2026-09-19T03:01:09Zhttps://dspace.mit.edu/server/oai/request

oai:dspace.mit.edu:1721.1/1648322026-02-13T03:49:09Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023

Mansinghka, Vikash Rojas Collins, Elias G. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science 2026-02-12T17:13:28Z 2026-02-12T17:13:28Z 2025-09 2025-09-15T14:56:40.051Z https://hdl.handle.net/1721.1/164832 Modern probabilistic programming applications, from large-scale Bayesian inference to real-time decision making, require both the expressiveness of CPU-oriented languages such as Gen.jl and the massive parallelism of GPU-backed array languages such as GenJAX, yet existing platforms force users to trade modeling flexibility for performance. This thesis introduces GenUflect, a metalanguage that embeds multiple Gen-compatible dialects inside a single program, allowing each sub-component to run on the most appropriate language and hardware target while preserving Gen’s programmable-inference interface. GenUflect extends Gen’s dynamic-modeling language with the @union, @vmap, @amortize, @amortize≤, and @runtime_union combinators; these macros compile at build-time (or justin-time) to autonomous generative functions written in the target dialect, link them through a lightweight FFI layer, and manage cross-device data via zero-copy MirrorArrays and lazily materialized traces. The resulting programs remain sound by construction because each foreign subtrace is itself a valid Gen generative function. Empirical studies demonstrate that this hybrid approach yields large practical gains. On a split linear-vs-sinusoidal regression task, GenUflect matches pure GenJAX throughput while running higher-order control logic on the CPU, and is up to two orders of magnitude faster than a pure Gen implementation for datasets of 105 points. In a collapsed-Gibbs sampler for a Dirichlet-process mixture model, GenUflect’s elastic allocation (@amortize≤) lets vectorized GPU kernels adapt to a growing number of clusters; the same inference that takes over an hour in Gen executes in seconds with GenUflect. A probabilistic inverse-graphics pipeline further showcases how heterogeneous submodels can cooperate seamlessly within unified inference code. By coupling language interoperability with automated data movement and compile-time code generation, GenUflect bridges the gap between flexibility and speed, enabling scalable, expressive probabilistic programs that natively exploit both CPUs and accelerators. M.Eng. Massachusetts Institute of Technology In Copyright - Educational Use Permitted Copyright retained by author(s) https://rightsstatements.org/page/InC-EDU/1.0/ Probabilistic Programming over Heterogeneous Language and Hardware Targets Thesis application/pdf Master Master of Engineering in Electrical Engineering and Computer Science Publication unknown unknown <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="8e031fe2-347b-45f0-b45d-dea13d29511f"> <Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type> <Title>Probabilistic Programming over Heterogeneous Language and Hardware Targets</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2025-09</PublicationDate> <Authors> <Author> <DisplayName>Rojas Collins, Elias G.</DisplayName> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> </Authors> <Editors> </Editors> <Publishers> <Publisher> <DisplayName>Massachusetts Institute of Technology</DisplayName> <OrgUnit /> </Publisher> </Publishers> <License>https://rightsstatements.org/page/InC-EDU/1.0/</License> <Abstract>Modern probabilistic programming applications, from large-scale Bayesian inference to real-time decision making, require both the expressiveness of CPU-oriented languages such as Gen.jl and the massive parallelism of GPU-backed array languages such as GenJAX, yet existing platforms force users to trade modeling flexibility for performance. This thesis introduces GenUflect, a metalanguage that embeds multiple Gen-compatible dialects inside a single program, allowing each sub-component to run on the most appropriate language and hardware target while preserving Gen’s programmable-inference interface. GenUflect extends Gen’s dynamic-modeling language with the @union, @vmap, @amortize, @amortize≤, and @runtime_union combinators; these macros compile at build-time (or justin-time) to autonomous generative functions written in the target dialect, link them through a lightweight FFI layer, and manage cross-device data via zero-copy MirrorArrays and lazily materialized traces. The resulting programs remain sound by construction because each foreign subtrace is itself a valid Gen generative function. Empirical studies demonstrate that this hybrid approach yields large practical gains. On a split linear-vs-sinusoidal regression task, GenUflect matches pure GenJAX throughput while running higher-order control logic on the CPU, and is up to two orders of magnitude faster than a pure Gen implementation for datasets of 105 points. In a collapsed-Gibbs sampler for a Dirichlet-process mixture model, GenUflect’s elastic allocation (@amortize≤) lets vectorized GPU kernels adapt to a growing number of clusters; the same inference that takes over an hour in Gen executes in seconds with GenUflect. A probabilistic inverse-graphics pipeline further showcases how heterogeneous submodels can cooperate seamlessly within unified inference code. By coupling language interoperability with automated data movement and compile-time code generation, GenUflect bridges the gap between flexibility and speed, enabling scalable, expressive probabilistic programs that natively exploit both CPUs and accelerators.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>