Compiler Optimisation
|
|
|
- Isaac Norton
- 6 years ago
- Views:
Transcription
1 Compiler Optimisation 6 Instruction Scheduling Hugh Leather IF 1.18a hleather@inf.ed.ac.uk Institute for Computing Systems Architecture School of Informatics University of Edinburgh 2018
2 Introduction This lecture: Scheduling to hide latency and exploit ILP Dependence graph Local list Scheduling + priorities Forward versus backward scheduling Software pipelining of loops
3 Latency, functional units, and ILP Instructions take clock cycles to execute (latency) Modern machines issue several operations per cycle Cannot use results until ready, can do something else Execution time is order-dependent Latencies not always constant (cache, early exit, etc) Operation Cycles load, store 3 load / cache 100s loadi, add, shift 1 mult 2 div 40 branch 0 8
4 Machine types In order Deep pipelining allows multiple instructions Superscalar Multiple functional units, can issue > 1 instruction Out of order Large window of instructions can be reordered dynamically VLIW Compiler statically allocates to FUs
5 Effect of scheduling Superscalar, 1 FU: New op each cycle if operands ready Simple schedule 1 a := 2*a*b*c Cycle Operations Operands waiting loadai r r 1 add r 1, r 1 r 1 loadai r r 2 mult r 1, r 2 r 1 loadai r r 2 mult r 1, r 2 r 1 storeai r 1 r Done 1 loads/stores 3 cycles, mults 2, adds 1
6 Effect of scheduling Superscalar, 1 FU: New op each cycle if operands ready Simple schedule 1 a := 2*a*b*c Cycle Operations Operands waiting 1 loadai r r 1 r 1 2 r 1 3 r 1 add r 1, r 1 r 1 loadai r r 2 mult r 1, r 2 r 1 loadai r r 2 mult r 1, r 2 r 1 storeai r 1 r Done 1 loads/stores 3 cycles, mults 2, adds 1
7 Effect of scheduling Superscalar, 1 FU: New op each cycle if operands ready Simple schedule 1 a := 2*a*b*c Cycle Operations Operands waiting 1 loadai r r 1 r 1 2 r 1 3 r 1 4 add r 1, r 1 r 1 r 1 loadai r r 2 mult r 1, r 2 r 1 loadai r r 2 mult r 1, r 2 r 1 storeai r 1 r Done 1 loads/stores 3 cycles, mults 2, adds 1
8 Effect of scheduling Superscalar, 1 FU: New op each cycle if operands ready Simple schedule 1 a := 2*a*b*c Cycle Operations Operands waiting 1 loadai r r 1 r 1 2 r 1 3 r 1 4 add r 1, r 1 r 1 r 1 5 loadai r r 2 r 2 6 r 2 7 r 2 mult r 1, r 2 r 1 loadai r r 2 mult r 1, r 2 r 1 storeai r 1 r Done 1 loads/stores 3 cycles, mults 2, adds 1
9 Effect of scheduling Superscalar, 1 FU: New op each cycle if operands ready Simple schedule 1 a := 2*a*b*c Cycle Operations Operands waiting 1 loadai r r 1 r 1 2 r 1 3 r 1 4 add r 1, r 1 r 1 r 1 5 loadai r r 2 r 2 6 r 2 7 r 2 8 mult r 1, r 2 r 1 r 1 9 Next op does not use r 1 r 1 loadai r r 2 mult r 1, r 2 r 1 storeai r 1 r Done 1 loads/stores 3 cycles, mults 2, adds 1
10 Effect of scheduling Superscalar, 1 FU: New op each cycle if operands ready Simple schedule 1 a := 2*a*b*c Cycle Operations Operands waiting 1 loadai r r 1 r 1 2 r 1 3 r 1 4 add r 1, r 1 r 1 r 1 5 loadai r r 2 r 2 6 r 2 7 r 2 8 mult r 1, r 2 r 1 r 1 9 loadai r r 2 r 1, r 2 10 r 2 11 r 2 mult r 1, r 2 r 1 storeai r 1 r Done 1 loads/stores 3 cycles, mults 2, adds 1
11 Effect of scheduling Superscalar, 1 FU: New op each cycle if operands ready Simple schedule 1 a := 2*a*b*c Cycle Operations Operands waiting 1 loadai r r 1 r 1 2 r 1 3 r 1 4 add r 1, r 1 r 1 r 1 5 loadai r r 2 r 2 6 r 2 7 r 2 8 mult r 1, r 2 r 1 r 1 9 loadai r r 2 r 1, r 2 10 r 2 11 r 2 12 mult r 1, r 2 r 1 r 1 13 r 1 storeai r 1 r Done 1 loads/stores 3 cycles, mults 2, adds 1
12 Effect of scheduling Superscalar, 1 FU: New op each cycle if operands ready Simple schedule 1 a := 2*a*b*c Cycle Operations Operands waiting 1 loadai r r 1 r 1 2 r 1 3 r 1 4 add r 1, r 1 r 1 r 1 5 loadai r r 2 r 2 6 r 2 7 r 2 8 mult r 1, r 2 r 1 r 1 9 loadai r r 2 r 1, r 2 10 r 2 11 r 2 12 mult r 1, r 2 r 1 r 1 13 r 1 14 storeai r 1 r store to complete 15 store to complete 16 store to complete Done 1 loads/stores 3 cycles, mults 2, adds 1
13 Effect of scheduling Superscalar, 1 FU: New op each cycle if operands ready Schedule loads early 2 a := 2*a*b*c Cycle Operations Operands waiting loadai r r 1 loadai r r 2 loadai r r 3 add r 1, r 1 r 1 mult r 1, r 2 r 1 mult r 1, r 2 r 1 storeai r 1 r Done 2 loads/stores 3 cycles, mults 2, adds 1
14 Effect of scheduling Superscalar, 1 FU: New op each cycle if operands ready Schedule loads early 2 a := 2*a*b*c Cycle Operations Operands waiting 1 loadai r r 1 r 1 loadai r r 2 loadai r r 3 add r 1, r 1 r 1 mult r 1, r 2 r 1 mult r 1, r 3 r 1 storeai r 1 r Done 2 loads/stores 3 cycles, mults 2, adds 1
15 Effect of scheduling Superscalar, 1 FU: New op each cycle if operands ready Schedule loads early 2 a := 2*a*b*c Cycle Operations Operands waiting 1 loadai r r 1 r 1 2 loadai r r 2 r 1, r 2 loadai r r 3 add r 1, r 1 r 1 mult r 1, r 2 r 1 mult r 1, r 3 r 1 storeai r 1 r Done 2 loads/stores 3 cycles, mults 2, adds 1
16 Effect of scheduling Superscalar, 1 FU: New op each cycle if operands ready Schedule loads early 2 a := 2*a*b*c Cycle Operations Operands waiting 1 loadai r r 1 r 1 2 loadai r r 2 r 1, r 2 3 loadai r r 3 r 1, r 2, r 3 add r 1, r 1 r 1 mult r 1, r 2 r 1 mult r 1, r 3 r 1 storeai r 1 r Done 2 loads/stores 3 cycles, mults 2, adds 1
17 Effect of scheduling Superscalar, 1 FU: New op each cycle if operands ready Schedule loads early 2 a := 2*a*b*c Cycle Operations Operands waiting 1 loadai r r 1 r 1 2 loadai r r 2 r 1, r 2 3 loadai r r 3 r 1, r 2, r 3 4 add r 1, r 1 r 1 r 1, r 2, r 3 mult r 1, r 2 r 1 mult r 1, r 3 r 1 storeai r 1 r Done 2 loads/stores 3 cycles, mults 2, adds 1
