CODEWITHSUNDEEP
c++floating-pointbfloat16
oawad
oawad

Reputation: 101

Convert FP32 to Bfloat16 in C++

How can I convert from float (1bit sign, 8bit exp, 23bit mantissa) to Bfloat16 (1bit sign, 8bit exp, 7bit mantissa) in C++?

Upvotes: 9

Views: 10532

Answers (3)

Akihito Nakayama
Akihito Nakayama

Reputation: 41

memcpy wouldn't compile for me in the little endian case for some reason. This is my solution. I have it as a struct here so that I can easily access the data and run through different ranges of values to confirm that it works properly.

struct bfloat16{
   unsigned short int data;
   public:
   bfloat16(){
      data = 0;
   }
   //cast to float
   operator float(){
      unsigned int proc = data<<16;
      return *reinterpret_cast<float*>(&proc);
   }
   //cast to bfloat16
   bfloat16& operator =(float float_val){
      data = (*reinterpret_cast<unsigned int *>(&float_val))>>16;
      return *this;
   }
};

//an example that enumerates all the possible values between 1.0f and 300.0f
using namespace std;

int main(){
   bfloat16 x;
   for(x = 1.0f; x < 300.0f; x.data++){
      cout<<x.data<<" "<<x<<endl;
   }
   
   return 0;
}

Upvotes: 4

Mark Ransom
Mark Ransom

Reputation: 308452

As demonstrated in the answer by Botje it is sufficient to copy the upper half of the float value since the bit patterns are the same. The way it is done in that answer violates the rules about strict aliasing in C++. The way around that is to use memcpy to copy the bits.

static inline tensorflow::bfloat16 FloatToBFloat16(float float_val)
{
    tensorflow::bfloat16 retval;
#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
    memcpy(&retval, &float_val, sizeof retval);
#else
    memcpy(&retval, reinterpret_cast<char *>(&float_val) + sizeof float_val - sizeof retval, sizeof retval);
#endif
    return retval;
}

If it's necessary to round the result rather than truncating it, you can multiply by a magic value to push some of those lower bits into the upper bits.

float_val *= 1.001957f;

Upvotes: 5

Botje
Botje

Reputation: 31020

From the Tensorflow implementation:

static inline tensorflow::bfloat16 FloatToBFloat16(float float_val) {
#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
    return *reinterpret_cast<tensorflow::bfloat16*>(
        reinterpret_cast<uint16_t*>(&float_val));
#else
    return *reinterpret_cast<tensorflow::bfloat16*>(
        &(reinterpret_cast<uint16_t*>(&float_val)[1]));
#endif
}

Upvotes: 1

Related Questions