发明名称 Performing arithmetic operations using both large and small floating point values
摘要 Mechanisms are provided for performing a floating point arithmetic operation in a data processing system. A plurality of floating point operands of the floating point arithmetic operation are received and bits in a mantissa of at least one floating point operand of the plurality of floating point operands are shifted. One or more bits of the mantissa that are shifted outside a range of bits of the mantissa of at least one floating point operand are stored and a vector value is generated based on the stored one or more bits of the mantissa that are shifted outside of the range of bits of the mantissa of the at least one floating point operand. A resultant value is generated for the floating point arithmetic operation based on the vector value and the plurality of floating point operands.
申请公布号 US8909690(B2) 申请公布日期 2014.12.09
申请号 US201113324025 申请日期 2011.12.13
申请人 International Business Machines Corporation 发明人 Carter John B.;Mealey Bruce G.;Rajamani Karthick;Retter Eric E.;Stuecheli Jeffrey A.
分类号 G06F7/38 主分类号 G06F7/38
代理机构 代理人 Walder, Jr. Stephen J.;Tyson Thomas E.
主权项 1. An apparatus, comprising: hardware logic configured to receive a plurality of floating point operands of a floating point arithmetic operation; hardware logic configured to shift bits in a mantissa of at least one floating point operand of the plurality of floating point operands; hardware logic configured to store one or more bits of the mantissa that are shifted outside a range of bits of the mantissa of the at least one floating point operand; hardware logic configured to generate a vector value based on the stored one or more bits of the mantissa that are shifted outside the range of bits of the mantissa of the at least one floating point operand; and hardware logic configured to generate a resultant value for the floating point arithmetic operation based on the vector value and the plurality of floating point operands, wherein: the hardware logic configured to store one or more bits of the mantissa that are shifted outside a range of bits of the mantissa of the at least one floating point operand comprises hardware logic configured to set bits in bit positions of a separate register corresponding to the one or more bits of the mantissa shifted outside of the range of hits of the mantissa,each bit position in the separate register has a different associated probability weight, andthe hardware logic configured to generate the vector value based on the stored one or more bits of the mantissa that are shifted outside the range of bits of the mantissa of the at least one floating point operand comprises hardware logic configured to generate the vector value based on probability weights associated with bit positions having corresponding hit values set in the separate register.
地址 Armonk NY US