Author(s): Dr. Constantinos Evangelinos
Publisher: Massachusetts Institute of Technology (MIT)
Year: 2010
Language: English
City: Cambridge, MA
Tags: 12.950; concurrent; concurrency; high-performance computing; supercomputing; parallel programming; multiprocessor; multithreading
Title
Slide 2
Slide 3
Slide 4
Slide 5
Slide 6
Slide 7
Outline
Ack
Shared Memory
OpenMP
concept
Timeline
Directives
Environment
varP
Basic Directives
Conditional
Extent
Orphans
Parallel
Example
Clauses
Examples
Defaults
DEFAULT Example
PRIVATE
First
REDUCTION
Worksharing
DO/for
DO/for Clauses
WORKSHARE
SECTION
SECTION Clauses
MASTER
NOWAIT
LASTPRIVATE
Combo
Allowed
Synchro
BARRIER
CRITICAL
ATOMIC
Synch Examples
ex CRITICAL
Slide 47
Runtime
Example Programs
Slide 50
Slide 51
Slide 52
Slide 53
Slide 54
Slide 55
Slide 56
Slide 57
THREADPRIVATE
In Action
Flow
SCHEDULE
STATIC
DYNAMIC
GUIDED
ORDERED
FLUSH
routines
Performance
Bugs
PSE
Linux
Slide 72
Slide 73
Slide 74
Summary
Further
Title
Slide 2
Slide 3
Slide 4
Slide 5
Slide 6
Slide 7
Slide 8
Ack
Shared Memory
DM
MPMD
MPI
Timeline
Tpic
Basics
Minimal
Init
COMM
size
rank
exit
hello
Comms
Datatypes
Messages
P2PC
SyncAsync
MPI_Send
Sends
caveats
Perf
MPI_Recv
more recv
Restrictions
Ping-Pong
Agenda
BLT
Latency graphs
Bandwidth graphs
ring
SendRecv
Nonblock
MPI_Isend
MPI_Irecv
no deadlock
other nb
NBSS
implement
MPI_Test
All,Any
Other P2PC
Probes
Persist
Persist2
Constants
Collective
barrier
Bcast
Gather
Scatter
Allgather
VVariants
Scatters
Trees
TreeVar
AAPC
All to All basics
Reductions
Userdef
Reduce
Allreduce
Reduce-Scatter
Prefix
MPI_Scan
Agenda
Slide 2
Slide 3
Slide 4
Slide 5
Motivation
What DD
DD example
DD details
extent
contig
vector
indexed
struct
align
address
correct
Creation
equivalent types
match2
count
example
Complex Example
G-C-C
GConstr
OtherGr
Communicators
Inter-Communicators
VT
cartesian
cart functions
ranks
rfunc
shift
part
More functions
Slide 37
Slide 38
runtime
environment
Exception
ExcRout
Profiling
ProfTools
XMPI
XMPIScr
MPE
Jumpshot
Jumpshot 2
Jumpshot 3
Slide 1
Slide 2
Slide 3
Slide 4
Slide 5
Slide 6
Slide 7
Slide 8
Slide 9
Slide 10
Slide 11
Slide 12
Slide 13
Slide 14
Slide 15
Slide 16
Slide 17
Slide 18
Slide 19
Slide 20
Slide 21
Slide 22
Slide 23
Slide 24
Slide 25
Slide 26
Slide 27
Slide 28
Slide 29
Slide 30
Slide 31
Slide 32
Slide 33
Slide 34
Slide 35
Slide 36
Slide 37
Slide 38
Slide 39
Slide 40
Slide 41
Slide 42
Slide 43
Slide 44
Slide 45
Slide 46
Slide 47
Slide 48
Slide 49
Slide 50
Slide 51
Slide 52
Slide 53
Slide 54
Slide 55
Slide 56
Slide 57
Slide 58
Slide 59
Slide 60
Slide 61
Slide 62
Slide 63
Slide 64
Performance Models
Performance Rules
Performance Tuning
PortablePerf
Programming in Parallel
Problem
Options
Slide 72
Slide 73
Slide 74
Slide 75
Slide 76
Slide 77
Slide 78
Slide 79
Slide 80
Slide 81
Existing
3rd party libraries
LinAlg
Graph & Mesh
Ownlib
