초록 ▼

An internetworking device having a set of network interface cards, where each network interface card is able to address and send data to any of the other network interface cards. According to one embodiment, when one of the network interface cards receives a network layer packet that should be forwa

An internetworking device having a set of network interface cards, where each network interface card is able to address and send data to any of the other network interface cards. According to one embodiment, when one of the network interface cards receives a network layer packet that should be forwarded to another one of the network interface cards, a process running on the network interface card that received the network layer packet determines a destination address of the network layer packet and determines whether the destination address matches a network layer address of the internetworking device. If the destination address does not match a network layer address of the internetworking device, the process further determines, based on the destination address of the network layer packet, the network interface card to which the network layer packet should be forwarded. Otherwise the process examines a destination port field within a transport layer packet encapsulated by the network layer packet to determine a destination port number and determines, based at least in part on the destination port number, the network interface card to which the network layer packet should be forwarded. In this manner, transport layer processing does not have to be centralized within the internetworking device. Instead, the present invention allows each network interface card to have a transport layer process, wherein each transport layer process has the same network layer addresses.

대표청구항 ▼

An internetworking device having a set of network interface cards, where each network interface card is able to address and send data to any of the other network interface cards. According to one embodiment, when one of the network interface cards receives a network layer packet that should be forwa

An internetworking device having a set of network interface cards, where each network interface card is able to address and send data to any of the other network interface cards. According to one embodiment, when one of the network interface cards receives a network layer packet that should be forwarded to another one of the network interface cards, a process running on the network interface card that received the network layer packet determines a destination address of the network layer packet and determines whether the destination address matches a network layer address of the internetworking device. If the destination address does not match a network layer address of the internetworking device, the process further determines, based on the destination address of the network layer packet, the network interface card to which the network layer packet should be forwarded. Otherwise the process examines a destination port field within a transport layer packet encapsulated by the network layer packet to determine a destination port number and determines, based at least in part on the destination port number, the network interface card to which the network layer packet should be forwarded. In this manner, transport layer processing does not have to be centralized within the internetworking device. Instead, the present invention allows each network interface card to have a transport layer process, wherein each transport layer process has the same network layer addresses. 58348, 19760500, Sakamoto, 040/374; US-3973344, 19760800, Frankel, 040/706; US-4202122, 19800500, Namiki, 040/710; US-4832482, 19890500, Kallenberg, 353/120; US-5835201, 19981100, Itano et al., 355/075; US-6157440, 20001200, Ikeda, 355/075; US-6169611, 20010100, Brook, III et al., 358/487; US-6195182, 20010200, Kunishige, 358/487; US-6295143, 20010900, Lee et al., 358/487 ed greyscale value of the pixel with a threshold to select an output value representing the pixel; (c) calculating a second error term having a value that is less than the difference between the output value and the modified greyscale value; (d) distributing the second error term to a preselected plurality of neighboring pixels at positions (n+1, l), (n-1, l+1), (n, l+1), (n+1, l+1), wherein the portion of the second error term distributed to the pixel at position (n+1, l+1) equals the portion of the second error term distributed to the pixel at position (n-1, l+1), and the portion of the second error term distributed to the pixel at position (n-1, l+1) combined with the portion of the second error term for the pixel at position (n+1, l+1) equals the portion of the second error term for the pixel at position (n, l+1), and the portion of the second error term distributed to the pixel at position (n+1, l) equals the sum of the portion of the second error term of the pixel at position (n+1, l+1) combined with the portion of the second error term of the pixel at position (n, l+1) and combined with the portion of the second error term of the pixel at position (n-1, l+1); and (e) repeating steps (a)-(d) for each pixel within the image. 11. The method of claim 10 wherein the order in which the pixels are processed is determined using raster scanning. 12. The method of claim 10 wherein the order in which the pixels are processed is determined using serpentine scanning. 13. The method of claim 10 wherein the portion of the second error term distributed to the pixel at position (n+1, l) is about 0.484375, the portion of the second error term distributed to the pixel at position (n-1, l+1) is about 0.12109375, the portion of the second error term distributed to the pixel at position (n, l+1) is about 0.2421875 and the portion of the second error term distributed to the pixel at position (n+1, l+1) is about 0.12109375. 14. An apparatus for diffusing error caused by quantizing each pixel within an image formed of a plurality of pixels, each pixel representing a greyscale value of the image at a location (n, l) within the image, and having an original greyscale value associated therewith, the apparatus comprising: a first summing module for adding to the original greyscale value of a pixel having a position (n, l) within the image a first error term resulting from quantization of previously processed pixels to derive a modified greyscale value; a second summing module operatively connected to the output of the first summing module and the output of the quantizer for calculating a second error term having a value that is less than the difference between the output value and the modified greyscale value; a quantizer operatively connected to the output of the first module comparing the modified greyscale value of the pixel with a threshold to select an output value representing the pixel; and an error filter module operatively connected to the input of the first summing module and the output of the second summing module for distributing the second error term, to preselected plurality of neighboring pixels at positions (n+1, l), (n-1, l+1), (n, l+1), (n+1, l+1) using a linear phase filter algorithm having a set of distribution coefficients with a sum less than one, wherein one of the coefficients within the set of coefficients is combined with the second error term for each pixel position. 15. The apparatus of claim 14 wherein the linear phase filter algorithm of the error filter module uses finite impulse response techniques. 16. The apparatus of claim 14 wherein the combining of one coefficient with the second error term for each pixel position is accomplished by multiplying each coefficient by the second error term. 17. The apparatus of claim 14 wherein the error filter module further distributes the second error term such that the pixel at position (n+1, l+1) equals the portion of the second error term distributed to the pixel at position (n-1, l+1). 18. The apparatus of claim 17 wherein the error filter module further distributes the second error term such that the pixel at position (n-1, l+1) combined with the portion of the second error term for the pixel at position (n+1, l+1) equals the portion of the second error term for the pixel at position (n, l+1). 19. The apparatus of claim 18 wherein the error filter module further distributes the second error term such that the pixel at position (n+1, l) equals the sum of the portion of the second error term of the pixel at position (n+1, l+1) combined with the portion of the second error term of the pixel at position (n, l+1) and combined with the portion of the second error term of the pixel at position (n-1, l+1). 20. The apparatus of claim 19 wherein the error filter module further distributes the second error term to preselected plurality of pixels, including pixels at positions (n+1, l), (n-1, l+1), (n, l+1), (n+1, l+1), such that the portion of the second error term distributed to the pixel at position (n+1, l) is about 0.484375, the portion of the second error term distributed to the pixel at position (n-1, l+1) is about 0.12109375, the portion of the second error term distributed to the pixel at position (n, l+1) is about 0.2421875 and the portion of the second error term distributed to the pixel at position (n+1, l+1) is about 0.12109375. 21. The apparatus of claim 14 wherein the order in which the pixels are processed is determined using raster scanning. 22. The apparatus of claim 14 wherein the order in which the pixels are processed is determined using serpentine scanning. 23. The apparatus of claim 14 wherein the output of the quantizer is operatively connected to a device used to print the image. 24. The apparatus of claim 14 further comprising: a memory element, including a storage location for at least some of the pixels in the plurality of pixels of an image, wherein the portion of the second error term distributed to a particular pixel is added to contents of the designated storage location of that particular pixel. WO 00/62998, WO; WO 01/83193, WO; WO 02/20246, WO