20190601, 20:33  #34 
Oct 2007
London, UK
2^{2}·5^{2}·13 Posts 
I thought the world of finance used binary coded decimal to avoid such rounding errors.

20190601, 20:43  #35  
Oct 2008
n00bville
5^{2}·29 Posts 
Quote:
Quake and gaming and stuff ... ;) In all seriousness, every time you use a float or double in C++ you're using the fpu unit. 

20190601, 20:47  #36 
Undefined
"The unspeakable one"
Jun 2006
My evil lair
2^{2}·3·7·67 Posts 
The FPU also natively supports BCD formats. But "no one" ever used it, it was too cumbersome to deal with. And it doesn't help with a table mortgage payment computation for 30 years with monthly rests at 4.56% p/a.

20190601, 21:24  #37 
Oct 2008
n00bville
5^{2}·29 Posts 

20190601, 21:27  #38 
Undefined
"The unspeakable one"
Jun 2006
My evil lair
2^{2}·3·7·67 Posts 

20190601, 23:31  #39 
Tribal Bullet
Oct 2004
2^{3}×3^{2}×7^{2} Posts 
Double precision frees you from having to do numerical analysis every time you implement an algorithm in floating point; William Kahan has a series of papers on how various computations will silently give wrong results when not given enough precision or shortcuts in how floating point is implemented (i.e. flush to zero instead of denormals which are expensive in hardware).
Likewise linear algebra on illconditioned systems only gets good answers if you throw more digits at it; applications such as Bailey's Inverse Symbolic Calculator need higher precision floating point IIRC. Linear algebra is a subroutine inside lots of other algorithms and you don't want it to silently give you garbage. Shewchuck's work in robust automatic triangulation is hugely important because it relies on increasing precision when problems get hard, including switching to doubledouble arithmetic if necessary. This is another subroutine deep inside other stuff (i.e. finite element analysis) that has to work or all the layers above it will break. Of course around here the killer app for double precision floating point is FFTs :) 
20190602, 16:01  #40 
Oct 2008
n00bville
5^{2}×29 Posts 

20190602, 16:49  #41  
"Curtis"
Feb 2005
Riverside, CA
1093_{16} Posts 
Quote:
Mortgage rates in USA are around 4.0% for classic 30yearfixedrate notes. At those rates, there are many many places in the US where home prices are (1) not very high, and (2) low enough that a 20% down payment leaves a mortgage cheaper than rent. There remain places where buying homes (with a mortgage) simply to rent out is profitable; while home prices may fall, rent is much less likely to do so and will fall less if it does. If homes as investment are profitable, surely one can find more value in living in such a home. Last fiddled with by VBCurtis on 20190602 at 19:36 Reason: spellcheck: primes > prices, ii > i 

20190602, 19:04  #42  
∂^{2}ω=0
Sep 2002
República de California
2^{3}×1,427 Posts 
Quote:


20190603, 01:05  #43  
Oct 2007
London, UK
514_{16} Posts 
This sounds suspiciously like an argument for quadp in modern processors:
Quote:
This seems like a fairly sensible way to include quad precision support without adding a ton of extra silicon devoted specifically to it. And hey, if they wanted to include all the same FMA and vectorisation support for quads too that'd be excellent. Even if quad FLOPS were 1/4 (or lower) than double FLOPS, that's still perfectly acceptable. The registers could still be maintained at 64 bits wide if the 128 bit floats were simply given and returned as an upper and lower half. It would just mean that the CPU instruction would need to be given 6 arguments instead of 3 for a mul. 

20190603, 01:10  #44  
Oct 2007
London, UK
2^{2}×5^{2}×13 Posts 
Quote:
"Buy a house for the price of a VCR" 

Thread Tools  
Similar Threads  
Thread  Thread Starter  Forum  Replies  Last Post 
Ryzen help  Prime95  Hardware  9  20180514 04:06 
Ryzen 2 efficiency improvements  M344587487  Hardware  3  20180425 15:23 
Help to choose components for a Ryzen rig  robert44444uk  Hardware  50  20180407 20:41 
29.2 benchmark help #2 (Ryzen only)  Prime95  Software  10  20170508 13:24 
AMD Ryzen is risin' up.  jasong  Hardware  11  20170302 19:56 