Hardware Multithreading

Slides:



Advertisements
Similar presentations
Multiprocessors— Large vs. Small Scale Multiprocessors— Large vs. Small Scale.
Advertisements

ILP: IntroductionCSCE430/830 Instruction-level parallelism: Introduction CSCE430/830 Computer Architecture Lecturer: Prof. Hong Jiang Courtesy of Yifeng.
Computer Structure 2014 – Out-Of-Order Execution 1 Computer Structure Out-Of-Order Execution Lihu Rappoport and Adi Yoaz.
Multithreading processors Adapted from Bhuyan, Patterson, Eggers, probably others.
Instruction-Level Parallelism (ILP)
Single-Chip Multiprocessor Nirmal Andrews. Case for single chip multiprocessors Advances in the field of integrated chip processing. - Gate density (More.
Computer Architecture 2011 – Out-Of-Order Execution 1 Computer Architecture Out-Of-Order Execution Lihu Rappoport and Adi Yoaz.
1 COMP 206: Computer Architecture and Implementation Montek Singh Mon, Dec 5, 2005 Topic: Intro to Multiprocessors and Thread-Level Parallelism.
1 Lecture 11: ILP Innovations and SMT Today: out-of-order example, ILP innovations, SMT (Sections 3.5 and supplementary notes)
Multithreading and Dataflow Architectures CPSC 321 Andreas Klappenecker.
Computer Architecture 2011 – out-of-order execution (lec 7) 1 Computer Architecture Out-of-order execution By Dan Tsafrir, 11/4/2011 Presentation based.
Computer Architecture 2010 – Out-Of-Order Execution 1 Computer Architecture Out-Of-Order Execution Lihu Rappoport and Adi Yoaz.
1 Multi-core processors 12/1/09. 2 Multiprocessors inside a single chip It is now possible to implement multiple processors (cores) inside a single chip.
COMP Multithreading. Coarse Grain Multithreading Minimal pipeline changes – Need to abort instructions in “shadow” of miss – Resume instruction.
Hardware Multithreading. Increasing CPU Performance By increasing clock frequency By increasing Instructions per Clock Minimizing memory access impact.
1 Advanced Computer Architecture Dynamic Instruction Level Parallelism Lecture 2.
COMP25212 CPU Multi Threading Learning Outcomes: to be able to: –Describe the motivation for multithread support in CPU hardware –To distinguish the benefits.
Thread Level Parallelism Since ILP has inherent limitations, can we exploit multithreading? –a thread is defined as a separate process with its own instructions.
Processor Level Parallelism. Improving the Pipeline Pipelined processor – Ideal speedup = num stages – Branches / conflicts mean limited returns after.
EKT303/4 Superscalar vs Super-pipelined.
Advanced Computer Architecture pg 1 Embedded Computer Architecture 5SAI0 Chip Multi-Processors (ch 8) Henk Corporaal
Computer Structure 2015 – Intel ® Core TM μArch 1 Computer Structure Multi-Threading Lihu Rappoport and Adi Yoaz.
Out-of-order execution Lihu Rappoport 11/ MAMAS – Computer Architecture Out-Of-Order Execution Dr. Lihu Rappoport.
Lecture 1: Introduction CprE 585 Advanced Computer Architecture, Fall 2004 Zhao Zhang.
PipeliningPipelining Computer Architecture (Fall 2006)
Computer Architecture: Multithreading (II)
CS 352H: Computer Systems Architecture
COMP 740: Computer Architecture and Implementation
William Stallings Computer Organization and Architecture 8th Edition
/ Computer Architecture and Design
Prof. Onur Mutlu Carnegie Mellon University
Simultaneous Multithreading
Multi-core processors
Computer Structure Multi-Threading
5.2 Eleven Advanced Optimizations of Cache Performance
CS203 – Advanced Computer Architecture
Chapter 14 Instruction Level Parallelism and Superscalar Processors
Pipeline Implementation (4.6)
Embedded Computer Architecture 5SAI0 Chip Multi-Processors (ch 8)
/ Computer Architecture and Design
CDA 3101 Spring 2016 Introduction to Computer Organization
Pipelining: Advanced ILP
Morgan Kaufmann Publishers The Processor
Lecture: SMT, Cache Hierarchies
Computer Architecture: Multithreading (I)
Instruction Scheduling for Instruction-Level Parallelism
Out of Order Processors
From before the Break Classic 5-stage pipeline
Levels of Parallelism within a Single Processor
Computer Architecture Lecture 4 17th May, 2006
Lecture 8: ILP and Speculation Contd. Chapter 2, Sections 2. 6, 2
Hardware Multithreading
Lecture: SMT, Cache Hierarchies
Dr. Javier Navaridas Pipelining Dr. Javier Navaridas COMP25212 System Architecture.
15-740/ Computer Architecture Lecture 5: Precise Exceptions
Control unit extension for data hazards
Lecture: SMT, Cache Hierarchies
/ Computer Architecture and Design
Chapter 8. Pipelining.
/ Computer Architecture and Design
Embedded Computer Architecture 5SAI0 Chip Multi-Processors (ch 8)
Lecture: SMT, Cache Hierarchies
Levels of Parallelism within a Single Processor
CSC3050 – Computer Architecture
Lecture 22: Multithreading
The University of Adelaide, School of Computer Science
CIS 6930: Chip Multiprocessor: Parallel Architecture and Programming
Presentation transcript:

