McCormick, B.T., The Illinois Pattern Recognition Computer -- ILLIAC III, IEEE Trans. on Elect. Computers, Dec., 1963, pp. 791-813.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....in the opposite direction as far as the next break. Processors that have not broken the bus are listeners. This scheme is similar to those that were later proposed by [15, 18, 20] and is a generalization of the propagate operation in the CLIP 4 [4] and the flashthrough mode of the ILLIAC III [19]. Because all of the processors in a bus segment can listen to the message being transmitted, there is also some similarity to a broadcast protocol multiprocessor [17] In an implementation with chained pass transistors and buffers, the propagation speed can be quite slow. A practical ....

McCormick, B.T., The Illinois Pattern Recognition Computer -- ILLIAC III, IEEE Trans. on Elect. Computers, Dec., 1963, pp. 791-813.

....A coterie is a bus in the sense that, at any time, a single incident PE can talk while all other incident PEs listen. See Fig. 8. Techniques similar to those described here will work on relatives of the ECN, such as the RMesh [17] the Polymorphic Torus [15] and the networks of the Illiac III [18] and Clip 4 [6] 4.3.1 Algorithmic Issues We assess unit time for each point to point communication in C t n as with other arrays. For each coterie communication, such an assessment is unrealisticbecause of switch traversals and distancesunless we restrict the sidedimension n to a fixed ....

B.T. McCormick, The Illinois Pattern Recognition Computer- ILLIAC III., IEEE Trans. Electronic Computers, vol. 12, pp. 791813, 1963.

....smaller. General Communication Many SIMD arrays have additional interPE communication networks. These have included the CM 2 packet switched network, which supports broadcast, reduction, and scans [34] the MasPar circuit switched network [2] and various networks based on broadcast buses [8, 20, 25, 29, 39]. Nearly all of these networks have the property that the communication takes from a few to a few thousand PE instruction cycles during which time the PEs are idle. Feedback from Array to Controller Nearly all SIMD array systems have a mechanism to summarize array information through a global OR ....

McCormick, B. T. The Illinois Pattern Recognition Computer { ILLIAC III. IEEE Trans. on Electronic Computers C-12, 12 (1963), 791-813.

....full indirect addressing, but can only use it to access off chip memory which is ten times slower than on chip. Broadcast Buses The ability to transmit data through direct electrical connections over long distances has been included in many architectures, starting perhaps with the ILLIAC III [25]. One manifestation is row and column broadcast buses: PEs initiate a broadcast by writing to a communication register, the signal then propagates along either the rows or the columns for some small, predetermined number of cycles. PEs then acquire the signal broadcast on their own row or column ....

McCormick, B.T. The Illinois Pattern Recognition Computer -- ILLIAC III. IEEE Trans. on Elec. Comp. C-12, 12 (Dec. 1963), 791-813.

....in many areas of computation. Some of the applications for which particular machines have been used and the types of computations that dominate these applications are now described. ffl Image Analysis. One of the earliest MPAs, the Illiac III, was designed to process bubble chamber negatives [107]. The input consisted of binary images of ion tracks. The output was a list of nodes (defined as end points and branches) that characterize each track. The preliminary tasks in processing the tracks are computing edges, line thinning, gap filling, and line smoothing. To obtain the node information ....

McCormick, B. T. The Illinois Pattern Recognition Computer -- ILLIAC III. IEEE Transactions on Electronic Computers C-12, 12 (1963), 791--813.

....information by writing to a specified register connected to the coterie network. PEs then read a register which will have been set to the OR of these signals, within a local group as defined by the network configuration. This scheme is a generalization of the flash through mode of the ILLIAC III [23] and the propagate operation in the CLIP 4 [8] and is similar to those proposed by [24, 20] In order to distinguish broadcast by PEs from the usual broadcast by the controller, we refer to this operation as coterie multicast . The coterie network is one powerful addition that the CAAPP has over ....

B.T. McCormick (1963): "The Illinois Pattern Recognition Computer -- ILLIAC III," IEEE Trans. on Elect. Computers, C-12 (12).

....University of Missouri Columbia, Columbia, MO 65211. E mail: shi cecs.missouri.edu. 2 Wilson, et al. An Image Algebra Based SIMD Image Processing Environment 1 Introduction The advent of vlsi technology led image processing researchers to use such simd, mesh connected computers as the illiac [2], the clip series [3, 4, 5] the dap [6] the mpp [7] the gapp [8, 9] and the Hughes 3D Computer [10] for improving their codes performance. Both the performance and cost effectiveness of simd machines have improved steadily. However, the current software development systems are still ....

B. H. McCormick. The Illinois pattern recognition computer -- Illiac iii. IEEE Transactions on Electronic Computers, 12:791--813, 1963.

....real time performance [3, 4] The SIMD mesh architecture is considered as a natural parallel architecture for image processing because it directly mirrors image data structures and can be easily implemented in hardware. Parallel computers based on the SIMD mesh architecture, such as the ILLIAC [5], the CLIP series [6, 7, 8] the DAP [9] the MPP [10] the 3D machine [11] and the GAPP [12, 13] have been built. However, fuzzy integral filters require parallelism within the processing elements (PEs) in addition to a large number of PEs in the processor array. Computing the output value ....

B. H. McCormick. The Illinois pattern recognition computer -- ILLIAC III. IEEE Transactions on Electronic Computers, 12:791--813, 1963.

.... since the late 1950 s that SIMD arrays are well suited for image to image computing [37] By the early 1960 s it had been discovered that they were also excellent for extracting features from images: for example, the Illiac III was built specifically to extract tracks in bubble chamber images [26]. Several decades of further study have found SIMD arrays useful in an increasingly wide variety of computer NetAd: herbordt uh.edu. Supported in part by an IBM Fellowship and by the NSF through CAREER award #9702483. y NetAd: burrill cs.umass.edu. Supported in part by DARPA ....

McCormick, B. T. The Illinois Pattern Recognition Computer -- ILLIAC III. IEEE Trans. on Electronic Computers C-12, 12 (1963), 791--813.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC