|
HU Credits:
3
Degree/Cycle:
1st degree (Bachelor)
Responsible Department:
Applied Physics
Semester:
1st Semester
Teaching Languages:
Hebrew
Campus:
E. Safra
Course/Module Coordinator:
Prof. Freddy Gabbay
Coordinator Office Hours:
Wednesday 11:00-12:00
Teaching Staff:
Prof. Freddy Gabbay,
Mr. Nadav Am-Shalom
Course/Module description:
As part of the course, we will learn about advanced computer architectures emphasizing system point of view, and system performance. The course continues the computer architecture course and expands the knowledge learned about advanced microprocessor architectures focusung on parallel processors such as super-scalar, VLIW and out-of-order processors using speculative execution. In addition, the course deals extensively with multi-core and multi-threaded parallel computer architectures which include graphic processors (GPUs). The second part of the course delves into domain specific accelerator architectures in the field of AI and generative AI.
Course/Module aims:
The course will provide students with architectural knowledge and the ability to deeply understand and analyze the performance of advanced computer architectures. The course forms a basis for students who intend to continue research in the field or for those who intend to specialize in this field in the industry.
Learning outcomes - On successful completion of this module, students should be able to:
The students will acquire an understanding and system analysis capabilities of advanced computing systems that include parallel processors, speculative execution and out-of-order processors, multi-core processors, multithreaded architectures, GPUs, DRAM memories, architectures of AI and Generative AI accelerators.
Attendance requirements(%):
0
Teaching arrangement and method of instruction:
Lecture and class exercise
Course/Module Content:
Introduction and Technology trends
Speculative execution based on branch prediction
Super scalar and VLIW processors microarchitecture, out-of order execution, dataflow graph and instruction-level parallelism
DRAM memory architecture
Multi-Core vs. Multi-Threading, Heterogeneous computing (Multi-Amdahl)
General Purpose GPU
ML introduction
ML hardware dataflows
ML training
Transformers and Generative AI
Summary
Required Reading:
none
Additional Reading Material:
D.A. Patterson, J.L. Hennessy, "Computer Organization & Design, The Hardware - Software Interface", Morgan Kaufman Pub. 5th ed., 2013.
John Paul Shen and Mikko H. Lipasti, “Modern Processor Design: Fundamentals of Superscalar Processors”
David B. Kirk, Wen-mei W. Hwu, “Programming Massively Parallel Processors”, 2nd edition, ISBN: 978-0-12-415992-1.
John Hennessy and David Patterson, “Computer Architecture – a Quantitative Approach”
Michael Dubois, Nurali Annavaram, Per Stenstrom, “Parallel Computer Organization and Design”
Vivienne Sze, Yu-Hsin Chen, Tien-Ju Yang, Joel S. Emer, “Efficient processing of deep neural networks”
Grading Scheme :
Written Exam % 85
Submission assignments during the semester: Exercises / Essays / Audits / Reports / Forum / Simulation / others 15 %
Additional information:
|
