Efficient I/O for Computational Grid Applications
|
|
- Alberta Gilmore
- 5 years ago
- Views:
Transcription
1 Efficient I/O for Computational Grid Applications Ron Oldfield hd. Thesis Defense Department of Computer cience, Dartmouth College May 5, 2003 Committee: David Kotz (chair), Thomas Cormen, Robert Gray, and David Womble Armada p.
2 Computational Grids Networks of geographically ributed heterogeneous systems and devices Data-intensive scientific applications Access large remote datasets (terabyte petabyte) Datasets often need pre/post-processing Often computationally intensive Examples Climate modeling Astronomy Computational biology High-energy physics Armada p.2
3 The Armada Framework Application deploys a graph of ributed objects (ships) Requests cause pipelined data flow through graph Graph has two inct portions: frag replacements from the data provider (describes layout of data set) from the application-programmer (pre/post-processing) client processors M filt rep storage servers from application from data provider Armada p.3
4 The Armada Framework Application deploys a graph of ributed objects (ships) Requests cause pipelined data flow through graph Graph has two inct portions: frag replacements from the data provider (describes layout of data set) from the application-programmer (pre/post-processing) client processors Requests M filt rep storage servers from application from data provider Armada p.3
5 The Armada Framework Application deploys a graph of ributed objects (ships) Requests cause pipelined data flow through graph Graph has two inct portions: frag replacements from the data provider (describes layout of data set) from the application-programmer (pre/post-processing) client processors Data (read) M filt rep storage servers from application from data provider Armada p.3
6 The Armada Framework Application deploys a graph of ributed objects (ships) Requests cause pipelined data flow through graph Graph has two inct portions: frag replacements from the data provider (describes layout of data set) from the application-programmer (pre/post-processing) client processors Data (write) M filt rep storage servers from application from data provider Armada p.3
7 Armada Armada is not a data storage system. Armada is not a parallel system. The data ments that make up a data set are stored in conventional data servers as s, databases, or the like. The Armada graph encodes most functionality provided by the I/O system: programmers interface, data layout, caching and prefetching policies, interfaces to heterogeneous data servers. Armada p.4
8 Armada can... With Armada, one can... build a graph for parallel access to a group of legacy s, present many similar data sets through a standard interface, and provide transparent access to derived virtual data either cached or calculated as needed. Armada p.5
9 Restructuring roblems with the example application: otential bottlenecks in composed graph original graph restricts placement alternatives for filter ments client processors Original graph storage servers frag bottleneck replacements M filt rep Restructured graph client processors rep M rep rep M storage servers filt filt filt filt from application from data providerbottleneck from application from data provider Armada restructures original graph to improve data flow. Armada p.6
10 lacement After restructuring:. Armada deploys ships to appropriate administrative domains to optimize data flow, then 2. domain-level resource manager decides placement of individual ships. client domain rep rep rep M M server domain filt filt filt filt G E server domain 2 Armada p.7
11 lacement After restructuring:. Armada deploys ships to appropriate administrative domains to optimize data flow, then 2. domain-level resource manager decides placement of individual ships. client domain rep rep rep M M server domain filt filt filt filt G E server domain 2 Armada p.7
12 Talk Outline Introduction Framework details hips Graph Representation Restructuring graphs to improve data flow artitioning graphs and placing ships Experiments Conclusion Armada p.8
13 hips Armada includes a rich set of extensible ship classes. Armada hips tructural Non- tructural Distribute (partition, select, copy) Merge Data rocessing Optimization Filter (>, <, =) Transform (FFT, unit conversion) Reduce (min, max, sum) ermute (sort, transpose) Cache refetch Interface Client (Matrix, Line, tring, stdio) torage (File, Query) Armada p.9
14 hips Armada includes a rich set of extensible ship classes. Armada hips tructural Non- tructural Distribute (partition, select, copy) Merge Data rocessing Optimization frag replacements Interface Filter (>, <, =) Transform (FFT, unit conversion) Reduce (min, max, sum) ermute (sort, transpose) Cache refetch Client (Matrix, Line, tring, stdio) torage (File, Query) Distribute ships partition requests or data to multiple output streams. R 2 3 Armada p.9
15 hips Armada includes a rich set of extensible ship classes. Armada hips tructural Non- tructural Distribute (partition, select, copy) frag replacements Merge Data rocessing Optimization Merge R Filter (>, <, =) Transform (FFT, unit conversion) Reduce (min, max, sum) ermute (sort, transpose) Cache refetch Interface 2 3 Client (Matrix, Line, tring, stdio) torage (File, Query) Merge ships interleave requests or data from multiple input streams. R R 2 R 3 Armada p.9
16 hips Armada includes a rich set of extensible frag replacements ship classes. Armada hips tructural Non- tructural Data Distribute (partition, select, copy) rocessing Merge Data rocessing Optimization Interface Filter (>, <, =) Transform (FFT, unit conversion) Reduce (min, max, sum) R R 2 R 3 ermute (sort, transpose) Cache refetch Client (Matrix, Line, tring, stdio) 2 torage (File, Query) 3 Data-processing ships manipulate data, either individually, or in groups as it passes through the ship. R Armada p.9
17 hips Armada includes a rich set of extensible ship classes. Armada hips tructural Non- tructural frag replacements Distribute (partition, select, copy) Optimization Merge Data rocessing Optimization Interface Filter (>, <, =) Transform (FFT, unit conversion) Reduce (min, max, sum) R R 2 R 3 ermute (sort, transpose) Cache refetch Client (Matrix, Line, tring, stdio) 2 torage (File, Query) 3 Optimization ships improve I/O performance through latency-reduction techniques like caching and prefetching. R Armada p.9
18 hips R 2 R 3 Armada includes a rich set of extensible frag replacements ship classes. Armada hips tructural Non- tructural Distribute (partition, select, copy) Merge Data rocessing Optimization Interface Interface Client-interface ships convert method calls to a set of requests for data. 2 3 Filter (>, <, =) Transform (FFT, unit conversion) R R 2 R 3 R 2 R Reduce (min, max, sum) ermute (sort, transpose) Cache refetch Client (Matrix, Line, tring, stdio) torage (File, Query) 2 3 R torage-interface ships access storage devices to process requests. R Armada p.9
19 roperties of hips roperties of ships are used by restructuring and placement algorithms assigned by the programmer encoded in the ship s definition roperties identify whether a ship is data- or request-equivalent increases or decreases data flow, is parallelizable Armada p.0
20 Request and Data Equivalent hips A sequence A is equivalent to sequence B (denoted A B) if B is a permutation of A, or if B is a set of subsequences that partition A. Examples: {, 2, 3, 4, 5} {2, 3, 5,, 4} {, 2, 3, 4, 5} {{2, 3}, {, 4, 5}} {, 2, 3, 4, 5} {{2, 3}, {, 5, 4}} In other words, order does not matter. Armada p.
21 Request and Data Equivalent hips A sequence A is equivalent to sequence B (denoted A B) if B is a permutation of A, or if B is a set of subsequences that partition A. A request-equivalent ship produces request sequence equivalent to its input. A data-equivalent ship produces data sequence equivalent to its input. Most structural ships are both request and data-equivalent. Armada p.
22 Request and Data Equivalent hips A sequence A is equivalent to sequence B (denoted A B) if B is a permutation of A, or if B is a set of subsequences frag replacements that partition A. Distribution ships partition requests or data, 2, and 3 are subsequences of R. R {, 2, 3 } R 2 3 Armada p.
23 Request and Data Equivalent hips A sequence A is equivalent to sequence B (denoted A B) if B is a permutation of A, or if B is a set of subsequences frag replacements that partition A. Merge ships interleave requests or data R, R 2, and R 3 are subsequences of. {R, R 2, R 3 } R R 2 R 3 Armada p.
