Abstract: A light-emitting diode (LED) panel and a driving method thereof are disclosed. The LED panel includes a clock generation module configured to provide a clock signal; a control module including a plurality of output terminal groups, wherein, each of the output terminal groups includes at least one first output terminal, and the control module is configured to output electrical signals through different output terminal groups in sequence in a same frame time according to the clock signal; and a plurality of LED modules, wherein, each of the LED modules is correspondingly connected to the at least one first output terminal by one to one, and the LED modules are configured to emit light in sequence according to the electrical signals.

Abstract: A driver chip, a display panel, and a driving method thereof are provided. The driver chip uses a pulse width modulation module and a pulse amplitude modulation module to control a waveform and a strength of a data signal respectively, which can obtain more display grayscales, a to-be-displayed brightness of a light emitting unit is larger, and a gradation level of the light-emitting unit is better. The pulse amplitude modulation module can modulate the strength of the data signal, can compensate the pixels, and improve the display quality of the display panel.

Abstract: The present application discloses a warp execution method used for SPs of an SM of a GPU and an associated GPU.

Abstract: A GPU and a GPU method are provided. The GPU includes stream multiprocessors, an available hardware resource table, resource comparator, stream scheduler, and global dispatcher. Each stream multiprocessor executes at least one thread block. The available hardware resource table records hardware resources available to the stream multiprocessors. The resource comparator selects from first-priority kernel codes in the kernel streams at least one first dispatchable kernel code whose required hardware resources are less than hardware resources available to the stream multiprocessors according to the available hardware resource table. The stream scheduler selects from the at least one first dispatchable kernel code a kernel code as a selected kernel code. The global dispatcher dispatches thread blocks in the selected kernel code to the stream multiprocessors for execution and updates the available hardware resource table according to usage conditions of hardware resources of the stream multiprocessors.

Abstract: The present application discloses a GPU and a method of the same. The GPU includes: a plurality of streaming multiprocessor (SMs), each including: a plurality of streaming processors (SPs), each including a register, wherein each SP has a predetermined upper bound of warp number, and the register has a predetermined upper bound of register capacity; and a global dispatcher, including: a register occupancy status table, for recording the warp number and an occupancy status of the register of each SP of each SM; a TB (TB) dispatch module, for dispatching the TB to a first SM of the SMs according to a warp type classification table and the register occupancy status table; and a warp dispatch module, for dispatching a plurality of warps to the plurality of SPs of the first SM according to the warp type classification table and the register occupancy status table.

Abstract: A stream multiprocessor, a GPU, and related methods are provided. The stream multiprocessor executes thread blocks. Each thread block includes warps. The stream multiprocessor includes stream processors and a local dispatcher. Each stream processor executes one or more warps. The local dispatcher includes a warp state table, a warp resource detection unit and a warp launching unit. The warp state table records dispatching states and processing states of warps of the thread blocks. The warp resource detection unit selects all the first warps of a first thread block and at least one second warp of a second thread block according to hardware resources available to the stream multiprocessor and hardware resources required for thread blocks. The warp launching unit dispatches the first warps to idle stream processors and at least one second warp to at least one idle stream processor.

Abstract: The present disclosure provides a power management method, a multi-processing unit system, and a power management module thereof. The multi-processing unit system comprises a plurality of local power management units and a global power management unit, each of the local power management units corresponds to a processing unit of the multi-processing unit system. The power management method comprises: obtaining, using the global power management unit, a global power budget for the multi-processing unit system; allocating, using the global power management unit, local power budget for each of the local power management units according to the global power budget and power management parameters of the processing units; managing, using the local power management unit, local power resources of corresponding processing unit based on the allocated local power budget; reporting, using the local power management unit, the power management parameters of the processing unit to the global power management unit.

Abstract: A backlight brightness control method, a backlight brightness control device, and a display equipment are provided. By using a constant current integrated circuit to input constant current to backlight sources in backlight partitions, uniformity of backlight brightness is allowed to be improved. By determining a target peak current inputted to the backlight sources in the backlight partitions according to a grayscale level of partition images, not only can the backlight brightness required by a high grayscale level be ensured, but fine adjustment of the backlight brightness under a low grayscale level can also be ensured.

Abstract: Neural network (NN) model training techniques can include computing activations in a forward pass using a sparse weight matrix that is transpose invariant. The neural network (NN) model training techniques can further include computing activation gradients and weight gradients in a backward pass using the sparse weight matrix.

Abstract: A driving circuit, a display panel, and a panel are provided. The driving circuit includes a substrate and signal lines and a plurality of load components disposed on the substrate. The plurality of load components are distributed along a first direction. Each of the load components is connected to the signal lines. The signal lines include at least two signal input terminals. Signals are loaded to signal lines through the at least two signal input terminals.

