Unlock Composable Parallelism in Python | Intel Software

Channel:
United States Intel Software
Subscribers:
257,000
Published on ● Video Link: https://www.youtube.com/watch?v=HuA6Zah752Y


Duration: 3:27
1,718 views
25

Get high performance Python at your fingertips with the free Intel® Distribution for Python, and access easy and safe composable parallelism and efficient thread scheduling with new Python modules. As the number of cores in central processing units continues to grow, numeric libraries such as NumPy, SciPy, Dask, and Numba continue to exploit multi-threading to provide higher throughput for their customers. When these libraries are used in a single Python application, unorchestrated use of threads can lead to a significant overhead resulting in inefficient use of the cores present in the system.

In this video, Anton will address limitations of existing approaches, and introduce new method to compose parallelism that supports both multi-threading and multi-processing types of parallelism in Python.

SciPy 2017 talk: http://bit.ly/2v5xa9j

Composability benchmarks: http://bit.ly/2v5dt1x

Original TBB Blogpost - Unleash the Parallel Performance of Python* Programs: http://intel.ly/2uv7xgP

TBB’s Github: http://intel.ly/2v5DePl

SMP’s Github: http://bit.ly/2v5IfqW

Intel® Distribution for Python: http://intel.ly/2rWmGrH

Intel® Distribution for Python* Forum: http://intel.ly/2rVFUOk

Intel® Math Kernel Library Forum: http://intel.ly/2rWllRN

SUBSCRIBE NOW: http://bit.ly/2iZTCsz

About Intel Software:
The Intel® Developer Zone encourages and supports software developers that are developing applications for Intel hardware and software products. The Intel Software YouTube channel is a place to learn tips and tricks, get the latest news, watch product demos from both Intel, and our many partners across multiple fields. You'll find videos covering the topics listed below, and to learn more you can follow the links provided!

Connect with Intel Software:
Visit INTEL SOFTWARE WEBSITE: https://software.intel.com/en-us
Like INTEL SOFTWARE on FACEBOOK: http://bit.ly/2z8MPFF
Follow INTEL SOFTWARE on TWITTER: http://bit.ly/2zahGSn

INTEL SOFTWARE GITHUB: http://bit.ly/2zaih6z
INTEL DEVELOPER ZONE LINKEDIN: http://bit.ly/2z979qs
INTEL DEVELOPER ZONE INSTAGRAM: http://bit.ly/2z9Xsby
INTEL GAME DEV TWITCH: http://bit.ly/2BkNshu

Unlock Composable Parallelism in Python | Intel Software
https://www.youtube.com/intelsoftware

#IntelSoftware



Other Videos By Intel Software


2017-08-31Intel® ISA-L Erasure Coding | Intel Software
2017-08-31Intel® ISA-L Erasure Coding Sample Application Overview | Intel Software
2017-08-30How Developers Can Benefit from the DPDK Packet Framework | Intel Software
2017-08-30Deep Dive Into the Architecture of a Pipeline Stage | Intel Software
2017-08-03August 2017 | AI News | Intel Software
2017-08-01August 2017 | Intel® Developer Zone Update | Intel Software
2017-07-28Intel® Clear Containers: How We Made Them Smaller and Faster Part 1 | Intel Software
2017-07-28Intel® Clear Containers: How We Made Them Smaller and Faster Part 2 | Intel Software
2017-07-28Intel® Clear Containers Overview | Intel Software
2017-07-19How Intel® Core™ i7 CPUs Make VR Games More Immersive | Intel Software
2017-07-17Unlock Composable Parallelism in Python | Intel Software
2017-07-13Intro to the NVM Libraries: Persistent Memory Programming Series | Intel Software
2017-07-13A C++ Example: Persistent Memory Programming Series | Intel Software
2017-07-13Thinking Transactionally: Persistent Memory Programming Series | Intel Software
2017-07-13The NVM Programming Model: Persistent Memory Programming Series | Intel Software
2017-07-13What is Persistent Memory: Persistent Memory Programming Series | Intel Software
2017-07-06July 2017 | AI News | Intel Software
2017-07-04July 2017 | Intel® Developer Zone Update | Intel Software
2017-06-29Build Open vSwitch with DPDK and Prepare to Launch Open vSwitch | Intel Software
2017-06-29Launch Open vSwitch with DPDK and Configure the Ports and Flows | Intel Software
2017-06-29Build and Launch Docker* Containers with DPDK Support | Intel Software


Tags:
Intel Python
Intel Developer Zone
umath functions
Developer TOols
Transcendental functions
Intel Software
Code Modernization
Python performance
machine learning
vectorization
pyDAAL
modern code training
Intel MKL
Modern Code
IDZ
FFT
HPC
trained
Fast Fourier Transforms
Intel optimized Python
NumPy memory
threading
AVX2
AVX512
Python
Math Kernel Library
Arithmetic functions
Intel Distribution for Python