Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

bug fix: hpctoolkit reader #116

Merged
merged 6 commits into from
Nov 14, 2023
Merged

bug fix: hpctoolkit reader #116

Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
3610726
fixed issue with HIT
movsesyanae Nov 3, 2023
8448561
forgot to add self variable
movsesyanae Nov 3, 2023
6b1e3a9
fixed bug in reading flex
movsesyanae Nov 3, 2023
612056f
cleanup
bhatele Nov 14, 2023
f76e2bb
updated style
movsesyanae Nov 3, 2023
e737400
flake8
bhatele Nov 14, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
62 changes: 39 additions & 23 deletions pipit/readers/hpctoolkit_reader.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -592,13 +592,13 @@ def __read_single_entry_point(self, entry_point_pointer: int) -> None:
# map context for this context
string_index = self.common_string_index_map[pretty_name_pointer]
context = {
"relation": -1,
"lexical_type": -1,
"function_index": -1,
"source_file_index": -1,
"source_file_line": -1,
"load_module_index": -1,
"load_module_offset": -1,
"relation": None,
"lexical_type": None,
"function_index": None,
"source_file_index": None,
"source_file_line": None,
"load_module_index": None,
"load_module_offset": None,
"string_index": string_index,
}
# context = {"string_index": string_index}
Expand Down Expand Up @@ -710,7 +710,7 @@ def __read_children_contexts(
sub_flex_2 = int.from_bytes(
flex[8:10], byteorder=self.byte_order, signed=self.signed
)
flex = flex[10:]
flex = flex[16:]
source_file_index = self.__get_source_file_index(sub_flex_1)
source_file_line = sub_flex_2

Expand Down Expand Up @@ -929,7 +929,6 @@ def __read_hit_section(self, section_pointer: int, section_size: int) -> None:
# hit pointer
hit_pointer = self.file.tell()

# print((self.file.tell() - section_pointer))
# Number of identifications in this tuple (u16)
num_tuples = int.from_bytes(
self.file.read(2), byteorder=self.byte_order, signed=self.signed
Expand All @@ -940,7 +939,7 @@ def __read_hit_section(self, section_pointer: int, section_size: int) -> None:

# Identifications for an application thread
# Read H.I.T.s
tuples_list = []
tuples_map = {}
for i in range(num_tuples):
# One of the values listed in the profile.db
# Identifier Names section. (u8)
Expand All @@ -964,8 +963,21 @@ def __read_hit_section(self, section_pointer: int, section_size: int) -> None:
self.file.read(8), byteorder=self.byte_order, signed=self.signed
)
identifier_name = self.meta_reader.get_identifier_name(kind)
tuples_list.append((identifier_name, physical_id))
self.hit_map[hit_pointer] = tuples_list
tuples_map[identifier_name] = physical_id

self.hit_map[hit_pointer] = self.__clean_hit(tuples_map)

def __clean_hit(self, tuples_map: dict) -> dict:
# add None for information not present
if "Node" not in tuples_map:
tuples_map["Node"] = None
if "RANK" not in tuples_map:
tuples_map["RANK"] = None
if "THREAD" not in tuples_map:
tuples_map["THREAD"] = None
if "CORE" not in tuples_map:
tuples_map["CORE"] = None
return tuples_map

def __read_common_header(self) -> None:
"""
Expand Down Expand Up @@ -1144,6 +1156,7 @@ def __read_trace_headers_section(
"Name": [],
"Thread": [],
"Process": [],
"Core": [],
"Host": [],
"Node": [],
"Source File Name": [],
Expand Down Expand Up @@ -1242,9 +1255,10 @@ def __read_single_trace_header(self, header_pointer: int) -> None:
else:
self.data["Event Type"].append("Leave")
self.data["Timestamp (ns)"].append(timestamp)
self.data["Process"].append(hit[1][1])
self.data["Thread"].append(hit[2][1])
self.data["Host"].append(hit[0][1])
self.data["Process"].append(hit["RANK"])
self.data["Thread"].append(hit["THREAD"])
self.data["Host"].append(hit["NODE"])
self.data["Core"].append(hit["CORE"])
self.data["Node"].append(last_node)
self.data["Source File Name"].append(context_information["file"])
self.data["Source File Line Number"].append(
Expand Down Expand Up @@ -1276,9 +1290,10 @@ def __read_single_trace_header(self, header_pointer: int) -> None:
else:
self.data["Event Type"].append("Enter")
self.data["Timestamp (ns)"].append(timestamp)
self.data["Process"].append(hit[1][1])
self.data["Thread"].append(hit[2][1])
self.data["Host"].append(hit[0][1])
self.data["Process"].append(hit["RANK"])
self.data["Thread"].append(hit["THREAD"])
self.data["Host"].append(hit["NODE"])
self.data["Core"].append(hit["CORE"])
self.data["Node"].append(entry_node)
self.data["Source File Name"].append(context_information["file"])
self.data["Source File Line Number"].append(
Expand Down Expand Up @@ -1311,9 +1326,10 @@ def __read_single_trace_header(self, header_pointer: int) -> None:
else:
self.data["Event Type"].append("Leave")
self.data["Timestamp (ns)"].append(timestamp)
self.data["Process"].append(hit[1][1])
self.data["Thread"].append(hit[2][1])
self.data["Host"].append(hit[0][1])
self.data["Process"].append(hit["RANK"])
self.data["Thread"].append(hit["THREAD"])
self.data["Host"].append(hit["NODE"])
self.data["Core"].append(hit["CORE"])
self.data["Node"].append(last_node)
self.data["Source File Name"].append(context_information["file"])
self.data["Source File Line Number"].append(context_information["line"])
Expand Down Expand Up @@ -1358,5 +1374,5 @@ def read(self) -> pipit.trace.Trace:

# cct is needed to create trace in hpctoolkit,
# so always return it as part of the trace
self.trace_df = trace_df
return pipit.trace.Trace(None, trace_df, self.meta_reader.cct)
self.trace_df = trace_df.dropna(axis=1, how="all")
return pipit.trace.Trace(None, self.trace_df, self.meta_reader.cct)
Loading