Abstract: A display panel and a driving method thereof are provided, including a time schedule controller and at least one driver integrated circuit (driver IC). Pulse width modulation (PCM) data between the time schedule controller and the driver IC is transmitted in a decoded manner, and pulse amplitude modulation (PAM) data is transmitted in an undecoded manner, reducing a transmission rate between the time schedule controller and the driver IC, and thereby reducing or eliminating risks of electromagnetic interference (EMI). Furthermore, using this transmission method can reduce the number of latches used in the driver IC.

Abstract: A large-scale network node simulation method based on Linux container is provided, which solves problems of low packet transmission efficiency and multi-thread creation in real-time simulation in a large-scale network scenario. The method includes: scheduling all container nodes in a scenario; managing, by a container node, a dynamic thread through an idle thread management queue, and setting a finite state machine and a function pointer for the dynamic thread; registering, by a source container node, an output queue with a next-hop container node, and informing the next-hop container node to allocate a dynamic thread for receiving and processing the output queue. Packet transmission is realized between the container nodes through data units created in a shared memory. The sending thread and the receiving thread dynamically adjust the number of dynamic threads by checking the state of the output queue.

Abstract: A switch device includes: a switch circuit; a control signal input terminal configured to input a control signal to the switch circuit; a voltage input terminal configured to input an initial voltage to the switch circuit; and a voltage output terminal configured to output an output voltage to a light-emitting device. The switch circuit includes: a first input terminal and a second input terminal electrically connected to the control signal input terminal and the voltage input terminal, respectively; and a first output terminal electrically connected to the voltage output terminal.

Abstract: A computer-implemented method for preventing leaking a personal privacy from a chatbot under black-box personal attribute inference attack is provided. The chatbot is provided via a neural network executed by a processor of a server. The method includes: training, by the processor, a Language Model (LM) of the chatbot according to utility objectives; applying, by the processor, one or more defense objectives with personal attribute predictor to fine-tune a target LM of the chatbot by using a fake attacker model and pre-define attributes with annotated datasets; and using, by the processor, the target LM on the chatbot to defend inference attack, such that the personal privacy of content inputted and sent to the chatbot cannot be predicted by external predictor and a security level of the chatbot is assured.

Abstract: The present disclosure provides a power management method, a multi-processing unit system, and a power management module thereof. The multi-processing unit system comprises a plurality of local power management units and a global power management unit, each of the local power management units corresponds to a processing unit of the multi-processing unit system. The power management method comprises: obtaining, using the global power management unit, a global power budget for the multi-processing unit system; allocating, using the global power management unit, local power budget for each of the local power management units according to the global power budget and power management parameters of the processing units; managing, using the local power management unit, local power resources of corresponding processing unit based on the allocated local power budget; reporting, using the local power management unit, the power management parameters of the processing unit to the global power management unit.

Abstract: Managing data stored in a cache using a reinforcement learning agent may include: determining a set of current state observations with respect to a cache, wherein the set of current state observations is determined based on historical cache accesses to the cache; inputting the set of current state observations into an actor network of a reinforcement learning (RL) agent to obtain an action output by the actor network, wherein the RL agent is configured to manage data stored at the cache; inputting the set of current state observations and the action into a critic network of the RL agent to obtain a score corresponding to the action from the critic network; causing the RL agent to perform the action with respect to managing the data stored at the cache; using the score to update the actor network; and using a reward corresponding to the action to update the critic network.

Abstract: Provided is an apparatus, system and method for on-chip microfluids dispensing. The apparatus comprising a substrate; a plurality of first electrodes arranged one next to another on the substrate; a dielectric layer above and enclosing the plurality of first electrodes; and a second electrode on the substrate, wherein each of the plurality of first electrodes is in electric communication with a respective first driving signal input; wherein the second electrode is in electric communication with a second driving signal input; wherein the plurality of first electrodes define a continuous fluid path along a longitudinal direction for retaining microfluids, and wherein the second electrode is arranged within the continuous fluid path and defines a jetting position and an adjacent mixing position within the continuous fluid path.

Abstract: A display device and a controlling method thereof are provided. The display device includes a display panel, a backlight unit, and a time schedule controller. The display panel is configured to display images. Areas where afterimages of dynamic images occur are identified according to comparison results of dither values. Tailing phenomenon of the dynamic images may be relieved by transmitting backlight data without brightness to a second backlight sub-area corresponding to where the afterimages occur. Furthermore, because frequency multiplication is not applied, risks of display instability will not increase.