intel/compute-runtime
1
0
Fork 0
mirror of https://github.com/intel/compute-runtime.git synced 2026-01-12 09:30:36 +08:00
Code Issues Packages Projects Releases Wiki Activity
Files
56b30d18030f03aeb54a918b4cc3ede95c519e0a
compute-runtime/shared/source/command_stream/host_function_worker_interface.cpp

61 lines
1.9 KiB
C++
Raw Normal View History

feature: add host functions workers * add common host function worker interface * add worker as a single thread per csr with 3 modes * add logic for waiting on internal tag, check gpu hang * if tag is in pending state, read callback data, run callback and signal completion * threads will exit the work loop once stop request is called in finish * add multi thread unit tests Related-To: NEO-14577 Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-10-31 10:59:39 +00:00
/*
* Copyright (C) 2025 Intel Corporation
*
* SPDX-License-Identifier: MIT
*
*/
#include "shared/source/command_stream/host_function_worker_interface.h"
#include "shared/source/command_stream/host_function.h"
#include "shared/source/utilities/wait_util.h"
#include <chrono>
#include <type_traits>
namespace NEO {
feature: redesign host function workers Each host function gets its unique ID within a CSR, uses 1 mi store to write ID - to signal that host function is ready, and 1 mi semaphore wait will wait for the ID to be cleared, Use 0th bit from ID as pending/completed flag, host function ID is incremented by 2, and starts with 1. So each ID will always have 0bit set. This is a must have since semaphore wait can wait for 4 bytes only. Adjust command buffer programming and patching logic to IDs. Add hostFunction callable class - using invoke method, which stores required information about callback. Add host function streamer - stores all host function data for a given CSR. All user provided host functions are stored in unordered map, where key is host function ID. Add host function scheduler, and a thread pool - under debug flag Single threaded scheduler loops over all registered host function streamers, dispatch ready to execute host functions to thread pool. Allow for out of order host functions execution for OOQ - under debug flag, each host function has bool isInOrder flag which indicates if it can be executed Out Of Order - in this mode, ID tag will be cleared immediately, so semaphore wait will unblock before the host function execution. Remove Host Function worker CV and atomics based implementation. Rename classes Related-To: NEO-14577 Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-11-24 20:35:14 +00:00
HostFunctionSingleWorker::HostFunctionSingleWorker(bool skipHostFunctionExecution)
: HostFunctionWorker(skipHostFunctionExecution) {
feature: add host functions workers * add common host function worker interface * add worker as a single thread per csr with 3 modes * add logic for waiting on internal tag, check gpu hang * if tag is in pending state, read callback data, run callback and signal completion * threads will exit the work loop once stop request is called in finish * add multi thread unit tests Related-To: NEO-14577 Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-10-31 10:59:39 +00:00
}
feature: redesign host function workers Each host function gets its unique ID within a CSR, uses 1 mi store to write ID - to signal that host function is ready, and 1 mi semaphore wait will wait for the ID to be cleared, Use 0th bit from ID as pending/completed flag, host function ID is incremented by 2, and starts with 1. So each ID will always have 0bit set. This is a must have since semaphore wait can wait for 4 bytes only. Adjust command buffer programming and patching logic to IDs. Add hostFunction callable class - using invoke method, which stores required information about callback. Add host function streamer - stores all host function data for a given CSR. All user provided host functions are stored in unordered map, where key is host function ID. Add host function scheduler, and a thread pool - under debug flag Single threaded scheduler loops over all registered host function streamers, dispatch ready to execute host functions to thread pool. Allow for out of order host functions execution for OOQ - under debug flag, each host function has bool isInOrder flag which indicates if it can be executed Out Of Order - in this mode, ID tag will be cleared immediately, so semaphore wait will unblock before the host function execution. Remove Host Function worker CV and atomics based implementation. Rename classes Related-To: NEO-14577 Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-11-24 20:35:14 +00:00
HostFunctionSingleWorker::~HostFunctionSingleWorker() = default;
feature: add host functions workers * add common host function worker interface * add worker as a single thread per csr with 3 modes * add logic for waiting on internal tag, check gpu hang * if tag is in pending state, read callback data, run callback and signal completion * threads will exit the work loop once stop request is called in finish * add multi thread unit tests Related-To: NEO-14577 Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-10-31 10:59:39 +00:00
