high performance computing on graphics processing units: hgpu.org

hgpu.org » Thesis

Automatic Performance Optimisation of Parallel Programs for GPUs via Rewrite Rules

Toomas Remmelg

View

Tags: AMD Radeon R9 295X2, ARM, ATI, Computer science, nVidia, nVidia GeForce GTX Titan Black, OpenCL, Performance, performance portability, Thesis

December 29, 2019 by hgpu

Accelerating Molecular Docking by Parallelized Heterogeneous Computing – A Case Study of Performance, Quality of Results, and Energy-Efficiency using CPUs, GPUs, and FPGAs

Leonardo Solis Vasquez

View

Download (PDF)

Source codes

Tags: AMD Radeon RX Vega 56, ATI, Computer science, FPGA, Heterogeneous systems, Macromolecule, nVidia, OpenCL, Package, Physics, Tesla V100, Thesis

December 29, 2019 by hgpu

Scalable Applications on Heterogeneous System Architectures: A Systematic Performance Analysis Framework

Robert Dietrich

View

Download (PDF)

Tags: Computer science, CUDA, Data acquisition, Heterogeneous systems, MPI, nVidia, OpenACC, OpenCL, Tesla K80, Tesla V100, Thesis

December 1, 2019 by hgpu

Compiler-Driven Performance on Heterogeneous Computing Platforms

Artem Chikin

View

Download (PDF)

Tags: Compilers, Computer science, CUDA, Heterogeneous systems, Hybrid computing, nVidia, Performance, Tesla P100, Tesla V100, Thesis

November 17, 2019 by hgpu

Deep Learning Based FPGA-CPU Acceleration

R. Luis Jalabert

View

Download (PDF)

Source codes

Tags: Code generation, Computer science, Deep learning, FPGA, Machine learning, Neural networks, Package, Thesis

November 17, 2019 by hgpu

Framework for Parallel Kernels Auto-tuning

Filip Petrovič

View

Download (PDF)

Source codes

Tags: Auto-Tuning, Computer science, CUDA, nVidia, nVidia GeForce GTX 1070, nVidia GeForce GTX 750, nVidia GeForce GTX 970, OpenCL, Package, Performance, Thesis

November 10, 2019 by hgpu

Code Optimization on GPUs

Changwan Hong

View

Download (PDF)

Tags: Chemistry, Code generation, Computational chemistry, Computer science, CUDA, Intel Xeon Phi, Matrix multiplication, nVidia, Optimization, Sparse matrix, Tesla P100, Thesis

November 3, 2019 by hgpu

Performance Debugging Frameworks for FPGA High-Level Synthesis

Young-kyu Choi

View

Download (PDF)

Tags: Benchmarking, Computer science, Design space exploration, FPGA, HLS, Performance, Thesis

October 27, 2019 by hgpu

Performance Evaluation of Blocking and NonBlocking Concurrent Queues on GPUs

Hossein Pourmeidani

View

Download (PDF)

Tags: AMD Radeon R7, ATI, Benchmarking, Computer science, OpenCL, Performance, Thesis

October 13, 2019 by hgpu

Verification of GPU Program Optimizations in Lean

Björn Fischer

View

Download (PDF)

Source codes

Tags: Computer science, High-level Languages, Package, Thesis

October 6, 2019 by hgpu

Code optimization based on source to source transformations using profile guided metrics

Youenn Lebras

View

Download (PDF)

Tags: Code generation, Computer science, Performance, Thesis

September 15, 2019 by hgpu

Characterizing and Predicting Scientific Workloads for Heterogeneous Computing Systems

Beau Johnston

View

Download (PDF)

Source codes

Tags: Algorithms, AMD Radeon RX 480, ATI Radeon HD 7970, Benchmarking, Computer science, FPGA, Heterogeneous systems, Intel Xeon Phi, nVidia, nVidia GeForce GTX 1080, OpenCL, Package, Tesla K20, Tesla K40, Thesis

September 15, 2019 by hgpu

torchPDLP: Primal-Dual Linear Programming in PyTorch. In collaboration with AMD and IPAM

Accelerating a Linear Programming Algorithm on AMD GPUs

Benchmarks for Dissecting CPU-GPU Unified Physical Memory on AMD MI300A APUs

Dissecting CPU-GPU Unified Physical Memory on AMD MI300A APUs

kvcached: Elastic KV cache for dynamic GPU sharing and efficient multi-LLM inference

Towards Efficient and Practical GPU Multitasking in the Era of LLM

Bandicoot: C++ library for GPU accelerated linear algebra

Bandicoot: A Templated C++ Library for GPU Linear Algebra

Luthier: Bridging Auto-Tuning and Vendor Libraries for Efficient Deep Learning Inference

Fused Kernel Library (FKL)

The Fused Kernel Library: A C++ API to Develop Highly-Efficient GPU Libraries

GPUHammer: Rowhammer Attacks on GPU Memories are Practical

Block: Balance Loader of LLM Serving with Context, Knowledge and Predictive Scheduling

Block: Balancing Load in LLM Serving with Context, Knowledge and Predictive Scheduling

SIGMo: Scalable Isomorphism Graph Matching on GPUs

SIGMo: High-Throughput Batched Subgraph Isomorphism on GPUs for Molecular Matching

DGEMM without FP64 Arithmetic - using FP64 Emulation and FP8 Tensor Cores with Ozaki Scheme

DGEMM without FP64 Arithmetic – using FP64 Emulation and FP8 Tensor Cores with Ozaki Scheme

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Automatic Performance Optimisation of Parallel Programs for GPUs via Rewrite Rules

Accelerating Molecular Docking by Parallelized Heterogeneous Computing – A Case Study of Performance, Quality of Results, and Energy-Efficiency using CPUs, GPUs, and FPGAs

Scalable Applications on Heterogeneous System Architectures: A Systematic Performance Analysis Framework

Compiler-Driven Performance on Heterogeneous Computing Platforms

Deep Learning Based FPGA-CPU Acceleration

Framework for Parallel Kernels Auto-tuning

Code Optimization on GPUs

Performance Debugging Frameworks for FPGA High-Level Synthesis

Performance Evaluation of Blocking and NonBlocking Concurrent Queues on GPUs

Verification of GPU Program Optimizations in Lean

Code optimization based on source to source transformations using profile guided metrics

Characterizing and Predicting Scientific Workloads for Heterogeneous Computing Systems

Recent source codes

torchPDLP: Primal-Dual Linear Programming in PyTorch. In collaboration with AMD and IPAM

Benchmarks for Dissecting CPU-GPU Unified Physical Memory on AMD MI300A APUs

kvcached: Elastic KV cache for dynamic GPU sharing and efficient multi-LLM inference

Bandicoot: C++ library for GPU accelerated linear algebra

Luthier: Bridging Auto-Tuning and Vendor Libraries for Efficient Deep Learning Inference

Fused Kernel Library (FKL)

GPUHammer: Rowhammer Attacks on GPU Memories are Practical

Block: Balance Loader of LLM Serving with Context, Knowledge and Predictive Scheduling

SIGMo: Scalable Isomorphism Graph Matching on GPUs

DGEMM without FP64 Arithmetic - using FP64 Emulation and FP8 Tensor Cores with Ozaki Scheme

Most viewed papers (last 30 days)