Fault-Tolerant Routing Schemes in RDT(2,2,1)/α-Based Interconnection Network for Networks-on-Chip Designs

Size: px
Start display at page:

Download "Fault-Tolerant Routing Schemes in RDT(2,2,1)/α-Based Interconnection Network for Networks-on-Chip Designs"

Transcription

1 Fault-Toleant Routing Schemes in RDT(,,)/α-Based Inteconnection Netwok fo Netwoks-on-Chip Designs Mei Yang, Tao Li, Yingtao Jiang, and Yulu Yang Dept. of Electical & Compute Engineeing Univesity of Nevada, Las Vegas Las Vegas, NV 54, USA {meiyang, Dept. of Compute Science and Technology Nankai Univesity Tianjing, 37, China Abstact It has been well ecognized that the fault-toleance capability is vital fo a NoC system, since one faulty link/pocesso may isolate a lage faction of pocessos. Continuing fom a pevious pape [3] whee a RDT(,,)/α-based inteconnection netwok fo NoC designs was poposed, in this pape, we investigate fault-toleant outing schemes on NoC systems featuing a RDT-based inteconnection netwok. In specific, we popose two fault-toleant outing schemes in the pesence of eithe single link/node failue o multiple link/node failues. The poposed outing schemes ae based on deteministic outing. Altenative outes ae discoveed by popely selecting the intemediate nodes between the souce and the destination nodes on the ank toi. As of the single link/node failue case, we show that the numbe of outes on the detoued oute geneated by the poposed outing scheme is at most moe than the numbe of outes on the oiginal oute.. Intoduction Advances in VLSI technology will soon allow a single chip to contain moe than one billion tansistos [], indicating that a lage numbe of pocessing units (such as CPU, DSP, multimedia pocesso) shall be integated into one packaged chip. In these new systems, communication esouces ae competed by the vast volume computational esouces. With a communication-centic design style, Netwoks-on-Chip (NoC) [] was poposed to mitigate the complex communication poblems. A NoC system is composed of a lage numbe of pocessing units communicating to othe units though outes acoss the inteconnection netwok. Packets tavel though the netwok by passing one o moe hops between the souce and the destination tiles. As semiconducto technology scales down to nanomete domain, pocessing units (PUs), outes (nodes), and inteconnect links (links) ae all subject to new types of malfunctions and failues that ae hade to pedict and avoid [5]. Paticulaly, failues of nodes/links may isolate a lage numbe of fault-fee PUs. A majo challenge in NoC designs thus is to povide fault toleance unde link/node failue(s). In [3], we poposed an inteconnection netwok achitectue fo NoC based on a special Recusive Diagonal Tous (RDT) stuctue [], named as RDT(,,)/α. In RDT(,,)/α, each node has links to fom base tous (ank-) and uppe toi with the cadinal numbe. RDT(,,)/α povides a pomising solution fo inteconnection netwoks of NoC designs with its distinct advantages: ) high scalability due to its ecusive stuctue, ) low powe consumption due to its smalle diamete and aveage distance, 3) achitectual customizability with its embedded mesh/tous topologies, 4) fault-toleance capability with a constant node degee of, and 5) feasibility of layout compatible with cuent and futue VLSI technologies [7]. In this pape, we attempt to investigate vaious fault-toleant outing schemes applicable to the RDT(,,)/α-based inteconnection netwok. As pointed out in [4][7], adaptive outing which employs vitual [][3] is infeasible fo NoCs due to the need of lage buffes and lookup tables as well as complex shotest-path algoithms. Instead, we conside the deteministic outing based fault-toleant outing schemes which eoute the packets by popely selecting the intemediate outes between the souce and the destination nodes. The poposed fault-toleance outing schemes have no advese impacts on outing in the absence of faults. The est of the pape is oganized as follows. In Section, we give an oveview of the RDT stuctue. In Section 3, we descibe the NoC achitectue, the delay model, and the outing algoithms when no faults ae pesent in the inteconnection netwok. In Section 4, we pesent the fault-toleant outing algoithm unde single link/node failue. In Section 5, the faulttoleant outing algoithm unde multiple link/node failues is pesented. Section 6 concludes the pape.. RDT(,,)/α Stuctue The RDT stuctue [] is constucted by ecusively ovelaying -D diagonal meshes (toi). The base tous is a twodimensional squae aay of N by N nodes, each of which is numbeed with a two-dimensional numbe as follows: (, ) (, ) (, ) (N-, ) (, ) (, ) (, ) (N-, ) (, ) (, ) (, ) (N-, ) (, N-) (, N-) (, N-) (N-, N-) whee N = n k and both n and k ae natual numbes. The tous netwok is fomed with fou links between node(x, y) and its neighboing fou nodes: (mod(x±, N), y) and (x, mod(y±, N)). This base tous is also called ank- tous. On the ank- tous, a new tous-like netwok (ank- tous) is fomed by adding fou links between node (x, y) and nodes (x±n, y±n). The diection of the new tous-like netwok is at an angle of 45 degees to the oiginal tous. On the ank- tous, anothe

2 tous-like netwok (ank- tous) can be fomed by adding fou links in the same manne. Similaly, a ank-() tous can be fomed upon ank- tous. An independent tous on ank-i is one that does not have links to othe toi on ank-i. RDT(n, R, m) is a class of netwoks in which each node has links to fom base tous (ank-) and m uppe toi (the maximum ank is R) with the cadinal numbe n. Thus, the degee of the RDT(n, R, m) is 4(m) []. One of the uppe ank tous is assigned to each node in the RDT(n, R, m) afte n, R, and m ae set. Thus, the stuctue of the RDT(n, R, m) also vaies with diffeent assignments fo uppe ank toi to each node. This assignment is called tous assignment. A netwok in which evey node has links to fom all possible uppe ank toi (i.e. RDT(n, R, R)) is called a pefect RDT (PRDT(n, R)), whee n is the cadinal numbe, and R is the maximum ank. We efe a pefect tous as one that contains all links and no two links ovelap. A PRDT is unealistic due to its lage degee (4(R)). Vaious stuctues of the pactical RDT can be fomed by changing n and m, which povide vaious chaacteistics and can be applied to diffeent applications. We conside a pactical RDT stuctue, RDT(,, )/α, with its tous assignment shown in Fig.. In this assignment, each node has eight links, fou fo the base (ank-) tous and fou fo ank- o ank- toi. Fig. only shows pat of these links. In RDT(,,)/α, we only use fou independent ank- toi with thei souce nodes located at (,), (,), (,) and (3,), espectively. Thity-two ank- toi ae fomed on fou ank- toi (,), (,), (,) and (3,), espectively. Compaed with othe RDT(n, R, m) stuctues (such as RDT(, 4, )/α, RDT(, 4, )/ß []), RDT(,, )/α is much simple and suitable fo netwoks with a thousand o less nodes Figue. Tous assignment fo the RDT(,,)/α. 3. Routing Algoithms without Link/Node Faults 3. The NoC Achitectue Ou study is based on the NoC achitectue shown in Fig., whee each PU is attached on a switch/oute which is connected to the inteconnection links. Fig. 3 shows a possible oute stuctue which consists of input and output pots and inteface to the attached PU. At each input and/o output pot, a limited numbe of buffes ae povided to stoe packets, and a line contolle is used to select the packet to be eceived fom the input link o sent on the output link. A cental contolle pefoms the functions of outing and abitation. Input : link contolle Route Netwok Pocessing unit Figue. NOC achitectue. Injection Switching fabic Cental contolle Routing Pocesso inteface Abitation Ejection Figue 3. Route stuctue. inteface Output 3. Delay Model Fo an NoC application, an impotant pefomance metic is the delay, which depends on the taffic patten of the application and many othe factos, such as packet/flit size, oute s abitation scheme, etc. [7]. In this study, we employ a simple delay model as follows. Fo a NoC netwok shown in Fig., the delay expeienced by a packet on the oute fom the souce PU to its destination PU includes the tansmission delay on the wies (o wie delay), the pocessing delay of the outes and the queuing delay at the outes. We assume the pocessing delay and queuing delay ae the same fo all outes, denoted as T p, T q, espectively. Thee may exist diffeent types of wies with vaious lengths. We denote the unit length wie delay as T, the length of wie type i as l i, and the numbe of wies of type i as n i. Let N be the numbe of hops a packet tavels between a souce to a destination oute and m be the numbe of diffeent types of wies. Then we can detemine the total delay expeienced by a packet as T = ( T T )( N cn T l () total p q ) m i= i i whee c epesents the constant popotional to the poduct of the esistance pe unit length and the capacitance pe unit length. As discussed in [], the effect of length to wie delay can be alleviated by beaking long lines into shote sections with a epeate diving each section. Hence, it is possible to match the wie delay of a long line to the total wie delay of a set of shote lines assuming the length of the long line is less o equal to the sum of the lengths of shote lines in the set. And we assume the pocessing and the queuing delays expeienced at a oute ae fa longe than the wie delay of the line connecting two adjacent outes. Hence the total delay expeienced by a packet is

