high performance computing on graphics processing units: hgpu.org

Phitchaya Mangpo Phothilimthana, Archibald Samuel Elliott, An Wang, Abhinav Jangda, Bastian Hagedorn, Henrik Barthels, Samuel J. Kaufman, Vinod Grover, Emina Torlak, Rastislav Bodik

View

Download (PDF)

Tags: Code generation, Computer science, CUDA, nVidia, nVidia GeForce GTX Titan X, nVidia Quadro GV100

February 3, 2019 by hgpu

AutoPhase: Compiler Phase-Ordering for High Level Synthesis with Deep Reinforcement Learning

Ameer Haj-Ali, Qijing Huang, William Moses, John Xiang, Ion Stoica, Krste Asanovic, John Wawrzynek

View

Download (PDF)

Tags: Algorithms, Code generation, Compilers, Computer science, Deep learning, HLS, LLVM, Programming Languages

January 20, 2019 by hgpu

Parallel source code transformation techniques using design patterns

David del Rio Astorga

View

Download (PDF)

Tags: Algorithms, Auto-Tuning, Code generation, Computer science, CUDA, nVidia, nVidia GeForce GTX 680, Tesla K40, Thesis

December 2, 2018 by hgpu

FusionStitching: Deep Fusion and Code Generation for Tensorflow Computations on GPUs

Guoping Long, Jun Yang, Kai Zhu, Wei Lin

View

Download (PDF)

Tags: Code generation, Computer science, CUDA, Deep learning, Machine learning, nVidia, TensorFlow

November 18, 2018 by hgpu

Using Compiler Snippets to Exploit Parallelism on Heterogeneous Hardware: A Java Reduction Case Study

Juan Fumero, Christos Kotselidis

View

Download (PDF)

Source codes

Tags: Code generation, Computer science, Heterogeneous systems, Java, nVidia, nVidia Quadro GP100, OpenCL, Package

October 21, 2018 by hgpu

Using SIMD and SIMT vectorization to evaluate sparse chemical kinetic Jacobian matrices and thermochemical source terms

Nicholas J. Curtis, Kyle E. Niemeyer, Chih-Jen Sung

View

Download (PDF)

Source codes

Tags: Chemical Physics, Code generation, Computational Physics, Factorization, nVidia, OpenCL, Package, Physics, Tesla C2075, Tesla K40

September 9, 2018 by hgpu

MegaTrain: Full Precision Training of 100B+ Parameter Large Language Models on a Single GPU

Device Virtual Machine (DVM)

DVM: Real-Time Kernel Generation for Dynamic AI Models

Agentic Code Optimization via Compiler-LLM Cooperation

AutoKernel: Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels

AutoKernel: Autonomous GPU Kernel Optimization via Iterative Agent-Driven Search

Triton-Sanitizer: A Fast and Device-Agnostic Memory Sanitizer for Triton with Rich Diagnostic Context

LLM.Q: Quantized LLM training in pure CUDA/C++

LLMQ: Efficient Lower-Precision LLM Training for Consumer GPUs

SOL-ExecBench: Speed-of-Light Benchmarking for Real-World GPU Kernels Against Hardware Limits

* * *

high performance computing on graphics processing units: hgpu.org

A Case Study: Exploiting Neural Machine Translation to Translate CUDA to OpenCL

An optimizing multi-platform source-to-source compiler framework for the NEURON MODeling Language

Performance Engineering for a Tall & Skinny Matrix Multiplication Kernel on GPUs

A mechanism for balancing accuracy and scope in cross-machine black-box GPU performance modeling

On Optimizing Complex Stencils on GPUs

Custom Code Generation for a Graph DSL

Swizzle Inventor: Data Movement Synthesis for GPU Kernels

AutoPhase: Compiler Phase-Ordering for High Level Synthesis with Deep Reinforcement Learning

Parallel source code transformation techniques using design patterns

FusionStitching: Deep Fusion and Code Generation for Tensorflow Computations on GPUs

Using Compiler Snippets to Exploit Parallelism on Heterogeneous Hardware: A Java Reduction Case Study

Using SIMD and SIMT vectorization to evaluate sparse chemical kinetic Jacobian matrices and thermochemical source terms

Recent source codes

MegaTrain: Full Precision Training of 100B+ Parameter Large Language Models on a Single GPU

Device Virtual Machine (DVM)

Agentic Code Optimization via Compiler-LLM Cooperation

AutoKernel: Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels

Triton-Sanitizer: A Fast and Device-Agnostic Memory Sanitizer for Triton with Rich Diagnostic Context

LLM.Q: Quantized LLM training in pure CUDA/C++

SOL-ExecBench: Speed-of-Light Benchmarking for Real-World GPU Kernels Against Hardware Limits

True 4-Bit Quantized CNN Training on CPU

cuFuzz: A GPU-oriented coverage-guided fuzzer for userland CUDA application

KernelSkill: A Multi-Agent Framework for GPU Kernel Optimization

Most viewed papers (last 30 days)