high performance computing on graphics processing units: hgpu.org

hgpu.org » Code generation

CU2CL: A CUDA-to-OpenCL Translator for Multi-and Many-core Architectures

Gabriel Martinez, Wu-chun Feng, Mark Gardner

View

Tags: ATI, ATI Radeon HD 5870, Benchmarking, Code generation, Computer science, CUDA, Heterogeneous systems, MPI, nVidia, nVidia GeForce GTX 280, OpenCL

September 24, 2011 by hgpu

An MDE Approach for Automatic Code Generation from MARTE to OpenCL

Antonio Wendell De Oliveira Rodrigues, Frederic Guyomarc'H, Jean-Luc Dekeyser

View

Download (PDF)

Tags: Code generation, Computer science, Heterogeneous systems, nVidia, nVidia GeForce GTX 285, OpenCL

September 24, 2011 by hgpu

Embedding OpenCL in C++ for Expressive GPU Programming

Orion Lawlor

View

Download (PDF)

Source codes

Tags: ATI, ATI Radeon HD 6850, Benchmarking, Code generation, Computer science, GLSL, nVidia, nVidia GeForce GTX 280, nVidia GeForce GTX 460 M, nVidia GeForce GTX 580, OpenCL, OpenGL, Package

September 23, 2011 by hgpu

Simple optimizations for an applicative array language for graphics processors

Bradford Larsen

View

Download (PDF)

Tags: Code generation, Compilers, Computer science, CUDA, nVidia, nVidia GeForce 8800 GT, Optimization, Programming Languages, Programming techniques

September 23, 2011 by hgpu

Mint: realizing CUDA performance in 3D stencil methods with annotated C

Didem Unat, Xing Cai, Scott B. Baden

View

Download (PDF)

Source codes

Tags: Algorithms, Code generation, Compilers, Computer science, CUDA, nVidia, OpenMP, Optimization, Package, Performance, Programming Languages, Tesla C1060

September 21, 2011 by hgpu

Nikola: embedding compiled GPU functions in Haskell

Geoffrey Mainland, Greg Morrisett

View

Download (PDF)

Source codes

Tags: Code generation, Computer science, CUDA, nVidia, Package, Programming Languages, Tesla T10

September 14, 2011 by hgpu

AnySL: efficient and portable shading for ray tracing

Ralf Karrenberg, Dmitri Rubinstein, Philipp Slusallek, Sebastian Hack

View

Download (PDF)

Source codes

Tags: 3D Graphics and Realism, Code generation, Compilers, Computer science, nVidia, Package, Programming Languages, PTX, Raytracing, Rendering

September 13, 2011 by hgpu

Lightweight modular staging: a pragmatic approach to runtime code generation and compiled DSLs

Tiark Rompf, Martin Odersky

View

Download (PDF)

Tags: Code generation, Computer science, Optimization, Programming Languages, Software Engineering

September 11, 2011 by hgpu

High-performance SIMT code generation in an active visual effects library

Jay L.T. Cornwall, Lee Howes, Paul H.J. Kelly, Phil Parsonage, Bruno Nicoletti

View

Download (PDF)

Tags: Algorithms, Code generation, CUDA, Image processing, nVidia, nVidia GeForce 8800 GTX, nVidia GeForce GTX 260, Performance, Software Engineering, Visualization

September 11, 2011 by hgpu

MacroSS: macro-SIMDization of streaming applications

Amir H. Hormati, Yoonseo Choi, Mark Woh, Manjunath Kudlur, Rodric Rabbah, Trevor Mudge, Scott Mahlke

View

Download (PDF)

Tags: Code generation, Compilers, Computer science, Optimization, Performance, Programming Languages

September 7, 2011 by hgpu

CUDA-level performance with python-level productivity for Gaussian mixture model applications

H. Cook, E. Gonina, S. Kamil, G. Friedland, D. Patterson, A. Fox

View

Download (PDF)

Tags: Algorithms, Code generation, Computer science, CUDA, nVidia, OpenCL, Python

September 7, 2011 by hgpu

A mapping path for multi-GPGPU accelerated computers from a portable high level programming abstraction

Allen Leung, Nicolas Vasilache, Benoit Meister, Muthu Baskaran, David Wohlford, Cedric Bastoul, Richard Lethin

View

Download (PDF)

Tags: Algorithms, Code generation, Compilers, Computer science, CUBLAS, CUDA, nVidia, nVidia GeForce 9800 GX2, nVidia GeForce GTX 285, Programming Languages

August 24, 2011 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

CU2CL: A CUDA-to-OpenCL Translator for Multi-and Many-core Architectures

An MDE Approach for Automatic Code Generation from MARTE to OpenCL

Embedding OpenCL in C++ for Expressive GPU Programming

Simple optimizations for an applicative array language for graphics processors

Mint: realizing CUDA performance in 3D stencil methods with annotated C

Nikola: embedding compiled GPU functions in Haskell

AnySL: efficient and portable shading for ray tracing

Lightweight modular staging: a pragmatic approach to runtime code generation and compiled DSLs

High-performance SIMT code generation in an active visual effects library

MacroSS: macro-SIMDization of streaming applications

CUDA-level performance with python-level productivity for Gaussian mixture model applications

A mapping path for multi-GPGPU accelerated computers from a portable high level programming abstraction

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)