fixed point was a mistake
-
@eniko is it weird that i've literally never seen fixed point numbers in code
@midnaw not really no, they're rarely used nowadays
-
How so @eniko?
Overly complicated? No performance gains? Odd graphical quirks /results?
@dacmot head hurt
-
@dacmot head hurt
-
fixed point was a mistake
@eniko oops, all ints
-
fixed point was a mistake
fixed point was in fact *not* a mistake
-
@midnaw not really no, they're rarely used nowadays
-
fixed point was in fact *not* a mistake
@eniko pretty important for, like, finance and shit
-
fixed point was in fact *not* a mistake
@eniko what a rollercoaster of emotions!
-
@eniko pretty important for, like, finance and shit
-
@ratsnakegames @eniko I wanted to write COBOL not FORTRAN but my brain missed a beat
-
@ratsnakegames @eniko I wanted to write COBOL not FORTRAN but my brain missed a beat
@gabrielesvelto @eniko we still do that sh*t in Java or .NET these days because financial regulators really frown upon money vanishing because of floating point errors
-
@gabrielesvelto @eniko we still do that sh*t in Java or .NET these days because financial regulators really frown upon money vanishing because of floating point errors
@ratsnakegames and I commend you for that! In a past life I worked for a high-frquency trading firm and their software did financial calculations using floating point numbers 🤷
-
fixed point was in fact *not* a mistake
@eniko jumpscare
-
when 64kb ram was all anyone would ever need
-
@ratsnakegames and I commend you for that! In a past life I worked for a high-frquency trading firm and their software did financial calculations using floating point numbers 🤷
@gabrielesvelto @ratsnakegames
Eh, as long as there's enough bits in the mantissa... -
fixed point was in fact *not* a mistake
@eniko following with interest.
-
fixed point was in fact *not* a mistake
I have completed the triangle rasterizer fixed point conversion
The benchmarks have all improved between 0 and 35%
Except for threaded random triangles with flat color. That metric has increased 106%. As in its twice as fast as before
I have no idea why but I'm fairly sure I've ruled out bugs in my benchmarking
I am very confused
-
fixed point was in fact *not* a mistake
@eniko fixed point is very fun
-
I have completed the triangle rasterizer fixed point conversion
The benchmarks have all improved between 0 and 35%
Except for threaded random triangles with flat color. That metric has increased 106%. As in its twice as fast as before
I have no idea why but I'm fairly sure I've ruled out bugs in my benchmarking
I am very confused
@eniko Hyperthreading? That has very different behavior depending on the kind of code being run. A single core might have twice the int resources to handle two threads of throughput but not twice the float resources (and then it depends on how bottlenecked by things like memory latency the benchmark is).
-
@eniko Hyperthreading? That has very different behavior depending on the kind of code being run. A single core might have twice the int resources to handle two threads of throughput but not twice the float resources (and then it depends on how bottlenecked by things like memory latency the benchmark is).
@lina I don't know? >_> I just split the screen between 4 worker threads that all draw each triangle to their quadrant