24 hips that Change Data Flow Data-reducer: a ship that decreases the data flow filter compress reduce (min, max, sum) Data-increaser: a ship that increases the data flow cache decompress Armada p.2
25 arallelizable hips arallelizable: a ship that can transform into multiple ships process requests and data in parallel parallelized by swapping with structural ships parallel version produces equivalent output Types of parallelizable ships: replicatable, recursive Armada p.3
26 arallelizable hips arallelizable: a ship that can transform into multiple ships process requests and data in parallel parallelized by swapping with structural ships parallel version produces frag replacements equivalent output mentsfrag replacements Types of parallelizable ships: replicatable, recursive Right-parallelizable A A R A B 2 R B A 2 R M B A 2 Original 3 A 3 Replicated A Recursed 3 Armada p.3
27 arallelizable hips arallelizable: a ship that can transform into multiple ships process requests and data in parallel parallelized by swapping with structural ships ments parallel version produces frag replacements equivalent output frag replacements Types of parallelizable ships: replicatable, recursive Left-parallelizable R R 2 R 3 B A Original T R R 2 R 3 A A A B Replicated T R R 2 R 3 A A B M A Recursed T Armada p.3
28 Graph Representation We use a series-parallel tree (-tree) to describe the composition of an Armada graph. ents frag replacements yntactically easy to describe (we use XML) Easy to manipulate internally M filt rep essors ervers lication rovider ite) M filt rep 0 client processors storage servers from application from data provider Data (write) 0 Armada p.4
29 Graph Representation We use a series-parallel tree (-tree) to describe the composition of an Armada graph. ents frag replacements yntactically easy to describe (we use XML) Easy to manipulate internally M filt rep essors ervers lication rovider ite) M filt rep 0 client processors storage servers from application from data provider Data (write) 0 Armada p.4
30 Graph Representation We use a series-parallel tree (-tree) to describe the composition of an Armada graph. ents frag replacements yntactically easy to describe (we use XML) Easy to manipulate internally M filt rep essors ervers lication rovider ite) M filt rep 0 client processors storage servers from application from data provider Data (write) 0 Armada p.4
31 Graph Representation We use a series-parallel tree (-tree) to describe the composition of an Armada graph. ents frag replacements yntactically easy to describe (we use XML) Easy to manipulate internally M filt rep essors ervers lication rovider ite) M filt rep 0 client processors storage servers from application from data provider Data (write) 0 Armada p.4
32 Graph Representation We use a series-parallel tree (-tree) to describe the composition of an Armada graph. ents frag replacements yntactically easy to describe (we use XML) Easy to manipulate internally M filt essors ervers lication rovider ite) M filt rep client processors storage servers from application from data provider Data (write) rep Armada p.4
33 Graph Representation We use a series-parallel tree (-tree) to describe the composition of an Armada graph. ents frag replacements yntactically easy to describe (we use XML) Easy to manipulate internally essors ervers lication rovider ite) M filt rep client processors storage servers from application from data provider Data (write) M filt rep Armada p.4
34 Graph Representation We use a series-parallel tree (-tree) to describe the composition of an Armada graph. ents frag replacements yntactically easy to describe (we use XML) Easy to manipulate internally essors ervers lication rovider ite) M filt rep client processors storage servers from application from data provider Data (write) M filt rep Armada p.4
35 Graph Restructuring Goals: remove bottlenecks (increase parallelism) allow effective placement of ships We restructure by swapping adjacent ships in the -tree increase parallelism by swapping parallelizable ships with structural ships reduce network traffic on slow links by moving data-reducing ships toward data source, moving data-increasing ships toward data dest Armada p.5
36 The Restruct Algorithm The RETRUCT algorithm traverses the -tree (depth-first) from node N, revisiting when necessary (all series and parallel nodes are initially marked dirty).. if N is a leaf or clean (base case) (a) return 2. else if N is a parallel node (a) RETRUCT each child of N 3. else if N is a series node (a) create a new series node (b) while N has children i. child remove leftmost child of N ii. append child to iii. LIDE child left (c) N 4. mark N clean Armada p.6
37 The Restruct Algorithm The RETRUCT algorithm traverses the -tree (depth-first) from node N, revisiting when necessary (all series and parallel nodes are initially marked dirty).. if N is a leaf or clean (base case) (a) return 2. else if N is a parallel node frag replacements (a) RETRUCT each child of N 3. else if N is a series node (a) create a new series node (b) while N has children i. child remove leftmost child of N ii. append child to iii. LIDE child left (c) N 4. mark N clean Append B to N B C A D Armada p.6
38 The Restruct Algorithm The RETRUCT algorithm traverses the -tree (depth-first) from node N, revisiting when necessary (all series and parallel nodes are initially marked dirty).. if N is a leaf or clean (base case) (a) return 2. else if N is a parallel node frag replacements (a) RETRUCT each child of N 3. else if N is a series node (a) create a new series node (b) while N has children i. child remove leftmost child of N ii. append child to iii. LIDE child left (c) N 4. mark N clean Append B to N B C A D Armada p.6
39 The Restruct Algorithm The RETRUCT algorithm traverses the -tree (depth-first) from node N, revisiting when necessary (all series and parallel nodes are initially marked dirty).. if N is a leaf or clean (base case) (a) return 2. else if N is a parallel node frag replacements (a) RETRUCT each child of N 3. else if N is a series node (a) create a new series node (b) while N has children i. child remove leftmost child of N ii. append child to iii. LIDE child left (c) N 4. mark N clean Append C to N B C A D Armada p.6
40 The Restruct Algorithm The RETRUCT algorithm traverses the -tree (depth-first) from node N, revisiting when necessary (all series and parallel nodes are initially marked dirty).. if N is a leaf or clean (base case) (a) return 2. else if N is a parallel node frag replacements (a) RETRUCT each child of N 3. else if N is a series node (a) create a new series node (b) while N has children i. child remove leftmost child of N ii. append child to iii. LIDE child left (c) N 4. mark N clean Append C to N B C A D Armada p.6
41 The Restruct Algorithm The RETRUCT algorithm traverses the -tree (depth-first) from node N, revisiting when necessary (all series and parallel nodes are initially marked dirty).. if N is a leaf or clean (base case) (a) return 2. else if N is a parallel frag node replacements (a) RETRUCT each child of N 3. else if N is a series node (a) create a new series node (b) while N has children i. child remove leftmost child of N ii. append child to iii. LIDE child left (c) N lide C left N B C A D swap? 4. mark N clean Armada p.6
42 The Restruct Algorithm The RETRUCT algorithm traverses the -tree (depth-first) from node N, revisiting when necessary (all series and parallel nodes are initially marked dirty).. if N is a leaf or clean (base case) (a) return 2. else if N is a parallel node frag replacements (a) RETRUCT each child of N 3. else if N is a series node (a) create a new series node (b) while N has children i. child remove leftmost child of N ii. append child to iii. LIDE child left (c) N 4. mark N clean Append A to N B C A D Armada p.6
43 The Restruct Algorithm The RETRUCT algorithm traverses the -tree (depth-first) from node N, revisiting when necessary (all series and parallel nodes are initially marked dirty).. if N is a leaf or clean (base case) (a) return 2. else if N is a parallel node frag replacements (a) RETRUCT each child of N 3. else if N is a series node (a) create a new series node (b) while N has children i. child remove leftmost child of N ii. append child to iii. LIDE child left (c) N 4. mark N clean Append A to N B C A D Armada p.6
