[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [glob2-devel] Nicowar and desync
From: |
Cyrille Dunant |
Subject: |
Re: [glob2-devel] Nicowar and desync |
Date: |
Tue, 18 Jul 2006 18:59:13 +0200 |
User-agent: |
KMail/1.9.3 |
> It seems it does. Don't forget floating point format does not constrain
> handling of least significant bits, so different CPU (even both x86) can
> give different results.
worst : even the same CPU can.
> We had this bug in glob2 earlier in the same type
> of computation Nicowar is currently doing.
>
> I agree for the CPU.
>
> Steph
CU
-- CFD
- [glob2-devel] Nicowar and desync, Stéphane Magnenat, 2006/07/16
- Re: [glob2-devel] Nicowar and desync, Bradley Arsenault, 2006/07/16
- Re: [glob2-devel] Nicowar and desync, Stéphane Magnenat, 2006/07/18
- Re: [glob2-devel] Nicowar and desync,
Cyrille Dunant <=
- Re: [glob2-devel] Nicowar and desync, Bradley Arsenault, 2006/07/18
- Re: [glob2-devel] Nicowar and desync, Cyrille Dunant, 2006/07/18
- Re: [glob2-devel] Nicowar and desync, Bradley Arsenault, 2006/07/18
- Re: [glob2-devel] Nicowar and desync, Bradley Arsenault, 2006/07/18
- Re: [glob2-devel] Nicowar and desync, Cyrille Dunant, 2006/07/18
- Re: [glob2-devel] Nicowar and desync, Bradley Arsenault, 2006/07/19
- Re: [glob2-devel] Nicowar and desync, Cyrille Dunant, 2006/07/19
- Re: [glob2-devel] Nicowar and desync, Bradley Arsenault, 2006/07/19
- Re: [glob2-devel] Nicowar and desync, Cyrille Dunant, 2006/07/18