摘要:
The method and apparatus employ a texture filter in a graphics processor to perform a transform such as, for example, a Fast Fourier Transform. The texturizer can include an array of linear interpolators. The architecture reduces the computational complexity of the transform processes.
摘要:
A method an system provide that image processing operations and graphics processing are both performed by a graphics rendering system. The texture memory and a texture filter of the graphics rendering system are used to perform look-up table operations as well as multiply and accumulate operations typically associated with image processing.
摘要:
In a computer system including a processor coupled to a memory via a bus, a system for a reduced instruction set graphics processing subsystem. The graphics processing subsystem is configured to accept graphics data from a computer system via a bus. The graphics processing subsystem is deeply pipelined to achieve high bandwidth, and is operable for processing graphics data including a first and second set of graphics instructions. The graphics instructions from the second set are more complex than the graphics instructions from the first set. The graphics processing subsystem also includes a built-in recirculation path for enabling the execution of graphics instructions by multi-pass. The graphics pipeline is streamlined such that the graphics instructions from the first set are processed efficiently. The graphics instructions from the second set are processed by using multi-pass via the recirculation path. By being optimized for the first set of graphics instructions, the graphics pipeline is able to run at very high clock speeds, thereby increasing its aggregate bandwidth.
摘要:
The integers involved in the computation are embedded into a modular system whose index (i.e., its modulus) is an integer M that is bigger than all of these integers involved. In other words, these integers are treated not as belonging to ordinary integers anymore, but as “modular integers” belonging to the modular system indexed by M. Having completed the embedding, CRT provides the bridge which connects the single modular system indexed by M (ZM) with a collection of k modular systems indexed by m1,m2, . . . , mk respectively (Zm1, Zm2, . . . , Zmk), where M factorizes as m1*m2*m3* . . . *mk, and where each mi is slightly smaller than single precision. Then, after numbers are manipulated within modular arithmetic, the answer is reconstructed via the algorithm of CRT, also known as CRA. Finally, the present invention introduces the process of dinking that overcomes the major weakness of implementing division with modular arithmetic. Particularly, within a composite modular arithmetic system, any theoretically impossible modular division is altered slightly [dinked] to a theoretical possible modular division whose quotient is closed enough to the true quotient sought, thus allowing all four arithmetic operations of modular arithmetic in high precision computation.
摘要:
Methods, systems, and apparatus, including computer program products, in which access allocations to a spectrum band and transmit rights to the access allocations are defined. Real-time auction bids for the transmit rights to the access allocations to the spectrum band are received, and the transmit rights are awarded to biding devices based on the real-time auction bids.
摘要:
A spread spectrum system having data transmitted in a spread spectrum signal. Periodic and quasi-periodic signals which act as interference in the spectrum of interest is effectively filtered out by using a linear predictive coding filter. The LPC filter takes a digitized received spread spectrum signal and generates a set of predictive coefficients and a set of error coefficients. The predictive coefficients represent the interfering periodic and/or quasi-periodic signals. As such, the set of predictive coefficients are discarded. The remaining error coefficients represent what is left over and thereby contains the useful transmitted data found within the spread spectrum signal. The error coefficients are used by the signal processing block to extract the transmitted data.
摘要:
The present invention provides efficient and effective quality of service for information that is time sensitive (e.g., real time data). An intermediate network communication system and method (e.g., a router) of the present invention performs cut through switching to reduce latency problems for time sensitive information. In one embodiment of the present invention, communication packet header information is encoded with a time sensitive identifier that identifies the information as time sensitive. In one exemplary transfer control protocol/internet protocol TCP/IP implementation of the present invention, time sensitive indication is provided in the link layer information. In one embodiment of the present invention, time sensitive information is dropped if the intermediate network device can not communicate the information within specified timing constraints. In one embodiment of the present invention time sensitive information is cut through routed on a virtual channel and pre-empts non time sensitive information. In one embodiment a communication path probe is cut through routed via intermediate network devices to establish a communication path before other information is communicated from a originating source to a final destination. In one embodiment the present invention leverages previously collected information to establish a communication path. In one embodiment the present invention, an intermediate network device establishes a second communication link if a first communication link is unavailable.
摘要:
The present invention pertains to an apparatus for and method of mapping texture memory to a texture cache such that cache contention is minimized. Significantly, in one embodiment of the present invention, addresses of the texture memory are mapped to entries of the texture cache according to a predetermined hashing scheme. According to the one embodiment, texture memory is addressed as a virtually contiguous address space by a multi-dimensional index. The multi-dimensional index is further partitioned into a low order bit field and a high order bit field. Low order bits of the multi-dimensional index are directly mapped to low order bits of the cache address. High order bits of the multi-dimensional index are mapped to high order bits of the cache address according to a predetermined address-hashing scheme. Particularly, in one embodiment, high order bits of the multi-dimensional index are selectively “exclusive-or-ed” to generate corresponding addresses of the texture cache.
摘要:
A system and method for restoring bits of pixels prior to display where the original bits of the pixels were truncated compares each pixel to its neighbors to determine the relative value of each pixel as compared to its neighbors. First, the truncated pixel is shifted. That is, the remaining bits of the pixel are shifted to the left and additional bits are added in the least significant bit positions. Next, the pixel is compared to its neighbors to determine their relative values. For each neighbor that is greater than the pixel in question, the truncated shifted pixel is incremented by one. Similarly, for each neighbor that is less than the pixel in question, the truncated shifted pixel is decremented by one. Once the pixel is evaluated relative to its neighboring pixels, determination of the restored pixel is complete. The restored pixel can then be displayed.
摘要:
Methods, systems, and apparatus, including computer program products, for implementing interference cancellation across base stations. Communications information for transmitting to a receiving device is received from a first base station at a second base station. At the second base station, second communications information is generated for transmission to the receiving device from the second base station. The second communications information comprises data to reduce interference with the first communications information.