Birbla

Join the discussion

Write your take first — we'll ask for email only when you're ready to publish.

Sign in
  • Hacker News
  • Agner's table[1] for Intel IceLake/TigerLake shows FDIV to have higher latency, but slightly better throughput.

    For latency:

    - DIV/IDIV r32: 12 cycles

    - DIV/IDIV r64: 15 cycles

    - FDIV: 14–16 cycles

    Throughput:

    - DIV/IDIV r32: 6 cycles

    - DIV/IDIV r64: 10 cycles

    - FDIV: 4–5 cycles

    I didn't check for a more recent CPU.

    [1] https://www.agner.org/optimize/instruction_tables.pdf page 366 & 369

    by Genbox
  • DIVSD latency 13–14 cycles, reciprocal throughput 4 cycles

    Use this instead of x87’s FDIV

    by brewmarche
  • Why is floating point faster?
    by amelius
  • It’s a more important use case, so CPU vendors throw more resources at it.
    by tverbeure
  • As the article says, some processors only have an instruction that produces 1 bit of quotient per cycle. This gives a variable time for integer division which can be longer than the time it takes to do a floating point operation.

    This sort of limitation has a long pedigree and is surprisingly common. For instance, the CDC 6000 series had no general purpose integer arithmetic unit. The DEC Alpha had no integer divide and the standard RISC-5 spec also omits it. Same for low-end ARM chips.

    by ted_dunning
  • 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".
    by RossBencina
  • 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.
    by ranger_danger
  • 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

    by NooneAtAll3
  • 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.
    by mtklein
  • 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?
    by taeric
  • Floating-point division requires 53 bits instead of 64 bits for integers. A lot of the increased latency comes from the wider datatypes.
    by jcranmer
  • 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.

    by mtklein
  • > Typically very long latency and poor throughput.

    Recently I have been investigating what operations modern compilers for modern CPUs can optimize. I fond, that for floating-point types there are vector division instructions (which compilers use if they can vectorize), but for integers there are still only scalar instructions. It's unclear for me why no vector instructions exist for such basic arithmetic.

    by Panzerschrek
  • 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.

    by juancn
  • > Integer division q=(x/y) and remainder (of Euclidean division) r=(x%y) hardware operations are very sad on current hardware. Typically very long latency and poor throughput. In contrast floating-point division is pretty happy: shorter latency, higher throughput and often more execution units to perform the operation.

    oh wow I missed when this started to happen

    by BiraIgnacio
  • IT started in the 60s with the CDC6400, actually. It's no wonder you missed it.
    by ted_dunning
  • There is a paper by Vincent Lefèvre that indeed proves that floating point division and a floor implement the euclidean division, with a careful analysis of when. [1] A corollary of the main theorem in the paper is that, with round to nearest, if x and y fit in 53 bits unsigned then it works out.

    [1] https://hal.univ-lorraine.fr/inria-00070403v1

    by sjrd