Università degli Studi di Siena Department of Information Engineering and Mathematics (DIISM) Course of High-Performance Computer Architecture 2023-2024

Latest News (home)   Registration   Lessons (restricted access)   Errata slides   Tools for lab   Syllabus   Office Hours   previus exams   Projects   Group registration (restricted access)   Exam Rules   Feedback   RELATED LINKS   BEST PROJECTS bgcolor="#FFFFFF" width="840" height="3900" border="0" cellpadding="0" cellspacing="0" valign="top" align="left">  FIRST PART SLIDES (THEORY) IN A SINGLE FILE  SECOND PART SLIDES (THEORY) IN A SINGLE FILE  THIRD PART SLIDES (THEORY) IN A SINGLE FILE  BIBLIOGRAPHY OF THE COURSE IN A SINGLE FILE COURSE SCHEDULE (TENTATIVE): THE FOLLOWING DATES ARE INDICATIVE AND RELATED TO THE HYPOTHETIC REGULAR PROGRESS OF THE LESSONS. NOTE (THIS HAS BEEN ASKED TO ME ...) THE NUMBERING OF LESSON REFERS ONLY TO THE TOPIC, IT DOES NOT IMPLY BY ANY MEANS THAT THE LESSONS WILL BE GIVEN IN A CERTAIN ORDER. NOTE: the actual schedule will be updated weekly. BIBLIOGRAPHIC REFERENCES: M. Dubois, M. Annavaram, P. Stenstrom, "Parallel Computer Organization and Design", Cambridge University Press, 2012, ISBN: 978-0-521-88675-8  LESSON #01 of 02-Oct-2023 (14:30-16:00) Introduction, Evaluating Computers, Pipelining (PART A) PRESENTATION/SLIDES/VIDEO: c224lez01-intro_pipe.pdf BIBLIOGRAPHIC REFERENCES: Dubois: Chap. 1,3.3 (Hennessy-Patterson-4: 2.1,2.2) (Hennessy-Patterson-5: 3.1,3.2)  04-Oct-2023: No Lesson NO LESSON (Welcome Day)  LESSON #01 of 06-Oct-2023 (08:30-10:00) Introduction, Evaluating Computers, Pipelining (PART B) PRESENTATION/SLIDES/VIDEO: c224lez01-intro_pipe.pdf BIBLIOGRAPHIC REFERENCES: Dubois: Chap. 1,3.3 (Hennessy-Patterson-4: 2.1,2.2) (Hennessy-Patterson-5: 3.1,3.2)  LESSON #02 of 06-Oct-2023 (12:00-12:45) Dynamic Instruction Scheduling PRESENTATION/SLIDES/VIDEO: c224lez02-dynamic_instruction_scheduling.pdf BIBLIOGRAPHIC REFERENCES: Dubois: Chap. 3.4,3.4.1 (Hennessy-Patterson-4 - 2.4,2.5) (Hennessy-Patterson-5 - 3.4,3.5) An Efficient Algorithm for Exploiting Multiple Arithmetic Units tomasulo.c  PRACTICING/LAB #01 of 06-Oct-2023 (12:45-13:30) Dynamic Scheduling exercize. PRESENTATION/SLIDES/VIDEO: c224es01-tomasulo.pdf RESOURCES: Exercize #1 of the exam of 23-06-2005. Empty working sheet (for the above exercize)  LESSON #03 of 09-Oct-2023 (14:30-16:00) Branch Prediction: speculation of branch condition and branch target, BPRED, BTB. Predictor types, Bimodal, BHSR, BHT, PHT, 2-level adaptive. Other predictors (gshare, gselect). PRESENTATION/SLIDES/VIDEO: c224lez03-branch_prediction.pdf BIBLIOGRAPHIC REFERENCES: Dubois - 3.3.4,3.4.3 (Hennessy-Patterson-4 - 2.3) (Hennessy-Patterson-5 - 3.3) Optional reading: [Yeh, Patt - 1992] Optional reading: [Nair - 1995] Optional reading: [Young - 1995] Optional reading: [McFarling - 1993]  PRACTICING/LAB #90 of 11-Oct-2023 (08:30-10:00) Introduction to Linux (PART A) PRESENTATION/SLIDES/VIDEO: c224es90-linux_intro.pdf RESOURCES: A Linux Command Reference  PRACTICING/LAB #90 of 11-Oct-2023 (10:15-11:45) Introduction to Linux (PART B) PRESENTATION/SLIDES/VIDEO: c224es90-linux_intro.pdf RESOURCES: A Linux Command Reference  LESSON #05 of 16-Oct-2023 (14:30-15:15) Introduction to Superscalar Processors: general scheme and Renaming. PRESENTATION/SLIDES/VIDEO: c224lez05-superscalar1.pdf BIBLIOGRAPHIC REFERENCES: Dubois 3.3.3,3.4.6 (Hennessy-Patterson-4 - 2.6-2.9) (Hennessy-Patterson-5 - 3.6-3.10)  LESSON #06 of 16-Oct-2023 (15:15-16:00) Superscalar execution example: Re-Order Buffer and Instruction Window. Case studies: MIPS, Alpha, AMD, Intel, ARM. PRESENTATION/SLIDES/VIDEO: c224lez06-superscalar2.pdf BIBLIOGRAPHIC REFERENCES: Dubois 3.4.4,3.4.5,3.4.7,3.4.8,3.4.9 detailed output of the example analyzed during the lesson.  