Machine Learning CompilersΒΆ GETTING STARTED Building the Project Building the Documentation CHAPTERS Overview Documentation Assembly Base Neon Code Generation Tensor Operation Einsum Tree Individual Phase Assembly Hello Assembly Assembly Function Base Copying Data Instruction Throughput and Latency Neon Execution Throughput and Latency Microkernel Loops SIMD Lanes Accumulator Shapes Batch-Reduce GEMM Transposition Code Generation BRGEMM Primitive Unary Primitives Tensor Operations Backend Recursive Loops Over Primitives Optimization Passes Unary Operations Einsum Trees Lowering Optimization Individual Phase Draft Ideas Execution API mini_jit mini_jit::Brgemm mini_jit::EinsumTree mini_jit::Kernel mini_jit::TensorConfig mini_jit::TensorOperation mini_jit::TensorOptimization mini_jit::Unary arm_instructions kernels mlc ErrorType UnaryType fill_random() fill_number() fill_counting_up() fill_counting_down() fill_lambda() einsum() einsum() einsum_operation() contraction() contraction() gemm() unary_zero() unary_relu() unary_identity() mlc::EinsumOperation mlc::Error mlc::Tensor mlc::TensorOperation