INSTITUTO DE DEEP LEARNING DE NVIDIA

Te capacitamos para que resuelvas los problemas más desafiantes del mundo

El Instituto de Deep Learning de NVIDIA (DLI) ofrece capacitación práctica en inteligencia artificial, procesamiento acelerado y ciencia de datos acelerada. Los desarrolladores, científicos de datos, investigadores y estudiantes pueden obtener experiencia práctica con GPU en cloud y obtener un certificado de competencia para respaldar el crecimiento profesional. Comienza con DLI para acceder a capacitación online a tu propio ritmo para personas, workshops dirigidos por instructores para equipos y materiales de cursos descargables para educadores universitarios.

  • <span style=

    CURSOS
    ONLINE

  • <span style=

    WORKSHOPS A CARGO
    DE INSTRUCTORES

  • <span style=

    CAPACITACIÓN
    PARA UNIVERSIDADES

Para los estudiantes independientes y los equipos pequeños, recomendamos la capacitación online a tu propio ritmo a través de DLI y los cursos en línea a través de nuestros socios. Con DLI, tendrás acceso a un servidor acelerado por GPU totalmente configurado en el cloud, obtendrás habilidades prácticas para su trabajo y tendrás la oportunidad de obtener un certificado de competencia en la materia.

CAPACITACIÓN ONLINE CON DLI

Certificate Available

CURSOS DE DEEP LEARNING

ASPECTOS BÁSICOS DE DEEP LEARNING

  • Aspectos Básicos de Deep Learning para la Visión Artificial 

    Explore the fundamentals of deep learning by training neural networks and using results to improve performance and capabilities.

    Prerequisites: Familiarity with basic programming fundamentals such as functions and variables

    Technologies: Caffe, DIGITS

    Duration: 8 hours

    Price: $90 (excludes tax, if applicable)

  • Comenzar a Usar la IA en Jetson Nano

    Explore how to build a deep learning classification project with computer vision models using an NVIDIA® Jetson Nano Developer Kit.

    Prerequisites: Familiarity with Python (helpful, not required)

    Technologies: PyTorch, Jetson Nano

    Duration: 8 hours

    Price: Free

  • Optimización e Implementación de Modelos TensorFlow con TensorRT

    Learn how to optimize TensorFlow models to generate fast inference engines in the deployment stage.

    Prerequisites: Experience with TensorFlow and Python

    Technologies: TensorFlow, Python, NVIDIA TensorRT (TF-TRT)

    Duration: 2 hours

    Price: $30 (excludes tax, if applicable)

  • Deep learning a Escala con Horovod

    Learn how to scale deep learning training to multiple GPUs with Horovod, the open-source distributed training framework originally built by Uber and hosted by the LF AI Foundation.

    Prerequisites: Competency in Python and experience training deep learning models in Python

    Technologies: Horovod, TensorFlow, Keras, Python

    Duration: 2 hours

    Price: $30 (excludes tax, if applicable)

  • Comenzar a Usar la Segmentación de Imágenes

    Learn how to categorize segments of an image.

    Prerequisites: Basic experience training neural networks

    Technologies: TensorFlow

    Duration: 2 hours

    Price: $30 (excludes tax, if applicable)

  • Modelado de Datos de Series Temporales con Redes Neuronales Recurrentes en Keras

    Explore how to classify and forecast time-series data, such as modeling a patient's health over time, using recurrent neural networks (RNNs).

    Prerequisites: Basic experience with deep learning

    Technologies: Keras

    Duration: 2 hours

    Price: $30 (excludes tax, if applicable)

DEEP LEARNING PARA LA CREACIÓN DE CONTENIDO DIGITAL

  • Transferencia de Estilos de Imagen con Torch

    Learn how to transfer the look and feel of one image to another image by extracting distinct visual features using convolutional neural networks (CNNs).

    Prerequisites: Experience with CNNs

    Technologies: Torch, CNNs

    Duration: 2 hours

    Price: $30 (excludes tax, if applicable)

  • Superresolución de Imagen Usando Autocodificadores

    Leverage the power of a neural network with autoencoders to create high-quality images from low-quality source images.

