high performance computing on graphics processing units: hgpu.org

Programming

hgpu.org » Programming » OpenCL

BenchPress: A Deep Active Benchmark Generator

Foivos Tsimpourlas, Pavlos Petoumenos, Min Xu, Chris Cummins, Kim Hazelwood, Ajitha Rajan, Hugh Leather

View

Download (PDF)

Source codes

Tags: Benchmarking, Code generation, Computer science, Deep learning, nVidia, nVidia GeForce GTX 1080, OpenCL, Package, PyTorch

August 21, 2022 by hgpu

Performance analysis of matrix-free conjugate gradient kernels using SYCL

Igor Baratta, Chris Richardson, Garth Wells

View

Download (PDF)

Source codes

Tags: Benchmarking, Computer science, Latency, nVidia, nVidia A100, OpenCL, Package, Performance, SYCL

August 21, 2022 by hgpu

CPU-GPU Layer-Switched Low Latency CNN Inference

Ehsan Aghapour, Dolly Sapra, Andy Pimentel, and Anuj Pathania

View

Download (PDF)

Source codes

Tags: ARM, Computer science, Heterogeneous systems, Machine learning, Neural networks, OpenCL, Package, SoC

July 24, 2022 by hgpu

FPGA Accelerators on Heterogeneous Systems: An Approach Using High Level Synthesis

María Ángelica Dávila Gúzman

View

Download (PDF)

Source codes

Tags: Computer science, FPGA, HLS, nVidia, nVidia GeForce GTX Titan X, OpenCL, Package, Thesis

July 24, 2022 by hgpu

Design and Implementation of CNN-FPGA accelerator based on Open Computing Language

Praveena Bai Desavathu, A Ravi Raja, Er. Sipra Patra, Rabinarayan Satpathy, S. John Pimo, Sankararao Majji

View

Download (PDF)

Source codes

Tags: Algorithms, Computer science, Deep learning, FPGA, Neural networks, OpenCL, Package

July 10, 2022 by hgpu

On the Compilation Performance of Current SYCL Implementations

Peter Thoman, Facundo Molina Heredia, Thomas Fahringer

View

Download (PDF)

Source codes

Tags: Code generation, Compilers, Computer science, Heterogeneous systems, OpenCL, Package, Performance, SYCL

June 12, 2022 by hgpu

AnySeq/GPU: A Novel Approach for Faster Sequence Alignment on GPUs

André Müller, Bertil Schmidt, Richard Membarth, Roland Leißa, Sebastian Hack

View

Download (PDF)

Source codes

Tags: AMD Radeon Instinct MI100, ATI, Bioinformatics, Biology, CUDA, Next-Generation sequencing, nVidia, nVidia GeForce RTX 3090, OpenCL, Package, Sequence alignment, Tesla A100

May 22, 2022 by hgpu

Experience of Migrating a Parallel Graph Coloring Program from CUDA to SYCL

Zheming Jin

View

Download (PDF)

Source codes

Tags: Benchmarking, Computer science, CUDA, Graph theory, nVidia, OpenCL, Package, Performance, SYCL

May 8, 2022 by hgpu

Analytical Performance Estimation during Code Generation on Modern GPUs

Dominik Ernst, Markus Holzer, Georg Hager, Matthias Knorr, Gerhard Wellein

View

Download (PDF)

Source codes

Tags: Code generation, Computer science, CUDA, Lattice Boltzmann model, Machine learning, nVidia, OpenCL, Package, Tesla A100, Tesla V100

May 8, 2022 by hgpu

Performance study on GPU offloading techniques using the Gauss matrix inverse algorithm

Yannik Könneker

View

Download (PDF)

Source codes

Tags: Computer science, CUBLAS, CUDA, Linear Algebra, nVidia, nVidia GeForce GTX 1080, OpenACC, OpenCL, Package, Performance, Tesla V100, Thesis

April 17, 2022 by hgpu

Optimizing Performance and Energy Efficiency in Massively Parallel Systems

Raúl Nozal González

View

Download (PDF)

Source codes

Tags: AMD Radeon RX 5700 XT, ATI, Computer science, Heterogeneous systems, HPC, nVidia, nVidia GeForce GTX 950, nVidia GeForce GTX Titan X, OpenCL, Package, Performance, SYCL, Tesla K20, Thesis

April 10, 2022 by hgpu

ALPINIST: An Annotation-Aware GPU Program Optimizer

Ömer Sakar, Mohsen Safari, Marieke Huisman, Anton Wijs

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, nVidia, OpenCL, Optimization, Package

April 10, 2022 by hgpu

IntelliKit: Agent-first tooling for AMD hardware

Kerncap: Automated Kernel Extraction and Isolation for AMD GPUs

DITRON: Distributed Compiler based on Triton for Parallel Systems

DITRON: Distributed Multi-level Tiling Compiler for Parallel Tensor Programs

CuTile Benchmark Suite: Performance and Productivity Tradeoffs for GPU Kernel Programming on Blackwell Architecture

Evaluating CUDA Tile for AI Workloads on Hopper and Blackwell GPUs

Agentic Code Optimization via Compiler-LLM Cooperation

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

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

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Programming

BenchPress: A Deep Active Benchmark Generator

Performance analysis of matrix-free conjugate gradient kernels using SYCL

CPU-GPU Layer-Switched Low Latency CNN Inference

FPGA Accelerators on Heterogeneous Systems: An Approach Using High Level Synthesis

Design and Implementation of CNN-FPGA accelerator based on Open Computing Language

On the Compilation Performance of Current SYCL Implementations

AnySeq/GPU: A Novel Approach for Faster Sequence Alignment on GPUs

Experience of Migrating a Parallel Graph Coloring Program from CUDA to SYCL

Analytical Performance Estimation during Code Generation on Modern GPUs

Performance study on GPU offloading techniques using the Gauss matrix inverse algorithm

Optimizing Performance and Energy Efficiency in Massively Parallel Systems

ALPINIST: An Annotation-Aware GPU Program Optimizer

Recent source codes

IntelliKit: Agent-first tooling for AMD hardware

DITRON: Distributed Compiler based on Triton for Parallel Systems

CuTile Benchmark Suite: Performance and Productivity Tradeoffs for GPU Kernel Programming on Blackwell Architecture

Agentic Code Optimization via Compiler-LLM Cooperation

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

Device Virtual Machine (DVM)

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

Most viewed papers (last 30 days)