Ithemal: Accurate, Portable and Fast Basic Block Throughput Estimation using Deep Neural Networks

Abstract

Predicting the number of clock cycles a processor takes to execute a block of assembly instructions in steady state (the throughput) is important for both compiler designers and performance engineers. Building an analytical model to do so is especially complicated in modern x86-64 Complex Instruction Set Computer (CISC) machines with sophisticated processor microarchitectures in that it is tedious, error prone, and must be performed from scratch for each processor generation. In this paper we present Ithemal, the first tool which learns to predict the throughput of a set of instructions. Ithemal uses a hierarchical LSTM--based approach to predict throughput based on the opcodes and operands of instructions in a basic block. We show that Ithemal is more accurate than state-of-the-art hand-written tools currently used in compiler backends and static machine code analyzers. In particular, our model has less than half the error of state-of-the-art analytical models (LLVM's llvm-mca and Intel's IACA). Ithemal is also able to predict these throughput values just as fast as the aforementioned tools, and is easily ported across a variety of processor microarchitectures with minimal developer effort.

Published at 36th International Conference on Machine Learning (ICML) 2019

References in corpus (6)

• Sequence to Sequence Learning with Neural Networks
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Hierarchical Multiscale Recurrent Neural Networks
• Learning Memory Access Patterns
• Linguistic Knowledge as Memory for Recurrent Neural Networks
• DAG-Recurrent Neural Networks For Scene Labeling

Cited by in corpus (11)

• Hardware Acceleration of Sparse and Irregular Tensor Computations of ML Models: A Survey and Insights
• Mind Mappings: Enabling Efficient Algorithm-Accelerator Mapping Space Search
• nanoBench: A Low-Overhead Tool for Running Microbenchmarks on x86 Systems
• uiCA: Accurate Throughput Prediction of Basic Blocks on Recent Intel Microarchitectures
• The Dawn of AI-Native EDA: Opportunities and Challenges of Large Circuit Models
• RL4ReAl: Reinforcement Learning for Register Allocation
• ProTuner: Tuning Programs with Monte Carlo Tree Search
• Facile: Fast, Accurate, and Interpretable Basic-Block Throughput Prediction
• Optimizing DNN Compilation for Distributed Training with Joint OP and Tensor Fusion
• Programming with Neural Surrogates of Programs
• Proposition d'un modèle pour l'optimisation automatique de boucles dans le compilateur Tiramisu : cas d'optimisation de déroulage