Transcript Week 1 Power Point Slides

Why Parallel Computing?
• Annual performance improvements drops
from 50% per year to 20% per year
• Manufacturers focusing on multi-core
systems, not single-core
• Why?
– Smaller transistors = faster processors.
– Faster processors = increased power
– Increased power = increased heat.
– Increased heat = unreliable processors
Parallel Programming Examples
• Embarrassingly Parallel Applications
– Google searches employ > 1,000,000 processors
• Applications with unacceptable sequential run times
• Grand Challenge Problems
– 1991 High Performance Computing Act (Law 102-94)
“Fundamental Grand Challenge science and
engineering problems with broad economic and/or
scientific impact and whose solution can be advanced
by applying high performance computing techniques
and resources.”
• Promotes terascale level computation over high bandwidth
wide area computational grids
Grand Challenge Problems
• Require more processing power than available
on single processing systems
• Solutions would significantly benefit society
• There are not complete solutions for these,
which are commercially available
• There is a significant potential for progress with
today’s technology
• Examples: Climate modeling, Gene discovery,
energy research, semantic web-based
applications
Grand
Challenge
Problem
Examples
• Associations
– Computer Research
Association (CRA)
– National Science
Foundation (NSF)
Partial Grand Challenge Problem List
1. Predict contaminant seepage
2. Predict airborne contaminant affects
3. Gene sequence discovery
4. Short term weather forecasts
5. Predict long term global warming
6. Predict earthquakes and volcanoes,
7. Predict hurricanes and tornados
8. Automate natural language understanding
9. Computer vision
10. Nanotechnology
11. Computerized reasoning
12. Protein mechanisms
13. Predict asteroid collisions
14. Sub-atomic particle interactions
15. Model biomechanical processes
16. Manufacture new materials
17. Fundamental nature of matter
18. Transportation patterns
19. Computational fluid dynamics
Global Weather Forecasting Example
• Suppose whole global atmosphere divided into cells of size 1 mile  1
mile  1 mile to a height of 10 miles (10 cells high) - about 5  108 cells.
• Suppose each calculation requires 200 floating point operations. In one
time step, 1011 floating point operations necessary.
• To forecast the weather over 7 days using 1-minute intervals, a
computer operating at 1Gflops (109 floating point operations/s) takes
106 seconds or over 10 days.
• To perform calculation in 5 minutes requires computer operating at 3.4
Tflops (3.4  1012 floating point operations/sec).
1.5
Modeling Motion of Astronomical Bodies
• Astronomical bodies attracted to each other by
gravity; the force on each determines movement
• Required calculations: O(n2) or at best, O(n lg n)
• At each time step, calculate new position
• A galaxy might have1011 stars
• If each calculation requires 1 ms, one iteration
requires 109 years using the N2 algorithm and
almost a year using an efficient N lg N algorithm
Types of Parallelism
• Fine grain
– Vector Processors
• Matrix operations in single instructions
– High performance optimizing compilers
• Reorder instructions
• Loop partitioning
• Low level synchronizations
• Coarse grain
– Threads, critical sections, mutual exclusion
– Message passing
Von Neumann Bottleneck
CPU speed exceeds than memory access time
Modifications (Transparent to software)
• Device Controllers
• Cache: Fast memory to hold blocks of recently
used consecutive memory locations
• Pipelines to breakup an instruction into pieces
and execute the pieces in parallel
• Multiple issue replicates functional units to
enable executing instructions in parallel
• Fine grained multithreading after each
instruction
Parallel Systems
• Shared Memory Systems
– All cores see the same memory
– Coordination: Critical sections and mutual exclusion
• Distributed Memory Systems
– Beowulf Clusters; Clusters of Workstations
– Each core has access to local memory
– Coordination: message passing
• Hybrid (Distributed memory presented as shared)
– Uniform Memory Access (UMA)
– Cache Only Memory Access (COMA)
– Non-uniform Memory Access (NUMA)
• Computational Grids
– Heterogeneous and Geographically Separated
Hardware Configurations
• Flynn Categories
–
–
–
–
SISD (Single Core)
MIMD (*our focus*)
SIMD (Vector Processors)
MISD
• Within MIMD
– SPMD (*our focus*)
– MPMD
P0
P1
P2
P3
Memory
Shared Memory Multiprocessor
P0
P1
P2
P3
M0
M1
M2
M3
• Multiprocessor Systems
– Threads, Critical Sections
• Multi-computer Systems
– Message Passing
– Sockets, RMI
Distributed Memory Multi-computer
Hardware Configurations
• Shared Memory Systems
