[] Services
ACEN
rockfairy technology

Home > IP cores > Arithmetic floating point > Arithmetic floating point

Floating point arithmetic | ACEN

Arithmetic floating point

Monday 14 October 2013, by admin

In this version the arithmetic IPs operate on 32 bits floating point numbers compliant with IEEE 754-1985. The error on the mantissa (with respect to the result calculated with an infinite precision) is less or equal to 0.5 bit. Normalized and de-normalized numbers defined by the standard are processed.

Arithmetic operation IData sheetEvaluation kit for Lattice ECP3
PNG - 717 bytes
Inversion of floating point numbers
PDF - 81.3 kb
INVS FP
Inversion floating point
Zip - 415.2 kb
INVS FP
Inversion floating point
PNG - 673 bytes
Multiplication of floating point numbers
PDF - 92.2 kb
MULT FP
Multiplication floating point
Zip - 394.8 kb
MULT FP
Multiplication floating point
PNG - 752 bytes
Division of floating point numbers
PDF - 94.1 kb
DIVS FP
Division floating point
Zip - 691.8 kb
DIVS FP
Division floating point
PNG - 1.6 kb
Square root of floating point numbers
PDF - 80.7 kb
SQRT FP
Square root floating point
Zip - 402.5 kb
SQRT FP
Square root floating point
PNG - 1.6 kb
Cube root of floating point numbers
PDF - 79.6 kb
CBRT FP
Cube root floating point
Zip - 764.8 kb
CBRT FP
Cube root floating point
SPIP | | Site Map | Follow site activity RSS 2.0