The IR supports the natural relational algebra as well as complex operators that are used in production database systems, including outer joins, non-equi joins, and differences. We then show how to compile this IR to efficient C++ code that co-iterates over the physical data structures present in the relational algebra expression. Our approach lets us express fusion across disparate operators, leading to a 3.87x speedup (0.77--12.23x) on selected LSQB benchmarks and worst-case optimal triangle queries. We also demonstrate that our compiler generates code of high quality: it has similar sequential performance to Hyper on TPC-H with a 1.00x speedup (0.38--4.34x) and competitive parallel performance with a 0.61x speedup (0.23--1.80x). Finally, our approach is portable across data structures.

cs.PL↗

arXiv2024

Composing Distributed Computations Through Task and Kernel Fusion

We introduce Diffuse, a system that dynamically performs task and kernel fusion in distributed, task-based runtime systems. The key component of Diffuse is an intermediate representation of distributed computation that enables the necessary analyses for the fusion of distributed tasks to be performed in a scalable manner. We pair task fusion with a JIT compiler to fuse together the kernels within fused tasks. We show empirically that Diffuse's intermediate representation is general enough to be a target for two real-world, task-based libraries (cuNumeric and Legate Sparse), letting Diffuse find optimization opportunities across function and library boundaries. Diffuse accelerates unmodified applications developed by composing task-based libraries by 1.86x on average (geo-mean), and by between 0.93x--10.7x on up to 128 GPUs. Diffuse also finds optimization opportunities missed by the original application developers, enabling high-level Python programs to match or exceed the performance of an explicitly parallel MPI library.

cs.DC↗

arXiv2024

Automatic Tracing in Task-Based Runtime Systems

Implicitly parallel task-based runtime systems often perform dynamic analysis to discover dependencies in and extract parallelism from sequential programs. Dependence analysis becomes expensive as task granularity drops below a threshold. Tracing techniques have been developed where programmers annotate repeated program fragments (traces) issued by the application, and the runtime system memoizes the dependence analysis for those fragments, greatly reducing overhead when the fragments are executed again. However, manual trace annotation can be brittle and not easily applicable to complex programs built through the composition of independent components. We introduce Apophenia, a system that automatically traces the dependence analysis of task-based runtime systems, removing the burden of manual annotations from programmers and enabling new and complex programs to be traced. Apophenia identifies traces dynamically through a series of dynamic string analyses, which find repeated program fragments in the stream of tasks issued to the runtime system. We show that Apophenia is able to come between 0.92x--1.03x the performance of manually traced programs, and is able to effectively trace previously untraced programs to yield speedups of between 0.91x--2.82x on the Perlmutter and Eos supercomputers.

cs.DC↗

arXiv2024

Deegen: A JIT-Capable VM Generator for Dynamic Languages

Building a high-performance JIT-capable VM for a dynamic language has traditionally required a tremendous amount of time, money, and expertise. We present Deegen, a meta-compiler that allows users to generate a high-performance JIT-capable VM for their own language at an engineering cost similar to writing a simple interpreter. Deegen takes in the execution semantics of the bytecodes implemented as C++ functions, and automatically generates a two-tier VM execution engine with a state-of-the-art interpreter, a state-of-the-art baseline JIT, and the tier-switching logic that connects them into a self-adaptive system. We are the first to demonstrate the automatic generation of a JIT compiler, and the automatic generation of an interpreter that outperforms the state of the art. Our performance comes from a long list of optimizations supported by Deegen, including bytecode specialization and quickening, register pinning, tag register optimization, call inline caching, generic inline caching, JIT polymorphic IC, JIT IC inline slab, type-check removal and strength reduction, type-based slow-path extraction and outlining, JIT hot-cold code splitting, and JIT OSR-entry. These optimizations are either employed automatically, or guided by the language implementer through intuitive APIs. As a result, the disassembly of the Deegen-generated interpreter, baseline JIT, and the generated JIT code rivals the assembly code hand-written by experts in state-of-the-art VMs. We implement LuaJIT Remake (LJR), a standard-compliant Lua 5.1 VM, using Deegen. Across 44 benchmarks, LJR's interpreter is on average 179% faster than the official PUC Lua interpreter, and 31% faster than LuaJIT's interpreter. LJR's baseline JIT has negligible startup delay, and its execution performance is on average 360% faster than PUC Lua and only 33% slower (but faster on 13/44 benchmarks) than LuaJIT's optimizing JIT.

