[SYCL][XPTI] Performance improvements for performance oriented toolchains #19953
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -95,7 +95,7 @@ void GlobalHandler::TraceEventXPTI(const char *Message) { | |
| xpti::framework::tracepoint_scope_t TP( | ||
| CodeLocation.fileName(), CodeLocation.functionName(), | ||
| CodeLocation.lineNumber(), CodeLocation.columnNumber(), nullptr); | ||
| // Notify the subscriber with a diagnostic message when an exception occurs. | ||
| TP.stream(detail::GSYCLStreamID) | ||
| .traceType(xpti::trace_point_type_t::diagnostics) | ||
| .parentEvent(GSYCLCallEvent) | ||
|
|
||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -171,6 +171,8 @@ event queue_impl::memset(void *Ptr, int Value, size_t Count, | |
| .traceType(xpti::trace_point_type_t::node_create) | ||
| .parentEvent(detail::GSYCLGraphEvent); | ||
|
|
||
| // This information is necessary for memset, so we will not guard it by debug | ||
| // stream check. | ||
| TP.addMetadata([&](auto TEvent) { | ||
| xpti::addMetadata(TEvent, "sycl_device", | ||
| reinterpret_cast<size_t>(MDevice.getHandleRef())); | ||
|
|
@@ -223,6 +225,7 @@ event queue_impl::memcpy(void *Dest, const void *Src, size_t Count, | |
| .traceType(xpti::trace_point_type_t::node_create) | ||
| .parentEvent(GSYCLGraphEvent); | ||
| const char *UserData = "memory_transfer_node::memcpy"; | ||
| // We will include this metadata information as it is required for memcpy. | ||
| TP.addMetadata([&](auto TEvent) { | ||
| xpti::addMetadata(TEvent, "sycl_device", | ||
| reinterpret_cast<size_t>(MDevice.getHandleRef())); | ||
|
|
@@ -524,33 +527,32 @@ void *queue_impl::instrumentationProlog(const detail::code_location &CodeLoc, | |
| if (!xptiCheckTraceEnabled(StreamID, NotificationTraceType)) | ||
| return TraceEvent; | ||
|
|
||
| xpti_tracepoint_t *Event; | ||
| // We try to create a unique string for the wait() call by combining it with | ||
| // the queue address | ||
| xpti::utils::StringHelper NG; | ||
| Name = NG.nameWithAddress<queue_impl *>("queue.wait", this); | ||
|
|
||
| bool HasSourceInfo = CodeLoc.fileName() != nullptr; | ||
| // wait() calls could be at different user-code locations; We create a new | ||
| // event based on the code location info and if this has been seen before, a | ||
| // previously created event will be returned. | ||
| if (HasSourceInfo) { | ||
| Event = xptiCreateTracepoint(CodeLoc.functionName(), CodeLoc.fileName(), | ||
| CodeLoc.lineNumber(), CodeLoc.columnNumber(), | ||
| (void *)this); | ||
| } else { | ||
| Event = xptiCreateTracepoint(Name.c_str(), nullptr, 0, 0, (void *)this); | ||
| } | ||
|
|
||
| IId = xptiGetUniqueId(); | ||
| auto WaitEvent = Event->event_ref(); | ||
| // We will allow the device type to be set | ||
| xpti::addMetadata(WaitEvent, "sycl_device_type", queueDeviceToString(this)); | ||
| // We limit the amount of metadata that is added to streams if the | ||
| // "sycl.debug" stream is not subscribed to. This improves the performance | ||
| // when this data is not required by the tool or the collector. | ||
| if (xptiCheckTraceEnabled(detail::GSYCLDebugStreamID)) { | ||
| if (HasSourceInfo) { | ||
| xpti::addMetadata(WaitEvent, "sym_function_name", CodeLoc.functionName()); | ||
| xpti::addMetadata(WaitEvent, "sym_source_file_name", CodeLoc.fileName()); | ||
|
|
@@ -560,11 +562,11 @@ void *queue_impl::instrumentationProlog(const detail::code_location &CodeLoc, | |
