On Thu, Aug 25, 2011 at 7:38 AM, Alexander Terekhov <terekhov@web.de> wrote:
Gottlob Frege wrote:
What's the "independent reads, independent writes" problem? I've probably heard, seen, or mistakenly had a bug due to it once, but don't know it by name.
IRIW is an example that highlights remote write atomicity:
T1: X = 1; T2: Y = 1; T3: A = X; B = Y; T4: C = Y; D = X;
A == 1 && B == 0 && C == 1 && D == 0 is possible without remote write atomicity.
I would not be surprised by those resultant values.
Another example is
T1: X = 1; T2: if (X) Y = 1; T3: A = Y; B = X;
A == 1 && B == 0 is possible without remote write atomicity.
I'm comfortable with that as well.
SC is basically "no local reordering" plus remote write atomicity.
In 'modes' model, remote write atomicity is a separate mode apart from reordering.
regards, alexander.
Thanks Tony