18 Effect of scheduling Superscalar, 1 FU: New op each cycle if operands ready Schedule loads early 2 a := 2*a*b*c Cycle Operations Operands waiting 1 loadai r r 1 r 1 2 loadai r r 2 r 1, r 2 3 loadai r r 3 r 1, r 2, r 3 4 add r 1, r 1 r 1 r 1, r 2, r 3 5 mult r 1, r 2 r 1 r 1, r 3 6 r 1 mult r 1, r 3 r 1 storeai r 1 r Done 2 loads/stores 3 cycles, mults 2, adds 1
19 Effect of scheduling Superscalar, 1 FU: New op each cycle if operands ready Schedule loads early 2 a := 2*a*b*c Cycle Operations Operands waiting 1 loadai r r 1 r 1 2 loadai r r 2 r 1, r 2 3 loadai r r 3 r 1, r 2, r 3 4 add r 1, r 1 r 1 r 1, r 2, r 3 5 mult r 1, r 2 r 1 r 1, r 3 6 r 1 7 mult r 1, r 3 r 1 r 1 8 r 1 storeai r 1 r Done 2 loads/stores 3 cycles, mults 2, adds 1
20 Effect of scheduling Superscalar, 1 FU: New op each cycle if operands ready Schedule loads early 2 a := 2*a*b*c Cycle Operations Operands waiting 1 loadai r r 1 r 1 2 loadai r r 2 r 1, r 2 3 loadai r r 3 r 1, r 2, r 3 4 add r 1, r 1 r 1 r 1, r 2, r 3 5 mult r 1, r 2 r 1 r 1, r 3 6 r 1 7 mult r 1, r 3 r 1 r 1 8 r 1 9 storeai r 1 r store to complete 10 store to complete 11 store to complete Done Uses one more register 11 versus 16 cycles 31% faster! 2 loads/stores 3 cycles, mults 2, adds 1
21 Scheduling problem Schedule maps operations to cycle; a Ops, S(a) N Respect latency; a, b Ops, a dependson b = S(a) S(b) + λ(b) Respect function units; no more ops per type per cycle than FUs can handle Length of schedule, L(S) = max a Ops (S(a) + λ(a)) Schedule S is time-optimal if S 1, L(S) L(S 1 ) Problem: Find a time-optimal schedule 3 Even local scheduling with many restrictions is NP-complete 3 A schedule might also be optimal in terms of registers, power, or space
22 List scheduling Local greedy heuristic to produce schedules for single basic blocks 1 Rename to avoid anti-dependences 2 Build dependency graph 3 Prioritise operations 4 For each cycle 1 Choose the highest priority ready operation & schedule it 2 Update ready queue
23 List scheduling Dependence/Precedence graph Schedule operation only when operands ready Build dependency graph of read-after-write (RAW) deps Label with latency and FU requirements Example: a = 2*a*b*c
24 List scheduling Dependence/Precedence graph Schedule operation only when operands ready Build dependency graph of read-after-write (RAW) deps Label with latency and FU requirements Anti-dependences (WAR) restrict movement Example: a = 2*a*b*c
25 List scheduling Dependence/Precedence graph Schedule operation only when operands ready Build dependency graph of read-after-write (RAW) deps Label with latency and FU requirements Anti-dependences (WAR) restrict movement renaming removes Example: a = 2*a*b*c
26 List scheduling List scheduling algorithm Cycle 1 Ready leaves of (D) Active while(ready Active ) a Active where S(a) + λ(a) Cycle Active Active - a b succs(a) where isready(b) Ready Ready b if a Ready and b, a priority b priority Ready Ready - a S(op) Cycle Active Active a Cycle Cycle + 1
27 List scheduling Priorities Many different priorities used Quality of schedules depends on good choice The longest latency path or critical path is a good priority Tie breakers Last use of a value - decreases demand for register as moves it nearer def Number of descendants - encourages scheduler to pursue multiple paths Longer latency first - others can fit in shadow Random
28 List scheduling Example: Schedule with priority by critical path length
29 List scheduling Example: Schedule with priority by critical path length
30 List scheduling Example: Schedule with priority by critical path length
31 List scheduling Example: Schedule with priority by critical path length
32 List scheduling Example: Schedule with priority by critical path length
33 List scheduling Example: Schedule with priority by critical path length
34 List scheduling Example: Schedule with priority by critical path length
35 List scheduling Example: Schedule with priority by critical path length
36 List scheduling Example: Schedule with priority by critical path length
37 List scheduling Example: Schedule with priority by critical path length
38 List scheduling Example: Schedule with priority by critical path length
39 List scheduling Example: Schedule with priority by critical path length
40 List scheduling Forward vs backward Can schedule from root to leaves (backward) May change schedule time List scheduling cheap, so try both, choose best
41 List scheduling Forward vs backward Opcode loadi lshift add addi cmp store Latency
42 List scheduling Forward vs backward Forwards Int Int Stores 1 loadi 1 lshift 2 loadi 2 loadi 3 3 loadi 4 add 1 4 add 2 add 3 5 add 4 addi store 1 6 cmp store 2 7 store 3 8 store 4 9 store cbr Backwards Int Int Stores 1 loadi 1 2 addi lshift 3 add 4 loadi 3 4 add 3 loadi 2 store 5 5 add 2 loadi 1 store 4 6 add 1 store 3 7 store 2 8 store cmp 12 cbr
43 Scheduling Larger Regions Schedule extended basic blocks (EBBs) Super block cloning Schedule traces Software pipelining
44 Scheduling Larger Regions Extended basic blocks Extended basic block EBB is maximal set of blocks such that Set has a single entry, B i Each block B j other than B i has exactly one predecessor
45 Scheduling Larger Regions Extended basic blocks Extended basic block EBB is maximal set of blocks such that Set has a single entry, B i Each block B j other than B i has exactly one predecessor
46 Scheduling Larger Regions Extended basic blocks Schedule entire paths through EBBs Example has four EBB paths
47 Scheduling Larger Regions Extended basic blocks Schedule entire paths through EBBs Example has four EBB paths
