[llvm] r293261 - [opt-viewer] Put critical items in parallel

Adam Nemet via llvm-commits llvm-commits at lists.llvm.org
Thu Jan 26 22:38:32 PST 2017


Author: anemet
Date: Fri Jan 27 00:38:31 2017
New Revision: 293261

URL: http://llvm.org/viewvc/llvm-project?rev=293261&view=rev
Log:
[opt-viewer] Put critical items in parallel

Summary:
Put opt-viewer critical items in parallel

Patch by Brian Cain!

Requires features from Python 2.7

**Performance**
Below are performance results across various configurations. These were taken on an i5-5200U (dual core + HT). They were taken with a small subset of the YAML output of building Python 3.6.0b3 with LTO+PGO. 60 YAML files.

"multiprocessing" is the current submission contents. "baseline" is as of 544f14c6b2a07a94168df31833dba9dc35fd8289 (I think this is aka r287505).

"ImportError" vs "class<...CLoader>" below are just confirming the expected configuration (with/without CLoader).

The below was measured on AMD A8-5500B (4 cores) with 224 input YAML files, showing a ~1.75x speed increase over the baseline with libYAML.  I suspect it would scale well on high-end servers.

```
**************************************** MULTIPROCESSING ****************************************
PyYAML:
        Traceback (most recent call last):
          File "<string>", line 1, in <module>
        ImportError: cannot import name CLoader
        Python 2.7.10
489.42user 5.53system 2:38.03elapsed 313%CPU (0avgtext+0avgdata 400308maxresident)k
0inputs+31392outputs (0major+473540minor)pagefaults 0swaps

PyYAML+libYAML:
        <class 'yaml.cyaml.CLoader'>
        Python 2.7.10
78.69user 5.45system 0:32.63elapsed 257%CPU (0avgtext+0avgdata 398560maxresident)k
0inputs+31392outputs (0major+542022minor)pagefaults 0swaps

PyPy/PyYAML:
        Traceback (most recent call last):
          File "<builtin>/app_main.py", line 75, in run_toplevel
          File "<builtin>/app_main.py", line 601, in run_it
          File "<string>", line 1, in <module>
        ImportError: cannot import name 'CLoader'
        Python 2.7.9 (2.6.0+dfsg-3, Jul 04 2015, 05:43:17)
        [PyPy 2.6.0 with GCC 4.9.3]
154.27user 8.12system 0:53.83elapsed 301%CPU (0avgtext+0avgdata 627960maxresident)k
808inputs+30376outputs (0major+727994minor)pagefaults 0swaps
**************************************** BASELINE        ****************************************
PyYAML:
        Traceback (most recent call last):
          File "<string>", line 1, in <module>
        ImportError: cannot import name CLoader
        Python 2.7.10
        358.08user 4.05system 6:08.37elapsed 98%CPU (0avgtext+0avgdata 315004maxresident)k
0inputs+31392outputs (0major+85252minor)pagefaults 0swaps

PyYAML+libYAML:
        <class 'yaml.cyaml.CLoader'>
        Python 2.7.10
50.32user 3.30system 0:56.59elapsed 94%CPU (0avgtext+0avgdata 307296maxresident)k
0inputs+31392outputs (0major+79335minor)pagefaults 0swaps

PyPy/PyYAML:
        Traceback (most recent call last):
          File "<builtin>/app_main.py", line 75, in run_toplevel
          File "<builtin>/app_main.py", line 601, in run_it
          File "<string>", line 1, in <module>
        ImportError: cannot import name 'CLoader'
        Python 2.7.9 (2.6.0+dfsg-3, Jul 04 2015, 05:43:17)
        [PyPy 2.6.0 with GCC 4.9.3]
72.94user 5.18system 1:23.41elapsed 93%CPU (0avgtext+0avgdata 455312maxresident)k
0inputs+30392outputs (0major+110280minor)pagefaults 0swaps