3 dominated by the sum of the pocessing and queuing delays on the outes (including the intemediate outes, and the souce and destination outes). Hence, Eqn. () can be simplified to T total ( Tp Tq )( N ) () As one can see fom Fig. 4, on the RDT(,, )/α stuctue, if a oute on ank- tous is selected to connect S and D, the numbe of outes on this oute is. This is much less than an altenative oute on ank- tous that has 5 outes. In anothe example, the numbe of outes on the oute fom S to D on ank- tous is, which is much less than that of outes on the coesponding oute on ank- and ank- toi, 5 and, espectively. These two examples indicate that, accoding to Eqn. (), the total delay of a oute can be educed if moe links on highe ank toi ae included S S D Figue 4. Wies on RDT(,, )/α. Fo cleaness, we only show the nodes epesenting outes. All the outing schemes discussed in this pape ae based on the delay model shown in Eqn. (). Fo outing in the RDT(,, )/α-based inteconnection netwok without link/oute failue, we can diectly apply the floating vecto outing algoithm [][], which is based on the vecto outing algoithm [] poposed fo PRDT stuctues. In the following, we will biefly intoduce the two outing algoithms. 3.3 Vecto Routing Algoithm The basic idea of the vecto outing algoithm is to epesent the oute fom a souce node to the destination node with a combination of unit vectos, each of which coesponds to each ank of toi. Fig. 5 shows the diections of the unit vectos fo each ank tous fo RDT(,, )/α, which otate in clockwise diection at an angle of 45 degees as the ank inceases. Y ank- Y ank- Y ank-, ank- ank- D ank- Figue 5. Diections of unit vectos fo RDT(,, )/α. We ae given a vecto fom a souce node to the destination node epesented as A = a by whee and Y ae the unit vectos of the base (ank-) tous. A can be epesented with a combination of the unit vectos, R Y,, R, Y on ank-r to ank- toi as A = a by = vrh R vrvyr... vh vvy... vh vvy whee (v h, v v ) epesents the vecto on ank- tous, whee R. And v h and v v ae maximized in ode to use the uppe ank tous as much as possible. Given the vecto A = a by, we list the vecto outing algoithm as follows. Algoithm Vecto Routing (a, b): begin fo = to R do g (a b)/ f - (a - b)/ v h a - (n * g n * f) v v b - (n * g n * f) a g b f end The vectos ae computed at the souce node and encapsulated into the packet. Then we oute the packet to the nodes following the ode of ank-r, ank-(r-),, ank- vectos. On the same ank tous, the outing is pefomed accoding to a pedetemined ode, fo example, Y outing []. Theoem The maximum numbe of outes that a packet tavels on ank- tous is n when using the vecto outing algoithm, whee n is the cadinal numbe. The poof of Thm. follows the poof of Thm. 5 in []. 3.4 Floating Vecto Routing Algoithm The floating vecto outing algoithm [] was poposed fo pactical RDTs, such as RDT(,, )/α. In this algoithm, the vecto computation is done at the souce node accoding to the vecto outing algoithm fo the PRDT, and stoed in the packet heade. Each oute maintains a simple table indicating the diection to each the neaest node fo each ank of tous. A oute checks the vecto in the packet heade, and sends the packet to the neaest oute on the highest ank tous accoding to the simple table. This pocess is called floating, though which each oute can use any ank of tous by only a single step packet tansfe to a neighbo oute. Based on Thm. and the desciption of the floating vecto outing algoithm, we have: Coollay The maximum numbe of outes that a packet tavels on ank- tous is n when using the floating vecto outing algoithm, whee n is the cadinal numbe. In [3], we have showed the feasibility of using the RDT(,, )/α stuctue as the inteconnection netwok fo a NoC design. In this pape, we futhe exploe the fault-toleance capability of the RDT(,, )/α stuctue. In specific, we popose two faulttoleant outing schemes that intoduce the least exta pocessing and queuing delays (equivalent to the least incease of the numbe of outes as shown in Eqn. ()) on the RDT(,, )/αbased inteconnection netwoks. 4. Fault-Toleant Routing Algoithm unde Single Link/Node Failue 4. Fault Model The following assumptions ae used in this pape. ) Any link o node in the netwok can fail, and the faulty components ae unusable; that is, data will not be tansmitted ove a faulty link o outed though a faulty node. ) The fault model is static, that is, no new faults occu duing a outing pocess. 3) Both souce and

4 destination nodes (on any ank tous) ae fault-fee. 4) The faults occu independently. 5) If a node fails, the fou links associated with the node on ank- tous also fail. 6) Faulty link(s)/node(s) ae known to all othe nodes in the same ank. 4. Single Link/Node Failue Given a pai of souce and destination nodes S and D on the RDT(,, )/α stuctue, using the floating vecto outing algoithm, we know that the oute fom S to D is composed of oute segments on diffeent ank toi and floated oute segments on ank- tous. The oute thus can be epesented as S~S - D ~S -D /S -D /D, whee ~ epesents a floating on ank-, and S and D epesent the souce node and the destination node on the oute segment on a ank- tous, espectively. Note that a oute may consist of all the oute segments o subsets of these oute segments. Fo single link/node failue on one segment floating on ank- tous, we can always find one altenative oute without inceasing the numbe of outes since each oute has fou possible outes (each with the same numbe of hops/outes) to float to a oute on an uppe ank tous. In the following, we enumeate the cases of single link/node failue happening on the oute segment on one ank tous. S I D S I (a) (b) (c) Figue 6. Thee distinct cases of single link failue on ank- tous of the RDT(,, )/α stuctue. By Coollay, we know that on the RDT(,, )/α stuctue, using the floating vecto outing algoithm, the numbe of outes a packet tavels fom S to D is no moe than 3. Hence, thee ae thee possible single link failues on the oute segment on ank-, as shown in Fig. 6, whee faulty links ae maked by. N S I D (a) (b) Figue 7. Two distinct cases of single node failue on ank- tous of the RDT(,, )/α stuctue. D N Fo the same eason of single link failue, thee ae two possible cases of single node failue, as shown in Fig. 7, whee faulty nodes ae maked by. 4.3 Fault-Toleant Routing Algoithm unde Single Link/Node Failue As one can see fom Figs. 6 and 7, if the failue is on the (o Y) diection, then we should detou the packet by sending it though the Y (o ) diection fist. The vecto needs to be changed to eflect the detou if necessay. In each packet, we add a field flag, which is set as floating when the packet is floated to a node o outing when the packet S I S I D is outed to a node on a ank- link, and a vaiable to indicate the cuent ank value. Fig. shows the packet fomat. heade length flag ank-r vectos packet heade... ank- vectos payload length Figue. Packet fomat. Let denote the diection on ank-, diection on ank-, packet payload CRC denote the - Y denote the Y diection on ank-, and Y denote the -Y diection on ank-. A distibuted fault-toleant floating outing algoithm is listed as follows, whee (i x, i y ) epesents the vecto of a node i on ank- tous. Algoithm Floating Vecto Routing unde Single Failue (FVRSF): begin //Step : the souce node computes the vectos, othe nodes //check the flag and decement the vecto value accodingly if i = S and S D then call Vecto Routing to compute vectos fom ank R to set as max{i (v ih, v iv ) (, )} else if flag = outing then if the packet is eceived fom then v h v h - else v h v h if the packet is eceived fom Y then v v v v - else v v v v else if flag = floating then if the packet is eceived fom then v oh v oh - else v oh v oh if the packet is eceived fom Y then v ov v ov - else v ov v ov //Step : check the availability of the link and send the packet //accodingly if i is on ank- then set flag as outing if (v h, v v ) (, ) then if v h and the link on the v h diection (i.e., fo v h > o fo v h <) is not faulty then send the packet to v h diection else if v h = and the link on the v v diection (i.e., Y fo v v > o Y fo v v <) is not faulty then send the packet to v v diection else if v h and the link on the v h diection is faulty then if v v = then send the packet to Y else send the packet to v v diection else if the link on the v v diection is faulty then send the packet to else if find p = - to that (v ph, v pv ) (, ) then p, goto Step else goto end //Step 3: floating to a node neaest to node i on ank- find the non-faulty node j(j x, j y ) on ank- tous with min{abs(i x j x v h ) abs(i y j y v v )} by checking the table on node i set flag as floating if i x j x then send the packet to (j x i x ) diection else send the packet to (j y i y ) diection end

