IREE / Google: Intermediate Representation Execution Environment. An MLIR-based end-to-end compiler and runtime.
MLIR / LLVM: Multi-Level IR Compiler Framework. A novel approach to building reusable and extensible compiler infrastructure.
TC / Facebook: Tensor Comprehensions. A fully-functional C++ library to automatically synthesize high-performance machine learning kernels.
Tiramisu / MIT: Tiramisu. A polyhedral compiler for expressing image processing, DNN, and linear/tensor algebra applications.
TVM / Apache: Tensor Virtual Machine. An End to End Machine Learning Compiler Framework for CPUs, GPUs and accelerators.
XLA / Google: Accelerated Linear Algebra. A domain-specific compiler for linear algebra that can accelerate TensorFlow models with potentially no source code changes.
OpenXLA / Google: XLA (Accelerated Linear Algebra) is an open-source machine learning (ML) compiler for GPUs, CPUs, and ML accelerators.
语言
Halide: a language for fast, portable computation on images and tensors
Triton: a language and compiler for writing highly efficient custom Deep-Learning primitives
IREE / Google: Intermediate Representation Execution Environment. An MLIR-based end-to-end compiler and runtime.
MLIR / LLVM: Multi-Level IR Compiler Framework. A novel approach to building reusable and extensible compiler infrastructure.
TC / Facebook: Tensor Comprehensions. A fully-functional C++ library to automatically synthesize high-performance machine learning kernels.
Tiramisu / MIT: Tiramisu. A polyhedral compiler for expressing image processing, DNN, and linear/tensor algebra applications.
TVM / Apache: Tensor Virtual Machine. An End to End Machine Learning Compiler Framework for CPUs, GPUs and accelerators.
XLA / Google: Accelerated Linear Algebra. A domain-specific compiler for linear algebra that can accelerate TensorFlow models with potentially no source code changes.
OpenXLA / Google: XLA (Accelerated Linear Algebra) is an open-source machine learning (ML) compiler for GPUs, CPUs, and ML accelerators.
语言
Halide: a language for fast, portable computation on images and tensors
Triton: a language and compiler for writing highly efficient custom Deep-Learning primitives
