Fix usage of analyze_brprob.py script.

2018-01-19  Martin Liska  <mliska@suse.cz>

	* analyze_brprob.py: Support new format that can be easily
	parsed. Add new column to report.
2018-01-19  Martin Liska  <mliska@suse.cz>

	* predict.c (dump_prediction): Add new format for
	analyze_brprob.py script which is enabled with -details
	suboption.
	* profile-count.h (precise_p): New function.

From-SVN: r256886

2 files changed, 77 insertions, 31 deletions

diff --git a/contrib/ChangeLog b/contrib/ChangeLog
index b175060..a88e2f0 100644
--- a/contrib/ChangeLog
+++ b/contrib/ChangeLog
@@ -1,3 +1,8 @@
+2018-01-19  Martin Liska  <mliska@suse.cz>
+
+	* analyze_brprob.py: Support new format that can be easily
+	parsed. Add new column to report.
+
 2018-01-03  Jakub Jelinek  <jakub@redhat.com>
 
 	* update-copyright.py: Skip pdt-5.f03 in gfortran.dg subdir.
diff --git a/contrib/analyze_brprob.py b/contrib/analyze_brprob.py
index e03d1da..de5f474 100755
--- a/contrib/analyze_brprob.py
+++ b/contrib/analyze_brprob.py
@@ -71,6 +71,7 @@ from math import *
 
 counter_aggregates = set(['combined', 'first match', 'DS theory',
     'no prediction'])
+hot_threshold = 10
 
 def percentage(a, b):
     return 100.0 * a / b
@@ -131,47 +132,87 @@ class PredictDefFile:
             with open(self.path, 'w+') as f:
                 for l in modified_lines:
                     f.write(l + '\n')
+class Heuristics:
+    def __init__(self, count, hits, fits):
+        self.count = count
+        self.hits = hits
+        self.fits = fits
 
 class Summary:
     def __init__(self, name):
         self.name = name
-        self.branches = 0
-        self.successfull_branches = 0
-        self.count = 0
-        self.hits = 0
-        self.fits = 0
+        self.edges= []
+
+    def branches(self):
+        return len(self.edges)
+
+    def hits(self):
+        return sum([x.hits for x in self.edges])
+
+    def fits(self):
+        return sum([x.fits for x in self.edges])
+
+    def count(self):
+        return sum([x.count for x in self.edges])
+
+    def successfull_branches(self):
+        return len([x for x in self.edges if 2 * x.hits >= x.count])
 
     def get_hitrate(self):
-        return 100.0 * self.hits / self.count
+        return 100.0 * self.hits() / self.count()
 
     def get_branch_hitrate(self):
-        return 100.0 * self.successfull_branches / self.branches
+        return 100.0 * self.successfull_branches() / self.branches()
 
     def count_formatted(self):
-        v = self.count
+        v = self.count()
         for unit in ['', 'k', 'M', 'G', 'T', 'P', 'E', 'Z', 'Y']:
             if v < 1000:
                 return "%3.2f%s" % (v, unit)
             v /= 1000.0
         return "%.1f%s" % (v, 'Y')
 
+    def count(self):
+        return sum([x.count for x in self.edges])
+
     def print(self, branches_max, count_max, predict_def):
+        # filter out most hot edges (if requested)
+        self.edges = sorted(self.edges, reverse = True, key = lambda x: x.count)
+        if args.coverage_threshold != None:
+            threshold = args.coverage_threshold * self.count() / 100
+            edges = [x for x in self.edges if x.count < threshold]
+            if len(edges) != 0:
+                self.edges = edges
+
         predicted_as = None
         if predict_def != None and self.name in predict_def.predictors:
             predicted_as = predict_def.predictors[self.name]
 
         print('%-40s %8i %5.1f%% %11.2f%% %7.2f%% / %6.2f%% %14i %8s %5.1f%%' %
-            (self.name, self.branches,
-                percentage(self.branches, branches_max),
+            (self.name, self.branches(),
+                percentage(self.branches(), branches_max),
                 self.get_branch_hitrate(),
                 self.get_hitrate(),
-                percentage(self.fits, self.count),
-                self.count, self.count_formatted(),
-                percentage(self.count, count_max)), end = '')
+                percentage(self.fits(), self.count()),
+                self.count(), self.count_formatted(),
+                percentage(self.count(), count_max)), end = '')
 