44 The Restruct Algorithm The RETRUCT algorithm traverses the -tree (depth-first) from node N, revisiting when necessary (all series and parallel nodes are initially marked dirty).. if N is a leaf or clean (base case) (a) return 2. else if N is a parallel frag node replacements (a) RETRUCT each child of N 3. else if N is a series node (a) create a new series node (b) while N has children i. child remove leftmost child of N ii. append child to iii. LIDE child left (c) N lide A left N B C A D swap? 4. mark N clean Armada p.6
45 The Restruct Algorithm The RETRUCT algorithm traverses the -tree (depth-first) from node N, revisiting when necessary (all series and parallel nodes are initially marked dirty).. if N is a leaf or clean (base case) (a) return 2. else if N is a parallel frag node replacements (a) RETRUCT each child of N 3. else if N is a series node (a) create a new series node (b) while N has children i. child remove leftmost child of N ii. append child to iii. LIDE child left (c) N lide A left N B A C D swap? 4. mark N clean Armada p.6
46 The Restruct Algorithm The RETRUCT algorithm traverses the -tree (depth-first) from node N, revisiting when necessary (all series and parallel nodes are initially marked dirty).. if N is a leaf or clean (base case) (a) return 2. else if N is a parallel node frag replacements (a) RETRUCT each child of N 3. else if N is a series node (a) create a new series node (b) while N has children i. child remove leftmost child of N ii. append child to iii. LIDE child left (c) N 4. mark N clean Append D to N A B C D Armada p.6
47 The Restruct Algorithm The RETRUCT algorithm traverses the -tree (depth-first) from node N, revisiting when necessary (all series and parallel nodes are initially marked dirty).. if N is a leaf or clean (base case) (a) return 2. else if N is a parallel node frag replacements (a) RETRUCT each child of N 3. else if N is a series node (a) create a new series node (b) while N has children i. child remove leftmost child of N ii. append child to iii. LIDE child left (c) N 4. mark N clean A B C D Append D to N Armada p.6
48 The Restruct Algorithm The RETRUCT algorithm traverses the -tree (depth-first) from node N, revisiting when necessary (all series and parallel nodes are initially marked dirty).. if N is a leaf or clean (base case) (a) return 2. else if N is a parallel frag node replacements (a) RETRUCT each child of N 3. else if N is a series node (a) create a new series node (b) while N has children i. child remove leftmost child of N ii. append child to iii. LIDE child left (c) N A B C D lide D left swap? N 4. mark N clean Armada p.6
49 The Restruct Algorithm The RETRUCT algorithm traverses the -tree (depth-first) from node N, revisiting when necessary (all series and parallel nodes are initially marked dirty).. if N is a leaf or clean (base case) (a) return 2. else if N is a parallel frag node replacements (a) RETRUCT each child of N 3. else if N is a series node (a) create a new series node (b) while N has children i. child remove leftmost child of N ii. append child to iii. LIDE child left (c) N 4. mark N clean N N A B C D Assign to N Armada p.6
50 wapping hips Conditions for swapping two series-connected ships (labeled A and B) A and B are commutative (A or B is request-equivalent and A or B is data-equivalent) swapping A and B is beneficial to the application (see next slide), and the graph resulting from a swap is an -DAG (we allow four configurations). Armada p.7
51 wapping hips Conditions for swapping two series-connected ships (labeled A and B) A and B are commutative (A or B is request-equivalent and A or B is data-equivalent) swapping A and B is beneficial to the application (see next slide), and the graph resulting from a swap is an -DAG (we allow four configurations). ents frag replacements (A) Non-structural, (B) Non-structural A B A B B A B A Armada p.7
52 wapping hips Conditions for swapping two series-connected ships (labeled A and B) A and B are commutative (A or B is request-equivalent and A or B is data-equivalent) swapping A and B is beneficial to the application (see next slide), and the graph resulting from a swap is an -DAG (we allow four configurations). ents frag replacements (A) Non-structural, (B) Distribution, arallel node A B A B B A A A B A A A ARALLELIZE right Armada p.7
53 wapping hips Conditions for swapping two series-connected ships (labeled A and B) A and B are commutative (A or B is request-equivalent and A or B is data-equivalent) swapping A and B is beneficial to the application (see next slide), and the graph resulting from a swap is an -DAG (we allow four configurations). ents frag replacements arallel node, (A) Merge, (B) Non-structural A B A B B B B A B B B A ARALLELIZE left Armada p.7
54 wapping hips Conditions for swapping two series-connected ships (labeled A and B) A and B are commutative (A or B is request-equivalent and A or B is data-equivalent) swapping A and B is beneficial to the application (see next slide), and the graph resulting from a swap is an -DAG (we allow four configurations). ents frag replacements arallel node, (A) Merge, (B) Distrib, arallel node A B A B B B B A A A B B B A A A ARALLELIZE right and left Armada p.7
55 Beneficial wap A swap is deemed beneficial if it increases parallelism, moves a data-reducing ship closer to the data source, or moves a data-increasing ship closer to data destination. Algorithm to decide a beneficial swap of adjacent ships A and B. Assign a preferred direction to each ship ( for right, for left, or 0) Merge ships prefer to go right (increase parallelism) Distribution ships prefer to go left (increase parallelism) Data-reducing ships prefer to swap toward the data source Data-increasing ships prefer to swap toward the data destination 2. return true if preferred direction of A is greater than preferred direction of B 3. else return f alse Armada p.8
56 Restructuring the Example Graph frag replacements M filt rep M filt rep Armada p.9
57 Restructuring the Example Graph frag replacements M filt rep swap swap M filt rep Armada p.9
58 Restructuring the Example Graph frag replacements M rep filt filt filt M rep filt Armada p.9
59 Restructuring the Example Graph frag replacements M rep filt swap filt swap swap filt M rep swap filt Armada p.9
60 Restructuring the Example Graph rep M filt filt filt filt frag replacements rep M filt filt filt filt Armada p.9
61 Restructuring the Example Graph rep M filt filt filt filt swap frag replacements rep M filt filt filt filt swap Armada p.9
62 Restructuring the Example Graph rep rep rep M M filt filt filt filt frag replacements rep rep rep M M filt filt filt filt Armada p.9
63 lacement Hierarchical graph partitioning. artition the ships into k sets (each set represents an administrative domain). 2. artition the ships within each domain to processors provided by domain-level schedulers. The Graph artitioning roblem Given graph G(V, E) with weighted vertices and weighted edges, partition the vertices into k sets in such a way to balance the sum of the vertices and to minimize the weights of the edge crossings between sets (N-hard [Garey et al., 976]). Armada p.20
64 artitioning an Armada Graph Chaco Graph artitioning oftware [Hendrickson and Leland, NL] Algorithm for placement of Armada ships. Construct model from -tree (a) Assign edge weights (b) Assign vertex weights 2. partition graph (using CHACO) 3. for each domain (a) request procs from domain (b) partition sub-graph G E Armada p.2
65 artitioning an Armada Graph Chaco Graph artitioning oftware [Hendrickson and Leland, NL] Algorithm for placement of Armada ships. Construct model from -tree (a) Assign edge weights (b) Assign vertex weights 2. partition graph (using CHACO) for each domain (a) request procs from domain (b) partition sub-graph G E Armada p.2
66 artitioning an Armada Graph Chaco Graph artitioning oftware [Hendrickson and Leland, NL] Algorithm for placement of Armada ships. Construct model from -tree (a) Assign edge weights (b) Assign vertex weights 2. partition graph (using CHACO) 3. for each domain (a) request procs from domain (b) partition sub-graph G E Armada p.2
67 artitioning an Armada Graph Chaco Graph artitioning oftware [Hendrickson and Leland, NL] Algorithm for placement of Armada ships. Construct model from -tree (a) Assign edge weights (b) Assign vertex weights 2. partition graph (using CHACO) 3. for each domain (a) request procs from domain client domain server domain (b) partition sub-graph G server domain 2 E Armada p.2