feature: redesign host function workers Each host function gets its unique ID within a CSR, uses 1 mi store to write ID - to signal that host function is ready, and 1 mi semaphore wait will wait for the ID to be cleared, Use 0th bit from ID as pending/completed flag, host function ID is incremented by 2, and starts with 1. So each ID will always have 0bit set. This is a must have since semaphore wait can wait for 4 bytes only. Adjust command buffer programming and patching logic to IDs. Add hostFunction callable class - using invoke method, which stores required information about callback. Add host function streamer - stores all host function data for a given CSR. All user provided host functions are stored in unordered map, where key is host function ID. Add host function scheduler, and a thread pool - under debug flag Single threaded scheduler loops over all registered host function streamers, dispatch ready to execute host functions to thread pool. Allow for out of order host functions execution for OOQ - under debug flag, each host function has bool isInOrder flag which indicates if it can be executed Out Of Order - in this mode, ID tag will be cleared immediately, so semaphore wait will unblock before the host function execution. Remove Host Function worker CV and atomics based implementation. Rename classes Related-To: NEO-14577 Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-11-24 20:35:14 +00:00
void HostFunctionSingleWorker::processNextHostFunction(std::stop_token st) noexcept {
feature: add host functions workers * add common host function worker interface * add worker as a single thread per csr with 3 modes * add logic for waiting on internal tag, check gpu hang * if tag is in pending state, read callback data, run callback and signal completion * threads will exit the work loop once stop request is called in finish * add multi thread unit tests Related-To: NEO-14577 Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-10-31 10:59:39 +00:00
feature: redesign host function workers Each host function gets its unique ID within a CSR, uses 1 mi store to write ID - to signal that host function is ready, and 1 mi semaphore wait will wait for the ID to be cleared, Use 0th bit from ID as pending/completed flag, host function ID is incremented by 2, and starts with 1. So each ID will always have 0bit set. This is a must have since semaphore wait can wait for 4 bytes only. Adjust command buffer programming and patching logic to IDs. Add hostFunction callable class - using invoke method, which stores required information about callback. Add host function streamer - stores all host function data for a given CSR. All user provided host functions are stored in unordered map, where key is host function ID. Add host function scheduler, and a thread pool - under debug flag Single threaded scheduler loops over all registered host function streamers, dispatch ready to execute host functions to thread pool. Allow for out of order host functions execution for OOQ - under debug flag, each host function has bool isInOrder flag which indicates if it can be executed Out Of Order - in this mode, ID tag will be cleared immediately, so semaphore wait will unblock before the host function execution. Remove Host Function worker CV and atomics based implementation. Rename classes Related-To: NEO-14577 Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-11-24 20:35:14 +00:00
if (skipHostFunctionExecution == false) {
auto hostFunctionReady = waitUntilHostFunctionIsReady(st);
if (hostFunctionReady) {
auto hostFunction = streamer->getHostFunction();
streamer->prepareForExecution(hostFunction);
hostFunction.invoke();
streamer->signalHostFunctionCompletion(hostFunction);
}
}
}
bool HostFunctionSingleWorker::waitUntilHostFunctionIsReady(std::stop_token st) noexcept {
feature: add host functions workers * add common host function worker interface * add worker as a single thread per csr with 3 modes * add logic for waiting on internal tag, check gpu hang * if tag is in pending state, read callback data, run callback and signal completion * threads will exit the work loop once stop request is called in finish * add multi thread unit tests Related-To: NEO-14577 Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-10-31 10:59:39 +00:00
feature: redesign host function workers Each host function gets its unique ID within a CSR, uses 1 mi store to write ID - to signal that host function is ready, and 1 mi semaphore wait will wait for the ID to be cleared, Use 0th bit from ID as pending/completed flag, host function ID is incremented by 2, and starts with 1. So each ID will always have 0bit set. This is a must have since semaphore wait can wait for 4 bytes only. Adjust command buffer programming and patching logic to IDs. Add hostFunction callable class - using invoke method, which stores required information about callback. Add host function streamer - stores all host function data for a given CSR. All user provided host functions are stored in unordered map, where key is host function ID. Add host function scheduler, and a thread pool - under debug flag Single threaded scheduler loops over all registered host function streamers, dispatch ready to execute host functions to thread pool. Allow for out of order host functions execution for OOQ - under debug flag, each host function has bool isInOrder flag which indicates if it can be executed Out Of Order - in this mode, ID tag will be cleared immediately, so semaphore wait will unblock before the host function execution. Remove Host Function worker CV and atomics based implementation. Rename classes Related-To: NEO-14577 Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-11-24 20:35:14 +00:00