5 Theoem Conside a oute fom a souce node S to a destination node D on the RDT(,, )/α stuctue. If thee exists a single link/node failue on the oiginal oute geneated by the floating vecto outing algoithm, the numbe of outes on the detoued oute (also the shotest oute) geneated by the faulttoleant floating vecto outing algoithm is at most moe than the numbe of outes on the oiginal oute. Poof: As discussed in the fault model, single link/node failue only affects outing on one ank tous. Based on Coollay, we can deive thee possible cases of single link failue as shown in Fig. 6, and the two possible cases of single node failue as shown in Fig. 7. One can veify that, the fault-toleant floating outing algoithm, with the mbedded vecto outing algoithm, computes the shotest oute (with the least numbe of outes) fom S to D on each ank-, and futhe the shotest oute fom S to D. The numbe of outes on the detoued oute geneated by the faulttoleant floating vecto outing algoithm, compaed with the oiginal oute, is eithe equal to the numbe of outes on the oiginal oute (as the case shown in Fig. 7 (a)) o moe than the numbe of outes on the oiginal oute (as the case shown in Fig. 7(b) and the cases shown in Fig. 6). The incease of the numbe of outes on the detoued oute is minimized fo all thee cases. Hence the theoem follows. The above theoem indicates that the exta queuing and pocessing delays is minimized using the FVRSF algoithm. Anothe advantage of the FVRSF algoithm is that each oute decides the best oute based on the fault infomation of its fou links on one ank tous. No global fault infomation thus needs to be maintained at each oute. In this way, the ovehead intoduced is vey low. Fig. illustates two examples of the FVRSF algoithm. The oiginal oute fom S (, ) to D (7, 6) geneated by the floating vecto outing algoithm is (, )-(3, )-(5, 3)-(7, 5)-(7, 6), which tavels though 5 outes. Assume that the link between (3, )-(5, 3) on ank- fails. The detoued oute geneated by the FVRSF algoithm is (, )-(3, )-(, 3)-(3, 5)-(5, 7)-(7, 5)-(7, 6) with 7 outes, which is moe than the numbe of outes on the oiginal oute S S Figue. Two examples of the FVRSF algoithm. As anothe example, the oiginal oute fom S (, ) to D (, ) geneated by the floating outing algoithm is (, )-(, )-(, )-(, )-(, ), which includes 5 outes. In the case of failue of node (, ), the detoued oute geneated by the FVRSF algoithm is (, )-(, )-(, )-(, )-(, ) with 5 outes. Obviously, this is the best detoued oute with the least numbe of outes that a packet has to tavel. 5. Fault-Toleant Routing Algoithm unde Multiple Failues D D 5. Multiple Link/Node Failues Multiple link/node failues may exist on diffeent ank toi of the RDT(,,)/α stuctue. As discussed in Section 4., a node failue can be modeled as multiple link failues. As such, we only conside link failues hee. Based on the constuction of the RDT(,,)/α stuctue, we can decompose multiple link failues on diffeent ank toi into sets of link failues on the same independent tous on one ank tous. In the following, we discuss the fault-toleance outing scheme unde multiple link failues on the same independent tous on one ank- tous. When multiple link/node failues exist on a ank- tous, the FVRSF algoithm cannot geneate the detoued oute with the least numbe of outes since the decision made by each oute is not based on global view of othe failues. In this case, we adopt the method discussed in [6] to identify the best intemediate oute though which the detoued oute uses the least numbe of outes. Note that thee may exist moe than one such intemediate outes. We use I i to denote such intemediate outes between S and D. 5. Fault-Toleant Routing Algoithm unde Multiple Failues When applying the method of identifying the best intemediate oute in combination with the vecto outing algoithm, the following equiements have to be satisfied fo an intemediate oute I i to ensue that the faulty links ae avoided when outing fom S via I i to D on ank- tous. ) All the faulty links shall not appea on all possible S -I i outes geneated by the vecto outing algoithm. ) All the faulty links shall not appea on all possible I i -D outes geneated by the vecto outing algoithm. 3) Thee is no I i giving a shote oute than I i. The fist equiement guaantees that packets can be outed fom S to I i, and the second equiement guaantees that packets can be outed fom I i to D. Since the vecto outing algoithm is a deteministic outing scheme, these two equiements ae sufficient to ensue that packets can avoid the faulty links. The thid equiement guaantees that the final oute is the shotest possible oute. d Let R S be the set of outes eachable though vecto outing fom S, let R d D be the set of outes that can each D though vecto outing. Let n(i, j) be the numbe of outes on the minimal delay oute fom oute i to oute j. We define R k as follows: a oute I is in R k if and only if n(s, I) n(i, D) = n(s, D) k. Let k be the smallest k fo which R k R d S R d D is nonempty. Then we have: Theoem 3 A oute I satisfies all thee equiements if and only if I R k R d S R d D. The fault-toleant outing algoithm unde multiple failues is descibed as follows, whee (Iv ih, Iv iv ) epesents the vecto fo the intemediate oute on the ank- tous with link failues. Coespondingly, in the packet heade, a new field of the intemediate node vecto on the cuent ank will be inseted. Algoithm Floating Vecto Routing unde Multiple Failues (FVRMF): begin //Step : the souce node computes the vectos, othe nodes //check the flag and decement the vecto value accodingly if i = S and S D then call Vecto Routing to compute vectos fom ank R to else if flag = outing then set as the highest ank with (v h, v v ) (, )

6 if (Iv ih,iv iv ) (, ) then if the packet is eceived fom then Iv ih Iv ih - else Iv ih Iv ih if the packet is eceived fom Y then Iv iv Iv iv - else Iv iv Iv iv if (v h,v v ) (, ) then if the packet is eceived fom then v h v h - else v h v h if the packet is eceived fom Y then v v v v - else v v v v else if flag = floating then if the packet is eceived fom then v oh v oh - else v oh v oh if the packet is eceived fom Y then v ov v ov - else v ov v ov //Step : if the oute is the souce node on ank-, identify //the intemediate oute and update the vecto list if i is on ank- then if flag = floating then set flag as outing S i D (v h, v v ) compute R d S as defined compute R d D as defined k compute R k as defined while R k R d S R d D = do k k compute R k as defined set I as one oute in R k R S d R D d inset I=(Iv ih, Iv iv ) to the intemediate oute list on ank- if (Iv ih, Iv iv ) (, ) then if Iv ih then send the packet to Iv ih diection else send the packet to Iv iv diection if (v h, v v ) (, ) then if v h then send the packet to v h diection else send the packet to v v diection else if find p = - to that (v ph, v pv ) (, ) then p, goto step else goto end //Step 3: floating to a node neaest to node i on ank- find the non-faulty node j(j x, j y ) on ank- tous with min{abs(i x j x v h ) abs(i y j y -v v )} by checking the table on node i set flag as floating if i x j x then send the packet to (j x i x ) diection else send the packet to (j y i y ) diection end S Figue. An example of the FVRMF algoithm. I D Fig. shows an example of the FVRMF algoithm unde multiple failues on the same ank tous. Thee ae thee link failues on ank- tous shown in dotted lines. Accoding to the FVRMF algoithm, I will be selected as the best intemediate oute between S D with the minimized numbe of outes. If thee exists a possible oute between a souce node to a destination node, we can find a best detoued oute with the least numbe of outes using the FVRMF algoithm. Howeve, due to the complexness of multiple failues, thee is no bound on the numbe of outes that will be used on the detoued oute. 6. Conclusion In this pape, we investigate fault-toleant outing schemes on NoC systems featuing a RDT-based inteconnection netwok. We poposed the FVRSF and FVRMF algoithms fo faulttoleant outing unde single link/node failue o multiple link/node failues espectively. Both algoithms ae based on deteministic outing, and hence, no vitual channel is needed. We showed that using FVRSF algoithm, the numbe of outes on the detoued oute is at most moe than the numbe of outes on the oiginal oute. The FVRMF algoithm guaantees that an altenative oute is always found by identifying the best intemediate oute. Futue wok includes the study of the delay pefomance unde eal taffic pattens and the study of faulttoleant outing schemes unde diffeent delay and fault models. Refeences [] L. Benini and G.D. Micheli, Netwoks on chips: a new SoC paadigm, IEEE Compute, pp. 7-7, Jan.. [] R. Casado et al., A potocol fo deadlock-fee dynamic econfiguation in high speed local aea netwoks, IEEE Tans. Paallel & Distibuted Systems, vol., no., pp. 5-3,. [3] W. J. Dally and H. Aoki, Deadlock-fee adaptive outing in multicomputes netwoks using vitual, IEEE Tans. Paallel & Distibuted Systems, vol. 4, no. 4, pp , 3. [4] Dally W. J. and B. Towles, Route Packets, Not Wies: On-Chip Inteconnection Netwoks, in Poc. Design Automation Conf.,, pp [5] T. Dumitas, S. Kene, and S. Maculescu, Towads on-chip faulttoleant communication, in Poc. ASP-DAC, 3, pp [6] M.E. G omez, J. Duato, J. Flich, P. L opez, A. Robles, N.A. Nodbotten, O. Lysne, and T. Skeie, An efficient fault-toleant outing methodology fo meshes and toi, Compute Achitectue Lettes, vol. 3, pp. -3, Jul. 4. [7] J. Hu and R. Maculescu, Enegy- and pefomance-awae mapping fo egula NoC achitectues, IEEE Tans. Compute-Aided Design, vol. 4, no. 4, Ap. 5. [] ITRS, Intenational Technology Roadmap fo Semiconductos, Update. [] T. Li, Y. Yu, P. Li, J. u,. Ma and Y. Yang, Pactical outing and tous assignment fo RDT, in Poc. ISPAN, 4, pp [] J. Liu, M. Shen, L. Zheng, and H. Tenhunen, System level inteconnect design fo netwok-on-chip using inteconnect IPs, in Poc. Int l Wokshop System-Level Inteconnect, 3, pp [] L.M. Ni and P.K. McKinley, A suvey of womhole outing techniques in diect netwoks, Compute, vol. 6, no., pp. 6-76, 3. [] Y. Yang, A. Funahashi, A. Jouaku, H. Nishi, H. Amano, and T. Sueyoshi, Recusive diagonal tous: an inteconnection netwok fo massively paallel computes, IEEE Tans. Paallel & Distibuted Systems, vol., no. 7, pp. 7-75, Jul.. [3] Y. Yu, M. Yang, Y. Yang, and Y. Jiang, A RDT-based inteconnection netwok fo scalable NoC designs, in Poc. IEEE ITCC, 5, pp

