high performance computing on graphics processing units: hgpu.org

hgpu.org » Code generation

Toward Automatic Translation: From OpenACC to OpenMP 4

Nawrin Sultana

View

Download (PDF)

Tags: Algorithms, Code generation, Compilers, Computer science, nVidia, OpenACC, OpenMP, Tesla K40, Thesis

December 17, 2016 by hgpu

Automating the Last-Mile for High Performance Dense Linear Algebra

Richard Michael Veras, Tze Meng Low, Tyler Michael Smith, Robert van de Geijn, Franz Franchetti

View

Download (PDF)

Tags: Code generation, Computer science, Intel Xeon Phi, Linear Algebra, Performance

December 14, 2016 by hgpu

Translating OpenMP Device Constructs to OpenCL using Unnecessary Data Transfer Elimination

Junghyun Kim, Yong-Jun Lee, Jungho Park, Jaejin Lee

View

Download (PDF)

Tags: AMD Radeon R9 390X, ATI, Benchmarking, Code generation, Computer science, nVidia, nVidia GeForce GTX Titan X, OpenACC, OpenCL, OpenMP

December 14, 2016 by hgpu

Towards Comprehensive Parametric Code Generation Targeting Graphics Processing Units in Support of Scientific Computation

Ning Xie

View

Download (PDF)

Tags: Code generation, Computer science, CUDA, nVidia, OpenMP, Tesla M2050, Thesis

December 14, 2016 by hgpu

OpenACC cache Directive: Opportunities and Optimizations

Ahmad Lashgar, Amirali Baniasadi

View

Download (PDF)

Source codes

Tags: Code generation, Computer science, CUDA, nVidia, OpenACC, OpenCL, Package, Performance, Tesla K20

December 3, 2016 by hgpu

Efficient Kernel Synthesis for Performance Portable Programming

Li-Wen Chang, Izzat El Hajj, Christopher Rodrigues, Juan Gomez-Luna, Wen-mei Hwu

View

Download (PDF)

Tags: Code generation, Computer science, CUDA, Design space exploration, Heterogeneous systems, nVidia, performance portability, Tesla C2050, Tesla K20

November 25, 2016 by hgpu

A Metaprogramming and Autotuning Framework for Deploying Deep Learning Applications

Matthew W. Moskewicz, Ali Jannesari, Kurt Keutzer

View

Download (PDF)

Source codes

Tags: AMD R9 Nano, ARM, ATI, Code generation, Computer science, Computer vision, CUDA, Deep learning, Neural networks, nVidia, nVidia GeForce GTX Titan X, OpenCL, Package

November 23, 2016 by hgpu

Automatic code generation methods applied to numerical linear algebra in high performance computing

M. Ian Masliah

View

Download (PDF)

Tags: Algorithms, Code generation, Computer science, CUDA, Heterogeneous systems, Linear Algebra, Mixed precision, nVidia, nVidia Tegra TX1, Programming techniques, Tesla C2075, Tesla K40, Thesis

November 16, 2016 by hgpu

HPVM: A Portable Virtual Instruction Set for Heterogeneous Parallel Systems

Prakalp Srivastava, Maria Kotsifakou, Vikram Adve

View

Download (PDF)

Tags: Code generation, Computer science, Data parallelism, Heterogeneous systems, nVidia, nVidia GeForce GTX 680, OpenCL, performance portability

November 5, 2016 by hgpu

OpenMP as a High-Level Specification Language for Parallelism And its use in Evaluating Parallel Programming Systems

Max Grossman, Jun Shirako, Vivek Sarkar

View

Download (PDF)

Source codes

Tags: Code generation, Compilers, Computer science, CUDA, LLVM, nVidia, OpenMP, Package

September 13, 2016 by hgpu

OpenSBLI: A framework for the automated derivation and parallel execution of finite difference solvers on a range of computer architectures

Christian T. Jacobs, Satya P. Jammy, Neil D. Sandham

View

Download (PDF)

Tags: cfd, Code generation, Computer science, CUDA, Finite difference, Fluid dynamics, Mathematical Software, MPI, nVidia, OpenCL, Tesla K40

September 10, 2016 by hgpu

SafeGPU: Contract- and Library-Based GPGPU for Object-Oriented Languages

Alexey Kolesnichenko, Christopher M. Poskitt, Sebastian Nanz

View

Download (PDF)

Source codes

Tags: Algorithms, Code generation, Computer science, CUDA, nVidia, nVidia Quadro K 2000 M, Package

August 31, 2016 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

Toward Automatic Translation: From OpenACC to OpenMP 4

Automating the Last-Mile for High Performance Dense Linear Algebra

Translating OpenMP Device Constructs to OpenCL using Unnecessary Data Transfer Elimination

Towards Comprehensive Parametric Code Generation Targeting Graphics Processing Units in Support of Scientific Computation

OpenACC cache Directive: Opportunities and Optimizations

Efficient Kernel Synthesis for Performance Portable Programming

A Metaprogramming and Autotuning Framework for Deploying Deep Learning Applications

Automatic code generation methods applied to numerical linear algebra in high performance computing

HPVM: A Portable Virtual Instruction Set for Heterogeneous Parallel Systems

OpenMP as a High-Level Specification Language for Parallelism And its use in Evaluating Parallel Programming Systems

OpenSBLI: A framework for the automated derivation and parallel execution of finite difference solvers on a range of computer architectures

SafeGPU: Contract- and Library-Based GPGPU for Object-Oriented Languages

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)