Sanjiban Sengupta

OPTIMIZED C++ INFERENCE IN SOFIE FOR QUANTIZED MACHINE LEARNING MODELS

S. Lee, Sanjiban Sengupta, Lorenzo Moneta

Machine learning inference increasingly bounds what the LHC experiments can compute per event. Quantization is the most direct lever for it, and quantized models are the one place where bit-level reproducibility is attainable. Physics deployment adds two requirements that commodity stacks do …

us, ch (code pays fourni par la source)

OPTIMIZED C++ INFERENCE IN SOFIE FOR QUANTIZED MACHINE LEARNING MODELS

S. Lee, Sanjiban Sengupta, Lorenzo Moneta

Machine learning inference increasingly bounds what the LHC experiments can compute per event. Quantization is the most direct lever for it, and quantized models are the one place where bit-level reproducibility is attainable. Physics deployment adds two requirements that commodity stacks do …

us, ch (code pays fourni par la source)

Green BOA: Determining the environmental break-even point for ML-based data compression

C. Doglioni, Thomas Elliott, Akshat Gupta, Hanzila Hussain et autres

We summarise the outcome of two summer internship projects based at the University of Manchester, focused on the break-even point in terms of environmental sustainability for ML-based data compression algorithms. Using the example of a ML-based lossless compression algorithm, we compare estimates …

Benchmark Studies of Machine Learning Inference using SOFIE

Lorenzo Moneta, Sanjiban Sengupta, Ioanna-Maria Panagou, Neel Shah et autres

SOFIE is a fast Machine Learning inference engine developed at CERN, capable of translating trained deep learning models—provided in ONNX, Keras, or PyTorch formats—into C++ code for efficient inference. The generated code has minimal dependencies, making it easily integrable into the data …

Benchmark Studies of Machine Learning Inference using SOFIE

L. Moneta, Sanjiban Sengupta, Ioanna-Maria Panagou, Neel Shah et autres

SOFIE is a fast Machine Learning inference engine developed at CERN, capable of translating trained deep learning models—provided in ONNX, Keras, or PyTorch formats—into C++ code for efficient inference. The generated code has minimal dependencies, making it easily integrable into the data …

ch, gb, gr, de (code pays fourni par la source)

Accelerating Machine Learning Inference on GPUs with SYCL

Ioanna-Maria Panagou, Nikolaos Bellas, L. Moneta, Sanjiban Sengupta

Recently, machine learning has established itself as a valuable tool for researchers to analyze their data and draw conclusions in various scientific fields, such as High Energy Physics (HEP). Commonly used machine learning libraries, such as Keras and PyTorch, might provide functionality …

gr, ch (code pays fourni par la source)

C++ Code Generation for Fast Inference of Deep Learning Models in ROOT/TMVA

S. An, L. Moneta, Sanjiban Sengupta, Ahmat Hamdan et autres

Abstract We report the latest development in ROOT/TMVA, a new tool that takes trained ONNX deep learning models and emits C++ code that can be easily included and invoked for fast inference of the model, with minimal dependency. An introduction to SOFIE …

ch, us, in, Cameroun, it (code pays fourni par la source)

Assessing Mid-pleistocene to Holocene Sea-Ice Extent and Carbonate Compensation Depth Fluctuations in the Japan Sea: A Multiproxy Approach

Manisha Das, Nishant Vats, Raj K. Singh, S. Sova Barik et autres

in (code pays fourni par la source)