48 Scheduling Larger Regions Extended basic blocks Schedule entire paths through EBBs Example has four EBB paths
49 Scheduling Larger Regions Extended basic blocks Schedule entire paths through EBBs Example has four EBB paths
50 Scheduling Larger Regions Extended basic blocks Schedule entire paths through EBBs Example has four EBB paths Having B 1 in both causes conflicts Moving an op out of B 1 causes problems
51 Scheduling Larger Regions Extended basic blocks Schedule entire paths through EBBs Example has four EBB paths Having B 1 in both causes conflicts Moving an op out of B 1 causes problems Must insert compensation code
52 Scheduling Larger Regions Extended basic blocks Schedule entire paths through EBBs Example has four EBB paths Having B 1 in both causes conflicts Moving an op into B 1 causes problems
53 Scheduling Larger Regions Superblock cloning Join points create context problems
54 Scheduling Larger Regions Superblock cloning Join points create context problems Clone blocks to create more context
55 Scheduling Larger Regions Superblock cloning Join points create context problems Clone blocks to create more context Merge any simple control flow
56 Scheduling Larger Regions Superblock cloning Join points create context problems Clone blocks to create more context Merge any simple control flow Schedule EBBs
57 Scheduling Larger Regions Trace scheduling Edge frequency from profile (not block frequency)
58 Scheduling Larger Regions Trace scheduling Edge frequency from profile (not block frequency) Pick hot path Schedule with compensation code
59 Scheduling Larger Regions Trace scheduling Edge frequency from profile (not block frequency) Pick hot path Schedule with compensation code Remove from CFG
60 Scheduling Larger Regions Trace scheduling Edge frequency from profile (not block frequency) Pick hot path Schedule with compensation code Remove from CFG Repeat
61 Loop scheduling Loop structures can dominate execution time Specialist technique software pipelining Allows application of list scheduling to loops Why not loop unrolling?
62 Loop scheduling Loop structures can dominate execution time Specialist technique software pipelining Allows application of list scheduling to loops Why not loop unrolling? Allows loop effect to become arbitrarily small, but Code growth, cache pressure, register pressure
63 Software pipelining Consider simple loop to sum array
64 Software pipelining Schedule on 1 FU - 5 cycles load 3 cycles, add 1 cycle, branch 1 cycle
65 Software pipelining Schedule on VLIW 3 FUs - 4 cycles load 3 cycles, add 1 cycle, branch 1 cycle
66 Software pipelining A better steady state schedule exists load 3 cycles, add 1 cycle, branch 1 cycle
67 Software pipelining Requires prologue and epilogue (may schedule others in epilogue) load 3 cycles, add 1 cycle, branch 1 cycle
68 Software pipelining Respect dependences and latency including loop carries load 3 cycles, add 1 cycle, branch 1 cycle
69 Software pipelining Complete code load 3 cycles, add 1 cycle, branch 1 cycle
70 Software pipelining Some definitions Initiation interval (ii) Number of cycles between initiating loop iterations Original loop had ii of 5 cycles Final loop had ii of 2 cycles Recurrence Loop-based computation whose value is used in later loop iteration Might be several iterations later Has dependency chain(s) on itself Recurrence latency is latency of dependency chain
71 Software pipelining Algorithm Choose an initiation interval, ii Compute lower bounds on ii Shorter ii means faster overall execution Generate a loop body that takes ii cycles Try to schedule into ii cycles, using modulo scheduler If it fails, increase ii by one and try again Generate the needed prologue and epilogue code For prologue, work backward from upward exposed uses in the scheduled loop body For epilogue, work forward from downward exposed definitions in the scheduled loop body
72 Software pipelining Initial initiation interval (ii) Starting value for ii based on minimum resource and recurrence constraints Resource constraint ii must be large enough to issue every operation Let N u = number of FUs of type u Let I u = number of operations of type u I u /N u is lower bound on ii for type u max u ( I u /N u ) is lower bound on ii
73 Software pipelining Initial initiation interval (ii) Starting value for ii based on minimum resource and recurrence constraints Recurrence constraint ii cannot be smaller than longest recurrence latency Recurrence r is over k r iterations with latency λ r λ r /k u is lower bound on ii for type r max r ( λ r /k u ) is lower bound on ii
74 Software pipelining Initial initiation interval (ii) Starting value for ii based on minimum resource and recurrence constraints Start value = max(max u ( I u /N u ), max r ( λ r /k u ) For simple loop a = A[ i ] b = b + a i = i + 1 if i < n goto end Resource constraint Memory Integer Branch I u N u I u /N u Recurrence constraint b i k r 1 1 λ r 2 1 I u /N u 2 1
75 Software pipelining Modulo scheduling Modulo scheduling Schedule with cycle modulo initiation interval
76 Software pipelining Modulo scheduling Modulo scheduling Schedule with cycle modulo initiation interval
77 Software pipelining Modulo scheduling Modulo scheduling Schedule with cycle modulo initiation interval
78 Software pipelining Modulo scheduling Modulo scheduling Schedule with cycle modulo initiation interval
79 Software pipelining Modulo scheduling Modulo scheduling Schedule with cycle modulo initiation interval
