-
公开(公告)号：EP3958113A1
公开(公告)日：2022-02-23
申请号：EP21190433.9
申请日：2021-08-09
发明人： Ferrere, Thomas
摘要： A method and system for processing a set of 'k' floating point numbers to perform addition and/or subtraction is disclosed. Each floating-point number comprises a mantissa (m i ) and an exponent (e i ). The method comprises receiving the set of 'k' floating point numbers in a first format, each floating-point number in the first format comprising a mantissa (m i ) with a bit-length of 'b' bits. The method further comprises creating a set of 'k' numbers (y i ) based on the mantissas of the 'k' floating-point numbers, the numbers having a bit-length of 'n' bits obtained by adding both extra most-significant bits and extra least-significant bits to the bit length 'b' of the mantissa (m i ). The method includes identifying a maximum exponent (e max ) among the exponents e i , aligning the magnitude bits of the numbers (y i ) based on the maximum exponent (e max ) and processing the set of 'k' numbers concurrently.
-
公开(公告)号：EP4231135A1
公开(公告)日：2023-08-23
申请号：EP23155922.0
申请日：2023-02-09
发明人： Ferrere, Thomas
摘要： A method of performing dot product of an array of '2k' floating point numbers comprising two sets of k floating-point numbers a i and b i is disclosed. The method includes receiving both sets of 'k' floating point numbers and multiplying each floating point number a i with a floating point number b i to generate k product numbers (z i ), each product number (z i ) having a mantissa bit length of 'r' bits. The method further comprises creating a set of 'k' numbers (y i ) based on the k product numbers (z i ), the numbers (y i ) having a bit-length of 'n' bits. Further the method includes identifying a maximum exponent sum (e max ) among k exponent sums (eab i ) of each pair of floating point numbers a i and b i , aligning the magnitude bits of the numbers (y i ) based on the maximum exponent sum (e max ) and adding the set of 'k' numbers concurrently to obtain the dot product.
-
公开(公告)号：EP4231134A1
公开(公告)日：2023-08-23
申请号：EP23155921.2
申请日：2023-02-09
发明人： Ferrere, Thomas
摘要： A method of performing dot product of an array of '2k' floating point numbers comprising two sets of k floating-point numbers a i and b i is disclosed. The method includes receiving both sets of 'k' floating point numbers and multiplying each floating point number a i with a floating point number b i to generate k product numbers (z i ), each product number (z i ) having a mantissa bit length of 'r+ log (k-1) +1' bits. The method further comprises creating a set of 'k' numbers (y i ) based on the k product numbers (z i ), the numbers (y i ) having a bit-length of 'n' bits. Further the method includes identifying a maximum exponent sum (e max ) among k exponent sums (eab i ) of each pair of floating point numbers a i and b i , aligning the magnitude bits of the numbers (y i ) based on the maximum exponent sum (e max ) and adding the set of 'k' numbers concurrently to obtain the dot product.
-
公开(公告)号：EP3882761A1
公开(公告)日：2021-09-22
申请号：EP21161631.3
申请日：2021-03-09
发明人： Ferrere, Thomas , Gaulter, Simon , Nazar, Faizan , Elliott, Sam
IPC分类号： G06F7/24 , G06F30/3323
摘要： Methods and systems of verifying a hardware design for a sorter are disclosed. The methods include generating a modified version of the hardware design of the sorter accepting extended inputs and performing formal verification comprising: implementing a constraint that the least significant bits of each input in a set of extended inputs represent a unique value; and formally verifying aspects of the modified version of the hardware design of the sorter for the set of extended inputs.
-
-
-
搜索结果
4 条记录 (耗时 0.011 秒)