– Do not scale to high numbers of processors
– Considerations
• Enforcing critical sections through mutual exclusion
• Forks and joins of threads
• Distributed Memory Systems
– Topology: The graph that defines the network
• More connections means higher cost
• Latency: time to establish connections
• Bandwidth: width of the pipe
– Considerations
• Appropriate message passing framework
• Redesign algorithms to those that are less natural
Shared Memory Problems
• Memory contention
– Single bus inexpensive, sequential access
– Crossbar switches, parallel access but
expensive
• Cache Coherence
– Cache doesn’t match memory
• Write through writes all changes immediately
• Write back writes dirty line when expelled
– Processor cache requires broadcast of
changes and complex coherence algorithms
Distributed Memory
• Possible to use commodity systems
• Relatively inexpensive interconnects
• Requires message passing, which
programmers tend to find difficult
• Must deal with network, topology, and
security issues
• Hybrid systems are distributed, but
present a system to programmers as
shared, but with performance loss
Network Terminology
•
•
•
•
•
•
Latency – Time to send “null”, zero length message
Bandwidth – Maximum transmission rate (bits/sec)
Total edges – Total number of network connections
Degree – Maximum connections per network node
Connectivity – Minimum connections to disconnect
Bisection width – Number of connections to cut the
network into equal two parts
• Diameter – Maximum hops connecting two nodes
• Dilation – Number of extra hops needed to map one
topology to another
Web-based Networks
•
•
•
•
•
•
•
•
•
•
•
Generally uses TCP/IP protocol
The number of hops between nodes is not constant
Communication incurs high latencies
Nodes scattered over large geographical distances
High Bandwidths possible after connection established
The slowest link along the path limits speed
Resources are highly heterogeneous
Security becomes a major concern; proxies often used
Encryption algorithms can require significant overhead.
Subject to local policies at each node
Example: www.globus.org
Routing Techniques
• Packet Switching
– Message packets routed separately; assembled at the sink
• Deadlock free
– Guarantees sufficient resources to complete transmission
• Store and Forward
– Messages stored at node before transmission continues
• Cut Through
– Entire path of transmission established before transmission
• Wormhole Routing
– Flits (a couple of bits) held at each node; the “worm” of
flits move when the next node becomes available
Myranet
•
•
•
•
•
•
•
Proprietary technology (http://www.myri.com)
Point-to-point, full-duplex switch based technology
Custom chip settings for parallel topologies
Lightweight transparent cut-through routing protocol
Thousands of processors without TCP/IP limitations
Can embed TCP/IP messages to maximize flexibility
Gateway for wide area heterogeneous networks
Rectangles: Processors, Circles: Switches
Type
Bandwidth
Latency
Ethernet
10 MB/sec
10-15 ms
GB Ethernet
10 GB/sec
150 us
Myranet
10 GB/sec
2us
Parallel Techniques
• Peer-to-peer
– Independent systems coordinate to run a single
application
– Mechanisms: Threads, Message Passing
• Client-server
– Server responds to many clients running many
applications
– Mechanisms: Remote Method Invocation, Sockets
The focus is this class is peer-to-peer applications
Popular Network Topologies
•
•
•
•
•
•
•
Fully Connected and Star
Line and Ring
Tree and Fat Tree
Mesh and Torus
Hypercube
Hybrids: Pyramid
Multi-stage: Myrinet
Fully Connected and Star
 Degree?
 Connectivity?
 Total edges?
 Bisection width?
 Diameter?
Line and Ring
 Degree?
 Connectivity?
 Total edges?
 Bisection width?
 Diameter?
Tree and Fat Tree
Edges Connecting Node at level k to k-1 are twice the
number of edges connecting a Node from level k-2 to k-1
 Degree?
 Connectivity?
 Total edges?
 Bisection width?
 Diameter?
Mesh and Torus
 Degree?
 Connectivity?
 Total edges?
 Bisection width?
 Diameter?
Hypercube
•A Hypercube of degree zero is a single node
•A Hypercube of degree d is two hypercubes of degree d-1
With edges connecting the corresponding nodes
 Degree?
 Connectivity?
 Total edges?
 Bisection width?
 Diameter?
Pyramid
A Hybrid Network Combining a mesh and a Tree
 Degree?
 Connectivity?
 Total edges?
 Bisection width?
 Diameter?
Multistage Interconnection Network
Example: Omega network
switch elements with
straight-through or
crossover connections
000
001
010
011
Inputs
1.26
000
001
010
011
Outputs
100
101
100
101
110
111
110
111
Distributed Shared Memory
Making main memory of group of interconnected
computers look as though a single memory with single
address space. Then can use shared memory
programming techniques.
