high performance computing on graphics processing units: hgpu.org

hgpu.org » Compilers

MARC: A Many-Core Approach to Reconfigurable Computing

Ilia Lebedev, Shaoyi Cheng, Austin Doupnik, James Martin, Christopher Fletcher, Daniel Burke, Mingjie Lin, John Wawrzynek

Tags: Compilers, Computer science, FPGA, OpenCL, Performance

April 2, 2011 by hgpu

A framework for efficient and scalable execution of domain-specific templates on GPUs

Narayanan Sundaram, Anand Raghunathan, S. T. Chakradhar

View

Download (PDF)

Tags: Code generation, Compilers, Computer science, nVidia, nVidia GeForce 8800 GTX, Tesla C870

March 15, 2011 by hgpu

Obsidian: GPU Programming in Haskell

Koen Claessen, Mary Sheeran, Joel Svensson

View

Download (PDF)

Source codes

Tags: Code generation, Compilers, Computer science, CUDA, nVidia, nVidia GeForce 8800 GTS, Package

March 13, 2011 by hgpu

Obsidian: GPU Kernel Programming in Haskell (thesis)

Joel Svensson

View

Download (PDF)

Source codes

Tags: Code generation, Compilers, Computer science, CUDA, nVidia, nVidia GeForce GTX 320 M, nVidia GeForce GTX 480, Package, Thesis

March 13, 2011 by hgpu

Ocelot: a dynamic optimization framework for bulk-synchronous applications in heterogeneous systems

Gregory F. Diamos, Andrew R. Kerr, Sudhakar Yalamanchili, Nathan Clark

View

Download (PDF)

Source codes

Tags: Compilers, Computer science, CUDA, Heterogeneous systems, nVidia, Package, Programming Languages, PTX

March 9, 2011 by hgpu

Automatic data movement and computation mapping for multi-level parallel architectures with explicitly managed memories

Muthu Manikandan Baskaran, Uday Bondhugula, Sriram Krishnamoorthy, J. Ramanujam, Atanas Rountev, P. Sadayappan

View

Download (PDF)

Tags: Algorithms, Code generation, Compilers, Computer science, CUDA, nVidia, nVidia GeForce 8800 GTX, Optimization, Performance

February 28, 2011 by hgpu

A Domain-Specific Approach To Heterogeneous Parallelism

Hassan Chafi, Arvind K. Sujeeth, Kevin J. Brown, HyoukJoong Lee, Anand R. Atreya, Kunle Olukotun

View

Download (PDF)

Tags: Code generation, Compilers, Computer science, CUDA, Heterogeneous systems, High-level Languages, nVidia, nVidia GeForce GTX 275

February 27, 2011 by hgpu

A Tuning Framework for Software-Managed Memory Hierarchies

Manman Ren, Ji Young Park, Mike Houston, Alex Aiken, William J. Dally

View

Download (PDF)

Tags: Algorithms, Cell processor, Compilers, Computer science, Optimization, Performance, Playstation, Programming Languages

February 26, 2011 by hgpu

Achieving a single compute device image in OpenCL for multiple GPUs

Jungwon Kim, Honggyu Kim, Joo H. Lee, Jaejin Lee

Tags: Algorithms, Code generation, Compilers, Computer science, CUDA, nVidia, OpenCL, Optimization

February 25, 2011 by hgpu

An Automated Approach for SIMD Kernel Generation for GPU based Software Acceleration

Kanupriya Gulati and Sunil P Khatri

View

Download (PDF)

Tags: Code generation, Compilers, Computer science, CUDA, nVidia, nVidia GeForce GTX 280

February 21, 2011 by hgpu

Data parallel loop statement extension to CUDA: GpuC

Zeki Bozkus, Rajeev Thakur, William Gropp, Ewing Lusk

View

Download (PDF)

Tags: Compilers, Computer science, CUDA, High-level Languages, nVidia, OpenMP, Optimization

February 21, 2011 by hgpu

MCUDA: An Efficient Implementation of CUDA Kernels on Multi-cores

John A. Stratton, Sam S. Stone, and Wen-mei W. Hwu

View

Download (PDF)

Source codes

Tags: Compilers, Computer science, CUDA, High-level Languages, nVidia, Package

February 20, 2011 by hgpu

Data-efficient LLM Fine-tuning for Code Generation

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

DeepCompile: A Compiler-Driven Approach to Optimizing Distributed Deep Learning Training

Large Language Model Powered C-to-CUDA Code Translation: A Novel Auto-Parallelization Framework

GigaAPI: a user-space API that simplifies multi-GPU programming, bridging the gap between the capabilities of parallel GPU systems and the ability of developers to harness their full potential

GigaAPI for GPU Parallelization

Coccinelle: a C code transformation engine using SmPL for matches, refactorings, and bug fixing

Advances in Semantic Patching for HPC-oriented Refactorings with Coccinelle

DuoReduce: MLIR's benchmark

Hardware-Assisted Software Testing and Debugging for Heterogeneous Computing

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

MARC: A Many-Core Approach to Reconfigurable Computing

A framework for efficient and scalable execution of domain-specific templates on GPUs

Obsidian: GPU Programming in Haskell

Obsidian: GPU Kernel Programming in Haskell (thesis)

Ocelot: a dynamic optimization framework for bulk-synchronous applications in heterogeneous systems

Automatic data movement and computation mapping for multi-level parallel architectures with explicitly managed memories

A Domain-Specific Approach To Heterogeneous Parallelism

A Tuning Framework for Software-Managed Memory Hierarchies

Achieving a single compute device image in OpenCL for multiple GPUs

An Automated Approach for SIMD Kernel Generation for GPU based Software Acceleration

Data parallel loop statement extension to CUDA: GpuC

MCUDA: An Efficient Implementation of CUDA Kernels on Multi-cores

Recent source codes

PELSI: Power-Efficient Layer-Switched Inference

Ouroboros: Virtualized Queues for dynamic memory management

MSCCL++: A GPU-driven communication stack for scalable AI applications

Benchmark compute shader of Unity against InteropUnityCUDA

Data-efficient LLM Fine-tuning for Code Generation

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Large Language Model Powered C-to-CUDA Code Translation: A Novel Auto-Parallelization Framework

GigaAPI: a user-space API that simplifies multi-GPU programming, bridging the gap between the capabilities of parallel GPU systems and the ability of developers to harness their full potential

Coccinelle: a C code transformation engine using SmPL for matches, refactorings, and bug fixing

DuoReduce: MLIR's benchmark

Most viewed papers (last 30 days)