    Prerequisites: Experience with CNNs

    Technologies: Keras, CNNs

    Duration: 2 hours

    Price: $30 (excludes tax, if applicable)

DEEP LEARNING PARA LA ATENCIÓN DE LA SALUD

  • Clasificación de Imágenes Médicas con el Conjunto de Datos MedNIST

    Explore an introduction to deep learning for radiology and medical imaging by applying CNNs to classify images in a medical imaging dataset.

    Prerequisites: Basic experience with Python

    Technologies: PyTorch, Python

    Duration: 2 hours

    Price: $30 (excludes tax, if applicable)

  • Clasificación de Imágenes con TensorFlow: Radiómica - Clasificación del Estado del Cromosoma 1p19q

    Learn how to apply deep learning techniques to detect the 1p19q co-deletion biomarker from MRI imaging.

    Prerequisites: Basic experience with CNNs and Python

    Technologies: TensorFlow, CNNs, Python

    Duration: 2 hours

    Price: $30 (excludes tax, if applicable)

  • Memoria Contextual Amplia a Detallada para Imágenes Médicas

    Learn how to use Coarse-to-Fine Context Memory (CFCM) to improve traditional architectures for medical image segmentation and classification tasks.

    Prerequisites: Experience with CNNs and long short term memory (LSTMs)

    Technologies: TensorFlow, CNNs, CFCM

    Duration: 2 hours

    Price: $30 (excludes tax, if applicable)

  • Aumento de Datos y Segmentación con Redes Generativas para Crear Imágenes Médicas

    Learn how to use generative adversarial networks (GANs) for medical imaging by applying them to the creation and segmentation of brain MRIs.

    Prerequisites: Experience with CNNs

    Technologies: TensorFlow, GANs, CNNs

    Duration: 2 hours

    Price: $30 (excludes tax, if applicable)

DEEP LEARNING PARA EL ANÁLISIS DE VIDEOS INTELIGENTE

  • Workflows de IA para el Análisis de Videos Inteligente con DeepStream

    Learn how to build hardware-accelerated applications for intelligent video analytics (IVA) with DeepStream and deploy them at scale to transform video streams into insights.

    Prerequisites: Experience with C++ and Gstreamer

    Technologies: DeepStream3, C++, Gstreamer

    Duration: 2 hours

    Price: $30 (excludes tax, if applicable)

  • Comenzar a Usar DeepStream para el Análisis de Videos en Jetson Nano

    Learn how to build DeepStream applications to annotate video streams using object detection and classification networks.

    Prerequisites: Basic familiarity with C

    Technologies: DeepStream, TensorRT, Jetson Nano

    Duration: 8 hours; Self-paced

    Price: Free

CURSOS DE PROCESAMIENTO ACELERADO

  • Aspectos Básicos del Procesamiento Acelerado con CUDA C/C++ 

    Learn how to accelerate and optimize existing C/C++ CPU-only applications to leverage the power of GPUs using the most essential CUDA techniques and the Nsight Systems profiler.

    Prerequisites: Basic C/C++ competency including familiarity with variable types, loops, conditional statements, functions, and array manipulations.

    Technologies: C/C++, CUDA

    Duration: 8 hours

    Price: $90 (excludes tax, if applicable)

  • Aspectos Básicos del Procesamiento Acelerado con CUDA Python

    Explore how to use Numba—the just-in-time, type-specializing Python function compiler—to create and launch CUDA kernels to accelerate Python programs on GPUs.

    Prerequisites: Basic Python competency including familiarity with variable types, loops, conditional statements, functions, and array manipulations. NumPy competency including the use of ndarrays and ufuncs.

    Technologies: CUDA, Python, Numba, NumPy

    Duration: 8 hours

    Price: $90 (excludes tax, if applicable)

  • Escalar Workloads en Varias GPU con CUDA C++

    Aprenda a crear aplicaciones CUDA C++ sólidas y eficientes que pueden aprovechar todas las GPU disponibles en un solo nodo.

    REQUISITOS PREVIOS: Competencia en redacción de aplicaciones en CUDA C / C ++.

