Floating-Point IP Cores User Guide

Download
ID 683750
Date 9/13/2021
Public
Document Table of Contents

15.6. ALTFP_CONVERT Signals

Figure 40. ALTFP_CONVERT Signals
Table 88.  ALTFP_CONVERT Input Signals
Port Name Required Description
clock Yes The clock input to the ALTFP_CONVERT IP core.
clk_en No Clock enable that allows conversions to take place when asserted high. When asserted low, no operation occurs and the outputs are unchanged.
aclr No Asynchronous clear. The source is asynchronously reset when the aclr signal is asserted high.
dataa[] Yes Data input. The size of this input port depends on the WIDTH_DATA parameter value.

If the operation mode value is INT2FLOAT or FIXED2FLOAT, the data on the input bus is an integer.

If the operation mode value is FLOAT2INT or FLOAT2FIXED, the input bus is the IEEE floating-point representation. In the single-precision format, the input bus width value is 32. In the double-precision format, the input bus width value is 64.

In the single-extended precision format, the input bus range is from 43 to 64.

If the operation mode value is FLOAT2FLOAT, the input bus value is the IEEE floating-point representation. In the single-precision format, the input bus width value is 32. In the double-precision format, the input bus width value is 64. In the single-extended precision format, the input bus range is from 43 to 64.

Table 89.  ALTFP_CONVERT Output Signals
Port Name Required Description
result[] Yes Output for the floating-point converter. The size of this output port depends on the WIDTH_RESULT parameter value.

If the operation mode value is FLOAT2INT or FLOAT2FIXED, the output bus is an IEEE floating-point representation.

If the operation mode is FLOAT2INT, the output bus is an integer representation. If the selected precision is the single-precision format, the output bus width value is 32. If the selected precision is the double-precision format, the output bus width value is 64. If the selected precision is the single-extended precision format, the input bus range is from 43 to 64.

If the operation mode value is FLOAT2FLOAT, the output bus is an IEEE floating-point representation. If the selected precision is the single-precision format, the output bus is in the 64-bit double-precision format. If the selected precision is the double-precision format, the output bus is in the 32-bit single-precision format. If the selected precision is the single-extended precision format, the output bus ranges from 43 to 64.

overflow No Optional overflow exception output. This port is available only when the operation mode values are FLOAT2FIXED, FLOAT2INT, or FLOAT2FLOAT.

Asserted when the result of the conversion (after rounding), exceeds the maximum width of the result[] port, or when the dataa[] input is infinity.

underflow No Optional underflow exception output. This port is available only when the operation mode values are FLOAT2FIXED, FLOAT2INT, or FLOAT2FLOAT.

Asserted when the result of the conversion, after rounding, is fractional.

In FLOAT2INT operations, this port is asserted when the exponent value of the floating-point input is smaller than the exponent bias.

In FLOAT2FLOAT operations, this port is asserted when the floating-point input has a value smaller than the lowest exponent limit of the target floating-point format.

nan No Optional NaN exception output. This port is available only when the operation mode values are FLOAT2INT, FLOAT2FLOAT, or FLOAT2FIXED.

Asserted when the input port is a NaN representation.

If the operation mode value is FLOAT2INT or FLOAT2FIXED, the result[] port is set to zero.

If the operation mode value is FLOAT2FLOAT, the result[] port is set to a NaN representation.

Did you find the information on this page useful?

Characters remaining:

Feedback Message