| WaitEvent, "sym_column_no", | ||
| static_cast<xpti::object_id_t>((CodeLoc.columnNumber()))); | ||
| } | ||
| } | ||
| xptiNotifySubscribers(StreamID, xpti::trace_wait_begin, nullptr, WaitEvent, | ||
| IId, static_cast<const void *>(Name.c_str())); | ||
| TraceEvent = (void *)WaitEvent; | ||
|
|
||
| return TraceEvent; | ||
| } | ||
|
|
||
|
|
@@ -587,13 +589,11 @@ void queue_impl::instrumentationEpilog(void *TelemetryEvent, std::string &Name, | |
| void queue_impl::wait(const detail::code_location &CodeLoc) { | ||
| (void)CodeLoc; | ||
| #ifdef XPTI_ENABLE_INSTRUMENTATION | ||
| // xptiCheckTraceEnabled() is being performed in instrumentationProlog(). | ||
| void *TelemetryEvent = nullptr; | ||
| uint64_t IId; | ||
| std::string Name; | ||
| TelemetryEvent = instrumentationProlog(CodeLoc, Name, GSYCLStreamID, IId); | ||
| #endif | ||
|
|
||
| if (!MGraph.expired()) { | ||
|
|
@@ -673,51 +673,49 @@ void queue_impl::wait(const detail::code_location &CodeLoc) { | |
| } | ||
|
|
||
| #ifdef XPTI_ENABLE_INSTRUMENTATION | ||
| // There is an early return in instrumentationEpilog() if no subscribers are | ||
| // subscribing to queue.wait(). | ||
| instrumentationEpilog(TelemetryEvent, Name, GSYCLStreamID, IId); | ||
| #endif | ||
| } | ||
|
|
||
| void queue_impl::constructorNotification() { | ||
| #if XPTI_ENABLE_INSTRUMENTATION | ||
| // If there are no subscribers to queue_create, return immediately. | ||
| constexpr uint16_t NotificationTraceType = | ||
| static_cast<uint16_t>(xpti::trace_point_type_t::queue_create); | ||
| if (!xptiCheckTraceEnabled(detail::GSYCLStreamID, NotificationTraceType)) | ||
| return; | ||
| // We do not have CodeLoc for the queue constructor, so we will have to create | ||
| // a queue name with the queue ID to create an event; this step can be avoided | ||
| // by using CodeLoc. | ||
| xpti::utils::StringHelper SH; | ||
| std::string AddrStr = SH.addressAsString<size_t>(MQueueID); | ||
| std::string QueueName = SH.nameWithAddressString("queue", AddrStr); | ||
|
|
||
| xpti_tracepoint_t *Event = | ||
| xptiCreateTracepoint(QueueName.c_str(), nullptr, 0, 0, (void *)this); | ||
| MInstanceID = xptiGetUniqueId(); | ||
| xpti_td *TEvent = Event->event_ref(); | ||
| // Cache the trace event, stream id and instance IDs for the destructor. | ||
| MTraceEvent = (void *)TEvent; | ||
| // We will allow the queue metadata to be set as this is performed | ||
| // infrequently. | ||
| xpti::addMetadata(TEvent, "sycl_context", | ||
| reinterpret_cast<size_t>(MContext->getHandleRef())); | ||
| xpti::addMetadata(TEvent, "sycl_device_name", | ||
| MDevice.get_info<info::device::name>()); | ||
| xpti::addMetadata(TEvent, "sycl_device", | ||
| reinterpret_cast<size_t>(MDevice.getHandleRef())); | ||
| xpti::addMetadata(TEvent, "is_inorder", MIsInorder); | ||
| xpti::addMetadata(TEvent, "queue_id", MQueueID); | ||
| xpti::addMetadata(TEvent, "queue_handle", | ||
| reinterpret_cast<size_t>(getHandleRef())); | ||
| // Also publish to TLS before notification. | ||
| xpti::framework::stash_tuple(XPTI_QUEUE_INSTANCE_ID_KEY, MQueueID); | ||
| xptiNotifySubscribers( | ||
| detail::GSYCLStreamID, (uint16_t)xpti::trace_point_type_t::queue_create, | ||
| nullptr, TEvent, MInstanceID, static_cast<const void *>("queue_create")); | ||
| #endif | ||
| } | ||
|
|
||
|
|
||
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Uh oh!
There was an error while loading. Please reload this page.