Performance | Page 56

hgpu.org » Performance

LDetector: A Low Overhead Race Detector For GPU Programs

Pengcheng Li, Chen Ding, Xiaoyu Hu, Tolga Soyata

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, Performance, Tesla K20

February 16, 2014 by hgpu

Accelerator Aware MPI Micro-benchmarking using CUDA, OpenACC and OpenCL

Sadaf Alam, Ugo Varetto

View

Download (PDF)

Tags: Benchmarking, Computer science, CUDA, Intel Xeon Phi, MPI, nVidia, OpenACC, OpenCL, Performance, Tesla K20, Tesla M2090

February 15, 2014 by hgpu

Multi-Kepler GPU vs. Multi-Intel MIC for spin systems simulations

M. Bernaschi, M. Bisson, F. Salvadore

View

Download (PDF)

Source codes

Tags: Benchmarking, Computer science, CUDA, Intel Xeon Phi, nVidia, Package, Performance, Physics, Spin Systems, Tesla K20

February 14, 2014 by hgpu

Multi-tier Dynamic Vectorization for Translating GPU Optimizations into CPU Performance

Hee-Seok Kim, Izzat El Hajj, John A. Stratton, Wen-Mei W. Hwu

View

Download (PDF)

Tags: AMD, Computer science, nVidia, OpenCL, Performance

February 12, 2014 by hgpu

Exploring Multiple Levels of Performance Modeling for Heterogeneous Systems

Vivek K. Pallipuram

View

Download (PDF)

Tags: Computer science, CUDA, GPU cluster, Heterogeneous systems, nVidia, Performance, Tesla K20, Tesla M2075, Thesis

February 11, 2014 by hgpu

Benchmarking the Intel Xeon Phi Coprocessor

F. Masci

View

Download (PDF)

Tags: Benchmarking, Computer science, Intel Xeon Phi, Performance

February 11, 2014 by hgpu

Accurate Cross-Architecture Performance Modeling for Sparse Matrix-Vector Multiplication (SpMV) on GPUs

Ping Guo, Liqiang Wang

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, nVidia GeForce GTX 295, Performance, Sparse matrix, Tesla C2050, Tesla K20, Tesla M2090

February 11, 2014 by hgpu

A Scalable Multi-Path Microarchitecture for Efficient GPU Control Flow

Ahmed ElTantawy, Jessica Wenjie Ma, Mike O'Connor, Tor M. Aamodt

View

Download (PDF)

Tags: Computer science, Hardware Architecture, Performance

February 9, 2014 by hgpu

Strategies for Maximizing Utilization in multi-CPU & multi-GPU Heterogeneous Architectures

Angeles Navarro, Antonio Vilches, Francisco Corbera, Rafael Asenjo

View

Download (PDF)

Tags: Algorithms, Computer science, CUDA, Heterogeneous systems, nVidia, Performance, Tesla S2050

February 4, 2014 by hgpu

Comparing the Performance of Different x86 SIMD Instruction Sets for a Medical Imaging Application on Modern Multi- and Manycore Chips

Johannes Hofmann, Jan Treibig, Georg Hager, Gerhard Wellein

View

Download (PDF)

Tags: Algorithms, Computed tomography, Computer science, CT, CUDA, Image reconstruction, Intel Xeon Phi, Medicine, nVidia, nVidia GeForce GTX 680, Performance

January 30, 2014 by hgpu

Autotuning Programs with Algorithmic Choice

Jason Ansel

View

Download (PDF)

Source codes

Tags: Algorithms, ATI, ATI Radeon HD 6630 M, Computer science, nVidia, OpenCL, Package, Performance, Tesla C2070, Thesis

January 28, 2014 by hgpu

Improvement of the fused CUDA kernels performance prediction

Peter Novak

View

Download (PDF)

Tags: Computer science, CUDA, nVidia, nVidia GeForce GTX 580, Performance, Thesis

January 25, 2014 by hgpu

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

MSCCL++: Rethinking GPU Communication Abstractions for Cutting-edge AI Applications

Benchmark compute shader of Unity against InteropUnityCUDA

InteropUnityCUDA: A Tool for Interoperability Between Unity and CUDA

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

* * *

high performance computing on graphics processing units: hgpu.org

LDetector: A Low Overhead Race Detector For GPU Programs

Accelerator Aware MPI Micro-benchmarking using CUDA, OpenACC and OpenCL

Multi-Kepler GPU vs. Multi-Intel MIC for spin systems simulations

Multi-tier Dynamic Vectorization for Translating GPU Optimizations into CPU Performance

Exploring Multiple Levels of Performance Modeling for Heterogeneous Systems

Benchmarking the Intel Xeon Phi Coprocessor

Accurate Cross-Architecture Performance Modeling for Sparse Matrix-Vector Multiplication (SpMV) on GPUs

A Scalable Multi-Path Microarchitecture for Efficient GPU Control Flow

Strategies for Maximizing Utilization in multi-CPU & multi-GPU Heterogeneous Architectures

Comparing the Performance of Different x86 SIMD Instruction Sets for a Medical Imaging Application on Modern Multi- and Manycore Chips

Autotuning Programs with Algorithmic Choice

Improvement of the fused CUDA kernels performance prediction

Recent source codes

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

Shamrock: Multi-GPU hydrodynamics for astrophysics

LLMPerf: GPU Performance Modeling meets Large Language Models

Most viewed papers (last 30 days)