Type inference for parametric polymorphism is wildly successful, but has always suffered from an embarrassing flaw: polymorphic types are themselves not first class. We present Quick Look, a practical, implemented, and deployable design for impredicative type inference. To demonstrate our claims, we have modified GHC, a production-quality Haskell compiler, to support impredicativity. The changes required are modest, localised, and are fully compatible with GHC's myriad other type system extensions.

The design space for type systems that support impredicative instantiation is extremely complicated. One needs to strike a balance between expressiveness, simplicity for both the end programmer and the type system implementor, and how easily the system can be integrated with other advanced type system concepts. In this paper, we propose a new point in the design space, which we call guarded impredicativity. Its key idea is that impredicative instantiation in an application is allowed for type variables that occur under a type constructor. The resulting type system has a clean declarative specification — making it easy for programmers to predict what will type and what will not —, allows for a smooth integration with GHC’s OutsideIn(X) constraint solving framework, while giving up very little in terms of expressiveness compared to systems like HMF, HML, FPH and MLF. We give a sound and complete inference algorithm, and prove a principal type property for our system.

It is quite natural to define a software language as an extension of a base language. A compiler builder usually prefers to work on a representation in the base language, while programmers prefer to program in the extended language. As we define a language extension, we want to ensure that desugaring it into the base language is provably sound.

Abstract Constraint handling rules provide descriptions for constraint solvers. However, they fall short when those constraints specify some binding structure, like higher-rank types in a constraint-based type inference algorithm. In this paper, the term syntax of constraints is replaced by λ-tree syntax, in which binding is explicit, and a new ∇ generic quantifier is introduced, which is used to create new fresh constants.

Type classes and type families are key ingredients in Haskell programming. Type classes were introduced to deal with ad-hoc polymorphism, although with the introduction of functional dependencies, their use expanded to type-level programming. Type families also allow encoding type-level functions, but more directly in the form of rewrite rules. In this paper we show that type families are powerful enough to simulate type classes (without overlapping instances), and we provide a formal proof of the soundness and completeness of this simulation. Encoding instance constraints as type families eases the path to proposed extensions to type classes, like closed sets of instances, instance chains, and control over the search procedure. The only feature which type families cannot simulate is elaboration, that is, generating code from the derivation of a rewriting. We look at ways to solve this problem in current Haskell, and propose an extension to allow elaboration during the rewriting phase.

Abstract We present a novel general resource analysis for logic programs based on sized types. Sized types are representations that incorporate structural (shape) information and allow expressing both lower and upper bounds on the size of a set of terms and their subterms at any position and depth. They also allow relating the sizes of terms and subterms occurring at different argument positions in logic predicates. Using these sized types, the resource analysis can infer both lower and upper bounds on the resources used by all the procedures in a program as functions on input term (and subterm) sizes, overcoming limitations of existing resource analyses and enhancing their precision. Our new resource analysis has been developed within the abstract interpretation framework, as an extension of the sized types abstract domain, and has been integrated into the Ciao preprocessor, CiaoPP. The abstract domain operations are integrated with the setting up and solving of recurrence equations for inferring both size and resource usage functions. We show that the analysis is an improvement over the previous resource analysis present in CiaoPP and compares well in power to state of the art systems.