No article text was recorded for this version.
hardware-specific optimization complexity
Version 1 of 150 papers54 conceptsfrozen 2026-10-04
Papers in this version
- Blog: SynKer: Synthesize, Kernelize, Reinforce - Teaching GPU Kernel Generation to Small Language Models
- Blog: Leveraging AI for Productive and Trustworthy HPC Software: Challenges and Research Directions
- Blog: Hexcute: A Compiler Framework for Automating Layout Synthesis in GPU Programs
- Blog: Dr. Kernel: Reinforcement Learning Done Right for Triton Kernel Generations
- Blog: Implementing block-sparse matrix multiplication kernels using Triton
- Blog: Mastering Sparse CUDA Generation through Pretrained Models and Deep Reinforcement Learning
- Blog: What is a Lightweight Kernel?
- Blog: FlashMoE: Fast Distributed MoE in a Single Kernel
- Blog: AccelOpt: A Self-Improving LLM Agentic System for AI Accelerator Kernel Optimization
- Blog: KForge: A Multi-Agent System for Cross-Platform Kernel Synthesis
- Blog: CudaForge: An Agent Framework with Hardware Feedback for CUDA Kernel Optimization
- Blog: Chameleon: Adaptive Code Optimization for Expedited Deep Neural Network Compilation
- Blog: Learning to Optimize Tensor Programs
- Blog: Optimization for Classical Machine Learning Problems on the GPU
- Blog: AutoTriton: Automatic Triton Programming with Reinforcement Learning in LLMs
- Blog: Tensor Program Optimization with Probabilistic Programs
- Blog: Popcorn: Accelerating Kernel K-means on GPUs through Sparse Linear Algebra
- Blog: TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operators
- Blog: CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning
- Blog: KernelBench: Can LLMs Write Efficient GPU Kernels?
- Blog: Understanding the Power of Evolutionary Computation for GPU Code Optimization
- Blog: Machine learning and intelligence science: IScIDE (C)
- Blog: Hector: An Efficient Programming and Compilation Framework for Implementing Relational Graph Neural Networks in GPU Architectures
- Blog: QiMeng-TensorOp: One-Line Prompt is Enough for High-Performance Tensor Operator Generation with Hardware Primitives
- Blog: Productivity, Portability, Performance: Data-Centric Python
- Blog: REASONING COMPILER: LLM-Guided Optimizations for Efficient Model Serving
- Blog: MLModelCI: An Automatic Cloud Platform for Efficient MLaaS
- Blog: KernelBand: Steering LLM-based Kernel Optimization via Hardware-Aware Multi-Armed Bandits
- Blog: An Extension of the StarSs Programming Model for Platforms with Multiple GPUs
- Blog: Automated Deep Learning Optimization via DSL-Based Source Code Transformation
- Blog: QiMeng-Kernel: Macro-Thinking Micro-Coding Paradigm for LLM-Based High-Performance GPU Kernel Generation
- Blog: Mirage: A Multi-Level Superoptimizer for Tensor Programs
- Blog: NEURAghe: Exploiting CPU-FPGA Synergies for Efficient and Flexible CNN Inference Acceleration on Zynq SoCs
- Blog: LazyAttention: Efficient Retrieval-Augmented Generation with Deferred Positional Encoding
- Blog: KernelFoundry: Hardware-Aware Evolutionary GPU Kernel Optimization
- Blog: Using GPUs And LLMs Can Be Satisfying for Nonlinear Real Arithmetic Problems
- Blog: Efficient Automatic Scheduling of Imaging and Vision Pipelines for the GPU
- Blog: A Versatile Software Systolic Execution Model for GPU Memory-Bound Kernels
- Blog: From Large to Small: Transferring CUDA Optimization Expertise via Reasoning Graph
- Blog: KernelBot: A Competition Platform for Writing Heterogeneous GPU Code
- Blog: A GPU-accelerated face annotation system for smartphones
- Blog: STARK: Strategic Team of Agents for Refining Kernels
- Blog: NKI-Agent: Domain-Specific Fine-Tuning and Agentic Tool Use for Neuron Kernel Generation
- Blog: GPU Kernel Scientist: An LLM-Driven Framework for Iterative Kernel Optimization
- Blog: Boda-RTC: Productive generation of portable, efficient code for convolutional neural networks on mobile computing platforms
- Blog: TritonRL: Training LLMs to Think and Code Triton Without Cheating
- Blog: EvoEngineer: Mastering Automated CUDA Kernel Code Evolution with Large Language Models
- Blog: Unrolled Memory Inner-Products: An Abstract GPU Operator for Efficient Vision-Related Computations
- Blog: QiMeng-Attention: SOTA Attention Operator is generated by SOTA Attention Algorithm
- Blog: Kernel-Smith: A Unified Recipe for Evolutionary Kernel Optimization
History & citation
Current · Permanent link
- This direction split from Agentic GPU Kernel Optimization (64% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_hardware_specific_optimization_complexit_53db3580,
title = {hardware-specific optimization complexity},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/hardware-specific-optimization-complexity/rdr_53db3580410746af8c7fe5b5e49ef049},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_hardware_specific_optimization_complexit_53db3580_v1,
title = {hardware-specific optimization complexity},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/hardware-specific-optimization-complexity/rdr_53db3580410746af8c7fe5b5e49ef049/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}