Advanced Compiler and Runtime Optimizations for ML Workloads
Chapter 1: Foundation: ML Execution Stack and Challenges
The ML Model Deployment Gap
Overview of ML Compiler and Runtime Stacks
Performance Bottlenecks in ML Inference
Hardware for ML Acceleration
The Need for Specialized Optimizations
Chapter 2: Advanced Intermediate Representations for ML
Limitations of Traditional Compiler IRs
Principles of Multi-Level IRs
MLIR: Dialects and Operations
Representing High-Level ML Graphs (e.g., TF, TOSA)
Lowering Paths within MLIR
Extensibility and Custom Dialects
Hands-on Practical: Analyzing MLIR Representations
Chapter 3: Advanced Graph-Level Optimizations
Graph Rewriting Systems
Aggressive Operator Fusion Techniques
Memory-Aware Layout Transformations
Advanced Algebraic Simplification
Static Memory Planning and Allocation
Handling Control Flow in Graphs
Hands-on Practical: Implementing a Fusion Pass
Chapter 4: Tensor-Level Optimizations and Polyhedral Modeling
Representing Tensor Computations as Loop Nests
Introduction to Polyhedral Modeling
Iteration Domains, Access Functions, and Dependencies
Scheduling Transformations (Skewing, Tiling)
Code Generation from Polyhedral Schedules
Auto-Vectorization Techniques (SIMD)
Memory Hierarchy Optimization: Tiling and Prefetching
Hands-on Practical: Optimizing Loops with Polyhedral Tools
Chapter 5: Code Generation for Heterogeneous Hardware
Target-Specific Instruction Selection
Register Allocation for Vector/Matrix Units
GPU Code Generation: CUDA and ROCm Backends
Generating Code for Tensor Cores and Matrix Units
Targeting AI Accelerators (TPUs, NPUs)
Intermediate Formats for Heterogeneous Execution (SPIR-V)
Vendor-Specific Compiler Toolchains and Libraries (cuDNN, MIOpen)
Hands-on Practical: Analyzing Generated GPU Kernels
Chapter 6: Advanced Runtime Systems for ML
Runtime Architecture Overview
Handling Dynamic Shapes and Sizes
Efficient Memory Management Strategies
Asynchronous Execution and Scheduling
Scheduling for Heterogeneous Systems
Integrating Custom Operators and Kernels
Interoperability with ML Frameworks
Hands-on Practical: Implementing a Simple Allocator
Chapter 7: Just-In-Time (JIT) Compilation Techniques for ML
Motivation for JIT Compilation in ML
Tracing vs. Scripting Approaches
Intermediate Representation in JIT Systems
Runtime Specialization and Polymorphism
Profile-Guided Optimization (PGO) in JITs
Adaptive and Multi-Tier Compilation
Case Study: TensorFlow XLA
Case Study: PyTorch JIT (TorchScript)
Hands-on Practical: Analyzing JIT Compiled Code
Chapter 8: Quantization and Low-Precision Optimizations
Fundamentals of Model Quantization (INT8, FP8)
Representing Quantized Operations in IR
Compiler Passes for Quantization-Aware Training (QAT)
Post-Training Quantization (PTQ) Compilation Flows
Generating Low-Precision Kernels
Mixed-Precision Computation Optimization
Handling Quantization Scales and Zero Points
Hands-on Practical: Lowering Quantized Operations
Chapter 9: Profiling and Performance Analysis Tools
Challenges in Profiling Compiled ML Code
System-Level Profiling (CPU, GPU, Interconnect)
CPU Performance Analysis (VTune, perf)
GPU Kernel Profiling (Nsight Compute, ROCprof)
Correlating Framework Operations to Compiled Kernels
Memory Access Pattern Analysis
Interpreting Compiler Optimization Reports
Hands-on Practical: Profiling an Optimized Model
Scheduling for Heterogeneous Systems
Was this section helpful?
- TVM: An End-to-End Optimizing Compiler for Deep Learning, Tianqi Chen, Thierry Moreau, Ziheng Jiang, Lianmin Zheng, Eddie Yan, Haichen Shen, Meghan Cowan, Leyuan Wang, Yuwei Hu, Luis Ceze, Carlos Guestrin, Arvind Krishnamurthy, 2018 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18) (USENIX Association) DOI: 10.5555/3342371.3342416 - This paper introduces TVM, a deep learning compiler stack that optimizes and deploys models across diverse hardware backends, focusing on heterogeneous execution and hardware-specific optimizations.
- A Survey on Deep Learning System Optimization: From Algorithm to Hardware, Yujun Chen, Shuchang Sheng, Xiaolong Ma, Peiyan Dong, Zhiye Tang, Junru Zhao, Yuanjie Xie, and Shaoli Liu, 2020 Proceedings of the IEEE, Vol. 108 (IEEE) DOI: 10.1109/JPROC.2020.2991739 - This survey provides a comprehensive overview of various optimization techniques in deep learning systems, including extensive discussions on heterogeneous scheduling, communication optimization, and memory management.
- GSPMD: General and Efficient Parallelism for ML Workloads, Yuanzhong Xu, Jiri Simsa, Jeremy Smith, D. J. Bernstein, Yuan Zhang, Sarah Sirajuddin, and Anna Goldie, 2021 Proceedings of Machine Learning and Systems (MLSys '21), Vol. 3 (MLSys) DOI: 10.48550/arXiv.2105.04694 - This paper introduces GSPMD, a system for automatic and efficient parallelism of ML workloads across heterogeneous devices, incorporating advanced strategies for data movement and device placement.
- Ansor: Generating High-Performance Tensors with N-Dimensional Search Space Auto-Tuning, Lianmin Zheng, Chengfan Jia, Minmin Sun, Zhao Wu, Cody Hao Yu, Ameer Haj-Ali, Yida Wang, Jun Yang, Danyang Zhuo, Koushik Sen, Joseph E. Gonzalez, Ion Stoica, 2020 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20) (USENIX Association) DOI: 10.5555/3474345.3474397 - This paper details an auto-tuning framework for deep learning compilers that dynamically optimizes tensor programs for heterogeneous hardware, relying on accurate performance models and hardware characterization.