IP Network Design by Modified Branch Exchange Method

IP Network Design by Modified Branch Exchange Method Received: June 7, 207 98 IP Netwok Design by Modified Banch Method Kaiat Jaoenat Natchamol Sichumoenattana 2* Faculty of Engineeing at Kamphaeng Saen, Kasetsat Univesity, Thailand 2 Faculty of Management

More information

A Memory Efficient Array Architecture for Real-Time Motion Estimation

A Memory Efficient Array Architecture for Real-Time Motion Estimation A Memoy Efficient Aay Achitectue fo Real-Time Motion Estimation Vasily G. Moshnyaga and Keikichi Tamau Depatment of Electonics & Communication, Kyoto Univesity Sakyo-ku, Yoshida-Honmachi, Kyoto 66-1, JAPAN

More information

EE 6900: Interconnection Networks for HPC Systems Fall 2016

EE 6900: Interconnection Networks for HPC Systems Fall 2016 EE 6900: Inteconnection Netwoks fo HPC Systems Fall 2016 Avinash Kaanth Kodi School of Electical Engineeing and Compute Science Ohio Univesity Athens, OH 45701 Email: kodi@ohio.edu 1 Acknowledgement: Inteconnection

More information

The Internet Ecosystem and Evolution

The Internet Ecosystem and Evolution The Intenet Ecosystem and Evolution Contents Netwok outing: basics distibuted/centalized, static/dynamic, linkstate/path-vecto inta-domain/inte-domain outing Mapping the sevice model to AS-AS paths valley-fee

More information

Annales UMCS Informatica AI 2 (2004) UMCS

Annales UMCS Informatica AI 2 (2004) UMCS Pobane z czasopisma Annales AI- Infomatica http://ai.annales.umcs.pl Annales Infomatica AI 2 (2004) 33-340 Annales Infomatica Lublin-Polonia Sectio AI http://www.annales.umcs.lublin.pl/ Embedding as a

More information

Slotted Random Access Protocol with Dynamic Transmission Probability Control in CDMA System

Slotted Random Access Protocol with Dynamic Transmission Probability Control in CDMA System Slotted Random Access Potocol with Dynamic Tansmission Pobability Contol in CDMA System Intaek Lim 1 1 Depatment of Embedded Softwae, Busan Univesity of Foeign Studies, itlim@bufs.ac.k Abstact In packet

More information

Towards Adaptive Information Merging Using Selected XML Fragments

Towards Adaptive Information Merging Using Selected XML Fragments Towads Adaptive Infomation Meging Using Selected XML Fagments Ho-Lam Lau and Wilfed Ng Depatment of Compute Science and Engineeing, The Hong Kong Univesity of Science and Technology, Hong Kong {lauhl,

More information

Segmentation of Casting Defects in X-Ray Images Based on Fractal Dimension

Segmentation of Casting Defects in X-Ray Images Based on Fractal Dimension 17th Wold Confeence on Nondestuctive Testing, 25-28 Oct 2008, Shanghai, China Segmentation of Casting Defects in X-Ray Images Based on Factal Dimension Jue WANG 1, Xiaoqin HOU 2, Yufang CAI 3 ICT Reseach

More information

RANDOM IRREGULAR BLOCK-HIERARCHICAL NETWORKS: ALGORITHMS FOR COMPUTATION OF MAIN PROPERTIES

RANDOM IRREGULAR BLOCK-HIERARCHICAL NETWORKS: ALGORITHMS FOR COMPUTATION OF MAIN PROPERTIES RANDOM IRREGULAR BLOCK-HIERARCHICAL NETWORKS: ALGORITHMS FOR COMPUTATION OF MAIN PROPERTIES Svetlana Avetisyan Mikayel Samvelyan* Matun Kaapetyan Yeevan State Univesity Abstact In this pape, the class

More information

Separability and Topology Control of Quasi Unit Disk Graphs

Separability and Topology Control of Quasi Unit Disk Graphs Sepaability and Topology Contol of Quasi Unit Disk Gaphs Jiane Chen, Anxiao(Andew) Jiang, Iyad A. Kanj, Ge Xia, and Fenghui Zhang Dept. of Compute Science, Texas A&M Univ. College Station, TX 7784. {chen,

More information

Simulation and Performance Evaluation of Network on Chip Architectures and Algorithms using CINSIM

Simulation and Performance Evaluation of Network on Chip Architectures and Algorithms using CINSIM J. Basic. Appl. Sci. Res., 1(10)1594-1602, 2011 2011, TextRoad Publication ISSN 2090-424X Jounal of Basic and Applied Scientific Reseach www.textoad.com Simulation and Pefomance Evaluation of Netwok on

More information

DEADLOCK AVOIDANCE IN BATCH PROCESSES. M. Tittus K. Åkesson

DEADLOCK AVOIDANCE IN BATCH PROCESSES. M. Tittus K. Åkesson DEADLOCK AVOIDANCE IN BATCH PROCESSES M. Tittus K. Åkesson Univesity College Boås, Sweden, e-mail: Michael.Tittus@hb.se Chalmes Univesity of Technology, Gothenbug, Sweden, e-mail: ka@s2.chalmes.se Abstact:

More information

Modelling, simulation, and performance analysis of a CAN FD system with SAE benchmark based message set

Modelling, simulation, and performance analysis of a CAN FD system with SAE benchmark based message set Modelling, simulation, and pefomance analysis of a CAN FD system with SAE benchmak based message set Mahmut Tenuh, Panagiotis Oikonomidis, Peiklis Chachalakis, Elias Stipidis Mugla S. K. Univesity, TR;

More information

Controlled Information Maximization for SOM Knowledge Induced Learning

Controlled Information Maximization for SOM Knowledge Induced Learning 3 Int'l Conf. Atificial Intelligence ICAI'5 Contolled Infomation Maximization fo SOM Knowledge Induced Leaning Ryotao Kamimua IT Education Cente and Gaduate School of Science and Technology, Tokai Univeisity

More information

Prioritized Traffic Recovery over GMPLS Networks

Prioritized Traffic Recovery over GMPLS Networks Pioitized Taffic Recovey ove GMPLS Netwoks 2005 IEEE. Pesonal use of this mateial is pemitted. Pemission fom IEEE mu be obtained fo all othe uses in any cuent o futue media including epinting/epublishing

More information

Communication vs Distributed Computation: an alternative trade-off curve

Communication vs Distributed Computation: an alternative trade-off curve Communication vs Distibuted Computation: an altenative tade-off cuve Yahya H. Ezzeldin, Mohammed amoose, Chistina Fagouli Univesity of Califonia, Los Angeles, CA 90095, USA, Email: {yahya.ezzeldin, mkamoose,

More information

Performance Optimization in Structured Wireless Sensor Networks

Performance Optimization in Structured Wireless Sensor Networks 5 The Intenational Aab Jounal of Infomation Technology, Vol. 6, o. 5, ovembe 9 Pefomance Optimization in Stuctued Wieless Senso etwoks Amine Moussa and Hoda Maalouf Compute Science Depatment, ote Dame