80 Software pipelining Current research Much research in different software pipelining techniques Difficult when there is general control flow in the loop Predication in IA64 for example really helps here Some recent work in exhaustive scheduling -i.e. solve the NP-complete problem for basic blocks
81 Summary Scheduling to hide latency and exploit ILP Dependence graph - dependences between instructions + latency Local list Scheduling + priorities Forward versus backward scheduling Scheduling EBBs, superblock cloning, trace scheduling Software pipelining of loops
82 PPar CDT Advert 4-year programme: MSc by Research + PhD Research-focused: Work on your thesis topic from the start Collaboration between: University of Edinburgh s School of Informatics Ranked top in the UK by 2014 REF Edinburgh Parallel Computing Centre UK s largest supercomputing centre Research topics in software, hardware, theory and application of: Parallelism Concurrency Distribution Full funding available Industrial engagement programme includes internships at leading companies Now accepting applications! Find out more and apply at: pervasiveparallelism.inf.ed.ac.uk The biggest revolution in the technological landscape for fifty years
CMP 301B Computer Architecture. Appendix C
CMP 301B Computer Architecture Appendix C Dealing with Exceptions What should be done when an exception arises and many instructions are in the pipeline??!! Force a trap instruction in the next IF stage
Some material adapted from Mohamed Younis, UMBC CMSC 611 Spr 2003 course slides Some material adapted from Hennessy & Patterson / 2003 Elsevier
Some material adapted from Mohamed Younis, UMBC CMSC 611 Spr 2003 course slides Some material adapted from Hennessy & Patterson / 2003 Elsevier Science !!! Basic MIPS integer pipeline Branches with one
EN164: Design of Computing Systems Lecture 22: Processor / ILP 3
EN164: Design of Computing Systems Lecture 22: Processor / ILP 3 Professor Sherief Reda http://scale.engin.brown.edu Electrical Sciences and Computer Engineering School of Engineering Brown University
Project 5: Optimizer Jason Ansel
Project 5: Optimizer Jason Ansel Overview Project guidelines Benchmarking Library OoO CPUs Project Guidelines Use optimizations from lectures as your arsenal If you decide to implement one, look at Whale
Reading Material + Announcements
Reading Material + Announcements Reminder HW 1» Before asking questions: 1) Read all threads on piazza, 2) Think a bit Ÿ Then, post question Ÿ talk to Animesh if you are stuck Today s class» Wrap up Control
Instruction Level Parallelism Part II - Scoreboard
Course on: Advanced Computer Architectures Instruction Level Parallelism Part II - Scoreboard Prof. Cristina Silvano Politecnico di Milano email: cristina.silvano@polimi.it 1 Basic Assumptions We consider
CSE502: Computer Architecture CSE 502: Computer Architecture
CSE 502: Computer Architecture Out-of-Order Schedulers Data-Capture Scheduler Dispatch: read available operands from ARF/ROB, store in scheduler Commit: Missing operands filled in from bypass Issue: When
CSE502: Computer Architecture CSE 502: Computer Architecture
CSE 502: Computer Architecture Out-of-Order Execution and Register Rename In Search of Parallelism rivial Parallelism is limited What is trivial parallelism? In-order: sequential instructions do not have
Instruction Level Parallelism. Data Dependence Static Scheduling
Instruction Level Parallelism Data Dependence Static Scheduling Basic Block A straight line code sequence with no branches in except to the entry and no branches out except at the exit Loop: L.D ADD.D
CSE502: Computer Architecture CSE 502: Computer Architecture
CSE 502: Computer Architecture Out-of-Order Execution and Register Rename In Search of Parallelism rivial Parallelism is limited What is trivial parallelism? In-order: sequential instructions do not have
SCHEDULING Giovanni De Micheli Stanford University
SCHEDULING Giovanni De Micheli Stanford University Outline The scheduling problem. Scheduling without constraints. Scheduling under timing constraints. Relative scheduling. Scheduling under resource constraints.
Computer Science 246. Advanced Computer Architecture. Spring 2010 Harvard University. Instructor: Prof. David Brooks
Advanced Computer Architecture Spring 2010 Harvard University Instructor: Prof. dbrooks@eecs.harvard.edu Lecture Outline Instruction-Level Parallelism Scoreboarding (A.8) Instruction Level Parallelism
Out-of-Order Execution. Register Renaming. Nima Honarmand
Out-of-Order Execution & Register Renaming Nima Honarmand Out-of-Order (OOO) Execution (1) Essence of OOO execution is Dynamic Scheduling Dynamic scheduling: processor hardware determines instruction execution
Lecture 14 Instruction Selection: Tree-pattern matching
Lecture 14 Instruction Selection: Tree-pattern matching (EaC-11.3) Copyright 2003, Keith D. Cooper, Ken Kennedy & Linda Torczon, all rights reserved. The Concept Many compilers use tree-structured IRs
Dynamic Scheduling I
basic pipeline started with single, in-order issue, single-cycle operations have extended this basic pipeline with multi-cycle operations multiple issue (superscalar) now: dynamic scheduling (out-of-order
DAT105: Computer Architecture
Department of Computer Science & Engineering Chalmers University of Techlogy DAT05: Computer Architecture Exercise 6 (Old exam questions) By Minh Quang Do 2007-2-2 Question 4a [2006/2/22] () Loop: LD F0,0(R)
EECS 470 Lecture 5. Intro to Dynamic Scheduling (Scoreboarding) Fall 2018 Jon Beaumont
Intro to Dynamic Scheduling (Scoreboarding) Fall 2018 Jon Beaumont http://www.eecs.umich.edu/courses/eecs470 Many thanks to Prof. Martin and Roth of University of Pennsylvania for most of these slides.