68 artitioning an Armada Graph Chaco Graph artitioning oftware [Hendrickson and Leland, NL] Algorithm for placement of Armada ships. Construct model from -tree (a) Assign edge weights (b) Assign vertex weights 2. partition graph (using CHACO) 3. for each domain (a) request procs from domain client domain server domain (b) partition sub-graph G server domain 2 E Armada p.2
69 Experiments Evaluate performance benefit of restructuring and placement Representative application lacement considerations File copy and permutation Third-party transfers Data permutations Number of processors required by Armada eismic processing C++ interface Recursive filter Latency effects Armada p.22
70 Representative Application Examined four configurations of the example application with a filter that removed exactly 50% of the data. ements application ata provider same host ferent hosts lan M filt rep lan2 frag replacements from application from data provider same host different hosts lan M filt rep lan2 lan3 lan3 ements application ata provider ferent hosts lan rep rep rep (a) orig M M lan2 filt filt filt filt same host frag replacements from application from data provider same host lan rep rep rep (b) orig2 lan2 M M different hosts filt filt filt filt lan3 (c) restruct lan3 (d) restruct2 Armada p.23
71 Experiment etup The area between the blobs represents the WAN each LAN connected tofrag the replacements WAN by single router each WAN link has limited capacity lan WAN lan2 lan3 Ran experiments on the Emulab Network Testbed Three LANs, each with... Five 850 MHz entium III processors 00 Mbps switched network (0.5 msec latency) WAN consisted of... Three network links with 2.0 msec latency Bandwidth ranged from 2 to 00 Mbps Armada p.24
72 Results: Effective Throughput Effective Throughput (Mbit/sec) orig orig2 restruct restruct2 WAN bandwidth 2*WAN bandwidth Total client/server WAN bandwidth (Mbit/sec) Armada p.25
73 Results: Effective Throughput orig Effective Throughput (Mbit/sec) orig orig2 restruct restruct2 WAN bandwidth 2*WAN bandwidth Total client/server WAN bandwidth (Mbit/sec) Armada p.25
74 Results: Effective Throughput orig2 Effective Throughput (Mbit/sec) orig orig2 restruct restruct2 WAN bandwidth 2*WAN bandwidth Total client/server WAN bandwidth (Mbit/sec) Armada p.25
75 Results: Effective Throughput restruct same host Effective Throughput (Mbit/sec) orig orig2 restruct restruct2 WAN bandwidth 2*WAN bandwidth different hosts Total client/server WAN bandwidth (Mbit/sec) Armada p.25
76 Results: Effective Throughput restruct2 different hosts Effective Throughput (Mbit/sec) orig orig2 restruct restruct2 WAN bandwidth 2*WAN bandwidth same host Total client/server WAN bandwidth (Mbit/sec) Armada p.25
77 File Copy and ermutation Copy ributed from lan to ributed on lan0. ements Input Output disk disk2 disk3 disk4 frag replacements 2 ments Input Output disk disk2 disk3 disk swrt dec cmp srd dec dec dec dec srd srd srd srd swrt swrt swrt swrt swrt cmp cmp cmp cmp cmp Input Output disk disk disk2 disk3 disk disk2 8 8 swrt cmp Armada p.26
78 File Copy and ermutation ementscopy ributed from lan to ributed on lan0. Input Output disk disk2 disk3 disk4 np=all 2 frag replacements ments Input Output disk disk2 disk3 disk np=all swrt dec cmp srd dec dec dec dec srd srd srd srd swrt swrt swrt swrt swrt cmp cmp cmp cmp cmp Input Output disk disk disk2 disk3 disk disk2 8 8 swrt cmp Armada p.26
79 File Copy and ermutation ementscopy ributed from lan to ributed on lan0. Input Output disk disk2 disk3 disk4 np= 2 frag replacements ments Input Output disk disk2 disk3 disk np= dec dec dec dec swrt dec cmp srd srd srd srd srd swrt swrt swrt swrt swrt cmp cmp cmp cmp cmp Input Output disk disk disk2 disk3 disk disk2 8 8 swrt cmp Armada p.26
80 File Copy and ermutation ementscopy ributed from lan to ributed on lan0. Input Output disk disk2 disk3 disk4 np=0 2 frag replacements ments Input Output disk disk2 disk3 disk np=0 swrt dec cmp srd dec dec dec dec srd srd srd srd swrt swrt swrt swrt swrt cmp cmp cmp cmp cmp Input Output disk disk disk2 disk3 disk disk2 8 8 swrt cmp Armada p.26
81 Results (effective throughput) Effective Throughput (Mbit/sec) ingle Original Restructured WAN bandwidth WAN bandwidth (Mbit/sec) Armada p.27
82 Results (different placements) Effective Throughput (Mbit/sec) Compressed np=0 Compressed np= Compressed np=all WAN bandwidth WAN bandwidth (Mbit/sec) Armada p.28
83 ost-tack eismic Imaging roperties of seismic processing Compute intensive Large (terabyte) data sets Collections of s (> K) Each contains a set of traces (recorded pressure waves) reprocessing tack co-located traces FFT time traces Distribute frequencies to compute nodes Armada p.29
84 Constructing the Armada Graph lacements ω Row Column Tower X Y Base nodes interface with Armada Connect with the data provider and describe compute node ribution // called by all nodes, //... node0 gets graph from data provider //... constructor decomposes data (3D block decomposition) TraceDataset dataset(comm, pmesh, providerurl) Armada p.30
85 Constructing the Armada Graph fft stk lacements Column Tower ω Row X Compute partition. tdst torage servers.. Y Base nodes interface with Armada smg app-specific from data-provider Connect with the data provider and describe compute node ribution // called by all nodes, //... node0 gets graph from data provider //... constructor decomposes data (3D block decomposition) TraceDataset dataset(comm, pmesh, providerurl) Armada p.30
86 Constructing the Armada Graph fft stk lacements Column Tower ω Row X Compute partition. tdst torage servers.. Y Base nodes interface with Armada smg app-specific from data-provider Append operators. // called by node0 dataset.appendop(new FFTOp()); Armada p.30
87 Constructing the Armada Graph stk lacements Column Tower ω Row X Compute partition. tdst fft torage servers.. Y Base nodes interface with Armada smg app-specific from data-provider Append operators. // called by node0 dataset.appendop(new FFTOp()); dataset.appendop(new tackop()); Armada p.30
88 Constructing the Armada Graph lacements Column Tower ω Row X Compute partition. tdst fft stk torage servers.. Y Base nodes interface with Armada smg app-specific from data-provider Append operators. // called by node0 dataset.appendop(new FFTOp()); dataset.appendop(new tackop()); Armada p.30
89 Constructing the Armada Graph lacements Column Tower ω Row X Compute partition. tdst fft stk torage servers.. Y Base nodes interface with Armada smg app-specific from data-provider Restructure and Deploy the Armada graph. // called by node0 dataset.open(); Armada p.30
90 Constructing the Armada Graph lacements Column Tower ω Row X Compute partition. tdst fft stk torage servers.. Y Base nodes interface with Armada smg app-specific from data-provider Restructure and Deploy the Armada graph. // called by node0 dataset.open(); //... connect app-specific with data-provider portion Armada p.30
91 Constructing the Armada Graph lacements Column Tower ω Row X Compute partition fft smg. fft smg fft smg fft smg tdst tdst smg smg torage servers stk stk stk stk.. Y Base nodes interface with Armada app-specific from data-provider Restructure and Deploy the Armada graph. // called by node0 dataset.open(); //... connect app-specific with data-provider portion //... restructure graph Armada p.30
92 Constructing the Armada Graph lacements Column Tower ω Row X Compute partition fft smg. fft smg fft smg fft smg tdst tdst smg smg torage servers stk stk stk stk.. Y Base nodes interface with Armada app-specific from data-provider Restructure and Deploy the Armada graph. // called by node0 dataset.open(); //... construct entire Armada graph //... restructure graph //... assign placement Armada p.30
93 Constructing the Armada Graph lacements Column Tower ω Row X Compute partition fft smg. fft smg fft smg fft smg tdst tdst smg smg torage servers stk stk stk stk.. Y Base nodes interface with Armada app-specific from data-provider Restructure and Deploy the Armada graph. // called by node0 dataset.open(); //... construct entire Armada graph //... restructure graph //... assign placement //... deploy Armada p.30