More information

On the Forwarding Area of Contention-Based Geographic Forwarding for Ad Hoc and Sensor Networks

On the Forwarding Area of Contention-Based Geographic Forwarding for Ad Hoc and Sensor Networks On the Fowading Aea of Contention-Based Geogaphic Fowading fo Ad Hoc and Senso Netwoks Dazhi Chen Depatment of EECS Syacuse Univesity Syacuse, NY dchen@sy.edu Jing Deng Depatment of CS Univesity of New

More information

Number of Paths and Neighbours Effect on Multipath Routing in Mobile Ad Hoc Networks

Number of Paths and Neighbours Effect on Multipath Routing in Mobile Ad Hoc Networks Numbe of Paths and Neighbous Effect on Multipath Routing in Mobile Ad Hoc Netwoks Oday Jeew School of Infomation Systems and Accounting Univesity of Canbea Canbea ACT 2617, Austalia oday.jeew@canbea.edu.au

More information

Optical Flow for Large Motion Using Gradient Technique

Optical Flow for Large Motion Using Gradient Technique SERBIAN JOURNAL OF ELECTRICAL ENGINEERING Vol. 3, No. 1, June 2006, 103-113 Optical Flow fo Lage Motion Using Gadient Technique Md. Moshaof Hossain Sake 1, Kamal Bechkoum 2, K.K. Islam 1 Abstact: In this

More information

Erasure-Coding Based Routing for Opportunistic Networks

Erasure-Coding Based Routing for Opportunistic Networks Easue-Coding Based Routing fo Oppotunistic Netwoks Yong Wang, Sushant Jain, Magaet Matonosi, Kevin Fall Pinceton Univesity, Univesity of Washington, Intel Reseach Bekeley ABSTRACT Routing in Delay Toleant

More information

IP Multicast Simulation in OPNET

IP Multicast Simulation in OPNET IP Multicast Simulation in OPNET Xin Wang, Chien-Ming Yu, Henning Schulzinne Paul A. Stipe Columbia Univesity Reutes Depatment of Compute Science 88 Pakway Dive South New Yok, New Yok Hauppuage, New Yok

More information

Accurate Diffraction Efficiency Control for Multiplexed Volume Holographic Gratings. Xuliang Han, Gicherl Kim, and Ray T. Chen

Accurate Diffraction Efficiency Control for Multiplexed Volume Holographic Gratings. Xuliang Han, Gicherl Kim, and Ray T. Chen Accuate Diffaction Efficiency Contol fo Multiplexed Volume Hologaphic Gatings Xuliang Han, Gichel Kim, and Ray T. Chen Micoelectonic Reseach Cente Depatment of Electical and Compute Engineeing Univesity

More information

ANALYTIC PERFORMANCE MODELS FOR SINGLE CLASS AND MULTIPLE CLASS MULTITHREADED SOFTWARE SERVERS

ANALYTIC PERFORMANCE MODELS FOR SINGLE CLASS AND MULTIPLE CLASS MULTITHREADED SOFTWARE SERVERS ANALYTIC PERFORMANCE MODELS FOR SINGLE CLASS AND MULTIPLE CLASS MULTITHREADED SOFTWARE SERVERS Daniel A Menascé Mohamed N Bennani Dept of Compute Science Oacle, Inc Geoge Mason Univesity 1211 SW Fifth

More information

Embeddings into Crossed Cubes

Embeddings into Crossed Cubes Embeddings into Cossed Cubes Emad Abuelub *, Membe, IAENG Abstact- The hypecube paallel achitectue is one of the most popula inteconnection netwoks due to many of its attactive popeties and its suitability

More information

Journal of World s Electrical Engineering and Technology J. World. Elect. Eng. Tech. 1(1): 12-16, 2012

Journal of World s Electrical Engineering and Technology J. World. Elect. Eng. Tech. 1(1): 12-16, 2012 2011, Scienceline Publication www.science-line.com Jounal of Wold s Electical Engineeing and Technology J. Wold. Elect. Eng. Tech. 1(1): 12-16, 2012 JWEET An Efficient Algoithm fo Lip Segmentation in Colo

More information

Efficient protection of many-to-one. communications

Efficient protection of many-to-one. communications Efficient potection of many-to-one communications Miklós Molná, Alexande Guitton, Benad Cousin, and Raymond Maie Iisa, Campus de Beaulieu, 35 042 Rennes Cedex, Fance Abstact. The dependability of a netwok

More information

a Not yet implemented in current version SPARK: Research Kit Pointer Analysis Parameters Soot Pointer analysis. Objectives

a Not yet implemented in current version SPARK: Research Kit Pointer Analysis Parameters Soot Pointer analysis. Objectives SPARK: Soot Reseach Kit Ondřej Lhoták Objectives Spak is a modula toolkit fo flow-insensitive may points-to analyses fo Java, which enables expeimentation with: vaious paametes of pointe analyses which

More information

An Unsupervised Segmentation Framework For Texture Image Queries

An Unsupervised Segmentation Framework For Texture Image Queries An Unsupevised Segmentation Famewok Fo Textue Image Queies Shu-Ching Chen Distibuted Multimedia Infomation System Laboatoy School of Compute Science Floida Intenational Univesity Miami, FL 33199, USA chens@cs.fiu.edu

More information

INFORMATION DISSEMINATION DELAY IN VEHICLE-TO-VEHICLE COMMUNICATION NETWORKS IN A TRAFFIC STREAM

INFORMATION DISSEMINATION DELAY IN VEHICLE-TO-VEHICLE COMMUNICATION NETWORKS IN A TRAFFIC STREAM INFORMATION DISSEMINATION DELAY IN VEHICLE-TO-VEHICLE COMMUNICATION NETWORKS IN A TRAFFIC STREAM LiLi Du Depatment of Civil, Achitectual, and Envionmental Engineeing Illinois Institute of Technology 3300

More information

Analysis of Wired Short Cuts in Wireless Sensor Networks

Analysis of Wired Short Cuts in Wireless Sensor Networks Analysis of Wied Shot Cuts in Wieless Senso Netwos ohan Chitaduga Depatment of Electical Engineeing, Univesity of Southen Califonia, Los Angeles 90089, USA Email: chitadu@usc.edu Ahmed Helmy Depatment

More information

Detection and Recognition of Alert Traffic Signs

Detection and Recognition of Alert Traffic Signs Detection and Recognition of Alet Taffic Signs Chia-Hsiung Chen, Macus Chen, and Tianshi Gao 1 Stanfod Univesity Stanfod, CA 9305 {echchen, macuscc, tianshig}@stanfod.edu Abstact Taffic signs povide dives

More information

Illumination methods for optical wear detection

Illumination methods for optical wear detection Illumination methods fo optical wea detection 1 J. Zhang, 2 P.P.L.Regtien 1 VIMEC Applied Vision Technology, Coy 43, 5653 LC Eindhoven, The Nethelands Email: jianbo.zhang@gmail.com 2 Faculty Electical

More information

HISTOGRAMS are an important statistic reflecting the

HISTOGRAMS are an important statistic reflecting the JOURNAL OF L A T E X CLASS FILES, VOL. 14, NO. 8, AUGUST 2015 1 D 2 HistoSketch: Disciminative and Dynamic Similaity-Peseving Sketching of Steaming Histogams Dingqi Yang, Bin Li, Laua Rettig, and Philippe

More information

A modal estimation based multitype sensor placement method

A modal estimation based multitype sensor placement method A modal estimation based multitype senso placement method *Xue-Yang Pei 1), Ting-Hua Yi 2) and Hong-Nan Li 3) 1),)2),3) School of Civil Engineeing, Dalian Univesity of Technology, Dalian 116023, China;

More information

Hierarchically Clustered P2P Streaming System

Hierarchically Clustered P2P Streaming System Hieachically Clusteed P2P Steaming System Chao Liang, Yang Guo, and Yong Liu Polytechnic Univesity Thomson Lab Booklyn, NY 11201 Pinceton, NJ 08540 Abstact Pee-to-pee video steaming has been gaining populaity.

