摘要:
A method of preventing a bank conflict in a memory includes determining processing timing of each of threads of function units to access a first memory bank in which occurrence of a bank conflict is expected, setting a variable latency of each of the threads for sequential access of the threads according to the determined processing timing, sequentially storing the threads in a data memory queue according to the determined processing timing, and performing an operation by allowing the threads stored in the data memory queue to sequentially access the first memory bank whenever the variable latency of each of the threads passes.
摘要:
A method of preventing a bank conflict in a memory includes determining processing timing of each of threads of function units to access a first memory bank in which occurrence of a bank conflict is expected, setting a variable latency of each of the threads for sequential access of the threads according to the determined processing timing, sequentially storing the threads in a data memory queue according to the determined processing timing, and performing an operation by allowing the threads stored in the data memory queue to sequentially access the first memory bank whenever the variable latency of each of the threads passes.
摘要:
A method of decoding a bitstream, a method of accelerating an inverse transform, an apparatus, a video decoder, and a non-transitory computer-readable recording medium are provided. The method includes receiving an encoded bitstream, extracting transformation coefficients from the received bitstream, determining a position of a block including at least one nonzero transformation coefficient from among the extracted transformation coefficients, and generating decoded video data by inverse-transforming transformation coefficients in the block by using the determined position.
摘要:
An electronic device and a control method therefor are provided. The electronic device comprises: a microphone for receiving an external audio signal; an analog/digital converter (ADC) for processing the audio signal into a digital signal; a memory for storing the audio signal; and a processor for identifying whether the audio signal inputted from the microphone is a user's voice, and compressing the audio signal on the basis of the determination result so as to store the compressed audio signal in the memory, wherein the ADC and the processor can be implemented as one chip.
摘要:
A method of generating a multi-channel audio signal includes: representing locations of a plurality of speakers as a plurality of polygons whose vertices are located at locations of corresponding speakers; acquiring a location of an object sound; calculating distances between the plurality of polygons and the location of the object sound; selecting one of the plurality of polygons on the basis of the calculated distances; and generating a multi-channel audio signal that corresponds to speakers corresponding to the selected polygon by mapping the object sound to the speakers corresponding to the selected polygon.
摘要:
A method of performing quadrature mirror filter (QMF) synthesis filtering includes recording new samples corresponding to a current time slot at positions of samples to be discarded in a first array that includes modulated QMF sub-band samples. The method further includes extracting samples from the first array to remove aliasing between adjacent sub-bands, determining filter coefficients corresponding to the extracted samples by using modulo operation, and synthesizing a time domain sample where aliasing is removed by using the extracted samples and the filter coefficients.