94 Constructing the Armada Graph lacements Column Tower ω Row X Compute partition fft smg. fft smg fft smg fft smg tdst tdst smg smg torage servers stk stk stk stk.. Y Base nodes interface with Armada app-specific from data-provider Collectively read dataset. // called by all procs int size=dataset.getlocalize(); float *data = new float[size]; dataset.read(data); // do computation... Armada p.30
95 Experiment etup frag replacements Compute partition torage servers Original. tdst fft stk.. smg app-specific from data-provider Compute partition torage servers Restructured. fft fft fft fft smg smg smg smg tdst tdst smg smg stk stk stk stk.. Armada p.3
96 Results (effective throughput) 40 Effective Throughput (Mbit/sec) WAN bandwidth Original Restructured WAN bandwidth (Mbit/sec) Armada p.32
97 Results (different latencies) 40 Effective Throughput (Mbit/sec) WAN bandwidth 5 Original lat=0ms Original lat=25ms 0 Original lat=50ms Restruct lat=0ms 5 Restruct lat=25ms Restruct lat=50ms WAN bandwidth (Mbit/sec) Armada p.33
98 Related Work arallel processing of I/O streams 2 [Messerli, 999] data-flow model with automatic parallelization DataCutter [pencer et al., 2002] component-based, analytic model to decide parallelization Armada does not force the whole application into a data-flow model Armada widens data flow for parallel clients and parallel servers Operation re-ordering to improve data flow, e.g., in databases dquob [plale et al. 2000] optimize query tree to move high-filtering portions close to data exploit well-defined properties associated with query processing Armada provides a more general approach Armada p.34
99 Future Work Other Applications fmri application (time-series analysis of brain data) Can components be reused between applications? Modifications to BENEFICIAL and COMMUTATIVE Non-greedy methods Analytic models to approximate benefit lacement incorporate domain-specific information into the partitioner (compute capacity, memory capacity, etc...) dynamic re-deployment when network conditions change Tuning for cluster computing (in addition to the grid) Armada p.35
100 ummary The Armada framework data provider can describe complex ributed data sets application describes processing required before computation data-flow model provides a latency-tolerant approach Restructuring algorithm arranges graph to provide end-to-end parallel I/O enables effective placement of data-processing components lacement domain assignments to minimize data flow. host assignments based on administrative domain policies. Experiments demonstrate good performance in multiple environments. Armada p.36
101 Efficient I/O for Computational Grid Applications Ron Oldfield Department of Computer cience, Dartmouth College dfk/armada/ upported by andia National Laboratories under contract DOE-AV684. Armada p.37
A Novel Decode-Aware Compression Technique for Improved Compression and Decompression
A Novel Decode-Aware Compression Technique for Improved Compression and Decompression J. Suresh Babu, K. Tirumala Rao & P. Srinivas Department Of Electronics & Comm. Engineering, Nimra College of Engineering
More informationFast Floating Point Compression on the Cell BE Processor
Fast Floating Point Compression on the Cell BE Processor Ajith Padyana, T.V. Siva Kumar, P.K.Baruah Sri Satya Sai University Prasanthi Nilayam - 515134 Andhra Pradhesh, India ajith.padyana@gmail.com, tvsivakumar@gmail.com,
More informationGOLOMB Compression Technique For FPGA Configuration
GOLOMB Compression Technique For FPGA Configuration P.Hema Assistant Professor,EEE Jay Shriram Group Of Institutions ABSTRACT Bit stream compression is important in reconfigurable system design since it
More informationThe system design must obey these constraints. The system is to have the minimum cost (capital plus operating) while meeting the constraints.
Computer Algorithms in Systems Engineering Spring 2010 Problem Set 6: Building ventilation design (dynamic programming) Due: 12 noon, Wednesday, April 21, 2010 Problem statement Buildings require exhaust
More informationLossless Comparison of Nested Software Decompositions
Lossless Comparison of Nested Software Decompositions Mark Shtern and Vassilios Tzerpos York University Toronto, Ontario, Canada {mark,bil}@cse.yorku.ca Abstract Reverse engineering legacy software systems
More informationWHEN WILL YOUR MULTI-TERABYTE IMAGERY STOP REQUIRING YOU TO BUY MORE DATA STORAGE?
PRODUCT BROCHURE WHEN WILL YOUR MULTI-TERABYTE IMAGERY STOP REQUIRING YOU TO BUY MORE DATA STORAGE? WHEN YOU START COMPRESSING IT TO HEXAGON GEOSPATIAL S ECW FORMAT 2 WHEN WILL YOUR MULTI-TERABYTE IMAGERY
More informationReduction of Bitstream Transfer Time in FPGA
IOSR Journal of Electronics and Communication Engineering (IOSR-JECE) e-issn: 2278-2834,p- ISSN: 2278-8735.Volume 9, Issue 2, Ver. III (Mar - Apr. 2014), PP 82-86 Reduction of Bitstream Transfer Time in
More informationSIDDHARTH INSTITUTE OF ENGINEERING & TECHNOLOGY :: PUTTUR (AUTONOMOUS) Siddharth Nagar, Narayanavanam Road QUESTION BANK (DESCRIPTIVE)
Subject with Code : Data Structures(16MC806) Course & Specialization: MCA UNIT I Sorting, Searching and Directories 1. Explain how to sort the elements by using insertion sort and derive time complexity
More informationComputing s Energy Problem:
Computing s Energy Problem: (and what we can do about it) Mark Horowitz Stanford University horowitz@ee.stanford.edu 1 of 46 Everything Has A Computer Inside 2of 46 The Reason is Simple: Moore s Law Made
More informationVisual Traffic Jam Analysis Based on Trajectory Data
Visual Traffic Jam Analysis Based on Trajectory Data Zuchao Wang, Min Lu, Xiaoru Yuan, Peking University Junping Zhang, Fudan University Huub van de Wetering, Technische Universiteit Eindhoven Introduction
More informationIntroduction to Parallelism in CASTEP
to ism in CASTEP Phil Hasnip August 2016 Recap: what does CASTEP do? CASTEP solves the Kohn-Sham equations for electrons in a periodic array of nuclei: Ĥ k [ρ]ψ bk = E bk ψ bk where particle b has the
More informationDelta Compressed and Deduplicated Storage Using Stream-Informed Locality
Delta Compressed and Deduplicated Storage Using Stream-Informed Locality Philip Shilane, Grant Wallace, Mark Huang, & Windsor Hsu Backup Recovery Systems Division EMC Corporation Motivation and Approach
More informationNaval Postgraduate School, Operational Oceanography and Meteorology. Since inputs from UDAS are continuously used in projects at the Naval
How Accurate are UDAS True Winds? Charles L Williams, LT USN September 5, 2006 Naval Postgraduate School, Operational Oceanography and Meteorology Abstract Since inputs from UDAS are continuously used
More informationVolume A Question No : 1 You can monitor your Steelhead appliance disk performance using which reports? (Select 2)
Volume A~D: 342 Questions Volume A Question No : 1 You can monitor your Steelhead appliance disk performance using which reports? (Select 2) A. Data Store Cost B. Data Store Performance C. Disk Load D.
More informationSearch I. Tuomas Sandholm Carnegie Mellon University Computer Science Department. [Read Russell & Norvig Chapter 3]
Search I Tuomas Sandholm Carnegie Mellon University Computer Science Department [Read Russell & Norvig Chapter 3] Search I Goal-based agent (problem solving agent) Goal formulation (from preferences).
More informationVirtual Breadboarding. John Vangelov Ford Motor Company
Virtual Breadboarding John Vangelov Ford Motor Company What is Virtual Breadboarding? Uses Vector s CANoe product, to simulate MATLAB Simulink models in a simulated or real vehicle environment. Allows
More informationCT PET-2018 Part - B Phd COMPUTER APPLICATION Sample Question Paper
CT PET-2018 Part - B Phd COMPUTER APPLICATION Sample Question Paper Note: All Questions are compulsory. Each question carry one mark. 1. Error detection at the data link layer is achieved by? [A] Bit stuffing
More informationENHANCED PARKWAY STUDY: PHASE 2 CONTINUOUS FLOW INTERSECTIONS. Final Report
Preparedby: ENHANCED PARKWAY STUDY: PHASE 2 CONTINUOUS FLOW INTERSECTIONS Final Report Prepared for Maricopa County Department of Transportation Prepared by TABLE OF CONTENTS Page EXECUTIVE SUMMARY ES-1
More informationExploring the NFL. Introduction. Data. Analysis. Overview. Alison Smith <alison dot smith dot m at gmail dot com>
Exploring the NFL Alison Smith Introduction The National Football league began in 1920 with 12 teams and has grown to 32 teams broken into 2 leagues and 8 divisions.
