Abstract: State-of-the-art object detection algorithms (e.g., EfficientDet, Faster-RCNN, and YOLO) and their variants are integrated into an end-to-end IoT cloud-based system deployment. The system can (1) receive real-time video streaming (RTSP/RTMP/SDP) from most CCTV systems and devices with cameras, (2) extract frames from the video streams, (3) feed the frames to multiple AI models simultaneously, and (4) compute a probability for the presence of fire and/or smoke. Based on custom risk thresholds, the outputs can be compiled programmatically into a video clip that is sent to a user automatically for real-time alerts.

Abstract: Provided is a ventilator that includes a breathing system, a mechanical system coupled to breathing system, and a control system coupled to breathing system and mechanical system. The control system includes pressure sensors, processing circuitry, and memory configured to store a look-up table. The processing circuitry receives a set of values for plurality of parameters, identifies a compression value from a plurality of compression values in the look-up table based on the received set of values. The processing circuitry causes the mechanical system to compress a bag valve of the breathing system in accordance with the identified compression value. The compression of the bag valve causes a gaseous inhalant to flow through the breathing system within a time-interval. The processing circuitry determines an actual volume of the gaseous inhalant and iteratively modifies the compression value of the bag valve to match a desired volume of the gaseous inhalant.

Abstract: A processor having a sliceable architecture wherein a slice is the minimum configuration of the processor datapath. The processor can instantiate multiple slices and each slice has a separate datapath. The total processor datapath is the sum of the number of slices multiplied by the width of a slice. Accordingly, all general purpose registers in the processor are as wide as the total datapath. A program executing on the processor can determine the maximum number of slices available in a particular processor by reading a register. In addition, a program can select the number of slices it will use by writing to a different register. The processor replicates control signals for each active slice in the processor and supports instructions for transferring data among the slices. Furthermore, the processor supports a set of instructions for fetching and storing data between multiple slices and the memory.

Abstract: A processor having a modified Harvard architecture having first and second memories, an address register file divided into first and second sets of registers, first and second stream registers, and a general purpose register file for performing data streaming. The first and second sets of registers respectively address the first and second memories which, in turn, load data into the first and second stream registers. An arithmetic logic unit (ALU) accepts the stream registers and general purpose registers as inputs. Stream instructions are encoded such that a single instruction specifies an ALU operation performed on selected ALU inputs and where to store the results of the ALU operation, loads new values into the stream registers, and updates the address registers. A stream instruction has three operand fields respectively specifying two operands for the next ALU operation and a location to store the result of the current ALU operation.

Abstract: In a pipelined processor, an instruction queue and an instruction control unit is provided to group and issue m instructions simultaneously per clock cycle for execution. An integer and a floating point function unit capable of generating n.sub.1 and n.sub.2 integer and floating point results per clock cycle respectively, where n.sub.1 and n.sub.2 are sufficiently large to support m instructions being issued per clock cycle, is also provided to complement the instruction queue and instruction control unit. The pipeline stages are divided into integer and floating point pipeline stages where the early floating point stages overlap with the later integer pipeline stages. The instruction queue stores sequential instructions of a program and target instructions of a branch instruction of the program, fetched from the instruction cache.

Abstract: A method and apparatus for removing a page table entry from a plurality of translation lookaside buffers ("TLBs") in a multiprocessor computer system. The multiprocessor computer system includes at least two processors coupled to a packet-switched bus. Page table entries are removed from a plurality of TLBs in the multiprocessor computer system by first broadcasting a demap request packet on the packet-switched bus in response to one of the processors requesting that a page table entry be removed from its associated TLB. The demap request packet includes a virtual address and context information specifying this page table entry. Controllers reply to the demap request packet by sending a first reply packet to the controller that sent the original demap request packet to indicate receipt of the demap request packet.

Abstract: In a sequential logic design having two domains, each having opposing clock edge for its flip-flops, an inter-domain latch is provided for establishing a controllable and observable boundary point for the two domains. The inter-domain latch comprises three multiplexors and three latches. The first multiplexor, the first latch, the second multiplexor, the second latch, the third latch and the third multiplexor are coupled serially. Additionally, the output of the first latch is by-passed to the third multiplexor. The latches either open when the clock pulse is low or when the clock pulse is high. The first and third latches are driven by the same clock pulses, and the second latch is driven by an inverted clock pulse. Scan vectors for the first and second domains are scanned in through the first and second multiplexors respectively. The outputs of the first and second domains are observed at the second latch and the third multiplexor respectively.

Abstract: A method and apparatus for selecting an entry to be replaced in a translation lookaside buffer in a computer system. The translation lookaside buffer stores a plurality of entries of virtual-to-physical address translations with each entry having a used bit and a valid bit.

Abstract: An improved bit shifter to provide data block shifting in a graphics processor. The shifter allows a multiple word, data block shifting to be achieved simultaneously and independently of other graphic functions. The shifter provides character block transfer for rotation of characters of a display. The shifter also provides bit block transfers for moving data from a source location to a destination location.