Skip to main content

ECE 721 Spring 2019 Advanced Microarchitecture


Tues. Jan. 8Overview of class topicsppt
  TOPIC 1: Modern Superscalar Processors  
Thurs. Jan. 10Physical Register File management: phys. RF, RMT, freelistpptxppt
Tues. Jan. 15Physical Register File management:
committing and freeing registers, exception recovery, branch misprediction recovery
Thurs. Jan. 17overflow lecture  
Tues. Jan. 22overflow lecture
K. C. Yeager. The Mips R10000 superscalar microprocessor. IEEE Micro, 16(2):28-41, April 1996.
Thurs. Jan. 24Dynamic Scheduling Algorithm: Phys. RF ready bits, Issue Queue
Sizing structures
Tues. Jan. 29Handling loads and stores:
terminology (memory disambiguation and store-load forwarding), 
LQ/SQ operation, load speculation and memory dependence predictors
Thurs. Jan. 31overflow lecture
Tues. Feb. 5overflow lectureG. Chrysos and J. S. Emer. Memory Dependence Prediction Using Store Sets. ISCA-25, 1998.
Thurs. Feb. 7Canonical Superscalar Pipeline
Pipeline stages: fetch, decode, rename, dispatch
Tues. Feb. 12Pipeline stages: schedule, register read, execute, writeback, retirepptx
Thurs. Feb. 14overflow lecture
  TOPIC 2: High-ILP Processors  
Tues. Feb. 19Trace cachepptxE. Rotenberg, S. Bennett, and J. E. Smith. Trace Cache: a Low Latency Approach to High Bandwidth Instruction Fetching. MICRO-29, Dec. 1996.
Thurs. Feb. 21overflow lecture
Tues. Feb. 26Value predictionpptxY. Sazeides and J. E. Smith. The Predictability of Data Values. MICRO-30, Dec. 1997.
Thurs. Feb. 28Midterm Exam
Tues. Mar. 5 Predicationpptx
(aux. pptx)
A. Klauser, T. Austin, D. Grunwald, and B. Calder. Dynamic Hammock Predication for Non-predicated Instruction Set Architectures. PACT, Oct. 1998.
Thurs. Mar. 7 overflow lecture  
Tues. Mar. 12 Spring Break  
Thurs. Mar. 14 Spring Break  
Tues. Mar. 19 overflow lecture  
Thurs. Mar. 21 Trace processorspptxE. Rotenberg, Q. Jacobson, Y. Sazeides, and J. E. Smith. Trace processors. MICRO-30, Dec. 1997.
Tues. Mar. 26 Simultaneous multithreading (SMT)pptxD. M. Tullsen et al.  Exploiting Choice: Instruction Fetch and Issue on an Implementable Simultaneous Multithreading Processor. ISCA-23, May 1996.
Thurs. Mar. 28 SMT cont.  
Tues. Apr. 2 Advice on research projects:
Report formatProject guidelinesPresentation guidelines
  TOPIC 3: Large-Window Processors  
Thurs. Apr. 4 Checkpoint Processing and Recovery (CPR):

 fine-grain (ROB) vs. coarse-grain (Checkpoint) recovery, aggressive register reclamation

 operation, example simulation


H. Akkary, R. Rajwar, and S. Srinivasan. Checkpoint Processing and Recovery:
Towards Scalable Large Instruction Window Processors.  MICRO-36, 2003.
Tues. Apr. 9 Continual Flow Pipelines (CFP)pptxS. Srinivasan, R. Rajwar, H. Akkary, A. Gandhi, and M. Upton. Continual Flow Pipelines. ASPLOS’04, 2004.
Thurs. Apr. 11 Runahead Execution(see prev.)O. Mutlu, J. Stark, C. Wilkerson, and Y. Patt. Runahead Execution: An Alternative to Very Large Instruction Windows for Out-of-Order Processors. HPCA-9, 2003.
Tues. Apr. 16 project presentations  
Thurs. Apr. 18 project presentations  
Tues. Apr. 23 project presentations  
Thurs. Apr. 25 project presentations