LESSON #08 of 18-Oct-2023 (08:30-10:00) Software methods to extract Instruction Level Parallelsim. Animated slide for the software pipelining example. PRESENTATION/SLIDES/VIDEO: c224lez08-software_ilp.pdf BIBLIOGRAPHIC REFERENCES: Dubois 3.3.5,3.5,3.5.1-5 (Hennessy-Patterson-4 2.7-2.8)  PRACTICING/LAB #03 of 18-Oct-2023 (10:15-11:45) Exercizes on VLIW processors. PRESENTATION/SLIDES/VIDEO: IN PREPARATION RESOURCES: Exercize #1 of the exam of the 23-06-2005. Exercize #1 of the exam of the 07-07-2009. Exercize #2 of the exam of the 07-07-2009. Exercize #1 of the exam of the 30-06-2008.  PRACTICING/LAB #04 of 23-Oct-2023 (14:30-16:00) Various excersizes. PRESENTATION/SLIDES/VIDEO: IN PREPARATION RESOURCES: Exercize #1 of the exam of the 20-01-2010. Exercize #1 of the exam of the 04-02-2013.  PRACTICING/LAB #05 of 25-Oct-2023 (08:30-10:00) Various excersizes. PRESENTATION/SLIDES/VIDEO: IN PREPARATION RESOURCES: Exercize #1 of the exam of the 05-07-2006. Exercize #1 of the exam of the 07-11-2014.  PRACTICING/LAB #02 of 25-Oct-2023 (10:15-11:00) Using the Superscalar simulator FREESS PRESENTATION/SLIDES/VIDEO: c224es02-freess.pdf RESOURCES: Educational Simulator FreeSs Exercize #1 of the exam of the 31-10-2018.  PRACTICING/LAB #06 of 25-Oct-2023 (11:00-11:45) Various excersizes. PRESENTATION/SLIDES/VIDEO: IN PREPARATION RESOURCES: Exercize #1 of the exam of the 31-10-2017. Exercize #1 of the exam of the 30-10-2019.  30-Oct-2023 - MIDTERM TEST (13:45-14:30)  30-Oct-2023 - MIDTERM TEST (14:30-16:00)  01-Nov-2023: No Lesson Tutti i Santi  LESSON #11 of 06-Nov-2023 (14:30-15:15) Introduction to multiprocessor systems, Flynn's taxonomy, UMA, NUMA, COMA systems, programming models PRESENTATION/SLIDES/VIDEO: c224lez11-multiprocessor_introduction.pdf BIBLIOGRAPHIC REFERENCES: Dubois 5.1,5.4 (see also Culler-Singh, Cap.1)  LESSON #12 of 06-Nov-2023 (15:15-16:00) Coherence Protocols: Write Update, Write Invalidate, Hybrid. Snoopy based protocols: the MESI and DRAGON protocols (PART A) PRESENTATION/SLIDES/VIDEO: c224lez12-multiprocessor_coherency.pdf BIBLIOGRAPHIC REFERENCES: Dubois 5.4,5.5,7.3 (see also Culler-Singh, Cap.5)  LESSON #12 of 08-Nov-2023 (08:30-10:00) Coherence Protocols: Write Update, Write Invalidate, Hybrid. Snoopy based protocols: the MESI and DRAGON protocols (PART B) PRESENTATION/SLIDES/VIDEO: c224lez12-multiprocessor_coherency.pdf BIBLIOGRAPHIC REFERENCES: Dubois 5.4,5.5,7.3 (see also Culler-Singh, Cap.5)  PRACTICING/LAB #09 of 08-Nov-2023 (10:15-11:45) Exercizes on Coherency from past exams. PRESENTATION/SLIDES/VIDEO: c224es09-coherency_exercize1.pdf RESOURCES: Exercize #3 of the exam of the 07-07-2009 - (Coherence: Dragon vs. MESI). Exercize #1 of the exam of the 20-01-2010 - (MSI protocol). spreadsheet for this excercize (20-01-2010) Exercize #1 of the exam of the 16-01-2015 - (Competitive Protocol).  