Abstract: A memory device includes at least three digital storage circuits arranged in parallel, the digital storage circuits each configured to store state data representing a bit of data in a first or second state; a data input configured to receive input data, the input data representing a bit of data in the first or second state; a voter having a voter output, the voter configured to generate output data at the voter output, the output data representing which of the first and second state are in a majority among the state data stored in each of the digital storage circuits; and a multiplexer operatively coupled to the data input, the voter output, and an input of each of the digital storage circuits, the multiplexer configured to output, to each of the digital storage circuits, one of the input data and the output data based on a functional enable signal.

Abstract: Techniques are provided for an error resistant radiation hardened memory system based on spreading of data bits among multiple random access memories (RAMs). A memory system implementing the techniques according to an embodiment includes a first plurality of RAMs configured to store data bits written to the memory system, the data bits distributed over the first plurality of RAMs. The system also includes an error correction coding (ECC) circuit configured to generate ECC codes, each of the codes associated with a unique group of the data bits. The system further includes a second plurality of RAMs configured to store bits of the ECC codes such that the bits of each ECC code are distributed over the second plurality of RAMs. The system further includes a reporting circuit configured to report a single bit error correction or a double bit error detection, resulting from a read operation on the memory system.

Abstract: A memory device includes at least three digital storage circuits arranged in parallel, the digital storage circuits each configured to store state data representing a bit of data in a first or second state; a data input configured to receive input data, the input data representing a bit of data in the first or second state; a voter having a voter output, the voter configured to generate output data at the voter output, the output data representing which of the first and second state are in a majority among the state data stored in each of the digital storage circuits; and a multiplexer operatively coupled to the data input, the voter output, and an input of each of the digital storage circuits, the multiplexer configured to output, to each of the digital storage circuits, one of the input data and the output data based on a functional enable signal.

Abstract: A memory device includes a memory module having a plurality of memory cells, a read port, a write port, and an output port; a first multiplexer having a functional read input, a scrub read input, a scrub read enable input, and a read request output, the read request output coupled to the read port; a second multiplexer having a functional write input, a scrub write input, a scrub write enable input, and a write request output, the write request output coupled to the write port; and a logic circuit configured to scrub, via the scrub write input, at least one of the memory cells based on the scrub read input while the scrub read enable input and/or the scrub write enable input are asserted.

Abstract: A secure system includes a data port, a network on chip (NoC) module, a processor communicatively coupled to the NoC module, a communication interface operatively coupled to the processor and to the data port, an electronic field-programmable gate array (eFPGA) configuration module operatively coupled to the NoC module, and a clock operatively coupled to the NoC module. In a first modality, the communication interface is at least partially disabled. In a second modality, the communication interface is at least partially disabled, boundary scan operations are disabled, a RESET signal is held in a constant state, and/or redacted code is rendered inoperable. In a third modality, the communication interface is at least partially enabled to send and receive commands and data via the data port, the boundary scan operations are enabled, the RESET signal is not held in the constant state, and/or the redacted code is operable.

Abstract: A system that includes a plurality of encapsulation blocks having a plurality of digital signal processing (DSP) blocks provided with preconfigured logic functions and a plurality of pacing control networks operatively connected with the plurality of DSP blocks. The system also includes a streaming cross bar operatively connected with each encapsulation block of the plurality of encapsulation blocks. Each encapsulation block of the plurality of encapsulation blocks includes a DSP block of the plurality of DSP blocks and a pacing control network of the plurality of the pacing control networks. Each DSP block of the plurality of DSP blocks is independently and separately connected with the streaming cross bar via the plurality of pacing control networks.

Abstract: A semiconductor device includes a data port, a programmable logic block for executing a manufacturer test, and a processor operatively coupled to the data port. The processor is configured to assert, in a first modality, a configuration isolation signal to the data port. The data port is configured to be communicatively isolated from the programmable logic block while the configuration isolation signal is asserted. The processor is configured to de-assert, in a second modality, the configuration isolation signal from the data port. The data port is configured to be communicatively coupled to the programmable logic block while the configuration isolation signal is de-asserted. In some examples, the semiconductor device includes a communication interface communicatively coupled to the programmable logic block, wherein the processor is further configured to cause, in the first modality, data to be loaded into the programmable logic block from a first-in-first-out (FIFO) buffer of the communication interface.

