3. Floating Point Functions IP
This IP replaces all the functions supported by the FP_FUNCTIONS IP core for devices in the Quartus® Prime Standard Edition software.
Item | Description |
---|---|
Version | 19.1 |
Quartus® Prime Version | 20.1 |
Release Date | 2020.04.13 |
Function | Description |
---|---|
Arithmetic | |
Add | Two input addition |
Sub | Two input subtraction |
Add/Sub | Two input addition and or subtraction supporting two configurations. By default, the IP core computes both the sum (output port q) and the difference (output port s) of the two inputs. You may also select to generate an IP core that provides a single shared output for both the sum and the difference of inputs. In this configuration an additional input port (opSel) allows you to select the desired operation at run-time. When opSel is low (0), the IP core computes the sum of the two inputs. When opSel is high (1), it computes their difference. Enable this configuration by turning on Use Select Signal. |
Multiply | Two input multiplication |
Divide | Two input division |
Reciprocal | Performs the function of 1/a where a is the input.
Note: This function replaces the ALTFP_INV IP core in Arria® 10 devices.
|
Absolute | Generates absolute value of the input |
Scalar Product | Performs the scalar product between two vectors with the dimensions that you set |
Multiply-Accumulate | Two input multiplication followed by a single cycle accumulation |
Accumulate | Perform single input accumulation in a single cycle |
Multiply-Add | Performs two input multiplication followed by addition |
Complex-Multiply | Performs multiplication of two complex values |
Roots | |
Square Root | Calculates the square root of the input value |
Reciprocal Square Root | Performs the function of 1/√a where a is the input
Note: This function replaces the ALTFP_INV_SQRT IP core in Arria® 10 devices.
|
Cube Root | Calculates the cube root of the input value |
3D Hypotenuse | Performs the function of Q=√(a^2+b^2+c^2) |
Conversions | |
Fixed-Point to Floating-Point | Converts a fixed point input to floating point representation |
Floating-Point to Fixed-Point | Converts a floating-point input to fixed point representation |
Floating to Floating Point | Converts a floating-point input to floating-point representation of a different precision |
Comparisons | |
Minimum | Compares and produces the smallest value of two inputs |
Maximum | Compares and produces the biggest value of two inputs |
Less Than | Compares and returns true if input a is less than input b |
Less Than or Equal | Compares and returns true if input a is less than or equal to input b |
Equal | Compares and returns true if input a is equal to input b |
Greater Than | Compares and returns true if input a is greater than input b |
Greater Than or Equal | Compares and returns true if input a is greater than or equal to input b |
Not Equal | Compares and returns true if input a is not equal to input b |
Exp/Log/Pow | |
Exponent | Performs the function of ea where a is the input |
Exponent base 2 | Performs the function of 2a where a is the input |
Exponent base 10 | Performs the function of 10a where a is the input |
Log | Performs the function of loge(a) where a is the input |
Log2 | Performs the function of log2(a) where a is the input |
Log10 | Performs the function of log10(a) where a is the input |
Log(1+x) | Performs the function of loge(1+a) where a is the input |
Power | Provides an implementation of the power function that computes a to the power of b, where a is ≥0. |
LdExp | Sets the exponential value of a floating-point input. Performs the function a * 2^b where a is a floating-point input and b is an integer input. You specify both the format of input a and the width of input b |
Trigonometry | |
Sin | Performs sine function of a single input |
Cos | Performs cosine function of a single input |
Tan | Performs tangent function of a single input |
Arcsin | Performs arc sine function of a single input |
Arccos | Performs arc cosine function of a single input |
Arctan | Performs arc tangent function of a single input |
Arctan2 | Performs the function of arctan (b/a) where a and b are the inputs |