Abstract:
Efficient memory fetching techniques are described that can improve data fetching during a motion compensation decoding process. The techniques propose several different memory fetching modes that may be very efficient in different scenarios of the motion compensation decoding process. A motion compensator may a particular memory fetch mode from a plurality of possible modes on a case-by-case basis for the memory fetches associated with a motion compensation decoding process of a macroblock. The techniques described herein may be particularly useful when fractional interpolation to sub-integer pixels is used in the inter-frame compression.
Abstract:
In one embodiment, this disclosure provides an encoding device comprising a mode selection engine that performs mode selection for intra-prediction encoding regardless of whether the encoding device is programmed to comply with first encoding standard or a second encoding standard. The device also includes a first encoder to perform the intra prediction encoding according to the selected mode in compliance with the first encoding standard when the encoding device is programmed to comply with the first encoding standard, and a second encoder to perform the intra-prediction encoding according to the selected mode in compliance with the second encoding standard when the encoding device is programmed to comply with the second encoding standard. The techniques can simplify mode selection in support of multiple different intra-prediction encoding standards.
Abstract:
A device that includes a region comprising an integrated device and a heat dissipating device coupled to the region comprising the integrated device. The heat dissipating device is configured to dissipate heat away from the region. The heat dissipating device includes a fluid, an evaporator configured to evaporate the fluid, a first condenser configured to condense the fluid, where the first condenser is located in a first wall of the device, an evaporation portion coupled to the evaporator and the first condenser, and a collection portion coupled to the first condenser and the evaporator. The evaporation portion is configured to channel an evaporated fluid from the evaporator to the first condenser. The collection portion is configured to channel a condensed fluid from the first condenser to the evaporator through the help of gravity.
Abstract:
The disclosure relates to a programmable streaming processor that is capable of executing mixed-precision (e.g., full-precision, half-precision) instructions using different execution units. The various execution units are each capable of using graphics data to execute instructions at a particular precision level. An exemplary programmable shader processor includes a controller and multiple execution units. The controller is configured to receive an instruction for execution and to receive an indication of a data precision for execution of the instruction. The controller is also configured to receive a separate conversion instruction that, when executed, converts graphics data associated with the instruction to the indicated data precision. When operable, the controller selects one of the execution units based on the indicated data precision. The controller then causes the selected execution unit to execute the instruction with the indicated data precision using the graphics data associated with the instruction.
Abstract:
This disclosure describes efficient transformation techniques that can be used in video coding. In particular, intermediate results of computations associated with transformation of a first block of video data are reused in the transformation of a second block of video data. The techniques may be used during a motion estimation process in which video blocks of a search space are transformed, but this disclosure is not necessarily limited in this respect. Pipelining techniques may be used to accelerate the efficient transformation techniques, and transposition memories can be implemented to facilitate efficient pipelining.
Abstract:
This disclosure describes techniques for processing audio files that comply with the musical instrument digital interface (MIDI) format. In particular, various tasks associated with MIDI file processing are delegated between software operating on a general purpose processor, firmware associated with a digital signal processor (DSP), and dedicated hardware that is specifically designed for MIDI file processing. Alternatively, a multi-threaded DSP may be used instead of a general purpose processor and the DSP. In one aspect, this disclosure provides a method comprising parsing MIDI files and scheduling MIDI events associated with the MIDI files using a first process, processing the MIDI events using a second process to generate MIDI synthesis parameters, and generating audio samples using a hardware unit based on the synthesis parameters.
Abstract:
The disclosure relates to systems, methods and apparatus to convert speech to text and vice versa. One apparatus comprises a vocoder, a speech to text conversion engine, a text to speech conversion engine, and a user interface. The vocoder is operable to convert speech signals into packets and convert packets into speech signals. The speech to text conversion engine is operable to convert speech to text. The text to speech conversion engine is operable to convert text to speech. The user interface is operable to receive a user selection of a mode from among a plurality of modes, wherein a first mode enables the speech to text conversion engine, a second mode enables the text to speech conversion engine, and a third mode enables the speech to text conversion engine and the text to speech conversion engine.