More informationIntegrating Best of Breed Outage Management Systems with Mobile Data Systems. Abstract
Integrating Best of Breed Outage Management Systems with Mobile Data Systems Donald Shaw Partner ExtenSys Inc. 31 Plymbridge Crescent North York, ON M2P 1P4 Canada Telephone: (416) 481-1546 Fax: (416)
More informationCS Lecture 5. Vidroha debroy. Material adapted courtesy of Prof. Xiangnan Kong and Prof. Carolina Ruiz at Worcester Polytechnic Institute
CS 3353 Lecture 5 Vidroha debroy Material adapted courtesy of Prof. Xiangnan Kong and Prof. Carolina Ruiz at Worcester Polytechnic Institute Searching for a number Find a specific number 91-3 26 54 73
More informationUNIVERSITY OF WATERLOO
UNIVERSITY OF WATERLOO Department of Chemical Engineering ChE 524 Process Control Laboratory Instruction Manual January, 2001 Revised: May, 2009 1 Experiment # 2 - Double Pipe Heat Exchanger Experimental
More informationChapter 6. Analysis of the framework with FARS Dataset
Chapter 6 Analysis of the framework with FARS Dataset. Having represented each phase of the structure with the aid of different data sets at each stage, to support the efficacy of the proposed framework
More informationAGA Swiss McMahon Pairing Protocol Standards
AGA Swiss McMahon Pairing Protocol Standards Final Version 1: 2009-04-30 This document describes the Swiss McMahon pairing system used by the American Go Association (AGA). For questions related to user
More informationWe release Mascot Server 2.6 at the end of last year. There have been a number of changes and improvements in the search engine and reports.
1 We release Mascot Server 2.6 at the end of last year. There have been a number of changes and improvements in the search engine and reports. I ll also be covering some enhancements and changes in Mascot
More informationMeasuring range Δp (span = 100%) Pa
4.4/ RLE 5: Volume-flow controller, continuous How energy efficiency is improved Enables demand-led volume flow control for the optimisation of energy consumption in ventilation systems. Areas of application
More informationInternational Journal of Engineering Trends and Technology (IJETT) Volume 18 Number2- Dec 2014
Compression and Decompression of FPGA Bit Stream Using Bitmask Technique K.Khuresh Gouse 1 N.Chitra 2 K.Maheshwari 3 1 PG Student (M.Tech), 2 Associate Professor, 3 Associate Professor, Dept. of ECE, Gates
More informationDecision Trees. Nicholas Ruozzi University of Texas at Dallas. Based on the slides of Vibhav Gogate and David Sontag
Decision Trees Nicholas Ruozzi University of Texas at Dallas Based on the slides of Vibhav Gogate and David Sontag Announcements Course TA: Hao Xiong Office hours: Friday 2pm-4pm in ECSS2.104A1 First homework
More informationCompression of FPGA Bitstreams Using Improved RLE Algorithm
International Journal of Scientific & Engineering Research, Volume 4, Issue 6, June-2013 1162 Compression of FPGA Bitstreams Using Improved RLE Algorithm P.Hemnath V.Prabhu Abstract - FPGA are configured
More informationIn memory of Dr. Kevin P. Granata, my graduate advisor, who was killed protecting others on the morning of April 16, 2007.
Acknowledgement In memory of Dr. Kevin P. Granata, my graduate advisor, who was killed protecting others on the morning of April 16, 2007. There are many others without whom I could not have completed
More informationOnline Companion to Using Simulation to Help Manage the Pace of Play in Golf
Online Companion to Using Simulation to Help Manage the Pace of Play in Golf MoonSoo Choi Industrial Engineering and Operations Research, Columbia University, New York, NY, USA {moonsoo.choi@columbia.edu}
More information1 PIPESYS Application
PIPESYS Application 1-1 1 PIPESYS Application 1.1 Gas Condensate Gathering System In this PIPESYS Application, the performance of a small gascondensate gathering system is modelled. Figure 1.1 shows the
More informationEfficient Placement of Compressed Code for Parallel Decompression
Efficient Placement of Compressed Code for Parallel Decompression Xiaoke Qin and Prabhat Mishra Department of Computer and Information Science and Engineering University of Florida, Gainesville FL 32611-6120,
More informationAn Efficient Code Compression Technique using Application-Aware Bitmask and Dictionary Selection Methods
An Efficient Code Compression Technique using Application-Aware Bitmask and Selection Methods Seok-Won Seong sseong@cise.ufl.edu Prabhat Mishra prabhat@cise.ufl.edu Department of Computer and Information
More informationTECHNICAL NOTE HOW TO USE LOOPERS. Kalipso_TechDocs_Loopers. Revision: 1.0. Kalipso version: Date: 16/02/2017.
TECHNICAL NOTE HOW TO USE LOOPERS Document: Kalipso_TechDocs_Loopers Revision: 1.0 Kalipso version: 4.0 20161231 Date: 16/02/2017 Author: RS Contents 1. About... 3 2. Application Examples... 4 2.1. List
More informationAn effective approach for wide area detailed seabed mapping
An effective approach for wide area detailed seabed mapping Busan, 15th November 2017 11/15/2017 1 Ocean Infinity & Partner Proving a comprehensive seabed exploration system for water depth down to 6000
More informationBlocking time reduction for level crossings using the genetic algorithm
Computers in Railways X 299 Blocking time reduction for level crossings using the genetic algorithm Y. Noguchi 1, H. Mochizuki 1, S. Takahashi 1, H. Nakamura 1, S. Kaneko 1 & M. Sakai 2 1 Nihon University,
More informationApplication of Bayesian Networks to Shopping Assistance
Application of Bayesian Networks to Shopping Assistance Yang Xiang, Chenwen Ye, and Deborah Ann Stacey University of Guelph, CANADA Abstract. We develop an on-line shopping assistant that can help a e-shopper
More informationEE 364B: Wind Farm Layout Optimization via Sequential Convex Programming
EE 364B: Wind Farm Layout Optimization via Sequential Convex Programming Jinkyoo Park 1 Introduction In a wind farm, the wakes formed by upstream wind turbines decrease the power outputs of downstream
More informationDatabase of Winds and Waves. -internet version-
2009.1.6 Database of Winds and Waves -internet version- http://www.nmri.go.jp/wavedb/wave2.html National Maritime Research Institute CONTENTS 1. Outline of the Database... 1 2. Use of the Database on the
More informationMicrosoft System Center Data
U ft i V F_R S! TA TSBIB L! OTHEK MAMMOVER J Microsoft System Center Data Protection Manager 2012 SP1 Learn how to deploy, monitor, and administer System Center Data Protection Manager 2012 SP1 Steve Buchanan
More informationDiver Training Options
MAIN INTERNET ON-SITE TAILORED PACKAGES INTER-COMPANY Diver Training Options DBI offers a menu of tailored courses Designed for users as well as IT Professionals to learn how to master the functionality
More informationCRICKET ONTOLOGY. Project Description :- Instructor :- Prof: Navjyothi Singh
Instructor :- Prof: Navjyothi Singh CRICKET ONTOLOGY Project Team :- PV Sai Krishna (200402036) Abhilash I (200501004) Phani Chaitanya (200501076) Kranthi Reddy (200502008) Vidyadhar Rao (200601100) Project
More informationAdaptation of Formation According to Opponent Analysis
Adaptation of Formation According to Opponent Analysis Jaroslav ZAJAC Slovak University of Technology Faculty of Informatics and Information Technologies Ilkovičova 3, 842 16 Bratislava, Slovakia ka zajacjaro@orangemail.sk
More informationMethods for the Anisotropic Wavelet Packet Transform
Methods for the Anisotropic Wavelet Packet Transform Rade Kutil and Dominik Engel Department of Computer Sciences University of Salzburg Jakob-Haringer-Str. 2, A 5020 Salzburg {rkutil, dengel}@cosy.sbg.ac.at
More informationInvestigating the Problems of Ship Propulsion on a Supercomputer
Ship Elbrus powered by What I See is What I Understand. Так мы его задумали Investigating the Problems of Ship Propulsion on a Supercomputer A.A. Aksenov, S.V. Zhluktov, D.P. Silaev, S.A. Kharchenko, E.A.