Interconnection
network
Messages
Processor
Shared
memory
Computers
1.27
Parallel Performance Metrics
• Complexity (Big Oh Notation)
– f(n) = O(g(n)) if for constants z, c>0 f(n)≤c g(n) when n>z
• Speed up: s(p) = t1/tp
• Cost: C(p) = tp*p
• Efficiency: E(p) = t1/C(p)
• Scalability
– Imprecise term to measure impact of adding processors
– We might say an application scales to 256 processors
– Can refer to hardware, software, or both
Parallel Run Time
• Sequential execution time: t1
– t1 = Computation time of best sequential algorithm
• Communication overhead: Tcomm = m(tstartup + ntdata)
–
–
–
–
tstartup = latency (time to send a message with no data)
tdata = time to send one data element
n = number of data elements
m = number of messages
• Computation overhead: tcomp=f (n, p))
• Parallel execution time: tp = tcomp + tcomm
– Tp = reflects the worst case execution time over all processors
Estimating Scalability
Parallel Visualization Tools
Observe using a space-time diagram (or process-time diagram)
Process 1
Process 2
Process 3
Computing
Time
Waiting
Message-passing system routine
Message
Superlinear speed-up (s(p)>p)
Reasons for:
1. Non-optimal sequential algorithm
a. Solution: Compare to an optimal sequential algorithm
b. Parallel versions are often different from sequential versions
2. Specialized hardware on certain processors
a. Processor has fast graphics but computes slow
b. NASA superlinear distributed grid application
3. Average case doesn’t match single run
a. Consider a search application
b. What are the speed-up possibilities?
Speed-up Potential
• Amdahl’s “pessimistic” law
– Fraction of Sequential processing (f) is fixed
– S(p) = t1/ (f * t1 + (1-f)t1/p) → 1/f as p →∞
• Gustafson’s “optimistic” law
– Greater data implies parallel portion grows
– Assumes more capability leads to more data
– S(p) = f + (1-f)*p
• For each law
– What is the best speed-up if f=.25?
– What is the speed-up for 16 processors?
• Which assumption if valid?
Challenges
• Running multiple instances of a sequential
program won’t make effective use of
parallel resources
• Without programmer optimizations,
additional processors will not improve
overall system performance
• Connect networks of systems together in a
peer-to-peer manner
Solutions
• Rewrite and parallel existing programs
– Algorithms for parallel systems are drastically
different than those that execute sequentially
• Translation programs that automatically
parallelize serial programs.
– This is very difficult to do.
– Success has been limited.
• Operating system thread/process allocation
– Some benefit, but not a general solution
Compute and merge results
• Serial Algorithm:
result = 0;
for (int i=0; i<N; i++) { sum += merge(compute(i)); }
• Parallel Algorithm (first try) :
– Each processor, P, performs N/P computations
– IF P>0 THEN Send partial results to master (P=0)
– ELSE receive and merge partial results
Is this the best we can do?
How many compute calls? How many merge calls?
How is work distributed among the processors?
Multiple cores forming a global
sum
Copyright © 2010,
Elsevier Inc. All rights
•How many merges must the master do?
•Suppose 1024 processors. Then how many
merges would the master do?
•Note the difference from the first approach
Parallel Algorithms
• Problem: Three helpers must mow, weed
eat, and pull weeds on a large field
• Task Level
– Each helper perform one of the tasks over the
entire large field
• Data Level
– Each helper do all three tasks over one third
of the field
Case Study
• Millions of doubles
• Thousands of bins
• We want to create a histogram of the
number of values present in each bin
• How would we program this sequentially?
• What parallel algorithm would we use?
– Using a shared memory system
– Using a distributed memory system
In This Class We
• Investigate converting sequential
programs to make use of parallel facilities
• Devise algorithms that are parallel in
nature
• Use C with Industry Standard Extensions
– Message-Passing Interface (MPI) via mpich
– Posix Threads (Pthreads)
– OpenMP
Parallel Program Development
• Cautions
– Parallel program programming is harder than sequential programming
– Some algorithms don’t lend themselves to running in parallel
• Advised Steps of Development
–
–
–
–
–
–
Step 1: Program and test as much as possible sequentially
Step 2: Code the Parallel version
Step 3: Run in parallel; one processor with few threads
Step 4: Add more threads as confidence grows
Step 5: Run in parallel with a small number of processors
Step 6: Add more processes as confidence grows
• Tools
–
–
–
–
There are parallel debuggers that can help
Insert assertion error checks within the code
Instrument the code (add print statements)
Timing: time(), gettimeofday(), clock(), MPI_Wtime()