摘要:
Configurable specialized processing blocks, such as DSP blocks, are described that implement fixed and floating-point functionality in a single mixed architecture on a programmable device. The described architecture reduces the need to construct floating-point functions outside the configurable specialized processing block, thereby minimizing hardware cost and area. The disclosed architecture also introduces pipelining into the DSP block in order to ensure the floating-point multiplication and addition functions remain in synchronicity, thereby increasing the maximum frequency at which the DSP block can operate. Moreover, the disclosed architecture includes logic circuitry to support floating-point exception handling.
摘要:
Circuits, methods, and apparatus that prevent detection and erasure of encoding or encryption keys. These encoding keys may be used to encode a configuration bitstream or other data for an FPGA or other device. An exemplary embodiment of the present invention masks a first key to form an encoding key in order to prevent detection of the first key. In a specific embodiment, the first key is encoded using a second key. The encoded key is used to encode a configuration bitstream or other data. The encoded key is stored on an FPGA or other device. When the device is to be configured, the encoded key is retrieved and used to decode the bitstream or other data. A further embodiment stores an encryption key in a one-time programmable memory (OTP) array to prevent its erasure or modification. The encoding key may be further obfuscated before storage.
摘要:
Circuits, methods, and apparatus that prevent detection and erasure of a configuration bitstream or other data for an FPGA or other device. An exemplary embodiment of the present invention masks a user key in order to prevent its detection. In a specific embodiment, the user key is masked by software that performs a function on it a first number of times. The result is used to encrypt a configuration bitstream. The user key is also provided to an FPGA or other device, where the function is performed a second number of times and the result stored. When the device is configured, the result is retrieved, the function is performed on it the first number of times less the second number of times and then it is used to decrypt the configuration bitstream. A further embodiment uses a one-time programmable fuse (OTP) array to prevent erasure or modification.
摘要:
Digital signal processing (“DSP”) circuit blocks are provided that can more easily work together to perform larger (e.g., more complex and/or more arithmetically precise) DSP operations if desired. These DSP blocks may also include redundancy circuitry that facilitates stitching together multiple such blocks despite an inability to use some block (e.g., because of a circuit defect). Systolic registers may be included at various points in the DSP blocks to facilitate use of the blocks to implement systolic form, finite-impulse-response (“FIR”), digital filters.
摘要:
Digital signal processing (“DSP”) circuit blocks are provided that can more easily work together to perform larger (e.g., more complex and/or more arithmetically precise) DSP operations if desired. These DSP blocks may also include redundancy circuitry that facilitates stitching together multiple such blocks despite an inability to use some block (e.g., because of a circuit defect). Systolic registers may be included at various points in the DSP blocks to facilitate use of the blocks to implement systolic form, finite-impulse-response (“FIR”), digital filters.
摘要:
Configurable specialized processing blocks, such as DSP blocks, are described that implement fixed and floating-point functionality in a single mixed architecture on a programmable device. The described architecture reduces the need to construct floating-point functions outside the configurable specialized processing block, thereby minimizing hardware cost and area. The disclosed architecture also introduces pipelining into the DSP block in order to ensure the floating-point multiplication and addition functions remain in synchronicity, thereby increasing the maximum frequency at which the DSP block can operate. Moreover, the disclosed architecture includes logic circuitry to support floating-point exception handling.
摘要:
Configurable specialized processing blocks, such as DSP blocks, are described that implement fixed and floating-point functionality in a single mixed architecture on a programmable device. The described architecture reduces the need to construct floating-point functions outside the configurable specialized processing block, thereby minimizing hardware cost and area. The disclosed architecture also introduces pipelining into the DSP block in order to ensure the floating-point multiplication and addition functions remain in synchronicity, thereby increasing the maximum frequency at which the DSP block can operate. Moreover, the disclosed architecture includes logic circuitry to support floating-point exception handling.
摘要:
Configurable specialized processing blocks, such as DSP blocks, are described that implement fixed and floating-point functionality in a single mixed architecture on a programmable device. The described architecture reduces the need to construct floating-point functions outside the configurable specialized processing block, thereby minimizing hardware cost and area. The disclosed architecture also introduces pipelining into the DSP block in order to ensure the floating-point multiplication and addition functions remain in synchronicity, thereby increasing the maximum frequency at which the DSP block can operate. Moreover, the disclosed architecture includes logic circuitry to support floating-point exception handling.
摘要:
Configurable specialized processing blocks, such as DSP blocks, are described that implement fixed and floating-point functionality in a single mixed architecture on a programmable device. The described architecture reduces the need to construct floating-point functions outside the configurable specialized processing block, thereby minimizing hardware cost and area. The disclosed architecture also introduces pipelining into the DSP block in order to ensure the floating-point multiplication and addition functions remain in synchronicity, thereby increasing the maximum frequency at which the DSP block can operate. Moreover, the disclosed architecture includes logic circuitry to support floating-point exception handling.
摘要:
Circuits, methods, and apparatus that prevent detection and erasure of a configuration bitstream or other data for an FPGA or other device. An exemplary embodiment of the present invention masks a user key in order to prevent its detection. In a specific embodiment, the user key is masked by software that performs a function on it a first number of times. The result is used to encrypt a configuration bitstream. The user key is also provided to an FPGA or other device, where the function is performed a second number of times and the result stored. When the device is configured, the result is retrieved, the function is performed on it the first number of times less the second number of times and then it is used to decrypt the configuration bitstream. A further embodiment uses a one-time programmable fuse (OTP) array to prevent erasure or modification.