More informationLOCOMOTION CONTROL CYCLES ADAPTED FOR DISABILITIES IN HEXAPOD ROBOTS
LOCOMOTION CONTROL CYCLES ADAPTED FOR DISABILITIES IN HEXAPOD ROBOTS GARY B. PARKER and INGO CYLIAX Department of Computer Science, Indiana University, Bloomington, IN 47405 gaparker@cs.indiana.edu, cyliax@cs.indiana.edu
More informationDESIGN AND ANALYSIS OF ALGORITHMS (DAA 2017)
DESIGN AND ANALYSIS OF ALGORITHMS (DAA 2017) Veli Mäkinen 12/05/2017 1 COURSE STRUCTURE 7 weeks: video lecture -> demo lecture -> study group -> exercise Video lecture: Overview, main concepts, algorithm
More information7 th International Conference on Wind Turbine Noise Rotterdam 2 nd to 5 th May 2017
7 th International Conference on Wind Turbine Noise Rotterdam 2 nd to 5 th May 2017 Sound power level measurements 3.0 ir. L.M. Eilders, Peutz bv: l.eilders@peutz.nl ing. E.H.A. de Beer, Peutz bv: e.debeer@peutz.nl
More informationMoPac South: Impact on Cesar Chavez Street and the Downtown Network
MoPac South: Impact on Cesar Chavez Street and the Downtown Network Prepared by: The University of Texas at Austin Center for Transportation Research Prepared for: Central Texas Regional Mobility Authority
More informationCondor Week Condor WAN scalability improvements. A needed evolution to support the CMS compute model
Condor Week 2009 Condor WAN scalability improvements A needed evolution to support the CMS compute model by Dan Bradley, Igor Sfiligoi and Todd Tannenbaum Condor Week 09 Condor WAN scalability improvements
More informationWorld Leading Traffic Analysis
World Leading Traffic Analysis Over the past 25 years, has worked closely with road authorities and traffic managers around the world to deliver leading traffic monitoring equipment. With products now
More informationA Hybrid Code Compression Technique using Bitmask and Prefix Encoding with Enhanced Dictionary Selection
A Hybrid Code Compression Technique using Bitmask and Prefix Encoding with Enhanced Dictionary Selection Syed Imtiaz Haider and Leyla Nazhandali Virginia Polytechnic Institute and State University 302
More informationA Quadtree-Based Lightweight Data Compression Approach to Processing Large-Scale Geospatial Rasters
1 A Quadtree-Based Lightweight Data Compression Approach to Processing Large-Scale Geospatial Rasters Jianting Zhang 1,2 and Simin You 2 1 Department of Computer Science, City College of New York, New
More informationLab 4: Root Locus Based Control Design
Lab 4: Root Locus Based Control Design References: Franklin, Powell and Emami-Naeini. Feedback Control of Dynamic Systems, 3 rd ed. Addison-Wesley, Massachusetts: 1994. Ogata, Katsuhiko. Modern Control
More informationECE 697B (667) Spring 2003
ECE 667 - Synthesis & Verification - Lecture 2 ECE 697 (667) Spring 23 Synthesis and Verification of Digital Systems unctional Decomposition Slides adopted (with permission) from. Mishchenko, 23 Overview
More informationEfficient Minimization of Routing Cost in Delay Tolerant Networks
Computer Science Department Christos Tsiaras tsiaras@aueb.gr Master Thesis Presentation (short edition) Efficient Minimization of Routing Cost in Delay Tolerant Networks Supervised by Dr. Stavros Toumpis
More informationRUGBY is a dynamic, evasive, and highly possessionoriented
VISUALIZING RUGBY GAME STYLES USING SOMS 1 Visualizing Rugby Game Styles Using Self-Organizing Maps Peter Lamb, Hayden Croft Abstract Rugby coaches and analysts often use notational data describing match
More information#19 MONITORING AND PREDICTING PEDESTRIAN BEHAVIOR USING TRAFFIC CAMERAS
#19 MONITORING AND PREDICTING PEDESTRIAN BEHAVIOR USING TRAFFIC CAMERAS Final Research Report Luis E. Navarro-Serment, Ph.D. The Robotics Institute Carnegie Mellon University November 25, 2018. Disclaimer
More informationSEARCH TREE. Generating the children of a node
SEARCH TREE Node: State in state tree Root node: Top of state tree Children: Nodes that can be reached from a given node in 1 step (1 operator) Expanding: Generating the children of a node Open: Closed:
More informationPaul Burkhardt. May 19, 2016
GraphEx Symposium 2016 U.S. National Security Agency Research Directorate May 19, 2016 Graphs are everywhere! Why graph? Graph-theoretic approaches are appealing to many fields simple data abstraction
More informationHelium: A Data Driven User Tool for SAR Analysis. May 17 th 2011 Karen Worsfold
Helium: A Data Driven User Tool for SAR Analysis May 17 th 2011 Karen Worsfold Today s presentation Questions to be answered Why did GSK undertake development of Helium? How was the Helium idea conceived?
More informationUsing MATLAB with CANoe
Version 2.0 2017-03-09 Application Note AN-IND-1-007 Author Restrictions Abstract Vector Informatik GmbH Public Document This application note describes the usage of MATLAB /Simulink combined with CANoe.
More informationDecompression Method For Massive Compressed Files In Mobile Rich Media Applications
2010 10th IEEE International Conference on Computer and Information Technology (CIT 2010) Decompression Method For Massive Compressed Files In Mobile Rich Media Applications Houchen Li, Zhijie Qiu, Lei
More informationArithmetic Coding Modification to Compress SMS
G8-5 2011 International Conference on Electrical Engineering and Informatics 17-19 July 2011, Bandung, Indonesia Arithmetic Coding Modification to Compress SMS Ario Yudo Husodo #1, Rinaldi Munir *2 #*
More informationSeismic Survey Designs for Converted Waves
Seismic Survey Designs for Converted Waves James A. Musser* GMG/AXIS Inc., Denver, CO 1720 Red Cloud Road, Longmont, CO, 80501, USA jmusser@gmg.com ABSTRACT Designing converted wave 3D surveys is considerably
More informationHigh usability and simple configuration or extensive additional functions the choice between Airlock Login or Airlock IAM is yours!
High usability and simple configuration or extensive additional functions the choice between Airlock Login or Airlock IAM is yours! Airlock Login Airlock IAM When combined with Airlock WAF, Airlock Login
More informationINSTRUCTION FOR FILLING OUT THE JUDGES SPREADSHEET
INSTRUCTION FOR FILLING OUT THE JUDGES SPREADSHEET One Judge Spreadsheet must be distributed to each Judge for each competitor. This document is the only one that the Judge completes. There are no additional
More informationProtecting shared storage from rogue jobs by I/O profiling and dynamic load balancing
Ellexus: The I/O Profiling Company Dr Rosemary Francis, CEO and Co-founder Protecting shared storage from rogue jobs by I/O profiling and dynamic load balancing The I/O Profiling Company - Protect. Balance.
More informationDive Planet. Manual. Rev Basic User Interface. 2 How to organize your dives. 3 Statistics. 4 Location Service and Map View.
