Marvell International Limited

Arm Limited

Marvellworld Trade Ltd.

Adam George

Bradley C Aldrich

Michael Filippo

Ping-Sing Tsai

Thomas A Hartin

Muhammad Umar Farooq

Hongxin Li

Matthew Paul Elwood

Matthew P Wingert

Vasu Kudaravalli

Joseph Michael Pusdesris

Klas Magnus Bruce

Umar Farooq

A data processing apparatus contains branch prediction circuitry including a micro branch target buffer, a full branch target buffer and a global history buffer. The branch target buffer entries contain history data which indicates whether or not a number of the following blocks of program instructions, subsequent to and sequential to a block of program instruction identified by that branch target buffer entry containing a branch instruction, do themselves contain any branch instructions. If the history data indicates that the following blocks of program instructions do not contain branches, then the operation of the branch prediction circuitry is suppressed for these following blocks of program instructions so as to save energy.

Branch prediction suppression for blocks of instructions predicted to not include a branch instruction

A cache hierarchy and a method of operating the cache hierarchy are disclosed. The cache hierarchy comprises a first cache level comprising an instruction cache, and predecoding circuitry to perform a predecoding operation on instructions having a first encoding format retrieved from memory to generate predecoded instructions having a second encoding format for storage in the instruction cache. The cache hierarchy further comprises a second cache level comprising a cache and the first cache level instruction cache comprises cache control circuitry to control an eviction procedure for the instruction cache in which a predecoded instruction having the second encoding format which is evicted from the instruction cache is stored at the second cache level in the second encoding format. This enables the latency and power cost of the predecoding operation to be avoided when the predecoded instruction is then retrieved from the second cache level for storage in the first level instruction cache again.

Cache hierarchy management

An apparatus comprises processing circuitry, an instruction cache, decoding circuitry to decode program instructions fetched from the cache to generate macro-operations to be processed by the processing circuitry, and predecoding circuitry to perform a predecoding operation on a block of program instructions fetched from a data store to generate predecode information to be stored to the cache with the block of instructions. In one example the predecoding operation comprises generating information on how many macro-operations are to generated by the decoding circuitry for a group of one or more program instructions. In another example the predecoding operation comprises generating information indicating whether at least one of a given subset of program instructions within the prefetched block is a branch instruction.

Instruction predecoding

An apparatus, method, and other embodiments associated with performing interpolations to compute gain values that correct for varying spatial intensity are described. In one embodiment, a method includes determining, by an apparatus that processes image data, a gain value for a pixel in the image data for which there is no gain value available in the apparatus, by interpolating related gain values associated with corners of a rectangle bounding the pixel, wherein the interpolating includes determining at least two partial coefficients by interpolating pairs of the related gain values. Noise is filtered from the image data using a noise threshold, and the noise threshold is modified by using the at least two partial coefficients. The method also applies the gain value to the pixel in the image data.

Gain value interpolation

An image capture system including a statistics module. An image processing module is configured to receive image data corresponding to a plurality of pixels of a captured image, wherein the image data includes respective locations of each of the plurality of pixels, and implement an image processing pipeline configured to modified image data. The statistics module is configured to gather a plurality of sets of statistics using the image data and the modified image data, each of the sets of statistics corresponding to a different one of a plurality of zones within the captured image. To gather the statistics, the statistics module is further configured to determine, based on the respective location of a first pixel, a first zone of the plurality of zones that the first pixel is located in, and store data in a corresponding set of statistics for the first pixel based on the determined first zone.

Image capture system and method for gathering statistics for captured image data

A method of synthesizing color data through the use of what is called a Gradient Vector Synthesis method is comprised of calculating gradients at 0&#xb0;, 45&#xb0;, 90&#xb0;, and 135&#xb0; with respect to a generation point in a matrix of color data. A first-level edge test is performed by comparing each of the gradients to a noise threshold. If the first-level test indicates that an edge may be present along either of the diagonals, a second-level test may be performed. An interpolation technique is selected in response to the first-level edge test and, when performed, the second-level edge test. The selected interpolation technique is used to synthesize the missing color data at the generation point.

Method and apparatus for color data synthesis in digital image and video capture systems

A system includes a block module, a zone module, a statistics module, and a control module. The block module is configured to associate pixel values generated by pixel sensors of an image sensor with M regions. The zone module is configured to define N zones in the M regions. Each of the N zones includes an adjustable number of the M regions. N and M are integers greater than one and N is less than or equal to M. The statistics module is configured to gather statistics corresponding to the N zones. The control module is configured to adjust pixel values generated by the pixel sensors based on the statistics.

Method and apparatus for multiple zone statistics collection for digital image/video capture systems

A system and method of adaptive edge detection and noise reduction in an image where edge information is detected for each color component of each pixel, whether sensed or synthesized. In some embodiments, the filter applied to a selected non-edge pixel may be determined by the ultimate size of a region around the selected pixel, where the size of the region may be increased if a count of the non-edge pixels in the region is less than a threshold value.

Method and apparatus for spatial noise adaptive filtering for digital image and video capture systems

An apparatus and other embodiments associated with performing interpolations to compute gain values that correct for varying spatial intensity are described. In one embodiment, an apparatus includes interpolation logic configured to determine a gain value for a pixel in image data for which there is no gain value available in the apparatus. The interpolation logic is configured to determine the gain value by performing an interpolation of related gain values available in the apparatus. The apparatus also includes falloff correction logic configured to apply the gain value to the pixel in the image data.

Systems and methods for synthesizing color data. The method includes calculating gradients at a plurality of angles with respect to a generation point in a matrix of color data, performing a first-level edge test by comparing each of the gradients to a noise threshold, selecting an interpolation technique in response to the comparisons, and synthesizing missing color data at said generation point using the selected interpolation technique.

Method and apparatus for noise management for color data synthesis in digital image and video capture systems

A computer-implemented method for noise management in a digital image system measures noise levels of pixel data. The noise levels are adjusted with at least one of an intensity gain setting, a spatial gain setting, and a global gain setting to calculate noise adaptive thresholds for use during spatial processing of the pixel data.

Growing community of inventors

Austin, TX, United States of America

Adam George