high performance computing on graphics processing units: hgpu.org

Daniel Smilkov, Nikhil Thorat, Yannick Assogba, Ann Yuan, Nick Kreeger, Ping Yu, Kangyi Zhang, Shanqing Cai, Eric Nielsen, David Soergel, Stan Bileschi, Michael Terry, Charles Nicholson, Sandeep N. Gupta, Sarah Sirajuddin, D. Sculley, Rajat Monga, Greg Corrado, Fernanda B. Viegas, Martin Wattenberg

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Deep learning, Java, Machine learning, nVidia, nVidia GeForce GTX 1080, OpenGL, Package, TensorFlow, WebGL

February 17, 2019 by hgpu

Tutoring LLM into a Better CUDA Optimizer

Adaptivity in AdaptiveCpp: Optimizing Performance by Leveraging Runtime Information During JIT-Compilation

Kernel Library for LLM Serving

Compiler and Runtime Systems for Generative AI Models

Neptune: Advanced ML Operator Fusion for Locality and Parallelism on GPUs

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Programming

Improving GPU Performance through Instruction Redistribution and Diversification

On the Portability of GPU-Accelerated Applications via Automated Source-to-Source Translation

Energy Efficient Parallel K-Means Clustering for an Intel Hybrid Multi-Chip Package

Custom Code Generation for a Graph DSL

Cooperative CPU, GPU, and FPGA heterogeneous execution with EngineCL

Application level energy measurements and models for hybrid platform with accelerators

cuSten – CUDA Finite Difference and Stencil Library

Stateful Dataflow Multigraphs: A Data-Centric Model for High-Performance Parallel Programs

An Empirically Guided Optimization Framework for FPGA OpenCL

Optimizing Network Performance for Distributed DNN Training on GPU Clusters: ImageNet/AlexNet Training in 1.5 Minutes

Worst-Case Execution Time Guarantees for Runtime-Reconfigurable Architectures

TensorFlow.js: Machine Learning for the Web and Beyond

Recent source codes

OpScanner

Atlas CLI: Machine Learning (ML) Lifecycle & Transparency Manager

transformers_tvm: Implementation of Encoder Decoder transformer on TVM

INT v.s. FP: A framework to compare low-bit integer and float-point formats

AutoDock-GPU: AutoDock for GPUs and other accelerators

NCCLX: collective communication framework

Tutoring LLM into a Better CUDA Optimizer

Adaptivity in AdaptiveCpp: Optimizing Performance by Leveraging Runtime Information During JIT-Compilation

Kernel Library for LLM Serving

Neptune: Advanced ML Operator Fusion for Locality and Parallelism on GPUs

Most viewed papers (last 30 days)