Always false float comparisons
tsbockman via Digitalmars-d
digitalmars-d at puremagic.com
Wed May 18 14:02:03 PDT 2016
On Wednesday, 18 May 2016 at 19:53:10 UTC, Era Scarecrow wrote:
> On Wednesday, 18 May 2016 at 19:36:59 UTC, tsbockman wrote:
>> I agree that intrinsics for this would be nice. I doubt that
>> any current D platform is actually computing the full 128 bit
>> result for every 64 bit multiply though - that would waste
>> both power and performance, for most programs.
>
> Except the 128 result is _already_ there for 0 cost (at least
> for x86 instructions that I'm aware).
Can you give me a source for this, or at least the name of the
relevant op code? (I'm new to x86 assembly.)
> There's bound to be enough cases (say pseudo random number
> generation, encryption, or numerical processing above 64bits)
> I'd like access to it supported by the language and not having
> to inject instructions using the asm command.
Of course it would be useful to have in the language; I wasn't
disputing that. I'd like to have as much support for 128-bit
integers in the language as possible. Among other things, this
would greatly simplify getting 128-bit floating-point working.
I'm just surprised that the CPU would really calculate the upper
64 bits of a multiply without being explicitly asked to.
More information about the Digitalmars-d
mailing list