cs.PL↗

arXiv2024

Scorch: A Library for Sparse Deep Learning

The rapid growth in the size of deep learning models strains the capabilities of traditional dense computation paradigms. Leveraging sparse computation has become increasingly popular for training and deploying large-scale models, but existing deep learning frameworks lack extensive support for sparse operations. To bridge this gap, we introduce Scorch, a library that seamlessly integrates efficient sparse tensor computation into the PyTorch ecosystem, with an initial focus on inference workloads on CPUs. Scorch provides a flexible and intuitive interface for sparse tensors, supporting diverse sparse data structures. Scorch introduces a compiler stack that automates key optimizations, including automatic loop ordering, tiling, and format inference. Combined with a runtime that adapts its execution to both dense and sparse data, Scorch delivers substantial speedups over hand-written PyTorch Sparse (torch.sparse) operations without sacrificing usability. More importantly, Scorch enables efficient computation of complex sparse operations that lack hand-optimized PyTorch implementations. This flexibility is crucial for exploring novel sparse architectures. We demonstrate Scorch's ease of use and performance gains on diverse deep learning models across multiple domains. With only minimal code changes, Scorch achieves 1.05-5.78x speedups over PyTorch Sparse on end-to-end tasks. Scorch's seamless integration and performance gains make it a valuable addition to the PyTorch ecosystem. We believe Scorch will enable wider exploration of sparsity as a tool for scaling deep learning and inform the development of other sparse libraries.

cs.LG↗

arXiv2024

Compilation of Modular and General Sparse Workspaces

Recent years have seen considerable work on compiling sparse tensor algebra expressions. This paper addresses a shortcoming in that work, namely how to generate efficient code (in time and space) that scatters values into a sparse result tensor. We address this shortcoming through a compiler design that generates code that uses sparse intermediate tensors (sparse workspaces) as efficient adapters between compute code that scatters and result tensors that do not support random insertion. Our compiler automatically detects sparse scattering behavior in tensor expressions and inserts necessary intermediate workspace tensors. We present an algorithm template for workspace insertion that is the backbone of our code generation algorithm. Our algorithm template is modular by design, supporting sparse workspaces that span multiple user-defined implementations. Our evaluation shows that sparse workspaces can be up to 27.12$\times$ faster than the dense workspaces of prior work. On the other hand, dense workspaces can be up to 7.58$\times$ faster than the sparse workspaces generated by our compiler in other situations, which motivates our compiler design that supports both. Our compiler produces sequential code that is competitive with hand-optimized linear and tensor algebra libraries on the expressions they support, but that generalizes to any other expression. Sparse workspaces are also more memory efficient than dense workspaces as they compress away zeros. This compression can asymptotically decrease memory usage, enabling tensor computations on data that would otherwise run out of memory.

cs.PL↗

arXiv2024

Revet: A Language and Compiler for Dataflow Threads

Spatial dataflow architectures such as reconfigurable dataflow accelerators (RDA) can provide much higher performance and efficiency than CPUs and GPUs. In particular, vectorized reconfigurable dataflow accelerators (vRDA) in recent literature represent a design point that enhances the efficiency of dataflow architectures with vectorization. Today, vRDAs can be exploited using either hardcoded kernels or MapReduce languages like Spatial, which cannot vectorize data-dependent control flow. In contrast, CPUs and GPUs can be programmed using general-purpose threaded abstractions. The ideal combination would be the generality of a threaded programming model coupled with the efficient execution model of a vRDA. We introduce Revet: a programming model, compiler, and execution model that lets threaded applications run efficiently on vRDAs. The Revet programming language uses threads to support a broader range of applications than Spatial's parallel patterns, and our MLIR-based compiler lowers this language to a generic dataflow backend that operates on streaming tensors. Finally, we show that mapping threads to dataflow outperforms GPUs, the current state-of-the-art for threaded accelerators, by 3.8x.

cs.AR↗