const auto start = std::chrono::steady_clock::now();
feature: add host functions workers * add common host function worker interface * add worker as a single thread per csr with 3 modes * add logic for waiting on internal tag, check gpu hang * if tag is in pending state, read callback data, run callback and signal completion * threads will exit the work loop once stop request is called in finish * add multi thread unit tests Related-To: NEO-14577 Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-10-31 10:59:39 +00:00
feature: redesign host function workers Each host function gets its unique ID within a CSR, uses 1 mi store to write ID - to signal that host function is ready, and 1 mi semaphore wait will wait for the ID to be cleared, Use 0th bit from ID as pending/completed flag, host function ID is incremented by 2, and starts with 1. So each ID will always have 0bit set. This is a must have since semaphore wait can wait for 4 bytes only. Adjust command buffer programming and patching logic to IDs. Add hostFunction callable class - using invoke method, which stores required information about callback. Add host function streamer - stores all host function data for a given CSR. All user provided host functions are stored in unordered map, where key is host function ID. Add host function scheduler, and a thread pool - under debug flag Single threaded scheduler loops over all registered host function streamers, dispatch ready to execute host functions to thread pool. Allow for out of order host functions execution for OOQ - under debug flag, each host function has bool isInOrder flag which indicates if it can be executed Out Of Order - in this mode, ID tag will be cleared immediately, so semaphore wait will unblock before the host function execution. Remove Host Function worker CV and atomics based implementation. Rename classes Related-To: NEO-14577 Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-11-24 20:35:14 +00:00
while (true) {
feature: add host functions workers * add common host function worker interface * add worker as a single thread per csr with 3 modes * add logic for waiting on internal tag, check gpu hang * if tag is in pending state, read callback data, run callback and signal completion * threads will exit the work loop once stop request is called in finish * add multi thread unit tests Related-To: NEO-14577 Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-10-31 10:59:39 +00:00
feature: redesign host function workers Each host function gets its unique ID within a CSR, uses 1 mi store to write ID - to signal that host function is ready, and 1 mi semaphore wait will wait for the ID to be cleared, Use 0th bit from ID as pending/completed flag, host function ID is incremented by 2, and starts with 1. So each ID will always have 0bit set. This is a must have since semaphore wait can wait for 4 bytes only. Adjust command buffer programming and patching logic to IDs. Add hostFunction callable class - using invoke method, which stores required information about callback. Add host function streamer - stores all host function data for a given CSR. All user provided host functions are stored in unordered map, where key is host function ID. Add host function scheduler, and a thread pool - under debug flag Single threaded scheduler loops over all registered host function streamers, dispatch ready to execute host functions to thread pool. Allow for out of order host functions execution for OOQ - under debug flag, each host function has bool isInOrder flag which indicates if it can be executed Out Of Order - in this mode, ID tag will be cleared immediately, so semaphore wait will unblock before the host function execution. Remove Host Function worker CV and atomics based implementation. Rename classes Related-To: NEO-14577 Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-11-24 20:35:14 +00:00
if (st.stop_requested()) {
return false;
feature: add host functions workers * add common host function worker interface * add worker as a single thread per csr with 3 modes * add logic for waiting on internal tag, check gpu hang * if tag is in pending state, read callback data, run callback and signal completion * threads will exit the work loop once stop request is called in finish * add multi thread unit tests Related-To: NEO-14577 Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-10-31 10:59:39 +00:00
}
feature: redesign host function workers Each host function gets its unique ID within a CSR, uses 1 mi store to write ID - to signal that host function is ready, and 1 mi semaphore wait will wait for the ID to be cleared, Use 0th bit from ID as pending/completed flag, host function ID is incremented by 2, and starts with 1. So each ID will always have 0bit set. This is a must have since semaphore wait can wait for 4 bytes only. Adjust command buffer programming and patching logic to IDs. Add hostFunction callable class - using invoke method, which stores required information about callback. Add host function streamer - stores all host function data for a given CSR. All user provided host functions are stored in unordered map, where key is host function ID. Add host function scheduler, and a thread pool - under debug flag Single threaded scheduler loops over all registered host function streamers, dispatch ready to execute host functions to thread pool. Allow for out of order host functions execution for OOQ - under debug flag, each host function has bool isInOrder flag which indicates if it can be executed Out Of Order - in this mode, ID tag will be cleared immediately, so semaphore wait will unblock before the host function execution. Remove Host Function worker CV and atomics based implementation. Rename classes Related-To: NEO-14577 Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-11-24 20:35:14 +00:00