Abstract: A secure system includes a data port, a network on chip (NoC) module, a processor communicatively coupled to the NoC module, a communication interface operatively coupled to the processor and to the data port, an electronic field-programmable gate array (eFPGA) configuration module operatively coupled to the NoC module, and a clock operatively coupled to the NoC module. In a first modality, the communication interface is at least partially disabled. In a second modality, the communication interface is at least partially disabled, boundary scan operations are disabled, a RESET signal is held in a constant state, and/or redacted code is rendered inoperable. In a third modality, the communication interface is at least partially enabled to send and receive commands and data via the data port, the boundary scan operations are enabled, the RESET signal is not held in the constant state, and/or the redacted code is operable.

Abstract: An encapsulation block for a digital signal processing (DSP) block. The encapsulation block includes DSP block having an input terminal, an output terminal, and an input clock. The encapsulation block also includes pacing control network operatively connected with the input terminal, the output terminal, and the input clock of the DSP block. The input terminal of the DSP block is configured to receive a samples-in data stream inputted at a predefined clock period defined by the input clock. The output terminal of the DSP block is configured to receive a samples-out data stream outputted at a predefined paced parameter. The pacing control network is configured to control data flow at the samples-in data stream and the samples-out data stream independently of the DSP block.

Abstract: Techniques are provided for a radiation hardened memory system. A memory system implementing the techniques according to an embodiment includes a redundancy comparator configured to detect differences between data stored redundantly in a first memory, a second memory, and a third memory. The redundancy comparator is further configured to identify a memory error based on the detected differences. The memory system also includes an error collection buffer configured to store a memory address associated with the memory error, and a memory scrubber circuit configured to overwrite, at the memory address associated with the memory error, erroneous data with corrected data. The corrected data is based on a majority vote among the three memories. The memory system further includes a priority arbitrator configured to arbitrate between the memory scrubber overwriting and functional memory accesses associated with software execution performed by a processor configured to utilize the memory system.

Abstract: Techniques are provided for a fast Fourier transform (FFT) butterfly circuit. A circuit implementing the techniques according to an embodiment includes a first multiplexer configured to select a first channel or a delayed version of a second channel based on a frame index associated with the first or second channel; a second multiplexer configured to select the channel that was not selected by the first multiplexer; and a butterfly core circuit. The butterfly core circuit configured to receive a delayed version of the selected channel from the first multiplexer as a top butterfly branch; receive the selected channel from the second multiplexer as a bottom butterfly branch; apply FFT twiddle factors to the bottom butterfly branch to generate a scaled bottom butterfly branch; and generate sum and difference channel outputs of the top butterfly branch and the scaled bottom butterfly branch.

Abstract: Techniques are provided for a fast Fourier transform (FFT) sample reorder circuit for a dynamically reconfigurable oversampled channelizer. An FFT sample reorder circuit implementing the techniques according to an embodiment includes a plurality of dual port memory circuits. The circuit also includes a first crossbar circuit configured to route input data samples to write ports of the plurality of dual port memory circuits. The circuit further includes a second crossbar circuit configured to route reordered output data samples from read ports of the plurality of dual port memory circuits to a multi-stage FFT circuit. The circuit further includes a controller circuit configured to control the routing of the input data samples and the routing of the reordered output data samples based on a selection of a stage of the multi-stage FFT circuit.

Abstract: Techniques are provided for a polyphase filtering in a dynamically reconfigurable two times (2×) oversampled channelizer. A polyphase filter implementing the techniques according to an embodiment includes a first plurality of dual port memory circuits and a multiplexer circuit configured to distribute input data for storage to the first plurality of dual port memory circuits. The polyphase filter also includes a second plurality of dual port memory circuits configured to store polyphase filter coefficients and a data alignment crossbar circuit configured to align the input data stored in the first plurality of dual port memory circuits with the polyphase filter coefficients stored in the second plurality of dual port memory circuits. The polyphase filter further includes a multiply circuit configured to perform multiplications of the aligned input data with the polyphase filter coefficients and an adder circuit to sum the results of the multiplications to generate a filtered output.