LESSON #14 of 13-Nov-2023 (14:30-15:15) Memory Consistency Models: Sequential Consistency and Relaxed Consistency PRESENTATION/SLIDES/VIDEO: c224lez14-multiprocessor_consistency.pdf BIBLIOGRAPHIC REFERENCES: Dubois 7.4,7.5,7.6,7.7 (v. Culler-Singh, cap. 5.2, 5.5) Optional reading (open-access): A Primer on Memory Consistency and Cache Coherence, Second Edition Optional reading: Litmus Tests for checking Memory Models  LESSON #60 of 13-Nov-2023 (15:15-16:00) Introduction to FPGAs PRESENTATION/SLIDES/VIDEO: c224lez60-fpga1.pdf BIBLIOGRAPHIC REFERENCES: Optional reference: 1364-2001 - IEEE Standard Verilog Hardware Description Language Optional reference: 1076-2019 - IEEE Standard for VHDL Language Reference Manual Free book: L.H. Crockett et al. "The Zynq book"  LESSON #63 of 15-Nov-2023 (08:30-10:00) High-level FPGA Programming PRESENTATION/SLIDES/VIDEO: c224lez63-fpga4.pdf BIBLIOGRAPHIC REFERENCES: https://www.khronos.org/sycl  PRACTICING/LAB #61 of 15-Nov-2023 (10:15-11:45) Vitis Acceleration Application Flow PRESENTATION/SLIDES/VIDEO: c224es61-handson_vitis.pdf RESOURCES: https://github.com/Xilinx/Vitis-Tutorials  PRACTICING/LAB #19 of 20-Nov-2023 (14:30-16:00) Various exercizes from previous exams. PRESENTATION/SLIDES/VIDEO: c224es19-multiprocessor_exercize3.pdf RESOURCES: Exercize #2 of the exam of the 18-12-2015 - (Coherence and Interleaving - Jacobi). Exercize #3 of the exam of the 10-02-2016 - (Consistency and use of FENCE). Exercize #1 of the exam of the 31-01-2011 - (Coherence - Bit-Vector vs. Single-Sharer).  PRACTICING/LAB #20 of 22-Nov-2023 (08:30-10:00) Various exercizes from previous exams. PRESENTATION/SLIDES/VIDEO: c224es20-coherency_exercize2.pdf RESOURCES: Exercize #1 of the exam of the 21-12-2016 - (Coherence - Dragon patterns). Exercize #2 of the exam of the 10-02-2016 - (Coherence - MSI vs MESI, 3 streams).  PRACTICING/LAB #21 of 22-Nov-2023 (10:15-11:45) Various exercizes from previous exams. PRESENTATION/SLIDES/VIDEO: IN PREPARATION RESOURCES: Exercize #1 of the exam of the 18-12-2019 - (Coherence - MSI, TAS best/worst). Exercize #1 of the exam of the 23-12-2020 - (Coherence - Competitive, TAS best/worst). Exercize #1 of the exam of the 23-11-2022 - (Coherence - MESIF, TAS best/worst).  27-Nov-2023 - FINAL TEST (13:45-14:30)  27-Nov-2023 - FINAL TEST (14:30-16:00)  LESSON #21 of 29-Nov-2023 (08:30-10:00) Introduction to Parallel Programming PRESENTATION/SLIDES/VIDEO: c224lez21-parallel_programming_intro1.pdf BIBLIOGRAPHIC REFERENCES: OpenCilk @ MIT Programming in Cilk  LESSON #22 of 29-Nov-2023 (10:15-11:00) Parallelsim and Performance PRESENTATION/SLIDES/VIDEO: c224lez22-parallel_programming_intro2.pdf BIBLIOGRAPHIC REFERENCES: Reading: He et al., The Cilkview Scalability Analyzer Optional reading: Frigo et al., The implementation of the Cilk-5 multithreaded language  PRACTICING/LAB #11A of 29-Nov-2023 (11:00-11:45) Experimenting several programming models: Pthreads, OpenMP, TBB, Cilk PRESENTATION/SLIDES/VIDEO: c224es11A-cilk_lab1.pdf RESOURCES: Source code of the examples in Pthreads, OpenMP, TBB, Cilk  PRACTICING/LAB #11B of 04-Dec-2023 (14:30-15:15) Methodology for carrying out performance measurements; discussion on projects; visit to Computer Architecture Lab PRESENTATION/SLIDES/VIDEO: c224es11B-methodology.pdf RESOURCES: SAMPLE PROJECT USING CUDA  PRACTICING/LAB #11C of 04-Dec-2023 (15:15-16:00) Experimenting Cilk Tools. PRESENTATION/SLIDES/VIDEO: c224es11C-cilk_lab2.pdf RESOURCES: Using CILKTOOLS (cilkscale,cilksan)  LESSON #23 of 05-Dec-2023 (08:30-10:00) Introduction to CUDA parallel programming model (PART A) PRESENTATION/SLIDES/VIDEO: c224lez23-cuda1.pdf BIBLIOGRAPHIC REFERENCES: D. B. Kirk, W. W. Hwu, Programming Massively Parallel Processors 3rd Edition, Morgan kaugfman, 2017: CAP.1, CAP.2.  