hgpu.org » EM and MM algorithms
Hua Zhou, Kenneth Lange, Marc A. Suchard
Tags: Block relaxation, CUBLAS, CUDA, EM and MM algorithms, Mathematics, Multidimensional scaling, Nonnegative matrix factorization, nVidia, nVidia GeForce GTX 280, PET scanning, Statistics
October 30, 2010 by hgpu
Recent source codes
* * *
Most viewed papers (last 30 days)
- Profiling Apple Silicon Performance for ML Training
- Dissecting the NVIDIA Hopper Architecture through Microbenchmarking and Multiple Level Analysis
- Column-Oriented Datalog on the GPU
- GSParLib: A multi-level programming interface unifying OpenCL and CUDA for expressing stream and data parallelism
- Boosting Performance of Iterative Applications on GPUs: Kernel Batching with CUDA Graphs
- Compiler Support for Speculation in Decoupled Access/Execute Architectures
- Exploring data flow design and vectorization with oneAPI for streaming applications on CPU+GPU
- A User's Guide to KSig: GPU-Accelerated Computation of the Signature Kernel
- Demystifying Cost-Efficiency in LLM Serving over Heterogeneous GPUs
- Towards autonomous resource management: Deep learning prediction of CPU-GPU load balancing
* * *