FPGA Optimization Guide for Intel® oneAPI Toolkits

Developer Guide

Contents

Declare the
ac_int
 Data Type

Perform the following steps to declare the
ac_int
 data type:
  1. Include the
    ac_int.hpp
     header file as follows: 
    #include <sycl/ext/intel/ac_types/ac_int.hpp>
  2. Declare your
    ac_int
     variables in one of the following ways:
    • Template-based declaration: 
      ac_int<N, true> var_name; //Signed N-bit integer
      ac_int<N, false> var_name; //Unsigned N-bit integer
    • Predefined types up to 63 bits: 
      ac_intN::intN var_name; //Signed N-bit integer
      ac_intN::uintN var_name; //Unsigned N-bit integer
    Where,
    N
     is the total length of the integer in bits.
    The
    ac_int
     data type has several API calls. For more information about the Algorithmic C data types, refer to https://github.com/hlslibs/ac_types/blob/v3.7/pdfdocs/ac_datatypes_ref.pdf.
If you want to initialize an
ac_int
 variable to a value larger than 64 bits, you must use the
bit_fill
 or
bit_fill_hex
 utility function. For details, refer to the section
Methods to Fill Bits
in the documentation provided in https://github.com/hlslibs/ac_types/blob/v3.7/pdfdocs/ac_datatypes_ref.pdf.
The following code example shows the use of the
bit_fill
 or
bit_fill_hex
 utility functions: 
typedef ac_int<80,false> i80_t;
i80_t x;
x.bit_fill_hex("a9876543210fedcba987"); // member funtion
x = ac::bit_fill_hex<i80_t>("a9876543210fedcba987"); // global function
int vec[] = { 0xa987, 0x6543210f, 0xedcba987 };
x.bit_fill(vec); // member function
x = bit_fill<i80_t>(vec); // global function
// inlining the constant array
x.bit_fill( (int [3]) { 0xa987,0x6543210f,0xedcba987 } ); // member function
x = bit_fill<i80_t>( (int [3]) { 0xa987,0x6543210f,0xedcba987 } ); // global function

Debugging the
ac_int
 Data Type Use

The
ac_int.hpp
 header file provides tools to help you check
ac_int
 data type operations and assignments for overflow.
Currently, you can debug
ac_int
 data type operations and assignments for overflow only in the emulation flow and only for non-kernel code.
  • When you use
    DEBUG_AC_INT_WARNING
     and
    DEBUG_AC_INT_ERROR
     macros, you cannot declare
    constexpr ac_int
     variables or
    constexpr ac_int
     arrays.
    Macro
    Description
    DEBUG_AC_INT_WARNING
    Emits a warning for each detected overflow.
    DEBUG_AC_INT_ERROR
    Emits a message for the first overflow that is detected and then exits the code with an error.
  • Within your code, you must declare the macros before you include the
    ac_int.hpp
     header file.
For additional information, refer to the FPGA tutorial sample "Algorithmic C Integer Data Type ac_int" listed in the Intel® oneAPI Samples Browser on Linux* or Windows*, or access the code sample on GitHub.

Product and Performance Information

1

Performance varies by use, configuration and other factors. Learn more at www.Intel.com/PerformanceIndex.