Floating-point Division Circuitry with Subnormal Support

    公开(公告)号:US20220317971A1

    公开(公告)日:2022-10-06

    申请号:US17218041

    申请日:2021-03-30

    Applicant: Apple Inc.

    Abstract: Techniques are disclosed relating to circuitry for floating-point division. In some embodiments, the circuitry is configured to generate a subnormal result for a division operation that divides a numerator by a denominator. The circuitry may include floating-point circuitry configured to perform a reciprocal operation to determine a normalized mantissa value for the reciprocal of a floating-point representation of the denominator. The circuitry may further include fixed-point circuitry configured to multiply a fixed-point representation of the normalized mantissa value for the reciprocal by a mantissa of the numerator to generate an initial value. Control circuitry may determine error data for the initial value and generate a final subnormal mantissa result for the division operation based on the error data and the initial value. Embodiments with multiple modes with different accuracy guarantees are disclosed.

    Floating-point division circuitry with subnormal support

    公开(公告)号:US11836459B2

    公开(公告)日:2023-12-05

    申请号:US17218041

    申请日:2021-03-30

    Applicant: Apple Inc.

    CPC classification number: G06F7/4873 G06F7/4876 G06F7/49984

    Abstract: Techniques are disclosed relating to circuitry for floating-point division. In some embodiments, the circuitry is configured to generate a subnormal result for a division operation that divides a numerator by a denominator. The circuitry may include floating-point circuitry configured to perform a reciprocal operation to determine a normalized mantissa value for the reciprocal of a floating-point representation of the denominator. The circuitry may further include fixed-point circuitry configured to multiply a fixed-point representation of the normalized mantissa value for the reciprocal by a mantissa of the numerator to generate an initial value. Control circuitry may determine error data for the initial value and generate a final subnormal mantissa result for the division operation based on the error data and the initial value. Embodiments with multiple modes with different accuracy guarantees are disclosed.

    Circuitry for Floating-point Power Function

    公开(公告)号:US20210382687A1

    公开(公告)日:2021-12-09

    申请号:US16893051

    申请日:2020-06-04

    Applicant: Apple Inc.

    Abstract: Techniques are disclosed relating to floating-point circuitry configured to perform a corner check instruction for a floating-point power operation. In some embodiments, the power operation is performed by executing multiple instructions, including one or more instructions specify to generate an initial power result of a first input raised to the power of a second input as 2(second input*log2(first input)). In some embodiments, the corner check instruction operates on the first and second inputs and outputs output a corrected power result based on detection of a corner condition for the first and second inputs. Corner check circuitry may share circuits with other datapaths. In various embodiments, the disclosed techniques may reduce code size and power consumption for the power operation.

    Circuitry for floating-point power function

    公开(公告)号:US11372621B2

    公开(公告)日:2022-06-28

    申请号:US16893051

    申请日:2020-06-04

    Applicant: Apple Inc.

    Abstract: Techniques are disclosed relating to floating-point circuitry configured to perform a corner check instruction for a floating-point power operation. In some embodiments, the power operation is performed by executing multiple instructions, including one or more instructions specify to generate an initial power result of a first input raised to the power of a second input as 2(second input*log2(first input)). In some embodiments, the corner check instruction operates on the first and second inputs and outputs output a corrected power result based on detection of a corner condition for the first and second inputs. Corner check circuitry may share circuits with other datapaths. In various embodiments, the disclosed techniques may reduce code size and power consumption for the power operation.

    Floating-Point Execution Circuitry for Subset of Binary Logarithm Input Range

    公开(公告)号:US20240061650A1

    公开(公告)日:2024-02-22

    申请号:US17820766

    申请日:2022-08-18

    Applicant: Apple Inc.

    CPC classification number: G06F7/556 G06F7/4873

    Abstract: Techniques are disclosed relating to polynomial approximation of the base-2 logarithm. In some embodiments, floating-point circuitry is configured to perform an approximation of a base-2 logarithm operation and provide a fixed unit of least precision (ULP) error over a range of inputs. In some embodiments, the floating-point circuitry includes a set of parallel pipelines for polynomial approximation, where the output is chosen from a particular pipeline based on a determination of whether the input operand is in a first subset of a range of inputs. Disclosed techniques may advantageously provide fixed ULP error for an entire input operand range for the floating-point base-2 logarithmic function with minimal area and energy footprint, relative to traditional techniques.

    Floating-point Division Circuitry with Subnormal Support

    公开(公告)号:US20240053960A1

    公开(公告)日:2024-02-15

    申请号:US18489640

    申请日:2023-10-18

    Applicant: Apple Inc.

    CPC classification number: G06F7/4873 G06F7/49984 G06F7/4876

    Abstract: Techniques are disclosed relating to circuitry for floating-point division. In some embodiments, the circuitry is configured to generate a subnormal result for a division operation that divides a numerator by a denominator. The circuitry may include floating-point circuitry configured to perform a reciprocal operation to determine a normalized mantissa value for the reciprocal of a floating-point representation of the denominator. The circuitry may further include fixed-point circuitry configured to multiply a fixed-point representation of the normalized mantissa value for the reciprocal by a mantissa of the numerator to generate an initial value. Control circuitry may determine error data for the initial value and generate a final subnormal mantissa result for the division operation based on the error data and the initial value. Embodiments with multiple modes with different accuracy guarantees are disclosed.

Patent Agency Ranking