Chevron Left
返回到 Fundamentals of Parallelism on Intel Architecture

學生對 英特尔 提供的 Fundamentals of Parallelism on Intel Architecture 的評價和反饋

594 個評分


This course will introduce you to the multiple forms of parallelism found in modern Intel architecture processors and teach you the programming frameworks for handling this parallelism in applications. You will get access to a cluster of modern manycore processors (Intel Xeon Phi architecture) for experiments with graded programming exercises. This course can apply to various HPC and datacenter workloads and framework including artificial intelligence (AI). You will learn how to handle data parallelism with vector instructions, task parallelism in shared memory with threads, parallelism in distributed memory with message passing, and memory architecture parallelism with optimized data containers. This knowledge will help you to accelerate computational applications by orders of magnitude, all the while keeping your code portable and future-proof. Prerequisite: programming in C/C++ or Fortran in the Linux environment and Linux shell proficiency (navigation, file copying, editing files in text-based editors, compilation)....




Given that Intel Phi is already End of Life, it would be great if the course is augmented with methods to also offload processing to GPU. A great course with a great instructor.



This coursework helped me to know the working of Intel architecture. How to optimize the code over the existing architecture with the help of vectorization and multithreading.


1 - Fundamentals of Parallelism on Intel Architecture 的 25 個評論(共 125 個)

創建者 Aswin V


Nice course, really enjoyed every challenge in the course. Well laid out goals for a Computer Science student.

創建者 Каморзин Б Б


This course was designed (among other) for people who do scientific computations, but hardly know anything for optimizing the code for efficient use of the hardware. And it so happened, that I am EXACTLY from that category of people.

That was an incredible experience, that, no joke, allowed me to speed up my application for electrostatics problem by at least two orders of magnitude, which is crucial as I deal with very high numbers of atoms.

The only thing that makes me sad is that in this course, the second one is advertised, called "Performance optimization", yet it is absent from Coursera. Of the continuation course(s) ever happens to arrive here, I will sign up for it immediately.


創建者 Sachin M


I think the course is to the point, simple and very informative. I never felt that I was doing an intermediate-level course. Thanks for giving access to the PBS cluster and XEON Phi processors. All your assignments really challenged the programmer inside me and loved them all. Recommended for everyone who wants to do parallel programming. I am eagerly waiting for more courses on these topics.

創建者 keerthi k


Best course to understand the basics of parallel programming , this course covers the areas where parallelism can be performed and the hands on exercises hones your skills of what you have learnt.

It is worth to pay for certification, because it gives you graded software tools to evaluate your performance on given tasks.

創建者 vineeth b


Good introduction to OpenMP and MPI. Assignments are not hard (should be able to solve with decent understanding of course material).

創建者 Rohan V


Please bring advance courses by Intel also such as FPGA based courses.

創建者 Siddhartha D


This course will definitely help one to get started with vectorization, parallel computing, OpenMP, and MPI. It helped me learn about Intel's Xeon Phi architecture and various compiler optimization techniques. The hands-on lab tutorials and assignments are really helpful in understanding the topics. The instructor did a good job in explaining the subject and the provided study guides are very helpful too. I hope more intermediate courses regarding parallelism are introduced on Coursera.

創建者 Shahid M


The course is quite rich in content; It is, however, specific to C language. Fortran users might find it hard to digest. Also, the content needs to be revisited several times. The reference book by Colfax is quite handy. And the exercises are definitely not easy to be solved. The fundamental disadvantage is that the disucssion group is almost dead. If you are interested in parallel programming then you must take it. It will enhance your interest and knowledge, for sure.

創建者 Germán M C


Very well explained, very simple, well structured and interesting examples. Although, more diversity of the examples would be interesting, for example, mathematical operations (as matrix-matrix multiplication), bioinformatics, financial, and so on. Also, would be great more exercises, labs and resources.

創建者 Samarth P N


Amazing course, I really loved it. This course provided me with a lot of knowledge about the subject Computer Architecture and Organisation. This course was really very interesting and I am really fortunate to study this course. Thank you Coursera!

創建者 Perry S


I really learned a lot and enjoyed this course. I am much better versed at factorization, openMP and MPI as a result. I had experience with GPU programming but the methods here are vital for high end CPUs

創建者 Pradeepa B K


Enjoyed learning basics of parallelism and different methods to improve the performance. Thanks to Andrey Vladimirov for the nice clear explanations on the topics!

創建者 Sadhana R


I liked this course,fundamentals of parallelism is explained very clearly. The assignments were really good.

創建者 Eduard D L G


Muy bueno, enseña maneras muy poderosas de hacer el software mas rápido.

創建者 Рамиль Б


Хороший преподаватель, материал излагается приятно и доступно. Однако курс довольно поверхностный и потребуются дополнительные источники информации для базового освоения OpenMP и MPI. Есть презентации, но конспект лекций отсутствует.

創建者 Francisco G R


I miss some mentor or instructor that provides some kind of support or reply to doubts in the forum. Seems that if we have a doubt, there is not any mentor that can help you. The level of the exercises doesn't correspond to the lessons.

So far, it is been not a pleasant experience.Sorry to say that I'm starting to wonder if it's worth the time spent in this course.

創建者 Dheeraja K


Very difficult for beginners in their preferred environment, they assume that you have ample amount of knowledge already.

創建者 omar f


1) No supervision from instructors.

2) Assignments are not very clear

3) Forums are dead

創建者 Pieter v W


Thank you to Intel, Coursera and Colfax for this course on Parallelism on Intel Architecture. Though only basics are covered, the course presents a tour through different levels of parallelism (vectorization, multi-threading and cluster-computing) as well as exploitation of high-bandwidth cache memory, for speeding up scientific computation. Each section has a hands on programming exercise that is executed and graded on an intel Xeon Phi processor. Would love a follow up course covering more advanced topics and GPU acceleration.

創建者 Arkadijs S


V​ery useful and interesting course. Lectures are well structured, awesome instructor. I​n addition, one can get access to powerful Intel Xeon Phi ​processors.

T​here are many sources that go directly to OpenMP/MPI parallelization, yet don't pay enough attention to vectorization. Fundamentals of Parallelism on Intel Architecture covers it detail, as well many other aspects of optimization/parallelism.

創建者 Ziyuan


Enthusiastic and articulate lecturer; logically well-organized courses; a dedicated lab for the assignments. If I have to say a con: Intel Architecture is not bound to Intel toolchain that requires royalty, so maybe it'd be better if the lecturer can mention some open equivalents (especially the switches) alongside the introduction to the Intel products.

創建者 Thomas Z


Course is nicely structured, starting from vectorization, to shared-memory (OpenMP), cache-levels and finally distributed memory (MPI). Most of this can also be done on local machine without having access to a cluster - at least for testing purposes. The instructor explains each concept very well and in an easy to understand way.

創建者 Nourdine O


the course was really great I learn many tricks and tips for code optimization and parallel programming in general and with the access provided by Colfax to their Xeon phi cluster, I was able to practice and experiment with my implementation and see the performance of the code.

many thanks to all people working on this course.

創建者 Maicon L M d S


É um excelente curso sobre Programação Paralela, pois te introduz aos principais conceitos desde o zero e te permite desenvolver um conhecimento sólido devido aos exercícios desafiadores. Tenho um nível intermediário em Inglês e fiz o curso perfeitamente sem nenhuma dificuldade em entender o instrutor!

創建者 Varzonova N


I really enjoyed this course. Workloads were interesting and I enjoyed solving problems with OpenMP and MPI as well as optimizing code performance. Good start for those who want to master parallel programming and understand performance optimization. Andrey is a great instructor, cudos to him.