         if predicted_as != None:
             print('%12i%% %5.1f%%' % (predicted_as,
                 self.get_hitrate() - predicted_as), end = '')
+        else:
+            print(' ' * 20, end = '')
+
+        # print details about the most important edges
+        if args.coverage_threshold == None:
+            edges = [x for x in self.edges[:100] if x.count * hot_threshold > self.count()]
+            if args.verbose:
+                for c in edges:
+                    r = 100.0 * c.count / self.count()
+                    print(' %.0f%%:%d' % (r, c.count), end = '')
+            elif len(edges) > 0:
+                print(' %0.0f%%:%d' % (100.0 * sum([x.count for x in edges]) / self.count(), len(edges)), end = '')
+
         print()
 
 class Profile:
@@ -185,33 +226,29 @@ class Profile:
             self.heuristics[name] = Summary(name)
 
         s = self.heuristics[name]
-        s.branches += 1
 
-        s.count += count
         if prediction < 50:
             hits = count - hits
         remaining = count - hits
-        if hits >= remaining:
-            s.successfull_branches += 1
+        fits = max(hits, remaining)
 
-        s.hits += hits
-        s.fits += max(hits, remaining)
+        s.edges.append(Heuristics(count, hits, fits))
 
     def add_loop_niter(self, niter):
         if niter > 0:
             self.niter_vector.append(niter)
 
     def branches_max(self):
-        return max([v.branches for k, v in self.heuristics.items()])
+        return max([v.branches() for k, v in self.heuristics.items()])
 
     def count_max(self):
-        return max([v.count for k, v in self.heuristics.items()])
+        return max([v.count() for k, v in self.heuristics.items()])
 
     def print_group(self, sorting, group_name, heuristics, predict_def):
         count_max = self.count_max()
         branches_max = self.branches_max()
 
-        sorter = lambda x: x.branches
+        sorter = lambda x: x.branches()
         if sorting == 'branch-hitrate':
             sorter = lambda x: x.get_branch_hitrate()
         elif sorting == 'hitrate':
@@ -221,10 +258,10 @@ class Profile:
         elif sorting == 'name':
             sorter = lambda x: x.name.lower()
 
-        print('%-40s %8s %6s %12s %18s %14s %8s %6s %12s %6s' %
+        print('%-40s %8s %6s %12s %18s %14s %8s %6s %12s %6s %s' %
             ('HEURISTICS', 'BRANCHES', '(REL)',
             'BR. HITRATE', 'HITRATE', 'COVERAGE', 'COVERAGE', '(REL)',
-            'predict.def', '(REL)'))
+            'predict.def', '(REL)', 'HOT branches (>%d%%)' % hot_threshold))
         for h in sorted(heuristics, key = sorter):
             h.print(branches_max, count_max, predict_def)
 
@@ -266,19 +303,23 @@ parser.add_argument('-s', '--sorting', dest = 'sorting',
 parser.add_argument('-d', '--def-file', help = 'path to predict.def')
 parser.add_argument('-w', '--write-def-file', action = 'store_true',
     help = 'Modify predict.def file in order to set new numbers')
+parser.add_argument('-c', '--coverage-threshold', type = int,
+    help = 'Ignore edges that have percentage coverage >= coverage-threshold')
+parser.add_argument('-v', '--verbose', action = 'store_true', help = 'Print verbose informations')
 
 args = parser.parse_args()
 
 profile = Profile(args.dump_file)
-r = re.compile('  (.*) heuristics( of edge [0-9]*->[0-9]*)?( \\(.*\\))?: (.*)%.*exec ([0-9]*) hit ([0-9]*)')
 loop_niter_str = ';;  profile-based iteration count: '
+
 for l in open(args.dump_file):
-    m = r.match(l)
-    if m != None and m.group(3) == None:
-        name = m.group(1)
-        prediction = float(m.group(4))
-        count = int(m.group(5))
-        hits = int(m.group(6))
+    if l.startswith(';;heuristics;'):
+        parts = l.strip().split(';')
+        assert len(parts) == 8
+        name = parts[3]
+        prediction = float(parts[6])
+        count = int(parts[4])
+        hits = int(parts[5])
 
         profile.add(name, prediction, count, hits)
     elif l.startswith(loop_niter_str):