Abstract: Techniques are provided for a dynamically reconfigurable two times (2×) oversampled channelizer. A channelizer implementing the techniques according to an embodiment includes a polyphase filter, a two phase reorder circuit, a fast Fourier transform (FFT) circuit, and a two phase merge circuit. The polyphase filter is configured to filter time domain input data to control spectral shaping of frequency bins of the channelizer output. The two phase reorder circuit is configured to split a 2× oversampled data stream into two parallel, critically sampled data streams. The FFT circuit is configured to transform each stream into the frequency domain. The two phase merge circuit is configured to merge the two streams of frequency domain data into a single stream of 2× oversampled frequency domain data for distribution onto frames of frequency bins. Reconfigurable parameters for the channelizer include filter coefficients, number of filter folds, and number of frequency bins.

Abstract: A system that includes a plurality of encapsulation blocks having a plurality of digital signal processing (DSP) blocks provided with preconfigured logic functions and a plurality of pacing control networks operatively connected with the plurality of DSP blocks. The system also includes a streaming cross bar operatively connected with each encapsulation block of the plurality of encapsulation blocks. Each encapsulation block of the plurality of encapsulation blocks includes a DSP block of the plurality of DSP blocks and a pacing control network of the plurality of the pacing control networks. Each DSP block of the plurality of DSP blocks is independently and separately connected with the streaming cross bar via the plurality of pacing control networks.

Abstract: An encapsulation block for a digital signal processing (DSP) block. The encapsulation block includes DSP block having an input terminal, an output terminal, and an input clock. The encapsulation block also includes pacing control network operatively connected with the input terminal, the output terminal, and the input clock of the DSP block. The input terminal of the DSP block is configured to receive a samples-in data stream inputted at a predefined clock period defined by the input clock. The output terminal of the DSP block is configured to receive a samples-out data stream outputted at a predefined paced parameter. The pacing control network is configured to control data flow at the samples-in data stream and the samples-out data stream independently of the DSP block.

Abstract: A logic power network provided in an application-specific integrated circuit (ASIC). The ASIC includes a central processor. The ASIC also includes at least one intellectual property (IP) core operatively connected with the central processor and having a set of electrical components provided therein. The ASIC also includes a network-on-chip (NOC) operatively connected with the central processor and the at least one IP core. The ASIC also includes a logic power network operatively connected with the central processor, the at least one IP core and the set of electrical components therein, and the NOC. The logic power network is adapted to control power of the at least one IP core and the set of electrical components provided in the at least one IP Core individually and separately.

Abstract: A port protection network provided with a joint test action group (JTAG) core and method of use. The port protection network includes an agent device operatively connected with a streaming bus and a test access port (TAP) of the JTAG core. The port protection network also includes a master device operatively connected with the streaming bus and the TAP of the JTAG core. In the port protection network, the agent device is configured to selectively restrict access to the master device through the JTAG core.

Abstract: An on-chip firewall circuit for providing secure on-chip communication is disclosed. The firewall circuit includes a configurable table of port IDs along with a configurable setting for each port ID to either provide the corresponding port ID with open access to the components of a secure enclave (SE) module or restricted access. If access is restricted, then the command is rerouted to a portion of the secure memory within the SE module, where it can be read only via a secure processing device within the SE module. The secure processing device may require additional verification of the port ID before executing the command stored within the secure memory. In this way, unsecure devices from outside of the SE module can be configured to have no direct access to any of the components within the SE module.

Abstract: A clock phase control circuit includes a clock input gate module, first and second shift register divider modules, and a multiplexer. The clock input gate module is configured to produce, based on an oscillating input clock signal, first and second intermediate clock signals. The first shift register divider module is configured to produce at least one first phase clock signal based on the first intermediate clock signal, where the at least one first phase clock signal has a different frequency than the first intermediate clock signal. The second shift register divider module is configured to produce at least one second phase clock signal based on the second intermediate clock signal, where the at least one second phase clock signal has a different frequency than the second intermediate clock signal. The multiplexer is configured to produce an output clock signal by selecting one of the first or second phase clock signals.