CGO 2024
Sat 2 - Wed 6 March 2024 Edinburgh, United Kingdom
Mon 4 Mar 2024 11:30 - 11:50 at Tinto - Machine-Learning Guided Optimizations Chair(s): Zheng Wang

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 and, respectively.

Mon 4 Mar

Displayed time zone: London change

11:30 - 12:50
Machine-Learning Guided OptimizationsMain Conference at Tinto
Chair(s): Zheng Wang University of Leeds
AskIt: Unified Programming Interface for Programming with Large Language Models
Main Conference
Katsumi Okuda Massachusetts Institute of Technology; Mitsubishi Electric Corporation, Saman Amarasinghe Massachusetts Institute of Technology
Revealing Compiler Heuristics through Automated Discovery and Optimization
Main Conference
Volker Seeker Meta AI Research, Chris Cummins Meta AI Research, Murray Cole University of Edinburgh, Björn Franke University of Edinburgh, Kim Hazelwood Meta AI Research, Hugh Leather Meta AI Research
SLaDe: A Portable Small Language Model Decompiler for Optimized Assembly
Main Conference
Jordi Armengol-Estapé University of Edinburgh, Jackson Woodruff University of Edinburgh, Chris Cummins Meta AI Research, Michael F. P. O'Boyle University of Edinburgh
TapeFlow: Streaming Gradient Tapes in Automatic Differentiation
Main Conference
Milad Hakimi Simon Fraser University, Arrvindh Shriraman Simon Fraser University
Media Attached