Chapter 16 - Instruction-Level Parallelism and Superscalar Processors
Chapter 16 - Instruction-Level Parallelism and Superscalar Processors Luis Tarrataca luis.tarrataca@gmail.com CEFET-RJ L. Tarrataca Chapter 16 - Superscalar Processors 1 / 78 Table of Contents I 1 Overview
EECS 470. Tomasulo s Algorithm. Lecture 4 Winter 2018
omasulo s Algorithm Winter 2018 Slides developed in part by Profs. Austin, Brehob, Falsafi, Hill, Hoe, Lipasti, Martin, Roth, Shen, Smith, Sohi, yson, Vijaykumar, and Wenisch of Carnegie Mellon University,
7/11/2012. Single Cycle (Review) CSE 2021: Computer Organization. Multi-Cycle Implementation. Single Cycle with Jump. Pipelining Analogy
CSE 2021: Computer Organization Single Cycle (Review) Lecture-10 CPU Design : Pipelining-1 Overview, Datapath and control Shakil M. Khan CSE-2021 July-12-2012 2 Single Cycle with Jump Multi-Cycle Implementation
U. Wisconsin CS/ECE 752 Advanced Computer Architecture I
U. Wisconsin CS/ECE 752 Advanced Computer Architecture I Prof. Karu Sankaralingam Unit 5: Dynamic Scheduling I Slides developed by Amir Roth of University of Pennsylvania with sources that included University
Instruction Level Parallelism III: Dynamic Scheduling
Instruction Level Parallelism III: Dynamic Scheduling Reading: Appendix A (A-67) H&P Chapter 2 Instruction Level Parallelism III: Dynamic Scheduling 1 his Unit: Dynamic Scheduling Application OS Compiler
Instruction Selection via Tree-Pattern Matching Comp 412
COMP FALL 017 Instruction Selection via TreePattern Matching Comp source code IR Front End Optimizer Back End IR target code Copyright 017, Keith D. Cooper & Linda Torczon, all rights reserved. Students
Problem: hazards delay instruction completion & increase the CPI. Compiler scheduling (static scheduling) reduces impact of hazards
Dynamic Scheduling Pipelining: Issue instructions in every cycle (CPI 1) Problem: hazards delay instruction completion & increase the CPI Compiler scheduling (static scheduling) reduces impact of hazards
COSC4201. Scoreboard
COSC4201 Scoreboard Prof. Mokhtar Aboelaze York University Based on Slides by Prof. L. Bhuyan (UCR) Prof. M. Shaaban (RIT) 1 Overcoming Data Hazards with Dynamic Scheduling In the pipeline, if there is
Lecture 8-1 Vector Processors 2 A. Sohn
Lecture 8-1 Vector Processors Vector Processors How many iterations does the following loop go through? For i=1 to n do A[i] = B[i] + C[i] Sequential Processor: n times. Vector processor: 1 instruction!
Tomasolu s s Algorithm
omasolu s s Algorithm Fall 2007 Prof. homas Wenisch http://www.eecs.umich.edu/courses/eecs4 70 Floating Point Buffers (FLB) ag ag ag Storage Bus Floating Point 4 3 Buffers FLB 6 5 5 4 Control 2 1 1 Result
EECS 583 Class 7 Classic Code Optimization cont d
EECS 583 Class 7 Classic Code Optimization cont d University of Michigan October 2, 2016 Global Constant Propagation Consider 2 ops, X and Y in different BBs» 1. X is a move» 2. src1(x) is a literal» 3.
Instruction Scheduling for Low Power Dissipation in High Performance Microprocessors
Instruction Scheduling for Low Power Dissipation in High Performance Microprocessors Abstract Mark C. Toburen Thomas M. Conte Department of Electrical and Computer Engineering North Carolina State University
Chapter 4. Pipelining Analogy. The Processor. Pipelined laundry: overlapping execution. Parallelism improves performance. Four loads: Non-stop:
Chapter 4 The Processor Part II Pipelining Analogy Pipelined laundry: overlapping execution Parallelism improves performance Four loads: Speedup = 8/3.5 = 2.3 Non-stop: Speedup p = 2n/(0.5n + 1.5) 4 =
CISC 662 Graduate Computer Architecture. Lecture 9 - Scoreboard
CISC 662 Graduate Computer Architecture Lecture 9 - Scoreboard Michela Taufer http://www.cis.udel.edu/~taufer/teaching/cis662f07 Powerpoint Lecture tes from John Hennessy and David Patterson s: Computer
Lecture 13 Register Allocation: Coalescing
Lecture 13 Register llocation: Coalescing I. Motivation II. Coalescing Overview III. lgorithms: Simple & Safe lgorithm riggs lgorithm George s lgorithm Phillip. Gibbons 15-745: Register Coalescing 1 Review:
CS521 CSE IITG 11/23/2012
Parallel Decoding and issue Parallel execution Preserving the sequential consistency of execution and exception processing 1 slide 2 Decode/issue data Issue bound fetch Dispatch bound fetch RS RS RS RS
High-Performance Pipelined Architecture of Elliptic Curve Scalar Multiplication Over GF(2 m )
High-Performance Pipelined Architecture of Elliptic Curve Scalar Multiplication Over GF(2 m ) Abstract: This paper proposes an efficient pipelined architecture of elliptic curve scalar multiplication (ECSM)
Power-conscious High Level Synthesis Using Loop Folding
Power-conscious High Level Synthesis Using Loop Folding Daehong Kim Kiyoung Choi School of Electrical Engineering Seoul National University, Seoul, Korea, 151-742 E-mail: daehong@poppy.snu.ac.kr Abstract
Chapter 12. Cross-Layer Optimization for Multi- Hop Cognitive Radio Networks
Chapter 12 Cross-Layer Optimization for Multi- Hop Cognitive Radio Networks 1 Outline CR network (CRN) properties Mathematical models at multiple layers Case study 2 Traditional Radio vs CR Traditional
Dynamic Scheduling II
so far: dynamic scheduling (out-of-order execution) Scoreboard omasulo s algorithm register renaming: removing artificial dependences (WAR/WAW) now: out-of-order execution + precise state advanced topic:
Tomasulo s Algorithm. Tomasulo s Algorithm
Tomasulo s Algorithm Load and store buffers Contain data and addresses, act like reservation stations Branch Prediction Top-level design: 56 Tomasulo s Algorithm Three Steps: Issue Get next instruction
Loop Scheduling with Timing and Switching-Activity Minimization for VLIW DSP Λ
Loop Scheduling with Timing and Switching-Activity Minimization for VLIW DSP Λ Zili Shao, Chun Xue, Qingfeng Zhuge, Bin Xiao, Edwin H.-M. Sha y Abstract In embedded systems, high performance DSP needs
CS 110 Computer Architecture Lecture 11: Pipelining
CS 110 Computer Architecture Lecture 11: Pipelining Instructor: Sören Schwertfeger http://shtech.org/courses/ca/ School of Information Science and Technology SIST ShanghaiTech University Slides based on
Timed Games UPPAAL-TIGA. Alexandre David
Timed Games UPPAAL-TIGA Alexandre David 1.2.05 Overview Timed Games. Algorithm (CONCUR 05). Strategies. Code generation. Architecture of UPPAAL-TIGA. Interactive game. Timed Games with Partial Observability.