    HERRAMIENTAS, BIBLIOTECAS, FRAMEWORKS: C, C++

    DURACION: 4 horas

    IDIOMA: Inglés

    PRECIO: $30 (no incluye impuestos, si corresponde)

  • Aceleración de Aplicaciones CUDA C++ con Flujos Concurrentes

    Aprenda a mejorar el rendimiento de sus aplicaciones CUDA C/C++ superponiendo transferencias de memoria desde y hacia la GPU con cálculos en la GPU.

    REQUISITOS PREVIOS: Competencia en redacción de aplicaciones en CUDA C/C++..

    HERRAMIENTAS, BIBLIOTECAS, FRAMEWORKS: C, C++

    DURACION: 4 horas

    IDIOMA: Inglés

    PRECIO: $30 (no incluye impuestos, si corresponde)

  • Aspectos Básicos del Procesamiento Acelerado con OpenACC

    Explore how to build and optimize accelerated heterogeneous applications on multiple GPU clusters using OpenACC, a high-level GPU programming language.

    Prerequisites: Basic experience with C/C++

    Technologies: OpenACC, C/C++

    Duration: 8 hours

    Languages: English

    Price: $90 (excludes tax, if applicable)

  • Procesamiento de alto rendimiento con contenedores

    Learn how to reduce complexity and improve portability and efficiency of your code by using a containerized environment for high-performance computing (HPC) application development.

    Prerequisites: Proficiency programming in C/C++ and professional experience working on HPC applications

    Technologies: Docker, Singularity, HPCCM, C/C++

    Duration: 2 hours

    Price: $30 (excludes tax, if applicable)

  • OpenACC: Duplicar el Rendimiento en 4 Pasos

    Learn how to accelerate C/C++ or Fortran applications using OpenACC to harness the power of GPUs.

    Prerequisites: Basic experience with C/C++

    Technologies: C/C++, OpenACC

    Duration: 2 hours

    Price: $30 (excludes tax, if applicable)

CURSOS DE LA CIENCIA DE DATOS ACELERADA

  • Aspectos Básicos de la Ciencia de Datos Acelerada con RAPIDS

    Learn how to perform multiple analysis tasks on large datasets using RAPIDS, a collection of data science libraries that allows end-to-end GPU acceleration for data science workflows.

    Prerequisites: Experience with Python, including pandas and NumPy

    Technologies: RAPIDS, NumPy, XGBoost, DBSCAN, K-Means, SSSP, Python

    Duration: 6 hours

    Price: $90 (excludes tax, if applicable)

  • Acelerar los Workflows de Ciencia de Datos con RAPIDS

    Learn to build a GPU-accelerated, end-to-end data science workflow using RAPIDS open-source libraries for massive performance gains.

    Prerequisites: Advanced competency in Pandas, NumPy, and scikit-learn

    Technologies: RAPIDS, cuDF, cuML, XGBoost

    Duration: 2 hours

    Price: $30 (excludes tax, if applicable)

CURSOS DE IA PARA TI

  • Introducción a la IA en el Data Center

    Explore an introduction to AI, GPU computing, NVIDIA AI software architecture, and how to implement and scale AI workloads in the data center. You'll understand how AI is transforming society and how to deploy GPU computing to the data center to facilitate this transformation.

    Prerequisites: Basic knowledge of enterprise networking, storage, and data center operations

    Technologies: Artificial intelligence, machine learning, deep learning, GPU hardware and software

    Duration: 4 hours

    Price: $30 (excludes tax, if applicable)

CAPACITACIÓN ONLINE CON SOCIOS

DLI colabora con organizaciones educativas líderes para expandir el alcance de la capacitación de deep learning a los desarrolladores de todo el mundo.

UPCOMING INSTRUCTOR-LED WORKSHOPS

DLI offers public instructor-led workshops around the world at conferences and universities. View the schedule below to find a workshop near you.

Para los equipos interesados en la capacitación, recomendamos workshops de día completo dirigidos por instructores certificados por DLI. Puede solicitar un workshop de día completo en el sitio o de forma remota para su equipo. Con DLI, tendrá acceso a un servidor en el cloud totalmente configurado y acelerado por GPU, obtendrá habilidades prácticas para su trabajo y tendrá la oportunidad de obtener un certificado de competencia en la materia.

Eche un vistazo a la experiencia DLI en este breve video.