LESSON #23 of 06-Dec-2023 (08:30-09:15) Introduction to CUDA parallel programming model (PART B) PRESENTATION/SLIDES/VIDEO: c224lez23-cuda1.pdf BIBLIOGRAPHIC REFERENCES: D. B. Kirk, W. W. Hwu, Programming Massively Parallel Processors 3rd Edition, Morgan kaugfman, 2017: CAP.1, CAP.2.  LESSON #24 of 06-Dec-2023 (09:15-10:00) CUDA Threads, Atomics, and Memory (PART A) PRESENTATION/SLIDES/VIDEO: c224lez24-cuda2.pdf BIBLIOGRAPHIC REFERENCES: D. B. Kirk, W. W. Hwu, Programming Massively Parallel Processors 3rd Edition, Morgan kaugfman, 2017: CAP.4, CAP.5.  LESSON #24 of 06-Dec-2023 (10:15-11:45) CUDA Threads, Atomics, and Memory (PART B) PRESENTATION/SLIDES/VIDEO: c224lez24-cuda2.pdf BIBLIOGRAPHIC REFERENCES: D. B. Kirk, W. W. Hwu, Programming Massively Parallel Processors 3rd Edition, Morgan kaugfman, 2017: CAP.4, CAP.5.  PRACTICING/LAB #13 of 11-Dec-2023 (14:30-16:00) Overview of CUDA environment and simple examples. PRESENTATION/SLIDES/VIDEO: c224es13-cuda_lab0.pdf RESOURCES: In the lab, download: PPF-LAB-V07.tgz initial examples At home (you MUST have an NVIDIA card in your computer): docker pull robgiorgi/ppf-cuda-v07 CUDA CheatSheet MATRIX-MULTIPLY CODE (optional reference) CUDA Programming Guide (optional reference) CUDA Runtime API  LESSON #31 of 13-Dec-2023 (08:30-09:15) Clusters PRESENTATION/SLIDES/VIDEO: c224lez31-clusters.pdf BIBLIOGRAPHIC REFERENCES: Dubois 5.2.2, 5.3  LESSON #32 of 13-Dec-2023 (09:15-10:00) Introduction to MPI PRESENTATION/SLIDES/VIDEO: c224lez32-mpi_introduction.pdf BIBLIOGRAPHIC REFERENCES: Reference site for OpenMPI:https://www.open-mpi.org/doc/ Reference tutorial: A. Lumsdaine et al., OpenMPI Tutorial  PRACTICING/LAB #16 of 13-Dec-2023 (10:15-11:45) Using MPI PRESENTATION/SLIDES/VIDEO: c224es16-mpi_lab.pdf RESOURCES: hello.c HELLOWORLD MPI CODE testmpi.c TESTMPI CODE mmxmpi2.c MATRIX-MULTIPLICATION MPI CODE  PRACTICING/LAB #17 of 18-Dec-2023 (14:30-16:00) Study of specific parallel patterns in CUDA PRESENTATION/SLIDES/VIDEO: c224es17-histogram_on_CUDA.pdf RESOURCES: Exercize #2 of the exam of the 19-12-2017 - (CUDA - Histogram). CUDA - - Histogram Example Code  PRACTICING/LAB #18 of 20-Dec-2023 (08:30-10:00) Study of specific parallel patterns in Cilk/OpenMP/MPI PRESENTATION/SLIDES/VIDEO: c224es18-histogram_on_Cilk_OpenMP_MPI.pdf RESOURCES: Exercize #2 of the exam of the 18-12-2019 - (Cilk/Histogram). Exercize #2 of the exam of the 19-12-2018 - (OpenMP/Histogram). Exercize #2 of the exam of the 23-12-2020 - (MPI/Histogram). CILK - Histogram Example Code OPENMP - Histogram Example Code MPI - Histogram Example Code  PRACTICING/LAB #29 of 20-Dec-2023 (10:15-11:45) Review of Course Projects PRESENTATION/SLIDES/VIDEO: c224es29-ProjectReview.pdf RESOURCES: See also the dedicated project page and list of themes.  from 25-Dec-2023 to 03-Jan-2024: No Lesson VACANZA/PONTE  08-Jan-2024: No Lesson NO LESSON To visualize the content of the above presentations in Acrobat format (.pdf) you can use Acrobat Reader, freely realesed by Adobe (Download Acrobat Reader)