Module 3 Greedy Strategy
Module 3 Greedy Strategy Dr. Natarajan Meghanathan Professor of Computer Science Jackson State University Jackson, MS 39217 E-mail: natarajan.meghanathan@jsums.edu Introduction to Greedy Technique Main
Pipelined Processor Design
Pipelined Processor Design COE 38 Computer Architecture Prof. Muhamed Mudawar Computer Engineering Department King Fahd University of Petroleum and Minerals Presentation Outline Pipelining versus Serial
Lecture 20: Combinatorial Search (1997) Steven Skiena. skiena
Lecture 20: Combinatorial Search (1997) Steven Skiena Department of Computer Science State University of New York Stony Brook, NY 11794 4400 http://www.cs.sunysb.edu/ skiena Give an O(n lg k)-time algorithm
EE382V-ICS: System-on-a-Chip (SoC) Design
EE38V-CS: System-on-a-Chip (SoC) Design Hardware Synthesis and Architectures Source: D. Gajski, S. Abdi, A. Gerstlauer, G. Schirner, Embedded System Design: Modeling, Synthesis, Verification, Chapter 6:
Overview. 1 Trends in Microprocessor Architecture. Computer architecture. Computer architecture
Overview 1 Trends in Microprocessor Architecture R05 Robert Mullins Computer architecture Scaling performance and CMOS Where have performance gains come from? Modern superscalar processors The limits of
Department Computer Science and Engineering IIT Kanpur
NPTEL Online - IIT Bombay Course Name Parallel Computer Architecture Department Computer Science and Engineering IIT Kanpur Instructor Dr. Mainak Chaudhuri file:///e /parallel_com_arch/lecture1/main.html[6/13/2012
CUDA Threads. Terminology. How it works. Terminology. Streaming Multiprocessor (SM) A SM processes block of threads
Terminology CUDA Threads Bedrich Benes, Ph.D. Purdue University Department of Computer Graphics Streaming Multiprocessor (SM) A SM processes block of threads Streaming Processors (SP) also called CUDA
Register Allocation by Puzzle Solving
Register Allocation by Puzzle Solving EECS 322: Compiler Construction Simone Campanoni Robby Findler 4/19/2016 Materials Research paper: Authors: Fernando Magno Quintao Pereira, Jens Palsberg Title: Register
Instructor: Dr. Mainak Chaudhuri. Instructor: Dr. S. K. Aggarwal. Instructor: Dr. Rajat Moona
NPTEL Online - IIT Kanpur Instructor: Dr. Mainak Chaudhuri Instructor: Dr. S. K. Aggarwal Course Name: Department: Program Optimization for Multi-core Architecture Computer Science and Engineering IIT
Power Management in Multicore Processors through Clustered DVFS
Power Management in Multicore Processors through Clustered DVFS A THESIS SUBMITTED TO THE FACULTY OF THE GRADUATE SCHOOL OF THE UNIVERSITY OF MINNESOTA BY Tejaswini Kolpe IN PARTIAL FULFILLMENT OF THE
ECE 4750 Computer Architecture, Fall 2016 T09 Advanced Processors: Superscalar Execution
ECE 4750 Computer Architecture, Fall 2016 T09 Advanced Processors: Superscalar Execution School of Electrical and Computer Engineering Cornell University revision: 2016-11-28-17-33 1 In-Order Dual-Issue
Event-Driven Scheduling. (closely following Jane Liu s Book)
Event-Driven Scheduling (closely following Jane Liu s Book) Real-Time Systems, 2009 Event-Driven Systems, 1 Principles Admission: Assign priorities to Jobs At events, jobs are scheduled according to their
EECS 470. Lecture 9. MIPS R10000 Case Study. Fall 2018 Jon Beaumont
MIPS R10000 Case Study Fall 2018 Jon Beaumont http://www.eecs.umich.edu/courses/eecs470 Multiprocessor SGI Origin Using MIPS R10K Many thanks to Prof. Martin and Roth of University of Pennsylvania for
PRIORITY QUEUES AND HEAPS. Lecture 19 CS2110 Spring 2014
1 PRIORITY QUEUES AND HEAPS Lecture 19 CS2110 Spring 2014 Readings and Homework 2 Read Chapter 2 to learn about heaps Salespeople often make matrices that show all the great features of their product that
Set 4: Game-Playing. ICS 271 Fall 2017 Kalev Kask
Set 4: Game-Playing ICS 271 Fall 2017 Kalev Kask Overview Computer programs that play 2-player games game-playing as search with the complication of an opponent General principles of game-playing and search
Adversary Search. Ref: Chapter 5
Adversary Search Ref: Chapter 5 1 Games & A.I. Easy to measure success Easy to represent states Small number of operators Comparison against humans is possible. Many games can be modeled very easily, although
REVOLUTIONIZING THE COMPUTING LANDSCAPE AND BEYOND.