```

Reviewers: fhahn, anemet

Reviewed By: anemet

Subscribers: llvm-commits, mehdi_amini

Differential Revision: https://reviews.llvm.org/D26967

Modified:
    llvm/trunk/utils/opt-viewer/opt-viewer.py

Modified: llvm/trunk/utils/opt-viewer/opt-viewer.py
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/utils/opt-viewer/opt-viewer.py?rev=293261&r1=293260&r2=293261&view=diff
==============================================================================
--- llvm/trunk/utils/opt-viewer/opt-viewer.py (original)
+++ llvm/trunk/utils/opt-viewer/opt-viewer.py Fri Jan 27 00:38:31 2017
@@ -15,6 +15,13 @@ try:
     from yaml import CLoader as Loader
 except ImportError:
     from yaml import Loader
+
+import functools
+from collections import defaultdict
+import itertools
+from multiprocessing import Pool
+from multiprocessing import Lock, cpu_count
+import errno
 import argparse
 import os.path
 import re
@@ -24,18 +31,14 @@ from pygments import highlight
 from pygments.lexers.c_cpp import CppLexer
 from pygments.formatters import HtmlFormatter
 
-parser = argparse.ArgumentParser(description=desc)
-parser.add_argument('yaml_files', nargs='+')
-parser.add_argument('output_dir')
-parser.add_argument('-source-dir', '-s', default='', help='set source directory')
-args = parser.parse_args()
-
 p = subprocess.Popen(['c++filt', '-n'], stdin=subprocess.PIPE, stdout=subprocess.PIPE)
+p_lock = Lock()
 
 
 def demangle(name):
-    p.stdin.write(name + '\n')
-    return p.stdout.readline().rstrip()
+    with p_lock:
+        p.stdin.write(name + '\n')
+        return p.stdout.readline().rstrip()
 
 
 class Remark(yaml.YAMLObject):
@@ -156,16 +159,16 @@ class Missed(Remark):
 
 
 class SourceFileRenderer:
-    def __init__(self, filename):
+    def __init__(self, source_dir, output_dir, filename):
         existing_filename = None
         if os.path.exists(filename):
             existing_filename = filename
         else:
-            fn = os.path.join(args.source_dir, filename)
+            fn = os.path.join(source_dir, filename)
             if os.path.exists(fn):
                 existing_filename = fn
 
-        self.stream = open(os.path.join(args.output_dir, SourceFileRenderer.html_file_name(filename)), 'w')
+        self.stream = open(os.path.join(output_dir, SourceFileRenderer.html_file_name(filename)), 'w')
         if existing_filename:
             self.source_stream = open(existing_filename)
         else:
@@ -243,8 +246,8 @@ class SourceFileRenderer:
 
 
 class IndexRenderer:
-    def __init__(self):
-        self.stream = open(os.path.join(args.output_dir, 'index.html'), 'w')
+    def __init__(self, output_dir):
+        self.stream = open(os.path.join(output_dir, 'index.html'), 'w')
 
     def render_entry(self, r):
         print('''
@@ -278,41 +281,123 @@ class IndexRenderer:
 </html>''', file=self.stream)
 
 
-all_remarks = dict()
-file_remarks = dict()
+def get_remarks(input_file):
+    max_hotness = 0
+    all_remarks = dict()
+    file_remarks = defaultdict(functools.partial(defaultdict, list))
+
+    with open(input_file) as f:
+        docs = yaml.load_all(f, Loader=Loader)
+
+        for remark in docs:
+            # Avoid remarks withoug debug location or if they are duplicated
+            if not hasattr(remark, 'DebugLoc') or remark.key in all_remarks:
+                continue
+            all_remarks[remark.key] = remark
+
+            file_remarks[remark.File][remark.Line].append(remark)
+
+            max_hotness = max(max_hotness, remark.Hotness)
+
+    return max_hotness, all_remarks, file_remarks
+
+
+def _render_file(source_dir, output_dir, entry):
+    filename, remarks = entry
+    SourceFileRenderer(source_dir, output_dir, filename).render(remarks)
+
+
+def gather_results(pool, filenames):
+    all_remarks = dict()
+    remarks = pool.map(get_remarks, filenames)
 
