摘要:
Methods and apparatus for calculating Single-Instruction-Multiple-Data (SIMD) complex arithmetic. A coprocessor instruction has a format identifying a multiply and subtract instruction to generate real components for complex multiplication of first operand complex data and corresponding second operand complex data, a cross multiply and add instruction to generate imaginary components for complex multiplication of the first operand complex data and the corresponding second operand complex data, an add-subtract instruction to add real components of the first operand to imaginary components of the second operand and to subtract real components of the second operand from imaginary components of the first operand, and a subtract-add instruction to subtract the imaginary components of the second operand from the real components of the first operand and to add the real components of the second operand to the imaginary components of the first operand.
摘要:
Methods and apparatus for calculating Single-Instruction-Multiple-Data (SIMD) complex arithmetic. A coprocessor instruction has a format identifying a multiply and subtract instruction to generate real components for complex multiplication of first operand complex data and corresponding second operand complex data, a cross multiply and add instruction to generate imaginary components for complex multiplication of the first operand complex data and the corresponding second operand complex data, an add-subtract instruction to add real components of the first operand to imaginary components of the second operand and to subtract real components of the second operand from imaginary components of the first operand, and a subtract-add instruction to subtract the real components of the second operand from the imaginary components of the first operand and to add the real components of the first operand to the imaginary components of the second operand.
摘要:
Devices, systems, methods, and other embodiments associated with clipping instructions are described. In one embodiment, a method includes receiving a clipping instruction for clipping filtered values in a video image de-blocking operation. The clipping instruction references a video data value and a clipping value. The method includes decoding the clipping instruction. The method also includes retrieving the video data value and the clipping value. A video data magnitude of the video data value is determined. The method determines a clipping magnitude of the clipping value. A determination is made as to whether the video data magnitude exceeds the clipping magnitude. If the video data magnitude exceeds the clipping magnitude, the video data value is selectively clipped.
摘要:
Transfer functions are often used for image processing. Look-up tables can be used to implement transfer functions in a processor-efficient manner. In one embodiment, the invention is an apparatus that includes a look-up table (LUT) storing sample outputs from an output range of a transfer function, the sample outputs corresponding to sample inputs from an input range of the transfer function, the sample inputs being distributed so that more sample inputs are associated with a first region of the transfer function than a second region of the transfer function; and an address module to calculate an index into the LUT based on image data. In one embodiment, the apparatus uses the LUT to process the image data.
摘要:
In one or more embodiments, an apparatus comprises an alignment module implemented in hardware to identify requested data that is not aligned on a natural alignment boundary of a memory and load at least two sets of neighboring data such that each said set includes at least a portion of the requested data. The alignment module is further configured to extract the requested data from the at least two sets of neighboring data and output the extracted data to a processor.
摘要:
In one or more embodiments, a method, computer-readable media, system and or modules are capable of generating an address for a multimedia data block included in a stream of multimedia data. The address can be maintained in one or more local registers. The one or more local registers can be linked to one or more processor registers associated with a processor to synchronize communication of the stream of multimedia data with the processor.
摘要:
An apparatus includes an input module and a color synthesis module. The input module is configured to receive mosaic image data representing an image. The mosaic image data includes radial distortion. The color synthesis module, implemented in digital electronic circuitry, includes a radial distortion correction module and a synthesis module. The radial distortion correction module is configured to receive the mosaic image data and generate correction data to correct the radial distortion in the mosaic image data. The synthesis module is configured to receive the mosaic image data and the correction data, wherein the mosaic image data includes a plurality of input pixel values and respective input pixel locations prior to being corrected, and generate demosaiced image data using the mosaic image data and the correction data.
摘要:
Apparatus having corresponding methods and computer programs comprise an input module to receive image data representing an image, wherein the image data includes radial distortion; and a zoom module to scale the image based on the image data and a scaling factor, wherein the zoom module comprises a radial distortion correction module to correct the radial distortion in the image data while the zoom module scales the image.
摘要:
In an embodiment, an apparatus includes a trusted cryptographic processor that includes at least one functional unit. The trusted cryptographic processor also includes a controller to receive a primitive instruction that identifies which of the at least one functional unit is to perform an operation, wherein the controller is to reduce power to the at least one functional unit that is not identified by the primitive instruction. The apparatus includes a trusted power management unit to supply the power based on control from the controller, wherein the control is independent of a processor that is not in a trusted state.
摘要:
A system, apparatus, method, and article to reduce display bandwidth are described. The apparatus may include a display controller to identify an opaque region in windows defining an output image. The display controller determines an overlay order for any overlapping portions of the windows. A higher order window overlays a lower order window. The display controller fetches data defining the opaque region only from an uppermost overlay window prior to displaying the output image.