More information

On the Physicl Layout of PRDT-Based NoCs

On the Physicl Layout of PRDT-Based NoCs On the Physicl Layout of PRDT-Based NoCs Guoqiang Yang, Mei Yang, Yulu Yang, Yingtao Jiang Department of Computer Science, Nankai University, Tianin, 000, China Department of Electrical and Computer Engineering,

More information

WIRELESS sensor networks (WSNs), which are capable

WIRELESS sensor networks (WSNs), which are capable IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, VOL. XX, NO. XX, XXX 214 1 Lifetime and Enegy Hole Evolution Analysis in Data-Gatheing Wieless Senso Netwoks Ju Ren, Student Membe, IEEE, Yaoxue Zhang, Kuan

More information

XFVHDL: A Tool for the Synthesis of Fuzzy Logic Controllers

XFVHDL: A Tool for the Synthesis of Fuzzy Logic Controllers XFVHDL: A Tool fo the Synthesis of Fuzzy Logic Contolles E. Lago, C. J. Jiménez, D. R. López, S. Sánchez-Solano and A. Baiga Instituto de Micoelectónica de Sevilla. Cento Nacional de Micoelectónica, Edificio

More information

Dynamic Topology Control to Reduce Interference in MANETs

Dynamic Topology Control to Reduce Interference in MANETs Dynamic Topology Contol to Reduce Intefeence in MANETs Hwee Xian TAN 1,2 and Winston K. G. SEAH 2,1 {stuhxt, winston}@i2.a-sta.edu.sg 1 Depatment of Compute Science, School of Computing, National Univesity

More information

A Novel Automatic White Balance Method For Digital Still Cameras

A Novel Automatic White Balance Method For Digital Still Cameras A Novel Automatic White Balance Method Fo Digital Still Cameas Ching-Chih Weng 1, Home Chen 1,2, and Chiou-Shann Fuh 3 Depatment of Electical Engineeing, 2 3 Gaduate Institute of Communication Engineeing

More information

An Extension to the Local Binary Patterns for Image Retrieval

An Extension to the Local Binary Patterns for Image Retrieval , pp.81-85 http://x.oi.og/10.14257/astl.2014.45.16 An Extension to the Local Binay Pattens fo Image Retieval Zhize Wu, Yu Xia, Shouhong Wan School of Compute Science an Technology, Univesity of Science

More information

Tier-Based Underwater Acoustic Routing for Applications with Reliability and Delay Constraints

Tier-Based Underwater Acoustic Routing for Applications with Reliability and Delay Constraints Tie-Based Undewate Acoustic Routing fo Applications with Reliability and Delay Constaints Li-Chung Kuo Depatment of Electical Engineeing State Univesity of New Yok at Buffalo Buffalo, New Yok 14260 Email:

More information

Module 6 STILL IMAGE COMPRESSION STANDARDS

Module 6 STILL IMAGE COMPRESSION STANDARDS Module 6 STILL IMAE COMPRESSION STANDARDS Lesson 17 JPE-2000 Achitectue and Featues Instuctional Objectives At the end of this lesson, the students should be able to: 1. State the shotcomings of JPE standad.

More information

Combinatorial Mobile IP: A New Efficient Mobility Management Using Minimized Paging and Local Registration in Mobile IP Environments

Combinatorial Mobile IP: A New Efficient Mobility Management Using Minimized Paging and Local Registration in Mobile IP Environments Wieless Netwoks 0, 3 32, 200 200 Kluwe Academic Publishes. Manufactued in The Nethelands. Combinatoial Mobile IP: A New Efficient Mobility Management Using Minimized Paging and Local Registation in Mobile

More information

Topological Characteristic of Wireless Network

Topological Characteristic of Wireless Network Topological Chaacteistic of Wieless Netwok Its Application to Node Placement Algoithm Husnu Sane Naman 1 Outline Backgound Motivation Papes and Contibutions Fist Pape Second Pape Thid Pape Futue Woks Refeences

More information

Lifetime and Energy Hole Evolution Analysis in Data-Gathering Wireless Sensor Networks

Lifetime and Energy Hole Evolution Analysis in Data-Gathering Wireless Sensor Networks 788 IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, VOL. 12, NO. 2, APRIL 2016 Lifetime and Enegy Hole Evolution Analysis in Data-Gatheing Wieless Senso Netwoks Ju Ren, Student Membe, IEEE, Yaoxue Zhang,

More information

SYSTEM LEVEL REUSE METRICS FOR OBJECT ORIENTED SOFTWARE : AN ALTERNATIVE APPROACH

SYSTEM LEVEL REUSE METRICS FOR OBJECT ORIENTED SOFTWARE : AN ALTERNATIVE APPROACH I J C A 7(), 202 pp. 49-53 SYSTEM LEVEL REUSE METRICS FOR OBJECT ORIENTED SOFTWARE : AN ALTERNATIVE APPROACH Sushil Goel and 2 Rajesh Vema Associate Pofesso, Depatment of Compute Science, Dyal Singh College,

More information

Transmission Lines Modeling Based on Vector Fitting Algorithm and RLC Active/Passive Filter Design

Transmission Lines Modeling Based on Vector Fitting Algorithm and RLC Active/Passive Filter Design Tansmission Lines Modeling Based on Vecto Fitting Algoithm and RLC Active/Passive Filte Design Ahmed Qasim Tuki a,*, Nashien Fazilah Mailah b, Mohammad Lutfi Othman c, Ahmad H. Saby d Cente fo Advanced

More information

The Dual Round Robin Matching Switch with Exhaustive Service

The Dual Round Robin Matching Switch with Exhaustive Service The Dual Round Robin Matching Switch with Exhaustive Sevice Yihan Li, Shivenda S. Panwa, H. Jonathan Chao Abstact Vitual Output Queuing is widely used by fixed-length highspeed switches to ovecome head-of-line

More information

4.2. Co-terminal and Related Angles. Investigate

4.2. Co-terminal and Related Angles. Investigate .2 Co-teminal and Related Angles Tigonometic atios can be used to model quantities such as

More information

Color Correction Using 3D Multiview Geometry

Color Correction Using 3D Multiview Geometry Colo Coection Using 3D Multiview Geomety Dong-Won Shin and Yo-Sung Ho Gwangju Institute of Science and Technology (GIST) 13 Cheomdan-gwagio, Buk-ku, Gwangju 500-71, Republic of Koea ABSTRACT Recently,

More information

A Shape-preserving Affine Takagi-Sugeno Model Based on a Piecewise Constant Nonuniform Fuzzification Transform

A Shape-preserving Affine Takagi-Sugeno Model Based on a Piecewise Constant Nonuniform Fuzzification Transform A Shape-peseving Affine Takagi-Sugeno Model Based on a Piecewise Constant Nonunifom Fuzzification Tansfom Felipe Fenández, Julio Gutiéez, Juan Calos Cespo and Gacián Tiviño Dep. Tecnología Fotónica, Facultad

More information

Frequency Domain Approach for Face Recognition Using Optical Vanderlugt Filters

Frequency Domain Approach for Face Recognition Using Optical Vanderlugt Filters Optics and Photonics Jounal, 016, 6, 94-100 Published Online August 016 in SciRes. http://www.scip.og/jounal/opj http://dx.doi.og/10.436/opj.016.68b016 Fequency Domain Appoach fo Face Recognition Using

More information

An Efficient Handover Mechanism Using the General Switch Management Protocol on a Multi-Protocol Label Switching Network

An Efficient Handover Mechanism Using the General Switch Management Protocol on a Multi-Protocol Label Switching Network An Efficient andove Mechanism Using the Geneal Switch Management Potocol on a Multi-Potocol abel Switching Netwok Seong Gon hoi, yun Joo Kang, and Jun Kyun hoi Using the geneal switch management potocol

More information

Quality Aware Privacy Protection for Location-based Services

Quality Aware Privacy Protection for Location-based Services In Poceedings of the th Intenational Confeence on Database Systems fo Advanced Applications (DASFAA 007), Bangkok, Thailand, Apil 9-, 007. Quality Awae Pivacy Potection fo Location-based Sevices Zhen Xiao,,

More information

Spiral Recognition Methodology and Its Application for Recognition of Chinese Bank Checks

Spiral Recognition Methodology and Its Application for Recognition of Chinese Bank Checks Spial Recognition Methodology and Its Application fo Recognition of Chinese Bank Checks Hanshen Tang 1, Emmanuel Augustin 2, Ching Y. Suen 1, Olivie Baet 2, Mohamed Cheiet 3 1 Cente fo Patten Recognition

More information

On the Conversion between Binary Code and Binary-Reflected Gray Code on Boolean Cubes

On the Conversion between Binary Code and Binary-Reflected Gray Code on Boolean Cubes On the Convesion between Binay Code and BinayReflected Gay Code on Boolean Cubes The Havad community has made this aticle openly available. Please shae how this access benefits you. You stoy mattes Citation

More information

On Adaptive Bandwidth Sharing with Rate Guarantees

On Adaptive Bandwidth Sharing with Rate Guarantees On Adaptive Bandwidth Shaing with Rate Guaantees N.G. Duffield y T. V. Lakshman D. Stiliadis y AT&T Laboatoies Bell Labs Rm A175, 180 Pak Avenue Lucent Technologies Floham Pak, 101 Cawfods Cone Road NJ

