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
Representing High-Level ML Graphs (e.g., TF, TOSA)
Was this section helpful?
- MLIR: A Compiler Infrastructure for the End of Moore's Law, Chris Lattner, Mehdi Amini, River Riddle, Albert Cohen, Alan Daynes, John Field, Georges-Axel Jaloyan, Artem Krassovsky, Joshua Lee, Roman Popov, Siegfried Puchbauer, Tatiana Shpeisman, Nicolas Vasilache, 2021 Proceedings of the 2021 International Symposium on Code Generation and Optimization (CGO) (ACM) DOI: 10.1145/3441558.3446095 - Provides the foundational architecture and design principles of MLIR, including its multi-level IR approach, dialect system, and SSA form, essential for understanding its role in representing high-level ML graphs.
- TOSA (Tensor Operator Set Architecture) Specification, Khronos Group, 2023 (Khronos Group) - The official documentation defining the Tensor Operator Set Architecture, a standardized set of tensor operations for machine learning, directly relevant to the
tosadialect. - MLIR for TensorFlow: The Compiler Stack for the Next Generation of ML Hardware, River Riddle, Nicolas Vasilache, Chris Lattner, Mehdi Amini, Albert Cohen, Alan Daynes, John Field, Georges-Axel Jaloyan, Artem Krassovsky, Joshua Lee, Roman Popov, Siegfried Puchbauer, Tatiana Shpeisman, 2019 LLVM Developers' Meeting (Presentation) - A presentation by key MLIR and TensorFlow developers, detailing the motivation and design of integrating TensorFlow with MLIR, particularly the
tfdialect, for high-level graph representation and optimization. - StableHLO: An Open Standard for ML Models, OpenXLA Project, 2023 (OpenXLA Project) - The official website and specification for StableHLO, an open standard building upon MHLO, providing a portable and stable representation for machine learning models, relevant to the
stablehlodialect.