I'm curious that the latency of these is actually worse than the latency of floating operations. Yes, they are worse than many integer instructions, but they seem to be on basically the same order as the equivalent float operations?
My rule of thumb is that integer ops cost 1 cycle except divides, floats 3 but maybe divide is a bit more, then integer divides are like infinity at 20+ cycles that cannot be amortized by vectorization.
When you code simd it's best to assume the integer divide instruction does not exist. Just an impossibility, if you need to divide ints, rethink your whole program.
I would love to have some benchmarks for this on some reasonably practical scenario.
In many common cases shift and masking can replace integer division (i.e. hash tables) and you avoid division altogether, and that probably has about the cost of converting an int to a float.
x and y are integers represented as floating point
> d = trunc(x/y); // floor works for unsigned
>
> // NOTE: if only want 'd' and it's being converted to an
> // integer then the truncate or floor operation is
> // free in the float to integer conversion.
Please show me how to portably truncate or floor a floating point value to an int in C for "free".
They're typically like a 3-cycle op, right? Obviously that's not zero, but as far as floating point ops get it's a cheap as it gets, like an add, mul, fma, that sorta thing.
Perhaps they meant implicit instead of free, since the comment also explains that `d` is an integer and the intent is to truncate, so the trunc() call is not even necessary when the assigning type is an int.
I'm curious that the latency of these is actually worse than the latency of floating operations. Yes, they are worse than many integer instructions, but they seem to be on basically the same order as the equivalent float operations?
Floating-point division requires 53 bits instead of 64 bits for integers. A lot of the increased latency comes from the wider datatypes.
My rule of thumb is that integer ops cost 1 cycle except divides, floats 3 but maybe divide is a bit more, then integer divides are like infinity at 20+ cycles that cannot be amortized by vectorization.
When you code simd it's best to assume the integer divide instruction does not exist. Just an impossibility, if you need to divide ints, rethink your whole program.
I would love to have some benchmarks for this on some reasonably practical scenario.
In many common cases shift and masking can replace integer division (i.e. hash tables) and you avoid division altogether, and that probably has about the cost of converting an int to a float.
x and y are integers represented as floating point
Please show me how to portably truncate or floor a floating point value to an int in C for "free".They're typically like a 3-cycle op, right? Obviously that's not zero, but as far as floating point ops get it's a cheap as it gets, like an add, mul, fma, that sorta thing.
I think you misread?
{within float-to-integer conversion} trunc or floor is free
that is, if you are converting, you already get it by default
Perhaps they meant implicit instead of free, since the comment also explains that `d` is an integer and the intent is to truncate, so the trunc() call is not even necessary when the assigning type is an int.