More information

High performance CUDA based CNN image processor

High performance CUDA based CNN image processor High pefomance UDA based NN image pocesso GEORGE VALENTIN STOIA, RADU DOGARU, ELENA RISTINA STOIA Depatment of Applied Electonics and Infomation Engineeing Univesity Politehnica of Buchaest -3, Iuliu Maniu

More information

An Improved Resource Reservation Protocol

An Improved Resource Reservation Protocol Jounal of Compute Science 3 (8: 658-665, 2007 SSN 549-3636 2007 Science Publications An mpoved Resouce Resevation Potocol Desie Oulai, Steven Chambeland and Samuel Piee Depatment of Compute Engineeing

More information

THE THETA BLOCKCHAIN

THE THETA BLOCKCHAIN THE THETA BLOCKCHAIN Theta is a decentalized video steaming netwok, poweed by a new blockchain and token. By Theta Labs, Inc. Last Updated: Nov 21, 2017 esion 1.0 1 OUTLINE Motivation Reputation Dependent

More information

Adaptation of TDMA Parameters Based on Network Conditions

Adaptation of TDMA Parameters Based on Network Conditions Adaptation of TDMA Paametes Based on Netwok Conditions Boa Kaaoglu Dept. of Elect. and Compute Eng. Univesity of Rocheste Rocheste, NY 14627 Email: kaaoglu@ece.ocheste.edu Tolga Numanoglu Dept. of Elect.

More information

Lecture 27: Voronoi Diagrams

Lecture 27: Voronoi Diagrams We say that two points u, v Y ae in the same connected component of Y if thee is a path in R N fom u to v such that all the points along the path ae in the set Y. (Thee ae two connected components in the

More information

Obstacle Avoidance of Autonomous Mobile Robot using Stereo Vision Sensor

Obstacle Avoidance of Autonomous Mobile Robot using Stereo Vision Sensor Obstacle Avoidance of Autonomous Mobile Robot using Steeo Vision Senso Masako Kumano Akihisa Ohya Shin ichi Yuta Intelligent Robot Laboatoy Univesity of Tsukuba, Ibaaki, 35-8573 Japan E-mail: {masako,

More information

Dynamic Multiple Parity (DMP) Disk Array for Serial Transaction Processing

Dynamic Multiple Parity (DMP) Disk Array for Serial Transaction Processing IEEE TRANSACTIONS ON COMPUTERS, VOL. 50, NO. 9, SEPTEMBER 200 949 Dynamic Multiple Paity (DMP) Disk Aay fo Seial Tansaction Pocessing K.H. Yeung, Membe, IEEE, and T.S. Yum, Senio Membe, IEEE AbstactÐThe

More information

EFFICIENT ENERGY BASED CONGESTION CONTROL SCHEME FOR MOBILE AD HOC NETWORKS

EFFICIENT ENERGY BASED CONGESTION CONTROL SCHEME FOR MOBILE AD HOC NETWORKS FFICINT NRGY BASD CONGSTION CONTROL SCHM FOR MOBIL AD HOC NTWORKS 1 S.SHJA, 2 DR.RAMACHANDRA V PUJRI 1 Reseach Schola, Bhaathia Univesity, Coimbatoe. 2 Vice-Pincipal, KGiSL Institute of Technology, Saavanampatti,

More information

Point-Biserial Correlation Analysis of Fuzzy Attributes

Point-Biserial Correlation Analysis of Fuzzy Attributes Appl Math Inf Sci 6 No S pp 439S-444S (0 Applied Mathematics & Infomation Sciences An Intenational Jounal @ 0 NSP Natual Sciences Publishing o Point-iseial oelation Analysis of Fuzzy Attibutes Hao-En hueh

More information

View Synthesis using Depth Map for 3D Video

View Synthesis using Depth Map for 3D Video View Synthesis using Depth Map fo 3D Video Cheon Lee and Yo-Sung Ho Gwangju Institute of Science and Technology (GIST) 1 Oyong-dong, Buk-gu, Gwangju, 500-712, Republic of Koea E-mail: {leecheon, hoyo}@gist.ac.k

More information

A New Finite Word-length Optimization Method Design for LDPC Decoder

A New Finite Word-length Optimization Method Design for LDPC Decoder A New Finite Wod-length Optimization Method Design fo LDPC Decode Jinlei Chen, Yan Zhang and Xu Wang Key Laboatoy of Netwok Oiented Intelligent Computation Shenzhen Gaduate School, Habin Institute of Technology

More information

Wormhole Detection and Prevention in MANETs

Wormhole Detection and Prevention in MANETs Womhole Detection and Pevention in MANETs Lija Joy Compute Science and Engineeing KMEA Engineeing College Enakulum, Keala, India lijavj@gmail.com Sheena Kuian K Compute Science and Engineeing KMEA Engineeing

More information

IS-IS Protocol Hardware Implementation for VPN Solutions

IS-IS Protocol Hardware Implementation for VPN Solutions IS-IS Potocol Hadwae Implementation fo VPN Solutions MOHAMED ABOU-GABAL, RAYMOND PETERKIN, DAN IONESCU School of Infomation Technology and Engineeing (SITE) Univesity of Ottawa 161 Louis Pasteu, P.O. Box

More information

Conversion Functions for Symmetric Key Ciphers

Conversion Functions for Symmetric Key Ciphers Jounal of Infomation Assuance and Secuity 2 (2006) 41 50 Convesion Functions fo Symmetic Key Ciphes Deba L. Cook and Angelos D. Keomytis Depatment of Compute Science Columbia Univesity, mail code 0401

More information

Characterizing Data Deliverability of Greedy Routing in Wireless Sensor Networks

Characterizing Data Deliverability of Greedy Routing in Wireless Sensor Networks Chaacteizing Data Deliveability of Geedy Routing in Wieless Senso Netwoks Jinwei Liu, Lei Yu, Haiying Shen, Yangyang He and Jason Hallstom Depatment of Electical and Compute Engineeing, Clemson Univesity,

More information

Multi-azimuth Prestack Time Migration for General Anisotropic, Weakly Heterogeneous Media - Field Data Examples

Multi-azimuth Prestack Time Migration for General Anisotropic, Weakly Heterogeneous Media - Field Data Examples Multi-azimuth Pestack Time Migation fo Geneal Anisotopic, Weakly Heteogeneous Media - Field Data Examples S. Beaumont* (EOST/PGS) & W. Söllne (PGS) SUMMARY Multi-azimuth data acquisition has shown benefits

More information

arxiv: v2 [physics.soc-ph] 30 Nov 2016

arxiv: v2 [physics.soc-ph] 30 Nov 2016 Tanspotation dynamics on coupled netwoks with limited bandwidth Ming Li 1,*, Mao-Bin Hu 1, and Bing-Hong Wang 2, axiv:1607.05382v2 [physics.soc-ph] 30 Nov 2016 1 School of Engineeing Science, Univesity

More information

MapReduce Optimizations and Algorithms 2015 Professor Sasu Tarkoma

MapReduce Optimizations and Algorithms 2015 Professor Sasu Tarkoma apreduce Optimizations and Algoithms 2015 Pofesso Sasu Takoma www.cs.helsinki.fi Optimizations Reduce tasks cannot stat befoe the whole map phase is complete Thus single slow machine can slow down the

More information

A Two-stage and Parameter-free Binarization Method for Degraded Document Images

A Two-stage and Parameter-free Binarization Method for Degraded Document Images A Two-stage and Paamete-fee Binaization Method fo Degaded Document Images Yung-Hsiang Chiu 1, Kuo-Liang Chung 1, Yong-Huai Huang 2, Wei-Ning Yang 3, Chi-Huang Liao 4 1 Depatment of Compute Science and

More information

Coded Distributed Computing

Coded Distributed Computing Coded Distibuted Computing Salman Avestimeh USC joint wok with Songze Li (USC), Qian Yu (USC), and Mohammad Maddah-Ali (Bell-Labs) Asiloma Confeence Nov. 2016 Infastuctues fo (Big) Data Analytics How to

More information

A Full-mode FME VLSI Architecture Based on 8x8/4x4 Adaptive Hadamard Transform For QFHD H.264/AVC Encoder

A Full-mode FME VLSI Architecture Based on 8x8/4x4 Adaptive Hadamard Transform For QFHD H.264/AVC Encoder 20 IEEE/IFIP 9th Intenational Confeence on VLSI and System-on-Chip A Full-mode FME VLSI Achitectue Based on 8x8/ Adaptive Hadamad Tansfom Fo QFHD H264/AVC Encode Jialiang Liu, Xinhua Chen College of Infomation