Certificate Available

WORKSHOPS DE DEEP LEARNING

ASPECTOS BÁSICOS DE DEEP LEARNING

  • Fundamentos del deep learning (¡Nuevo!)

    Businesses worldwide are using artificial intelligence (AI) to solve their greatest challenges. Healthcare professionals use AI to enable more accurate, faster diagnoses in patients. Retail businesses use it to offer personalized customer shopping experiences. Automakers use AI to make personal vehicles, shared mobility, and delivery services safer and more efficient. Deep learning is a powerful approach to implementing AI that uses multi-layered artificial neural networks to deliver state-of-the-art accuracy in tasks such as object detection, speech recognition, and language translation. Using deep learning, computers are now able to learn and recognize patterns from data that are considered too complex or subtle for expert-written software.

    In this workshop, you’ll learn how deep learning works through hands-on exercises in computer vision and natural language processing. You will train deep learning models from scratch, learning tools and tricks to achieve highly accurate results. You’ll also learn to leverage freely available, state-of-the-art pre-trained models to save time and get your deep learning application up and running today.

    By participating in this is workshop you will:

    • Practice the fundamental techniques and tools required to train a deep learning model
    • Gain experience with common deep learning data types and model architectures
    • Enhance datasets through data augmentation to improve model accuracy
    • Leverage transfer learning between models to achieve efficient results with less data and computation
    • Build confidence to take on your own project with a modern, deep learning framework

    Prerequisites: Understanding of fundamental programming concepts in Python such as functions, loops,dictionaries, and arrays.

    Tools, libraries, and frameworks: Tensorflow, Keras, Pandas, Numpy

  • Creación de sistemas inteligentes de recomendación (¡Nuevo!)

    Deep learning-based recommender systems are the secret ingredient behind personalized online experiences and powerful decision support tools in retail, entertainment, healthcare, finance, and other industries. 

    Recommender systems work by understanding the preferences, previous decisions, and other characteristics of many people. For example, recommenders can help a streaming media service understand the types of movies an individual enjoys, which movies they’ve actually watched, and the languages they understand. Training a neural network to generalize this mountain of data and quickly provide specific recommendations for similar individuals or situations requires massive amounts of computation, which can be accelerated dramatically by GPUs. Organizations seeking to provide more delightful user experiences, deeper engagement with their customers, and better informed decisions can realize tremendous value by applying properly designed and trained recommender systems.

    This workshop covers the fundamental tools and techniques for building highly effective recommender systems, as well as how to deploy GPU-accelerated solutions for real-time recommendations. 

    By participating in this workshop, you’ll learn how to:

    • Build a content-based recommender system using the open-source cuDF library and Apache Arrow
    • Construct a collaborative filtering recommender system using alternating least squares (ALS) and CuPy
    • Design a wide and deep neural network using TensorFlow 2 to create a hybrid recommender system
    • Optimize performance for both training and inference using large, sparse datasets
    • Deploy a recommender model as a high-performance web service

    Prerequisites:

    • Intermediate knowledge of Python, including understanding of list comprehension.
    • Data science experience using Python.
    • Familiarity with NumPy and matrix mathematics.

    Tools, libraries, and frameworks: CuDF, CuPy, TensorFlow 2, and NVIDIA Triton™ Inference Server

  • Desarrollo del procesamiento del lenguaje natural basado en transformadores (¡Nuevo!)

    Applications for Natural Language Processing (NLP) have exploded in the past decade. With the proliferation of AI assistants, and organizations infusing their businesses with more interactive human/machine experiences, understanding how NLP techniques can be used to manipulate, analyze, and generate text-based data is essential. Modern techniques can be used to capture the nuance, context, and sophistication of language, just as humans do. And when designed correctly, developers can use these techniques to build powerful NLP applications that provide natural and seamless human-computer interactions within Chat Bots, AI Voice Agents, and many more.

    Deep learning models have gained widespread popularity for NLP because of their ability to accurately generalize over a range of contexts and languages. Transformer-based models, such as Bidirectional Encoder Representations from Transformers (BERT), have revolutionized progress in NLP by offering accuracy comparable to human baselines on benchmarks like SQuAD for question-answer, entity recognition, intent recognition, sentiment analysis, and more. NVIDIA provides software and hardware that helps you quickly build state-of-the-art NLP models. You can speed-up the training process up to 4.5x with mixed-precision, and easily scale performance to multi-GPU across multiple server nodes without compromising accuracy.