December 3-6, 2018 Santa Clara Convention Center CA, USA REVOLUTIONIZING THE COMPUTING LANDSCAPE AND BEYOND. https://tmt.knect365.com/risc-v-summit @risc_v ACCELERATING INFERENCING ON THE EDGE WITH RISC-V
Scheduling. Radek Mařík. April 28, 2015 FEE CTU, K Radek Mařík Scheduling April 28, / 48
Scheduling Radek Mařík FEE CTU, K13132 April 28, 2015 Radek Mařík (marikr@fel.cvut.cz) Scheduling April 28, 2015 1 / 48 Outline 1 Introduction to Scheduling Methodology Overview 2 Classification of Scheduling
Digital Integrated CircuitDesign
Digital Integrated CircuitDesign Lecture 13 Building Blocks (Multipliers) Register Adder Shift Register Adib Abrishamifar EE Department IUST Acknowledgement This lecture note has been summarized and categorized
Parallel architectures Electronic Computers LM
Parallel architectures Electronic Computers LM 1 Architecture Architecture: functional behaviour of a computer. For instance a processor which executes DLX code Implementation: a logical network implementing
Precise State Recovery. Out-of-Order Pipelines
Precise State Recovery in Out-of-Order Pipelines Nima Honarmand Recall Our Generic OOO Pipeline Instruction flow (pipeline front-end) is in-order Register and memory execution are OOO And, we need a final
Fast and Accurate RF component characterization enabled by FPGA technology
Fast and Accurate RF component characterization enabled by FPGA technology Guillaume Pailloncy Senior Systems Engineer Agenda RF Application Challenges What are FPGAs and why are they useful? FPGA-based
On the Combination of Constraint Programming and Stochastic Search: The Sudoku Case
On the Combination of Constraint Programming and Stochastic Search: The Sudoku Case Rhydian Lewis Cardiff Business School Pryfysgol Caerdydd/ Cardiff University lewisr@cf.ac.uk Talk Plan Introduction:
DIGITAL DESIGN WITH SM CHARTS
DIGITAL DESIGN WITH SM CHARTS By: Dr K S Gurumurthy, UVCE, Bangalore e-notes for the lectures VTU EDUSAT Programme Dr. K S Gurumurthy, UVCE, Blore Page 1 19/04/2005 DIGITAL DESIGN WITH SM CHARTS The utility
7/19/2012. IF for Load (Review) CSE 2021: Computer Organization. EX for Load (Review) ID for Load (Review) WB for Load (Review) MEM for Load (Review)
CSE 2021: Computer Organization IF for Load (Review) Lecture-11 CPU Design : Pipelining-2 Review, Hazards Shakil M. Khan CSE-2021 July-19-2012 2 ID for Load (Review) EX for Load (Review) CSE-2021 July-19-2012
CSE 2021: Computer Organization
CSE 2021: Computer Organization Lecture-11 CPU Design : Pipelining-2 Review, Hazards Shakil M. Khan IF for Load (Review) CSE-2021 July-14-2011 2 ID for Load (Review) CSE-2021 July-14-2011 3 EX for Load
High Speed ECC Implementation on FPGA over GF(2 m )
Department of Electronic and Electrical Engineering University of Sheffield Sheffield, UK Int. Conf. on Field-programmable Logic and Applications (FPL) 2-4th September, 2015 1 Overview Overview Introduction
Instability of Scoring Heuristic In games with value exchange, the heuristics are very bumpy Make smoothing assumptions search for "quiesence"
More on games Gaming Complications Instability of Scoring Heuristic In games with value exchange, the heuristics are very bumpy Make smoothing assumptions search for "quiesence" The Horizon Effect No matter
Games and Adversarial Search II
Games and Adversarial Search II Alpha-Beta Pruning (AIMA 5.3) Some slides adapted from Richard Lathrop, USC/ISI, CS 271 Review: The Minimax Rule Idea: Make the best move for MAX assuming that MIN always
Lecture Topics. Announcements. Today: Memory Management (Stallings, chapter ) Next: continued. Self-Study Exercise #6. Project #4 (due 10/11)
Lecture Topics Today: Memory Management (Stallings, chapter 7.1-7.4) Next: continued 1 Announcements Self-Study Exercise #6 Project #4 (due 10/11) Project #5 (due 10/18) 2 Memory Hierarchy 3 Memory Hierarchy
Introduction to Real-Time Systems
Introduction to Real-Time Systems Real-Time Systems, Lecture 1 Martina Maggio and Karl-Erik Årzén 16 January 2018 Lund University, Department of Automatic Control Content [Real-Time Control System: Chapter
Greedy Algorithms. Kleinberg and Tardos, Chapter 4
Greedy Algorithms Kleinberg and Tardos, Chapter 4 1 Selecting gas stations Road trip from Fort Collins to Durango on a given route with length L, and fuel stations at positions b i. Fuel capacity = C miles.
