Changes between Version 31 and Version 32 of CreditNew

Timestamp:

Mar 26, 2010, 1:43:06 PM (14 years ago)

Author:

davea

Comment:

--

CreditNew

@@ -7 +7 @@
 For GPUs, it's given by a manufacturer-supplied formula.
 
-Other factors, such as the speed of a host's memory system,
-affect application performance.
+Application performance depends on other factors as well,
+such as the speed of the host's memory system.
 So a given job might take the same amount of CPU time
 on 1 GFLOPS and 10 GFLOPS hosts.
@@ -19 +19 @@
 
 Notes:
-
  * For our purposes, the peak FLOPS of a device
    uses single or double precision, whichever is higher.
@@ -26 +25 @@
 
 Some goals in designing a credit system:
-
  * Device neutrality: similar jobs should get similar credit
    regardless of what processor or GPU they run on.
-
  * Project neutrality: different projects should grant
    about the same amount of credit per host, averaged over all hosts.
-
  * Gaming-resistance: there should be a bound on the
    impact of faulty or malicious hosts.
@@ -79 +75 @@
 
 This system has several problems:
-
  * It doesn't address GPUs properly; projects using GPUs
    have to write custom code.
@@ -88 +83 @@
 
  * Completely automated - projects don't have to change code, settings, etc.
-
  * Device neutrality
-
  * Limited project neutrality: different projects should grant
    about the same amount of credit per host-hour, averaged over hosts.
@@ -171 +164 @@
    After that we use an exponentially-weighted average
    (with appropriate parameter for app version and host)
-
  * A given sample may be wildly off,
    and we can't let this mess up the average.
    Samples after the first are capped at 10 times the current average.
-
  * We keep track of the number of samples,
    and use an average only if its number of samples
@@ -198 +189 @@
  * If app.min_avg_pfc is defined then
 
- D = app.min_avg_pfc * wu.fpops_est
+   D = app.min_avg_pfc * wu.fpops_est
 
  * Otherwise
 
- D = wu.fpops_est
+   D = wu.fpops_est
 
 == Cross-version normalization ==
@@ -221 +212 @@
    and at least 2 versions are above sample threshold,
    X is their average (weighted by # samples).
-
  * If there are both, and at least 1 of each is above sample
    threshold, let X be the min of the averages.
@@ -333 +323 @@
 The algorithm:
 
+{{{
  pfc = peak FLOP count(J)
  approx = true;
@@ -356 +347 @@
          if Scale(H, V) is defined and (H,V) is not on scale probation
        F *= Scale(H, V)
+}}}
 
 == Claimed and granted credit ==
@@ -370 +362 @@
 Otherwise:
 
+{{{
  if app.min_avg_pfc is defined
    C = app.min_avg_pfc*wu.fpops_est
  else
    C = wu.fpops_est * 200/86400e9
+}}}
 
 == Cross-project version normalization ==
@@ -397 +391 @@
 Projects will export the following data:
 
- for each app version
+{{{
+for each app version
    app name
    platform name
@@ -403 +398 @@
    plan class
    scale factor
+}}}
 
 The BOINC server will collect these from several projects
 and will export the following:
 
- for each plan class
+{{{
+for each plan class
    average scale factor (weighted by RAC)
+}}}
 
 We'll provide a script that identifies app versions
@@ -529 +527 @@
  R(J, H) = wu.fpops_est * ET^mean^(H, V)
 
-
 == Implementation ==