    In this workshop, you’ll learn how to use Transformer-based natural language processing models for text classification tasks, such as categorizing documents. You will also learn how to leverage Transformer-based models for named-entity recognition (NER) tasks and how to analyze various model features, constraints, and characteristics to determine which model is best suited for a particular use case based on metrics, domain specificity, and available resources.

    By participating in this workshop, you’ll be able to:

    • Understand how text embeddings have rapidly evolved in NLP tasks such as Word2Vec, recurrent neural network (RNN)-based embeddings, and Transformers
    • See how Transformer architecture features, especially self-attention, are used to create language models without RNNs
    • Use self-supervision to improve the Transformer architecture in BERT, Megatron, and other variants for superior NLP results
    • Leverage pre-trained, modern NLP models to solve multiple tasks such as text classification, NER, and question answering
    • Manage inference challenges and deploy refined models for live applications

    Prerequisites:

    • Experience with Python coding and use of library functions and parameters
    • Fundamental understanding of a deep learning framework such as TensorFlow, PyTorch, or Keras.
    • Basic understanding of neural networks.

    Herramientas, bibliotecas y frameworks: PyTorch, pandas, NVIDIA NeMo ™, Servidor de Inferencia NVIDIA Triton™ 

  • Fundamentals of Deep Learning for Multi-GPUs 

    Modern deep learning challenges leverage increasingly larger datasets and more complex models. As a result, significant computational power is required to train models effectively and efficiently.

    In this course, you will learn how to scale deep learning training to multiple GPUs. Using multiple GPUs for deep learning can significantly shorten the time required to train lots of data, making solving complex problems with deep learning feasible. This course will teach you how to use multiple GPUs to train neural networks. You'll learn:

    • Approaches to multi-GPU training
    • Algorithmic and engineering challenges to large-scale training
    • Key techniques used to overcome the challenges mentioned above

    Upon completion, you'll be able to effectively parallelize training of deep neural networks using Horovod.

    Prerequisites: Competency in the Python programming language and experience training deep learning models in Python

    Technologies: Python, Tensorflow

DEEP LEARNING POR INDUSTRIA

  • Deep Learning para Vehículos Autónomos: Perception

    Learn how to design, train, and deploy deep neural networks for autonomous vehicles using the NVIDIA DRIVE development platform.

    You'll learn how to:

    • Work with CUDA® code, memory management, and GPU acceleration on the NVIDIA DRIVE AGX System
    • Train a semantic segmentation neural network
    • Optimize, validate, and deploy a trained neural network using NVIDIA® TensorRT

    Upon completion, you'll be able to create and optimize perception components for autonomous vehicles using NVIDIA DRIVE.

    Prerequisites: Experience with CNNs and C++

    Technologies: TensorFlow, TensorRT, Python, CUDA C++, DIGITS

  • Deep Learning para Robótica

    AI is revolutionizing the acceleration and development of robotics across a broad range of industries. Explore how to create robotics solutions on a Jetson for embedded applications.

    You’ll learn how to:

    • Apply computer vision models to perform detection
    • Prune and optimize the model for embedded application
    • Train a robot to actuate the correct output based on the visual input

    Upon completion, you’ll know how to deploy high-performance deep learning applications for robotics.

    Prerequisites: Basic familiarity with deep neural networks, basic coding experience in Python or similar language

  • Aplicaciones de IA para la Detección de Anomalías

    The amount of information moving through our world’s telecommunications infrastructure makes it one of the most complex and dynamic systems that humanity has ever built. In this workshop, you’ll implement multiple AI-based solutions to solve an important telecommunications problem: identifying network intrusions.

    In this workshop, you’ll:

    • Implement three different anomaly detection techniques: accelerated XGBoost, deep learning-based autoencoders, and generative adversarial networks (GANs)
    • Build and compare supervised learning with unsupervised learning-based solutions
    • Discuss other use cases within your industry that could benefit from modern computing approaches

    Upon completion, you'll be able to detect anomalies within large datasets using supervised and unsupervised machine learning. 

