high performance computing on graphics processing units: hgpu.org

hgpu.org » nVidia

Themis: Fair and Efficient GPU Cluster Scheduling for Machine Learning Workloads

Kshiteej Mahajan, Arjun Singhvi, Arjun Balasubramanian, Varun Batra, Surya Teja Chavali, Shivaram Venkataraman, Aditya Akella, Amar Phanishayee, Shuchi Chawla

View

Download (PDF)

Tags: Computer science, GPU cluster, Machine learning, nVidia, Task scheduling, Tesla K80, Tesla M60

July 4, 2019 by hgpu

Automated Generation of OpenCL Programs Based on Algebra-Algorithmic Approach

Anatoliy Doroshenko, Oleksii Beketov, Mykola Bondarenko, Olena Yatsenko

View

Download (PDF)

Tags: Code generation, Computer science, CUDA, Heterogeneous systems, nVidia, nVidia GeForce GTX 840 M, OpenCL

June 30, 2019 by hgpu

Triton: An Intermediate Language and Compiler for Tiled Neural Network Computations

Philippe Tillet, H. T. Kung, David Cox

View

Download (PDF)

Source codes

Tags: Compilers, Computer science, CUDA, Deep learning, High-level Languages, LLVM, Matrix multiplication, Neural networks, nVidia, nVidia GeForce GTX 1070, Package

June 30, 2019 by hgpu

ReSYCLator: Transforming CUDA C++ source code into SYCL

Tobias Stauber, Peter Sommerlad

View

Download (PDF)

Tags: Code generation, Compilers, Computer science, CUDA, nVidia, OpenCL, SYCL

June 27, 2019 by hgpu

Mirovia: A Benchmarking Suite for Modern Heterogeneous Computing

Bodun Hu, Christopher J. Rossbach

View

Download (PDF)

Source codes

Tags: Benchmarking, Computer science, CUDA, Heterogeneous systems, Neural networks, nVidia, Package, Performance, Tesla P100

June 27, 2019 by hgpu

A Static Analysis-based Cross-Architecture Performance Prediction Using Machine Learning

Newsha Ardalani, Urmish Thakker, Aws Albarghouthi, Karu Sankaralingam

View

Download (PDF)

Tags: Computer science, Machine learning, nVidia, nVidia GeForce GTX 660 Ti, nVidia GeForce GTX 750, Performance

June 23, 2019 by hgpu

Data-Parallel Flattening by Expansion

Martin Elsman, Troels Henriksen, Niels Gustav Westphal Serup

View

Download (PDF)

Source codes

Tags: Code generation, Computer science, nVidia, nVidia GeForce RTX 2080 Ti, OpenCL, Package

June 23, 2019 by hgpu

GPU Volume Voxelization: Exploration of the performance characteristics of different GPU-based implementations

Grigory Glukhov, Aleksandra Soltan

View

Download (PDF)

Tags: 3D Graphics and Realism, AMD RX Vega 64, ATI, Neural networks, nVidia, nVidia GeForce GTX 1070, nVidia GeForce RTX 2070, Thesis, Voxelization, Vulkan

June 23, 2019 by hgpu

IA-SpGEMM: An Input-aware Auto-tuning Framework for Parallel Sparse Matrix-Matrix Multiplication

Zhen Xie, Guangming Tan, Weifeng Liu, Ninghui Sun

View

Download (PDF)

Source codes

Tags: Algorithms, Auto-Tuning, Computer science, CUDA, Deep learning, Matrix multiplication, nVidia, Sparse matrix, Tesla P100

June 23, 2019 by hgpu

TensorNetwork for Machine Learning

Stavros Efthymiou, Jack Hidary, Stefan Leichenauer

View

Download (PDF)

Source codes

Tags: Computer science, Deep learning, Machine learning, nVidia, Package, Tesla P100

June 20, 2019 by hgpu

Accelerating Concurrent Heap on GPUs

Yanhao Chen, Fei Hua, Chaozhang Huang, Jeremy Bierema, Chi Zhang, Eddy Z. Zhang

View

Download (PDF)

Tags: Algorithms, Computer science, nVidia, nVidia GeForce GTX Titan X

June 20, 2019 by hgpu

RTX Beyond Ray Tracing: Exploring the Use of Hardware Ray Tracing Cores for Tet-Mesh Point Location

Ingo Wald, Will Usher, Nate Morrical, Laura Lediaev, Valerio Pascucci

View

Download (PDF)

Tags: 3D Graphics and Realism, CUDA, nVidia, nVidia Titan RTX, Raytracing

June 16, 2019 by hgpu

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

Agentic Code Optimization via Compiler-LLM Cooperation

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

* * *

high performance computing on graphics processing units: hgpu.org

Themis: Fair and Efficient GPU Cluster Scheduling for Machine Learning Workloads

Automated Generation of OpenCL Programs Based on Algebra-Algorithmic Approach

Triton: An Intermediate Language and Compiler for Tiled Neural Network Computations

ReSYCLator: Transforming CUDA C++ source code into SYCL

Mirovia: A Benchmarking Suite for Modern Heterogeneous Computing

A Static Analysis-based Cross-Architecture Performance Prediction Using Machine Learning

Data-Parallel Flattening by Expansion

GPU Volume Voxelization: Exploration of the performance characteristics of different GPU-based implementations

IA-SpGEMM: An Input-aware Auto-tuning Framework for Parallel Sparse Matrix-Matrix Multiplication

TensorNetwork for Machine Learning

Accelerating Concurrent Heap on GPUs

RTX Beyond Ray Tracing: Exploring the Use of Hardware Ray Tracing Cores for Tet-Mesh Point Location

Recent source codes

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

Device Virtual Machine (DVM)

Agentic Code Optimization via Compiler-LLM Cooperation

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

True 4-Bit Quantized CNN Training on CPU

cuFuzz: A GPU-oriented coverage-guided fuzzer for userland CUDA application

KernelSkill: A Multi-Agent Framework for GPU Kernel Optimization

Most viewed papers (last 30 days)