intel webinars

Using Low-Precision Optimizations for High-Performance DL Inference Applications


Using Low-Precision Optimizations for High-Performance DL Inference Applications With advances in hardware acceleration and support for low precision, Deep Learning inference delivers higher throughput and lower latency. However, Data Scientists and AI developers often need to make a trade-off between accuracy and performance.


Visualize and Tune Heterogeneous Programs


Visualize and Tune Heterogeneous Programs Heterogeneous application development has introduced new challenges for experienced and novice developers alike. In particular, the need to understand how your programming language maps algorithms to each device.


Be a Cluster Champion! Tune Your Way to MPI Performance_


Be a Cluster Champion! Tune Your Way to MPI Performance. Message Passing Interface (MPI) is a powerful library standard that allows for the parallel execution of applications across multiple processors on a system while allowing users to run their applications across multiple nodes.


How Tangent Studios Creates Production-Quality Rendering


How Tangent Studios Creates Production-Quality Rendering When choosing the right rendering engine there is a lot to consider, including what type it is—3D, 2D, realtime, non-realtime, custom—and the technology, algorithms, and features it offers.


Efficient HPC Communications Profiling and Tuning MPI Applications


Efficient HPC Communications: Profiling and Tuning MPI Applications A cluster’s compute time is precious because its job queue is never ending. So when it’s your application’s turn on the cluster, you want to effectively use all of the compute resources while your applications runs.


Get Deep Learning Framework Performance on Intel® Architecture


Get Deep Learning Framework Performance on Intel® Architecture To build successful AI applications, developers must use highly optimized deep learning (DL) models—models that are developed and trained using DL frameworks such as TensorFlow* and MXNet*.


Industrial Cybersecurity Zero-Touch Provisioning


Industrial Cybersecurity: Zero-Touch Provisioning IoT Industrial Cloud systems are rapidly maturing as packaged systems that can sense, collect, analyze, and drive action on edge devices. However, the software-based device security and manual/proprietary provisioning methods delivered by platform providers are preventing deployments from scaling.


Optimize Your Apps for the Next Generation of Memory


Optimize Your Apps for the Next Generation of Memory Applications are increasingly being built with insatiable appetites for DRAM—which can be problematic if there’s limited availability of system memory (read: slow performance).


Tune Your Software for Cascade Lake


Tune Your Software for Cascade Lake With support for hybrid cloud infrastructures and your most demanding applications, the latest Intel® Xeon® Scalable Processors (formerly known as Cascade Lake) open new doors to industry-leading performance1.


Achieve Fast CPU Inference with New Optimization Features


Achieve Fast CPU Inference with New Optimization Features If you’re running deep learning inference on CPUs that support low-precision math, balancing model accuracy with energy-efficient performance is important for accelerating inference while reducing memory bandwidth and improving operations per cycle.