Abstract:
A processing apparatus includes floating point arithmetic circuitry coupled to monitoring circuitry. The monitoring circuitry stores exponent limit data indicating at least one of a maximum exponent value and a minimum exponent value processed when performing the floating point arithmetic operations. The monitoring circuitry may be selectively enabled in dependence upon a virtual machine identifier, an application specific identifier or a program counter value range. Exponent limit data may be gathered in respect of different portions of the floating point arithmetic circuitry and/or may be aggregated to form global exponent limit data for the system.
Abstract:
A data processing system uses alignment circuitry to align input operands in accordance with a programmable significance parameter to form aligned input operands. The aligned input operands are supplied to arithmetic circuitry, such as an integer adder or an integer multiplier, where a result value is formed. The result value is stored in an output operand storage element, such as a result register. The programmable significance parameter is independent of the result value.
Abstract:
A data processing system performs processing operations upon input operand(s) having a programmable bit significance. Exception generating circuitry generates exception indications representing exceptions such as overflow, underflow and inexact in respect of a result value having the programmable bit significance.
Abstract:
A dynamic element matching (DEM) scheme is implemented in a crawling code generator for converting a b-bit binary input code into a (2b−1)-bit digital output code. A random generator determines for every conversion step a direction. A decimal difference between the current and previous binary input is calculated. The new crawling output code is determined based on the previous crawling output code, the direction and the decimal difference. The DEM scheme is used in a digital-to-analog converter such that the crawling output code switches digital-to-analog converting elements that output analog signals that are then summed to be the final analog signal.
Abstract:
A dynamic element matching (DEM) scheme is implemented in a crawling code generator for converting a b-bit binary input code into a (2b−1)-bit digital output code. A random generator determines for every conversion step a direction. A decimal difference between the current and previous binary input is calculated. The new crawling output code is determined based on the previous crawling output code, the direction and the decimal difference. The DEM scheme is used in a digital-to-analog converter such that the crawling output code switches digital-to-analog converting elements that output analog signals that are then summed to be the final analog signal.
Abstract:
A method for converting from decimal to binary including receiving a binary coded decimal (BCD) number made up of one or more sets of three digits. A running sum and a running carry are set to zero. A process is performed for each set of three digits in the BCD number in order from the set of three digits containing the three most significant digits of the BCD number to the digits containing the three least significant digits of the BCD number. The process includes: creating six partial products based on the set of three digits, the running sum and the running carry; combining the six partial products into two partial products; and storing the two partial products in the running sum and the running carry. The running sum and the running carry from each set of three digits are combined into a final binary result.
Abstract:
The invention concerns a method for converting in a signed binary representation (rnullm, rnull0) of a number r based on a left-to-right processing of bits of the binary representation (rnullm, rnull0) and enabling to obtain a representation equivalent to the so-called Reitwiesner representation. The use of such a conversion method with left-to-right arithmetic processing enables to improve their hardware implementation.
Abstract:
A system and method are provided for encoding from decimal to binary and back again. The coding is based on representing 3 decimal digits as 10 binary bits and is a development of the Chen-Ho algorithm. This provides a storage efficiency of >99%, yet still allows decimal arithmetic to be readily performed. The decimal input is typically first converted to binary coded decimal (4 bits per decimal digit), before compression to 10 bits. Adopting the encoding of the present invention, if the leading (most significant) decimal digit is zero, then the first three bits of the binary output are zero; and if the first two decimal digits are zero, then the first six bits of the binary output are zero. Accordingly, the same coding can be flexibly used to code 2 decimal digits to 7 binary bits, and 1 decimal digit to 4 binary bits. This makes it particularly suitable for standard computer architectures which are based on a power of two (16-bit, 32-bit, 64-bit, etc), and therefore not directly divisible by 7 or by 10.
Abstract:
An image processing apparatus comprising binarization means for converting a multi-level color signal into binary form, removal means for removing edge component from the multi-level color signal, based on a binary color signal from said binarization means, and encoder means for encoding the binary color signal from said binarization means and the multi-level color signal having edge component removed with said removal means.
Abstract:
An image processing apparatus in which a multi-level color signal is input and converted into a binary color signal. An edge component is removed from the multi-level color signal based on the binary color signal and the binary color signal and the multi-level color signal of which the edge component is removed are encoded.