Dive Planet Manual Rev 1.2 1 Basic User Interface 2 How to organize your dives 3 Statistics 4 Location Service and Map View 5 Settings 6 Languages 7 Buddies and guide 8 Backup and restore of the data 9
More informationOpen Research Online The Open University s repository of research publications and other research outputs
Open Research Online The Open University s repository of research publications and other research outputs Developing an intelligent table tennis umpiring system Conference or Workshop Item How to cite:
More informationIncreased streamer depth for dual-sensor acquisition Challenges and solutions Marina Lesnes*, Anthony Day, Martin Widmaier, PGS
Increased streamer depth for dual-sensor acquisition Challenges and solutions Marina Lesnes*, Anthony Day, Martin Widmaier, PGS Summary The towing depth applicable to dual-sensor streamer acquisition has
More informationBlackwave Dive Table Creator User Guide
Blackwave Dive Table Creator User Guide Copyright 2002-2009 Blackwave. All rights reserved. These materials (including without limitation all articles, text, images, logos, compilation, and design) are
More informationMotoTally. Enduro Event Management and Reporting Application
MotoTally Enduro Event Management and Reporting Application The Problem The management of enduro events (signup, scoring, posting results) is either done manually, or involves a combination of manual effort
More informationParsimonious Linear Fingerprinting for Time Series
Parsimonious Linear Fingerprinting for Time Series Lei Li, B. Aditya Prakash, Christos Faloutsos School of Computer Science Carnegie Mellon University VLDB 2010 1 L. Li, 2010 VLDB2010, 36 th International
More informationSIDRA INTERSECTION 6.1 UPDATE HISTORY
Akcelik & Associates Pty Ltd PO Box 1075G, Greythorn, Vic 3104 AUSTRALIA ABN 79 088 889 687 For all technical support, sales support and general enquiries: support.sidrasolutions.com SIDRA INTERSECTION
More informationSpatio-temporal analysis of team sports Joachim Gudmundsson
Spatio-temporal analysis of team sports Joachim Gudmundsson The University of Sydney Page 1 Team sport analysis Talk is partly based on: Joachim Gudmundsson and Michael Horton Spatio-Temporal Analysis
More informationPrudhoe Bay Oil Production Optimization: Using Virtual Intelligence Techniques, Stage One: Neural Model Building
Prudhoe Bay Oil Production Optimization: Using Virtual Intelligence Techniques, Stage One: Neural Model Building Shahab D. Mohaghegh, West Virginia University Lynda A. Hutchins, BP Exploration (Alaska),
More informationIntelligent Decision Making Framework for Ship Collision Avoidance based on COLREGs
Intelligent Decision Making Framework for Ship Collision Avoidance based on COLREGs Seminar Trondheim June 15th 2017 Nordic Institute of Navigation Norwegian Forum for Autonomous Ships SINTEF Ocean, Trondheim
More informationMEMORANDUM. Earl Haugen and UND Transportation and Traffic Coordination Committee
SRF No. 7766 MEMORANDUM TO: FROM: Earl Haugen and UND Transportation and Traffic Coordination Committee Rick Lane, P.E. DATE: November 26, 2013 SUBJECT: UNIVERSITY AVE REVIEW Our review of the University
More informationFigure 1 Example feature overview.
1. Introduction This case focuses on the northeastern region of Onslow Bay, NC, and includes an initial shoreline, regional contour, wave gauges, inlets, dredging, and beach fills. Most of the features
More informationProblem Solving as Search - I
Problem Solving as Search - I Shobhanjana Kalita Dept. of Computer Science & Engineering Tezpur University Slides prepared from Artificial Intelligence A Modern approach by Russell & Norvig Problem-Solving
More informationAt each type of conflict location, the risk is affected by certain parameters:
TN001 April 2016 The separated cycleway options tool (SCOT) was developed to partially address some of the gaps identified in Stage 1 of the Cycling Network Guidance project relating to separated cycleways.
More informationNet$ync II. Net$ync II. System Controllers
Net$ync II Net$ync II System Controllers Net$ync II Conductor System System Optimization The Quincy Net$ync II Conductor system selects the most efficient combination of compressors based on demand. Consistent,
More informationWind farm Simulink modelling and control through dynamic adjustment of wind turbines power set-point Saman Poushpas, Prof. W.
Wind farm Simulink modelling and control through dynamic adjustment of wind turbines power set-point Saman Poushpas, Prof. W.E Leithead Department of Electronics and Electrical Engineering, University
More informationTrack B: Particle Methods Part 2 PRACE Spring School 2012
Track B: Particle Methods Part 2 PRACE Spring School 2012 Maciej Cytowski (ICM UW) PART2: Load-balancing and migration Zoltan set-up ~ 15 min. Load-balancing in Zoltan ~ 15 min. Hands-on exercises ~ 20
More informationReducing Code Size with Run-time Decompression
Reducing Code Size with Run-time Decompression Charles Lefurgy, Eva Piccininni, and Trevor Mudge Advanced Computer Architecture Laboratory Electrical Engineering and Computer Science Dept. The University
More informationAccuRAID iscsi Auto-Tiering Best Practice
AccuRAID iscsi Auto-Tiering Best Practice Overview From the perspective of storage features, the performance of SSDs are high, but the cost is also high per GB. Relatively speaking, the cost of a traditional
More informationUnisys. Imagine it. Done. c Consulting. c Systems Integration. c Outsourcing. c Infrastructure. c Server Technology. Unisys NDP 30 and NDP 110
Unisys NDP 30 and NDP 110 The modular document processing system with the flexibility to meet your requirements. RELIABLE CHECK PROCESSING SOLUTIONS. Unisys NDP 30 and NDP 110 Complete Document Processing.
More informationAutodesk Moldflow Communicator Process settings
Autodesk Moldflow Communicator 212 Process settings Revision 1, 3 March 211. Contents Chapter 1 Process settings....................................... 1 Profiles.................................................
More informationIntroduction to Interprocess Communication. Introduction to Interprocess Communication
Introduction to Interprocess Communication Saverio Giallorenzo sgiallor@cs.unibo.it DISI@Unibo 1 The rocess Text Data Heap Stack C AddNumbers: std clc pushf.top i = 3,14 e = 2,71 y = hi x = 5 SUB1 MAIN
More informationMEETPLANNER DESIGN DOCUMENT IDENTIFICATION OVERVIEW. Project Name: MeetPlanner. Project Manager: Peter Grabowski
MEETPLANNER DESIGN DOCUMENT IDENTIFICATION Project Name: MeetPlanner Project Manager: Peter Grabowski OVERVIEW Swim coaches are often faced with a dilemma while planning swim meets. On the one hand, they
More informationMEDICAL IMAGE WAVELET COMPRESSION- EFFECT OF DECOMPOSITION LEVEL
International Journal of Electronics and Communication Engineering and Technology (IJECET) Volume 8, Issue 5, September-October 2017, pp. 25 32, Article ID: IJECET_08_05_004 Available online at http://www.iaeme.com/ijecet/issues.asp?jtype=ijecet&vtype=8&itype=5
More informationBackground Information. Project Instructions. Problem Statement. EXAM REVIEW PROJECT Microsoft Excel Review Baseball Hall of Fame Problem
Background Information Every year, the National Baseball Hall of Fame conducts an election to select new inductees from candidates nationally recognized for their talent or association with the sport of
More informationDealing with Dependent Failures in Distributed Systems
Dealing with Dependent Failures in Distributed Systems Ranjita Bhagwan, Henri Casanova, Alejandro Hevia, Flavio Junqueira, Yanhua Mao, Keith Marzullo, Geoff Voelker, Xianan Zhang University California
More informationProject: OpenDRIVE Document No. Issue: Title: Style Guide For OpenDRIVE Databases VI C. Date: 05 th March 2014 no.
Project: OpenDRIVE Document No. Issue: Title: Style Guide For OpenDRIVE Databases VI2011.040 C Date: 05 th March 2014 no. of pages: 12 Issuing Party: Author: Distribution List: VIRES Simulationstechnologie
More information(12) United States Patent (10) Patent No.: US 6,618,728 B1
USOO6618728B1 (12) United States Patent (10) Patent No.: US 6,618,728 B1 Rail (45) Date of Patent: *Sep. 9, 2003 (54) MULTI-PROCESS COMPRESSION 5,684,716 11/1997 Freeman... 348/14 5,710,562 A 1/1998 Gormish
More informationFlyweight Pattern. Flyweight: Intent. Use sharing to support large numbers of fine-grained objects efficiently. CSIE Department, NTUT Chien-Hung Liu
Flyweight Pattern CSIE Department, NTUT Chien-Hung Liu Flyweight: Intent Use sharing to support large numbers of fine-grained objects efficiently 1 Flyweight: Motivation (1) Some applications could benefit
More informationSolving Problems by Searching chap3 1. Problem-Solving Agents
Chapter3 Solving Problems by Searching 20070315 chap3 1 Problem-Solving Agents Reflex agents cannot work well in those environments - state/action mapping too large - take too long to learn Problem-solving
More informationPedestrian Dynamics: Models of Pedestrian Behaviour
Pedestrian Dynamics: Models of Pedestrian Behaviour John Ward 19 th January 2006 Contents Macro-scale sketch plan model Micro-scale agent based model for pedestrian movement Development of JPed Results
More information