More information

A New and Efficient 2D Collision Detection Method Based on Contact Theory Xiaolong CHENG, Jun XIAO a, Ying WANG, Qinghai MIAO, Jian XUE

A New and Efficient 2D Collision Detection Method Based on Contact Theory Xiaolong CHENG, Jun XIAO a, Ying WANG, Qinghai MIAO, Jian XUE 5th Intenational Confeence on Advanced Mateials and Compute Science (ICAMCS 2016) A New and Efficient 2D Collision Detection Method Based on Contact Theoy Xiaolong CHENG, Jun XIAO a, Ying WANG, Qinghai

More information

IP MULTICAST. Adiseshu Hari, T. V. Lakshman and Gordon Wilfong Nokia Bell Labs

IP MULTICAST. Adiseshu Hari, T. V. Lakshman and Gordon Wilfong Nokia Bell Labs IP MULTICAST Adiseshu Hai, T. V. Lakshman and Godon Wilfong Nokia DIMACS Wokshop on Algoithms fo Data Cente Netwoks Rutges Univesity, NJ 1 Why is IP Multicast not deployed in public netwoks? Denial-of-Sevice

More information

And Ph.D. Candidate of Computer Science, University of Putra Malaysia 2 Faculty of Computer Science and Information Technology,

And Ph.D. Candidate of Computer Science, University of Putra Malaysia 2 Faculty of Computer Science and Information Technology, (IJCSIS) Intenational Jounal of Compute Science and Infomation Secuity, Efficient Candidacy Reduction Fo Fequent Patten Mining M.H Nadimi-Shahaki 1, Nowati Mustapha 2, Md Nasi B Sulaiman 2, Ali B Mamat

More information

Mobility Pattern Recognition in Mobile Ad-Hoc Networks

Mobility Pattern Recognition in Mobile Ad-Hoc Networks Mobility Patten Recognition in Mobile Ad-Hoc Netwoks S. M. Mousavi Depatment of Compute Engineeing, Shaif Univesity of Technology sm_mousavi@ce.shaif.edu H. R. Rabiee Depatment of Compute Engineeing, Shaif

More information

AN ANALYSIS OF COORDINATED AND NON-COORDINATED MEDIUM ACCESS CONTROL PROTOCOLS UNDER CHANNEL NOISE

AN ANALYSIS OF COORDINATED AND NON-COORDINATED MEDIUM ACCESS CONTROL PROTOCOLS UNDER CHANNEL NOISE AN ANALYSIS OF COORDINATED AND NON-COORDINATED MEDIUM ACCESS CONTROL PROTOCOLS UNDER CHANNEL NOISE Tolga Numanoglu, Bulent Tavli, and Wendi Heinzelman Depatment of Electical and Compute Engineeing Univesity

More information

RT-WLAN: A Soft Real-Time Extension to the ORiNOCO Linux Device Driver

RT-WLAN: A Soft Real-Time Extension to the ORiNOCO Linux Device Driver 1 RT-WLAN: A Soft Real-Time Extension to the ORiNOCO Linux Device Dive Amit Jain Daji Qiao Kang G. Shin The Univesity of Michigan Ann Abo, MI 4819, USA {amitj,dqiao,kgshin@eecs.umich.edu Abstact The cuent

More information

A Recommender System for Online Personalization in the WUM Applications

A Recommender System for Online Personalization in the WUM Applications A Recommende System fo Online Pesonalization in the WUM Applications Mehdad Jalali 1, Nowati Mustapha 2, Ali Mamat 2, Md. Nasi B Sulaiman 2 Abstact foeseeing of use futue movements and intentions based

More information

Event-based Location Dependent Data Services in Mobile WSNs

Event-based Location Dependent Data Services in Mobile WSNs Event-based Location Dependent Data Sevices in Mobile WSNs Liang Hong 1, Yafeng Wu, Sang H. Son, Yansheng Lu 3 1 College of Compute Science and Technology, Wuhan Univesity, China Depatment of Compute Science,

More information

Conservation Law of Centrifugal Force and Mechanism of Energy Transfer Caused in Turbomachinery

Conservation Law of Centrifugal Force and Mechanism of Energy Transfer Caused in Turbomachinery Poceedings of the 4th WSEAS Intenational Confeence on luid Mechanics and Aeodynamics, Elounda, Geece, August 1-3, 006 (pp337-34) Consevation Law of Centifugal oce and Mechanism of Enegy Tansfe Caused in

More information

Shortest Paths for a Two-Robot Rendez-Vous

Shortest Paths for a Two-Robot Rendez-Vous Shotest Paths fo a Two-Robot Rendez-Vous Eik L Wyntes Joseph S B Mitchell y Abstact In this pape, we conside an optimal motion planning poblem fo a pai of point obots in a plana envionment with polygonal

More information

APPLICATION OF STRUCTURED QUEUING NETWORKS IN QOS ESTIMITION OF TELECOMMUNICATION SERVICE

APPLICATION OF STRUCTURED QUEUING NETWORKS IN QOS ESTIMITION OF TELECOMMUNICATION SERVICE APPLICATION OF STRUCTURED QUEUING NETWORKS IN QOS ESTIMITION OF TELECOMMUNICATION SERVICE 1 YAROSLAVTSEV A.F., 2 Al-THUNEIBAT S.A., 3 AL TAWALBEH N.A 1 Depatment of Netwoking, SSUTI, Novosibisk, Russia

More information

Fifth Wheel Modelling and Testing

Fifth Wheel Modelling and Testing Fifth heel Modelling and Testing en Masoy Mechanical Engineeing Depatment Floida Atlantic Univesity Boca aton, FL 4 Lois Malaptias IFMA Institut Fancais De Mechanique Advancee ampus De lemont Feand Les

More information

Exploring non-typical memcache architectures for decreased latency and distributed network usage.

Exploring non-typical memcache architectures for decreased latency and distributed network usage. Syacuse Univesity SURFACE Electical Engineeing and Compute Science Technical Repots College of Engineeing and Compute Science 9-5-20 Exploing non-typical memcache achitectues fo deceased latency and distibuted

More information

On Error Estimation in Runge-Kutta Methods

On Error Estimation in Runge-Kutta Methods Leonado Jounal of Sciences ISSN 1583-0233 Issue 18, Januay-June 2011 p. 1-10 On Eo Estimation in Runge-Kutta Methods Ochoche ABRAHAM 1,*, Gbolahan BOLARIN 2 1 Depatment of Infomation Technology, 2 Depatment

More information

Configuring RSVP-ATM QoS Interworking

Configuring RSVP-ATM QoS Interworking Configuing RSVP-ATM QoS Intewoking Last Updated: Januay 15, 2013 This chapte descibes the tasks fo configuing the RSVP-ATM QoS Intewoking featue, which povides suppot fo Contolled Load Sevice using RSVP

More information

= dv 3V (r + a 1) 3 r 3 f(r) = 1. = ( (r + r 2

= dv 3V (r + a 1) 3 r 3 f(r) = 1. = ( (r + r 2 Random Waypoint Model in n-dimensional Space Esa Hyytiä and Joma Vitamo Netwoking Laboatoy, Helsinki Univesity of Technology, Finland Abstact The andom waypoint model (RWP) is one of the most widely used

More information

i-pcgrid Workshop 2016 April 1 st 2016 San Francisco, CA

i-pcgrid Workshop 2016 April 1 st 2016 San Francisco, CA i-pcgrid Wokshop 2016 Apil 1 st 2016 San Fancisco, CA Liang Min* Eddy Banks, Bian Kelley, Met Kokali, Yining Qin, Steve Smith, Philip Top, and Caol Woodwad *min2@llnl.gov, 925-422-1187 LDRD 13-ERD-043

More information

Cellular Neural Network Based PTV

Cellular Neural Network Based PTV 3th Int Symp on Applications of Lase Techniques to Fluid Mechanics Lisbon, Potugal, 6-9 June, 006 Cellula Neual Netwok Based PT Kazuo Ohmi, Achyut Sapkota : Depatment of Infomation Systems Engineeing,

More information

Chapter 4 Network Layer

Chapter 4 Network Layer Chapte 4 Netwok Laye Reti di Elaboatoi Coso di Lauea in Infomatica Univesità degli Studi di Roma La Sapienza Canale A-L Pof.ssa Chiaa Petioli Pate di queste slide sono state pese dal mateiale associato

More information

Decentralized Trust Management for Ad-Hoc Peer-to-Peer Networks

Decentralized Trust Management for Ad-Hoc Peer-to-Peer Networks Decentalized Tust Management fo Ad-Hoc Pee-to-Pee Netwoks Thomas Repantis Vana Kalogeaki Depatment of Compute Science & Engineeing Univesity of Califonia, Riveside Riveside, CA 92521 {tep,vana}@cs.uc.edu

More information