streamer->downloadHostFunctionAllocation();
feature: add host functions workers * add common host function worker interface * add worker as a single thread per csr with 3 modes * add logic for waiting on internal tag, check gpu hang * if tag is in pending state, read callback data, run callback and signal completion * threads will exit the work loop once stop request is called in finish * add multi thread unit tests Related-To: NEO-14577 Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-10-31 10:59:39 +00:00
feature: redesign host function workers Each host function gets its unique ID within a CSR, uses 1 mi store to write ID - to signal that host function is ready, and 1 mi semaphore wait will wait for the ID to be cleared, Use 0th bit from ID as pending/completed flag, host function ID is incremented by 2, and starts with 1. So each ID will always have 0bit set. This is a must have since semaphore wait can wait for 4 bytes only. Adjust command buffer programming and patching logic to IDs. Add hostFunction callable class - using invoke method, which stores required information about callback. Add host function streamer - stores all host function data for a given CSR. All user provided host functions are stored in unordered map, where key is host function ID. Add host function scheduler, and a thread pool - under debug flag Single threaded scheduler loops over all registered host function streamers, dispatch ready to execute host functions to thread pool. Allow for out of order host functions execution for OOQ - under debug flag, each host function has bool isInOrder flag which indicates if it can be executed Out Of Order - in this mode, ID tag will be cleared immediately, so semaphore wait will unblock before the host function execution. Remove Host Function worker CV and atomics based implementation. Rename classes Related-To: NEO-14577 Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-11-24 20:35:14 +00:00
auto waitTime = std::chrono::duration_cast<std::chrono::microseconds>(std::chrono::steady_clock::now() - start);
auto hostFunctionReady = WaitUtils::waitFunctionWithPredicate<uint64_t>(streamer->getHostFunctionIdPtr(),
HostFunctionStatus::completed,
std::greater<uint64_t>(),
waitTime.count());
feature: add host functions workers * add common host function worker interface * add worker as a single thread per csr with 3 modes * add logic for waiting on internal tag, check gpu hang * if tag is in pending state, read callback data, run callback and signal completion * threads will exit the work loop once stop request is called in finish * add multi thread unit tests Related-To: NEO-14577 Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-10-31 10:59:39 +00:00
feature: redesign host function workers Each host function gets its unique ID within a CSR, uses 1 mi store to write ID - to signal that host function is ready, and 1 mi semaphore wait will wait for the ID to be cleared, Use 0th bit from ID as pending/completed flag, host function ID is incremented by 2, and starts with 1. So each ID will always have 0bit set. This is a must have since semaphore wait can wait for 4 bytes only. Adjust command buffer programming and patching logic to IDs. Add hostFunction callable class - using invoke method, which stores required information about callback. Add host function streamer - stores all host function data for a given CSR. All user provided host functions are stored in unordered map, where key is host function ID. Add host function scheduler, and a thread pool - under debug flag Single threaded scheduler loops over all registered host function streamers, dispatch ready to execute host functions to thread pool. Allow for out of order host functions execution for OOQ - under debug flag, each host function has bool isInOrder flag which indicates if it can be executed Out Of Order - in this mode, ID tag will be cleared immediately, so semaphore wait will unblock before the host function execution. Remove Host Function worker CV and atomics based implementation. Rename classes Related-To: NEO-14577 Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-11-24 20:35:14 +00:00
if (hostFunctionReady) {
return true;
}
}
feature: add host functions workers * add common host function worker interface * add worker as a single thread per csr with 3 modes * add logic for waiting on internal tag, check gpu hang * if tag is in pending state, read callback data, run callback and signal completion * threads will exit the work loop once stop request is called in finish * add multi thread unit tests Related-To: NEO-14577 Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
2025-10-31 10:59:39 +00:00
}
} // namespace NEO
Reference in New Issue Copy Permalink