Hacker News Reader

When doing floating point arithmetic on the x86 though, it can extend to `80 - 1 (sign) - 15 (exponent) = 64` bits. So if the result of a floating point just so happens to have zero exponent, the mantissa can fit just right in a long int.

View on HN

This hasn't been dependably true on x86 for almost two decades. SSE2 does double-precision computation at native width, not in the extended 80-bit format. Some 32b compilers still use 80-bit x87, but almost no 64b compilers do so.

> This hasn't been dependably true on x86 for almost two decades. SSE2 does double-precision computation at native width, not in the extended 80-bit format. Some 32b compilers still use 80-bit x87, but almost no 64b compilers do so.

My experience has been different -- forcing SSE instructions gives me a different result on some math calculations. Core2 cpu, boost odeint calculations. Clang or gcc.

Do you have a reference for why it's rare?

x87 is the default for 32b processes on Windows and Linux. 32b processes on macOS and 64b processes on all three OSes use SSE2 for double precision.

Reply on news.ycombinator.com