opt-diff: Support splitting to multiple output files

When reading the resulting files back with opt-viewer, they will be parsed in
parallel.

llvm-svn: 326126

llvm/tools/opt-viewer/opt-diff.py

@@ -36,13 +36,19 @@ if __name__ == '__main__':
         default=None,
         type=int,
         help='Max job count (defaults to %(default)s, the current CPU count)')
+    parser.add_argument(
+        '--max-size',
+        '-m',
+        default=100000,
+        type=int,
+        help='Maximum number of remarks stored in an output file')
     parser.add_argument(
         '--no-progress-indicator',
         '-n',
         action='store_true',
         default=False,
         help='Do not display any indicator of how many YAML files were read.')
-    parser.add_argument('--output', '-o', default='diff.opt.yaml')
+    parser.add_argument('--output', '-o', default='diff{}.opt.yaml')
     args = parser.parse_args()
 
     files1 = optrecord.find_opt_files(args.yaml_dir_or_file_1)
@@ -60,9 +66,10 @@ if __name__ == '__main__':
     for r in removed:
         r.Added = False
 
-    result = added | removed
+    result = list(added | removed)
     for r in result:
         r.recover_yaml_structure()
 
-    with open(args.output, 'w') as stream:
-        yaml.dump_all(result, stream)
+    for i in range(0, len(result), args.max_size):
+        with open(args.output.format(i / args.max_size), 'w') as stream:
+            yaml.dump_all(result[i:i + args.max_size], stream)