A new square root instruction can be issued to the divide unit every 20 or 35 cycles for single precision and double precision respectively.
32.
In older versions of Flash player there existed one number type called'Number'which was a 64-bit double precision encoding.
33.
While 64-bit floating point values ( double precision float ) are commonly available on CPUs, these are not universally supported on GPUs.
34.
When one or both of the operands has a tag of 2, a double precision add is performed, otherwise tag 0 indicates single precision.
35.
The strictfp modifier accomplishes this by rounding all intermediate values to IEEE single precision and double precision, as occurred in earlier versions of the JVM.
36.
This simplification left the latency of single precision multiplies unchanged ( two cycles ), but increased the latency of double precision multiplies to three cycles.
37.
By default, 1 / 3 rounds up, instead of down like double precision, because of the even number of bits in the significand.
38.
Code generation for hardware assisted double precision floating point operations is supported for platforms based on ARM chips that support the VFP version 2 coprocessor architecture.
39.
Because of this, single precision format actually has a significand with 24 bits of precision, double precision format has 53, and quad has 113.
40.
A conversion of double precision hexadecimal float to decimal string would require at least 18 significant digits in order to convert back to the same hexadecimal float value.