VLSI System Testing. Outline
ECE 538 VLSI System Testing Krish Chakrabarty System-on-Chip (SOC) Testing ECE 538 Krish Chakrabarty 1 Outline Motivation for modular testing of SOCs Wrapper design IEEE 1500 Standard Optimization Test
SATSim: A Superscalar Architecture Trace Simulator Using Interactive Animation
SATSim: A Superscalar Architecture Trace Simulator Using Interactive Animation Mark Wolff Linda Wills School of Electrical and Computer Engineering Georgia Institute of Technology {wolff,linda.wills}@ece.gatech.edu
Routing ( Introduction to Computer-Aided Design) School of EECS Seoul National University
Routing (454.554 Introduction to Computer-Aided Design) School of EECS Seoul National University Introduction Detailed routing Unrestricted Maze routing Line routing Restricted Switch-box routing: fixed
Dr. D. M. Akbar Hussain
Course Objectives: To enable the students to learn some more practical facts about DSP architectures. Objective is that they can apply this knowledge to map any digital filtering algorithm and related
Programming an Othello AI Michael An (man4), Evan Liang (liange)
Programming an Othello AI Michael An (man4), Evan Liang (liange) 1 Introduction Othello is a two player board game played on an 8 8 grid. Players take turns placing stones with their assigned color (black
Prepared by Vaishnavi Moorthy Asst Prof- Dept of Cse
UNIT II-REPRESENTATION OF KNOWLEDGE (9 hours) Game playing - Knowledge representation, Knowledge representation using Predicate logic, Introduction tounit-2 predicate calculus, Resolution, Use of predicate
SOFTWARE IMPLEMENTATION OF THE
SOFTWARE IMPLEMENTATION OF THE IEEE 802.11A/P PHYSICAL LAYER SDR`12 WInnComm Europe 27 29 June, 2012 Brussels, Belgium T. Cupaiuolo, D. Lo Iacono, M. Siti and M. Odoni Advanced System Technologies STMicroelectronics,
: Principles of Automated Reasoning and Decision Making Midterm
16.410-13: Principles of Automated Reasoning and Decision Making Midterm October 20 th, 2003 Name E-mail Note: Budget your time wisely. Some parts of this quiz could take you much longer than others. Move
Parsimony II Search Algorithms
Parsimony II Search Algorithms Genome 373 Genomic Informatics Elhanan Borenstein Raw distance correction As two DNA sequences diverge, it is easy to see that their maximum raw distance is ~0.75 (assuming
Hardware Implementation of Automatic Control Systems using FPGAs
Hardware Implementation of Automatic Control Systems using FPGAs Lecturer PhD Eng. Ionel BOSTAN Lecturer PhD Eng. Florin-Marian BÎRLEANU Romania Disclaimer: This presentation tries to show the current
CS 4700: Artificial Intelligence
CS 4700: Foundations of Artificial Intelligence Fall 2017 Instructor: Prof. Haym Hirsh Lecture 10 Today Adversarial search (R&N Ch 5) Tuesday, March 7 Knowledge Representation and Reasoning (R&N Ch 7)
Performance Metrics. Computer Architecture. Outline. Objectives. Basic Performance Metrics. Basic Performance Metrics
Computer Architecture Prof. Dr. Nizamettin AYDIN naydin@yildiz.edu.tr nizamettinaydin@gmail.com Performance Metrics http://www.yildiz.edu.tr/~naydin 1 2 Objectives How can we meaningfully measure and compare
CSE548, AMS542: Analysis of Algorithms, Fall 2016 Date: Sep 25. Homework #1. ( Due: Oct 10 ) Figure 1: The laser game.
CSE548, AMS542: Analysis of Algorithms, Fall 2016 Date: Sep 25 Homework #1 ( Due: Oct 10 ) Figure 1: The laser game. Task 1. [ 60 Points ] Laser Game Consider the following game played on an n n board,
Control of the Contract of a Public Transport Service
Control of the Contract of a Public Transport Service Andrea Lodi, Enrico Malaguti, Nicolás E. Stier-Moses Tommaso Bonino DEIS, University of Bologna Graduate School of Business, Columbia University SRM
MITOCW watch?v=krzi60lkpek
MITOCW watch?v=krzi60lkpek The following content is provided under a Creative Commons license. Your support will help MIT OpenCourseWare continue to offer high quality educational resources for free. To
10/5/2015. Constraint Satisfaction Problems. Example: Cryptarithmetic. Example: Map-coloring. Example: Map-coloring. Constraint Satisfaction Problems
0/5/05 Constraint Satisfaction Problems Constraint Satisfaction Problems AIMA: Chapter 6 A CSP consists of: Finite set of X, X,, X n Nonempty domain of possible values for each variable D, D, D n where
10. BSY-1 Trainer Case Study
10. BSY-1 Trainer Case Study This case study is interesting for several reasons: RMS is not used, yet the system is analyzable using RMA obvious solutions would not have helped RMA correctly diagnosed
CS/ENGRD 2110 Object-Oriented Programming and Data Structures Spring 2012 Thorsten Joachims. Lecture 17: Heaps and Priority Queues
CS/ENGRD 2110 Object-Oriented Programming and Data Structures Spring 2012 Thorsten Joachims Lecture 17: Heaps and Priority Queues Stacks and Queues as Lists Stack (LIFO) implemented as list insert (i.e.
Architectural Core Salvaging in a Multi-Core Processor for Hard-Error Tolerance
Architectural Core Salvaging in a Multi-Core Processor for Hard-Error Tolerance Michael D. Powell, Arijit Biswas, Shantanu Gupta, and Shubu Mukherjee SPEARS Group, Intel Massachusetts EECS, University
Handling Search Inconsistencies in MTD(f)
Handling Search Inconsistencies in MTD(f) Jan-Jaap van Horssen 1 February 2018 Abstract Search inconsistencies (or search instability) caused by the use of a transposition table (TT) constitute a well-known
Surveillance strategies for autonomous mobile robots. Nicola Basilico Department of Computer Science University of Milan
Surveillance strategies for autonomous mobile robots Nicola Basilico Department of Computer Science University of Milan Intelligence, surveillance, and reconnaissance (ISR) with autonomous UAVs ISR defines
Pipeline Damping: A Microarchitectural Technique to Reduce Inductive Noise in Supply Voltage
Pipeline Damping: A Microarchitectural Technique to Reduce Inductive Noise in Supply Voltage Michael D. Powell and T. N. Vijaykumar School of Electrical and Computer Engineering, Purdue University {mdpowell,
Multi-user Space Time Scheduling for Wireless Systems with Multiple Antenna
Multi-user Space Time Scheduling for Wireless Systems with Multiple Antenna Vincent Lau Associate Prof., University of Hong Kong Senior Manager, ASTRI Agenda Bacground Lin Level vs System Level Performance
Detector Implementations Based on Software Defined Radio for Next Generation Wireless Systems Janne Janhunen
GIGA seminar 11.1.2010 Detector Implementations Based on Software Defined Radio for Next Generation Wireless Systems Janne Janhunen janne.janhunen@ee.oulu.fi 2 Outline Introduction Benefits and Challenges
Local search algorithms
Local search algorithms Some types of search problems can be formulated in terms of optimization We don t have a start state, don t care about the path to a solution We have an objective function that
PRIORITY QUEUES AND HEAPS
PRIORITY QUEUES AND HEAPS Lecture 1 CS2110 Fall 2014 Reminder: A4 Collision Detection 2 Due tonight by midnight Readings and Homework 3 Read Chapter 2 A Heap Implementation to learn about heaps Exercise:
CS 229 Final Project: Using Reinforcement Learning to Play Othello
CS 229 Final Project: Using Reinforcement Learning to Play Othello Kevin Fry Frank Zheng Xianming Li ID: kfry ID: fzheng ID: xmli 16 December 2016 Abstract We built an AI that learned to play Othello.