    Prerequisites: Experience with CNNs and Python

    Technologies: RAPIDS, Keras, GANs, XGBoost

  • Aplicaciones de IA para el Mantenimiento Predictivo

    Learn how to identify anomalies and failures in time-series data, estimate the remaining useful life of the corresponding parts, and use this information to map anomalies to failure conditions. 

    You’ll learn how to:

    • Leverage predictive maintenance to manage failures and avoid costly unplanned downtimes 
    • Identify key challenges around identifying anomalies that can lead to costly breakdowns
    • Use time-series data to predict outcomes using machine learning classification models with XGBoost
    • Apply predictive maintenance procedures by using a long short-term memory ( LSTM)-based model to predict device failure 
    • Experiment with autoencoders to detect anomalies by using the time-series sequences from the previous steps

    Upon completion, you’ll understand how to use AI to predict the condition of equipment and estimate when maintenance should be performed.

    Prerequisites: Experience with Python and deep neural networks

    Technologies: TensorFlow, Keras

  • Deep Learning para la Inspección Industrial

    Explore cómo crear un modelo de deep learning para automatizar la verificación de condensadores en la placa de circuito impreso (PCB) de NVIDIA utilizando un conjunto de datos de producción real. Esto puede reducir el costo de verificación y aumentar el rendimiento de la producción en una variedad de casos de uso de fabricación. Aprenderá a:

    • Extraiga información significativa del conjunto de datos proporcionado utilizando Pandas DataFrame y la biblioteca NumPy
    • Aplicar el aprendizaje por transferencia a un modelo de clasificación de deep learning conocido como InceptionV3
    • Ajuste el modelo de deep learning y configure métricas de evaluación
    • Optimice el modelo entrenado de InceptionV3 en la GPU V100 con TensorRT 5
    • Experimente con la inferencia rápida de precisión media FP16 utilizando TensorCore de V100

    Al finalizar, podrá diseñar, entrenar, probar e implementar los componentes básicos de una tubería de inspección industrial acelerada por hardware.

    Requisitos previos : experiencia con Python y redes neuronales convolucionales (CNN)

    Tecnologías: TensorFlow, NVIDIA TensorRT™, Keras

  • Deep Learning para el Análisis de Videos Inteligente

    With the increase in traffic cameras, growing prospect of autonomous vehicles, and promising outlook of smart cities, there's a rise in demand for faster and more efficient object detection and tracking models. This involves identification, tracking, segmentation and prediction of different types of objects within video frames.

    In this workshop, you’ll learn how to:

    • Efficiently process and prepare video feeds using hardware accelerated decoding methods
    • Train and evaluate deep learning models and leverage ""transfer learning"" techniques to elevate efficiency and accuracy of these models and mitigate data sparsity issues
    • Explore the strategies and trade-offs involved in developing high-quality neural network models to track moving objects in large-scale video datasets
    • Optimize and deploy video analytics inference engines by acquiring the DeepStream SDK

    Upon completion, you'll be able to design, train, test and deploy building blocks of a hardware-accelerated traffic management system based on parking lot camera feeds.

    Prerequisites: Experience with deep networks (specifically variations of CNNs), intermediate-level experience with C++ and Python

    Technologies: deep learning, intelligent video analytics, deepstream 3.0, tensorflow, iva, fmv, opencv, accelerated video decoding/encoding, object detection and tracking, anomaly detection, deployment, optimization, data preparation

  • Deep Learning para el Análisis de Imágenes de Atención de la Salud

    This workshop explores how to apply convolutional neural networks (CNNs) to MRI scans to perform a variety of medical tasks and calculations. You’ll learn how to:

    • Perform image segmentation on MRI images to determine the location of the left ventricle
    • Calculate ejection fractions by measuring differences between diastole and systole using CNNs applied to MRI scans to detect heart disease
    • Apply CNNs to MRI scans of low-grade gliomas (LGGs) to determine 1p/19q chromosome co-deletion status

    Upon completion, you’ll be able to apply CNNs to MRI scans to conduct a variety of medical tasks.