Hardware Multithreading COMP25212 1

…from Tuesday What are the differences between software multithreading and hardware multithreading? Software: OS support for several concurrent threads Large number of threads (effectively unlimited) ‘Heavy’ context switching Hardware: CPU support for several instructions flows Limited number of threads (typically 2 or 4) ‘Light’/’Immediate’ context switching

…from Tuesday Describe Trashing in the context of Multithreading Two threads are accessing independent regions of memory which occupy the same cache lines and keep retiring each other’s data Why is it a problem? Both threads will have a high cache miss rate, which will severely slow down their execution Describe Coarse-grain multithreading Threads are switched upon ‘expensive’ operations Describe fine-grain multithreading Threads are switched every single cycle, selecting among the ‘ready’ threads

Simultaneous Multi-Threading

Simultaneous Multi-Threading The main idea is to exploit instructions level parallelism and thread level parallelism at the same time In a superscalar processor issue instructions from different threads in the same cycle Schedule as many ‘ready’ instructions as possible Operand reading and result saving becomes much more complex Note that coarse-grain and fine-grain MT can also be implemented in superscalar processors

Simultaneous MultiThreading Let’s look simply at instruction issue: 1 2 3 4 5 6 7 8 9 10 Inst a IF ID EX MEM WB Inst b Inst M Inst N Inst c Inst P Inst Q Inst d Inst e Inst R

Simultaneous Multithreading We want to run these two Threads

Simultaneous Multithreading We want to run these two Threads Issue as many Ready instrs. as possible

SMT Design Considerations Fetch and prioritization policies Which thread to issue instructions from? Allocation policies How to prevent thread starvation? How to maximize overall computational throughput? How to provide fairness/QoS? How to measure performance Is total IPC across all threads the right metric? Total execution time? IPC per thread?

Which Thread to Fetch From? Static policies: Round-robin – which granularity? 1 instructions per thread 2 instructions per thread ... Dynamic policies Favor threads with minimal in-flight branches Favor threads with minimal outstanding misses Favor threads with minimal in-flight instructions

SMT issues with in-order processors Asymmetric pipeline stall One of the pipelines stalls – we want other pipelines to continue  in-order pipeline precludes that Overtaking – non-stalled threads should progress Independent instructions from a thread might get blocked by stalled instructions from other thread Cache misses – Abort instruction (and instructions in the shadow if Dcache miss) upon cache miss Most existing implementations are for O-o-O, register-renamed architectures (akin to tomasulo) e.g. PowerPC, Intel Hyperthreading

Asymmetric pipeline stall Pipeline 0 stalls due to a data dependency Pipeline 1 should be able to continue Superscalar in-order pipelines must advance at the same pace Pipeline 1 is stalled without need 1 2 3 4 5 6 7 Pipeline 0 Inst M IF ID EX MEM WB Pipeline 1 Inst b Inst N - Inst c

