A code generator for array-based code on CPUs and GPUs
-
Updated
Sep 19, 2026 - Python
A code generator for array-based code on CPUs and GPUs
Pluto: An automatic polyhedral parallelizer and locality optimizer
Offline manual loop closure editing and optimization tools for LiDAR mapping pose graphs. 用于激光雷达建图位姿图的离线手动闭环编辑与优化工具。
RV: A Unified Region Vectorizer for LLVM
Python wrapper for isl, an integer set library
A Fast DNN Accelerator Design Space Exploration Framework.
Dataflow-LoopAI is an intelligent system with self-optimization capabilities that automatically detects and evaluates generation deficiencies in LLMs within specific domains. Through dialog-based active data retrieval and self-driven optimization mechanisms, it enables continuous co-evolution between data and models.
TC Optimizing Compiler
Loop-Invariant Code Motion (LICM) optimization pass hoisting loop-invariant computations into preheader blocks.
Hand-tuned WebAssembly implementations for efficient execution of web-based sparse computations including Sparse Matrix-Vector Multiplication (SpMV), sparse triangular solve (SpTS) and other useful sparse matrix operations.
Loop-Invariant Code Motion (LICM) optimization pass hoisting loop-invariant computations into preheader blocks.
Benchmarks of loop fission algorithm.
Laboratory exercises on cards with ARM, FPGA and sensors for "Embedded System Design" course NTUA 2020 -2021
This c file demonstrates loop optimization using a technique called loop blocking, or also known as loop tiling.
Laboratory exercises on cards with ARM, FPGA and sensors
Loop Reordering, Register Blocking & SSE Unrolling
Loop Invariant Code Motion Optimization Pass - operates on LLVM Intermediate Representation (IR)
Operation-Role Coordination & Hedging Interface Daemon (ORCHID) — The low-level micro-architectural execution core of the RAMNET distributed computing protocol.
How much of GEMM performance is memory access order? Five CPU variants of the same matrix product, a shared-memory tiled CUDA kernel and a CUDA sum reduction, all measured on one shape. Loop reordering alone is worth 37.9x. C++17, CMake, no dependencies.
To associate your repository with the loop-optimization topic, visit your repo's landing page and select "manage topics."