    Prerequisites: Basic familiarity with deep neural networks; basic coding experience in Python or a similar language

    Technologies: R, MXNet, TensorFlow, Caffe, DIGITS

WORKSHOPS DE PROCESAMIENTO ACELERADO

  • Aspectos Básicos del Procesamiento Acelerado con CUDA C/C++ 

    The CUDA computing platform enables the acceleration of CPU-only applications to run on the world’s fastest massively parallel GPUs. Experience C/C++ application acceleration by:

    • Accelerating CPU-only applications to run their latent parallelism on GPUs
    • Utilizing essential CUDA memory management techniques to optimize accelerated applications
    • Exposing accelerated application potential for concurrency and exploiting it with CUDA streams
    • Leveraging Nsight Systems to guide and check your work

    Upon completion, you’ll be able to accelerate and optimize existing C/C++ CPU-only applications using the most essential CUDA techniques and Nsight Systems. You’ll understand an iterative style of CUDA development that will allow you to ship accelerated applications fast.

    Prerequisites: Basic C/C++ competency including familiarity with variable types, loops, conditional statements, functions, and array manipulations.

    Technologies: C/C++, CUDA

  • Aspectos Básicos del Procesamiento Acelerado con CUDA Python

    This workshop explores how to use Numba—the just-in-time, type-specializing Python function compiler—to accelerate Python programs to run on massively parallel NVIDIA GPUs. You’ll learn how to:

    • Use Numba to compile CUDA kernels from NumPy universal functions (ufuncs)
    • Use Numba to create and launch custom CUDA kernels
    • Apply key GPU memory management techniques
    • Upon completion, you’ll be able to use Numba to compile and launch CUDA kernels to accelerate your Python applications on NVIDIA GPUs.

    Prerequisites: Basic Python competency including familiarity with variable types, loops, conditional statements, functions, and array manipulations. NumPy competency including the use of ndarrays and ufuncs.

    Technologies: CUDA, Python, Numba, NumPy

  • Aceleración de aplicaciones CUDA C ++ con varias GPU (¡nuevo!)

    Este workshop cubre cómo escribir aplicaciones CUDA C ++ que utilizan de manera eficiente y correcta todas las GPU disponibles en un solo nodo, mejorando significativamente el rendimiento de sus aplicaciones y haciendo el uso más rentable de los sistemas con múltiples GPU.

    Al participar en este workshop, aprenderá a:

    • Utilizar los CUDA Streams concurrentes para superponer las transferencias de memoria con el cálculo de la GPU.
    • Utilizar todas las GPU disponibles en un solo nodo para escalar las cargas de trabajo en todas las GPU disponibles.
    • Combinar el uso de la superposición de copia / cálculo con varias GPU.
    • Confiar en el cronograma del Visual Profiler de los sistemas NVIDIA® Nsight™ para observar las oportunidades de mejora y el impacto de las técnicas cubiertas en el workshop.

    Prerrequisitos:

    • Experiencia profesional en la programación de aplicaciones CUDA C / C ++, incluido el uso del compilador nvcc, lanzamientos de kernel, bucles de cuadrícula, transferencias de memoria de host a dispositivo y de dispositivo a host, y manejo de errores CUDA
    • Familiaridad con la línea de comandos de Linux
    • Experiencia en el uso de Makefiles para compilar código C/C++

    Tecnologías: CUDA C++, nvcc, Sistemas Nsight

WORKSHOPS DE LA CIENCIA DE DATOS ACELERADA

  • Aspectos Básicos de la Ciencia de Datos Acelerada con RAPIDS

    RAPIDS is a collection of data science libraries that allows end-to-end GPU acceleration for data science workflows. In this training, you'll:

    • Use cuDF and Dask to ingest and manipulate massive datasets directly on the GPU
    • Apply a wide variety of GPU-accelerated machine learning algorithms, including XGBoost, cuGRAPH, and cuML, to perform data analysis at massive scale
    • Perform multiple analysis tasks on massive datasets in an effort to stave off a simulated epidemic outbreak affecting the UK

    Upon completion, you'll be able to load, manipulate, and analyze data orders of magnitude faster than before, enabling more iteration cycles and drastically improving productivity.

    Prerequisites: Experience with Python, ideally including pandas and NumPy

    Technologies: RAPIDS, NumPy, XGBoost, DBSCAN, K-Means, SSSP, Python