-for input_file in args.yaml_files:
-    f = open(input_file)
-    docs = yaml.load_all(f, Loader=Loader)
-    for remark in docs:
-        # Avoid remarks withoug debug location or if they are duplicated
-        if not hasattr(remark, 'DebugLoc') or remark.key in all_remarks:
-            continue
-        all_remarks[remark.key] = remark
-
-        file_remarks.setdefault(remark.File, dict()).setdefault(remark.Line, []).append(remark)
-
-        Remark.max_hotness = max(Remark.max_hotness, remark.Hotness)
-
-# Set up a map between function names and their source location for function where inlining happened
-for remark in all_remarks.itervalues():
-    if type(remark) == Passed and remark.Pass == "inline" and remark.Name == "Inlined":
-        for arg in remark.Args:
-            caller = arg.get('Caller')
-            if caller:
+    def merge_dicts(dicts):
+        ''' Takes an iterable of dicts and merges them into
+            a single dict.  Nested dicts are merged as well.
+        >>> merge_dicts([ {'a': [3], }, {'a': [4], }, {'b': [6] }])
+        {'a': [3,4,], 'b': [6]}
+        >>> merge_dicts([ {'a': {'q': [6,3], 'f': [30],}, }, {'a': {'f': [4,10]}, }, {'b': [6] }])
+        {'a': [{'q': [6,3]}, {'f': [4,10,30]}], 'b': [6]}
+
+        '''
+        merged = defaultdict(functools.partial(defaultdict, list))
+
+        for k, v in itertools.chain(*[d.iteritems() for d in dicts]):
+            for k_, v_ in v.items():
+                merged[k][k_] += v_
+
+        return merged
+
+    file_remark_dicts = [entry[2] for entry in remarks]
+    # merge the list of remarks at each line of each file
+    file_remarks = merge_dicts(file_remark_dicts)
+
+    # merge individual 'all_remark' results:
+    for _, all_rem, _ in remarks:
+        all_remarks.update(all_rem)
+
+    Remark.max_hotness = max(entry[0] for entry in remarks)
+
+    return all_remarks, file_remarks
+
+
+def map_remarks(all_remarks):
+    # Set up a map between function names and their source location for
+    # function where inlining happened
+    for remark in all_remarks.itervalues():
+        if isinstance(remark, Passed) and remark.Pass == "inline" and remark.Name == "Inlined":
+            for arg in remark.Args:
+                caller = arg.get('Caller')
+                if caller:
                     Remark.caller_loc[caller] = arg['DebugLoc']
 
-if Remark.should_display_hotness():
-    sorted_remarks = sorted(all_remarks.itervalues(), key=lambda r: r.Hotness, reverse=True)
-else:
-    sorted_remarks = sorted(all_remarks.itervalues(), key=lambda r: (r.File, r.Line, r.Column))
 
-if not os.path.exists(args.output_dir):
-    os.mkdir(args.output_dir)
+def generate_report(pool, all_remarks, file_remarks, source_dir, output_dir):
+    try:
+        os.makedirs(output_dir)
+    except OSError as e:
+        if e.errno == errno.EEXIST and os.path.isdir(output_dir):
+            pass
+        else:
+            raise
+
+    _render_file_bound = functools.partial(_render_file, source_dir, output_dir)
+    pool.map(_render_file_bound, file_remarks.items())
+
+    if Remark.should_display_hotness():
+        sorted_remarks = sorted(all_remarks.itervalues(), key=lambda r: r.Hotness, reverse=True)
+    else:
+        sorted_remarks = sorted(all_remarks.itervalues(), key=lambda r: (r.File, r.Line, r.Column))
+    IndexRenderer(args.output_dir).render(sorted_remarks)
+
+    shutil.copy(os.path.join(os.path.dirname(os.path.realpath(__file__)),
+            "style.css"), output_dir)
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser(description=desc)
+    parser.add_argument('yaml_files', nargs='+')
+    parser.add_argument('output_dir')
+    parser.add_argument(
+        '--jobs',
+        '-j',
+        default=cpu_count(),
+        type=int,
+        help='Max job count (defaults to current CPU count)')
+    parser.add_argument(
+        '-source-dir',
+        '-s',
+        default='',
+        help='set source directory')
+    args = parser.parse_args()
+
+    if len(args.yaml_files) == 0:
+        parser.print_help()
+        sys.exit(1)
 
-for (filename, remarks) in file_remarks.iteritems():
-    SourceFileRenderer(filename).render(remarks)
+    pool = Pool(processes=args.jobs)
+    all_remarks, file_remarks = gather_results(pool, args.yaml_files)
 
-IndexRenderer().render(sorted_remarks)
+    map_remarks(all_remarks)
 
-shutil.copy(os.path.join(os.path.dirname(os.path.realpath(__file__)), "style.css"), args.output_dir)
+    generate_report(pool, all_remarks, file_remarks, args.source_dir, args.output_dir)




More information about the llvm-commits mailing list