This instruction could have overtaken the previous two Overtaking Pipeline 0 stalls due to a data dependency in orange thread Inst c from blue thread was issued in pipeline0 and is stalled because of Inst N from the orange thread 1 2 3 4 5 6 7 Pipeline 0 Inst M IF ID EX MEM WB Pipeline 1 Inst b Inst N - Inst O Inst c Inst P This instruction could have overtaken the previous two

Simultaneous Multi Threading Extracts the most parallelism from instructions and threads Implemented mostly in out-of-order processors because they are the only able to exploit that much parallelism Has a significant hardware overhead Replicate (and MUX) thread state (registers, TLBs, etc) Operand reading and result saving increases datapath complexity Per-thread instruction handling/scheduling engine in out-of-order implementations … but significantly less than adding more cores

Multithreading Example We want to execute 2 programs with 100 instructions each. The first program suffers an i-cache miss at instruction #31, and the second program another at instruction #71. Assume that: + There is parallelism enough to execute all instructions independently (no hazards, apart from the two cache misses highlighted) + Switching threads can be done instantaneously + A cache miss requires 20 cycles to get the instruction to the cache. + The two programs would not interfere with each other’s caches lines Calculate the execution time observed by each of the programs (cycles elapsed between the execution of the first and the last instruction of that application) and the total time to execute the workload a) Sequentially (no multithreading) b) With coarse-grain multithreading c) With fine-grain multithreading d) With 2-way simultaneous multithreading

Hardware Multithreading Summary

Benefits of HW MT Multithreading techniques improve the utilisation of processor resources and, hence, the overall performance If the different threads are accessing the same input data they may be using the same regions of memory Cache efficiency improves in these cases

Disadvantages of HW MT Single-thread performance may be degraded when compared to a single-thread CPU Multiple threads interfere with each other Shared caches mean that, effectively, threads would use a fraction of the whole cache Trashing may exacerbate this issue Thread scheduling at hardware level adds high complexity to processor design Thread state, managing priorities, OS-level information, …

Multithreading Summary A cost-effective way of finding additional parallelism for the CPU pipeline Available in x86, Itanium, Power and SPARC Intel Hyperthreading (SMT) PowerPC uses SMT UltraSparc T1/T2 used fine-grain, later models used SMT Sparc64 VI used coarse-grain, later models moved to SMT Present additional hardware thread as an additional virtual CPU to Operating System Multiprocessor OS is required

Multithreading in 4-way superscalar

Some Advanced Uses of Multithreading

Speculative Execution When reaching a conditional branch we could spawn 2 threads One runs the true path Another runs the false Once we know which one is correct kill the other thread Effects of Control Hazards alleviated Supported by current OoO cpus But not as a full-fledged thread Can reach several levels of nested conditions Requires memory support (e.g. reordering buffers) A.k.a. Branch Predication Branch Kill Thread

Memory Prefetching Compile applications into two threads One runs the whole application The other thread (scout thread) only has the memory accesses The scout thread runs ahead and fetches memory in advance Ensures data will be in the cache when the original thread needs it cache hit rate increases Synchronization is needed Scout has to run ahead enough so that memory delay is hidden … But not too much so that it does not replace useful data from the cache Beware trashing!!! Single threaded Original thread Scout thread xCM xCH xCM Data in cache

Slipstreaming Compile sequential applications into two threads One runs the application itself The slipstream thread only has a critical path of the application The slipstream thread runs ahead and passes results Delay of slow operations (e.g. float point division) is improved Synchronization and communication among the threads is needed Requires extra hardware to deal with this ‘special’ behaviour Could be used in multicore as well Single threaded Original thread Slipstream thread Non-critical Results Critical

Transient Fault Detection When reaching a block of code that requires reliable computation, we can replicate the thread Two or more copies of the computation run in different threads We compare the result of all threads If the result is the same, we can proceed with execution Sometimes a majority vote could be enough Otherwise we need to rollback execution Split Compare

Questions