Neil R. Spruit
934b24cbe1
refactor: Simplify the include of StateSaveAreaHeader
...
Related-To: NEO-17009
Signed-off-by: Neil R. Spruit <neil.r.spruit@intel.com >
2025-12-12 00:22:05 +01:00
Neil R. Spruit
b580e4e023
feature: Enable Support for reading updated StateSaveHeaders
...
Related-To: NEO-16518
Signed-off-by: Neil R. Spruit <neil.r.spruit@intel.com >
2025-11-19 16:42:42 +01:00
Jemale Lockett
3d8a19cc13
fix: Correct KMD API in log
...
Related-To: NEO-13743
Signed-off-by: Jemale Lockett <jemale.lockett@intel.com >
2025-11-12 19:13:36 +01:00
Jakub Nowacki
2af0f514ec
fix: make readModuleDebugArea() thread-safe
...
Related-To: NEO-15630
Signed-off-by: Jakub Nowacki <jakub.nowacki@intel.com >
2025-10-24 14:25:46 +02:00
Jemale Lockett
33ca1169d0
feature: Add support for new Windows KMD APIs
...
Related-To: NEO-13743
Signed-off-by: Jemale Lockett <jemale.lockett@intel.com >
2025-05-30 07:52:52 +02:00
Jemale Lockett
8b508fd15f
feature: Add sync host event handling on windows
...
Resolves: NEO-13744
Signed-off-by: Jemale Lockett <jemale.lockett@intel.com >
2025-05-13 08:44:45 +02:00
Compute-Runtime-Validation
23d7a4af73
Revert "feature: Add sync host event handling on windows"
...
This reverts commit 1ce4d0fdf7 .
Signed-off-by: Compute-Runtime-Validation <compute-runtime-validation@intel.com >
2025-04-29 04:33:45 +02:00
Jemale Lockett
1ce4d0fdf7
feature: Add sync host event handling on windows
...
Resolves: NEO-13744
Signed-off-by: Jemale Lockett <jemale.lockett@intel.com >
2025-04-28 21:14:25 +02:00
Katarzyna Cencelewska
b2f8da5109
fix: return pointer instead of reference from getOsInterface
...
on tbx this will be a nullpointer
Related-To: HSD-18040897834
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com >
2025-01-21 12:52:39 +01:00
Mateusz Jablonski
7ac41615cd
fix: create thread with function pointer
...
don't create async thread in neo shared tests
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com >
2024-08-21 18:02:37 +02:00
Jemale Lockett
79f8993220
refactor: move GPR15 to separate debugger context
...
Signed-off-by: Jemale Lockett <jemale.lockett@intel.com >
2024-04-18 10:42:23 +02:00
Mateusz Jablonski
c48e57e2de
refactor: rename register offsets and constants
...
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com >
2023-12-04 18:31:39 +01:00
Jablonski, Mateusz
d724627098
fix: fix compilation error in clang on Windows (1/n)
...
Signed-off-by: Jablonski, Mateusz <mateusz.jablonski@intel.com >
2023-10-23 10:36:23 +02:00
Mateusz Hoppe
8e07dd30cb
performance(debugger): optimize ATT handling - minimize mem allocs
...
- do not allocate state save area every time attention event
is handled
- keep allocated memory for subsequent events
- remove not needed DBEUG_BREAK
Related-To: NEO-8183
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com >
2023-07-18 08:37:04 +02:00
Mateusz Hoppe
9a53f20e6c
performance(debugger): optimize ATT event handling
...
- check threads with attention state before reading SR_IDENT
- memory read is costly, for threads already in stopped state
there is no need to read sr_ident and check thread state again
- single stepping one thread performance is substantially improved,
by the factor of 6x
Related-To: NEO-8183
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com >
2023-07-17 10:42:34 +02:00
Mateusz Hoppe
079105a5c2
fix: optimize ATT handling - read state save area once for all threads
...
- reading state save area for every threads takes too long when all
application threads have completed and there are stale ATT events to
process
- on detach gdb seemed to be frozen waiting for ATT event to be handled
- fix is to read state save area once - and check SIP counter for every
thread in ATT bitmask
Related-To: NEO-7897
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com >
2023-04-14 10:57:18 +02:00
Mateusz Hoppe
e26ebfc51b
fix: check exception reason for stopped threads
...
- before marking interrupt request check exception reason. If there is
exception other than forced exception or forced external halt treat
thread as stopped and generate distinct event for it.
Related-To: NEO-7869
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com >
2023-04-05 12:01:20 +02:00
Yates, Brandon
0f6140deb0
fix(l0debug): windows topology map should always be created
...
Topology map was only being created when ZET_ENABLE_PROGAM_DEBUGGING was
set. This was not correct. Now it is unconditionally created at init,
and debug attach will fail if it is not valid.
Related-to: LOCI-3937
Signed-off-by: Yates, Brandon <brandon.yates@intel.com >
2023-03-27 16:24:57 +02:00
Filip Hazubski
bd6349724b
feature(debugger): Increase buffer size used in readAndHandleEvent function
...
Signed-off-by: Filip Hazubski <filip.hazubski@intel.com >
2023-03-17 15:54:32 +01:00
Warchulski, Jaroslaw
64f735481d
Cleanup includes 48
...
Cleaned up files:
shared/source/command_container/command_encoder.inl
shared/source/os_interface/hw_info_config.h
Related-To: NEO-5548
Signed-off-by: Warchulski, Jaroslaw <jaroslaw.warchulski@intel.com >
2023-02-10 17:23:02 +01:00
Warchulski, Jaroslaw
a2e6a8284b
Cleanup includes 47
...
Cleaned up files:
level_zero/tools/source/debug/windows/debug_session.h
level_zero/tools/source/sysman/memory/windows/os_memory_imp.h
level_zero/tools/source/sysman/windows/kmd_sys_manager.h
opencl/test/unit_test/aub_tests/command_stream/copy_engine_aub_tests_xehp_and
shared/source/command_container/command_encoder.inl
shared/source/command_stream/command_stream_receiver_hw_xehp_and_later.inl
shared/source/helpers/blit_commands_helper_base.inl
shared/test/unit_test/image/image_surface_state_fixture.h
shared/test/unit_test/os_interface/windows/os_interface_win_tests.h
Related-To: NEO-5548
Signed-off-by: Warchulski, Jaroslaw <jaroslaw.warchulski@intel.com >
2023-02-10 17:07:30 +01:00
Kamil Kopryk
524d945e8c
refactor: rename l0 hw_helpers dir to gfx_core_helpers
...
Related-To: NEO-6853
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com >
2023-02-02 11:15:56 +01:00
Kamil Kopryk
eb002acaa1
refactor: rename l0_gfx_core_helper files
...
Related-To: NEO-6853
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com >
2023-01-24 12:59:26 +01:00
Warchulski, Jaroslaw
bd81b5546d
Cleanup includes 25
...
Cleaned up files:
level_zero/core/source/device/device.h
opencl/source/helpers/dispatch_info.h
shared/source/os_interface/os_interface.h
Related-To: NEO-5548
Signed-off-by: Warchulski, Jaroslaw <jaroslaw.warchulski@intel.com >
2023-01-10 12:54:45 +01:00
Warchulski, Jaroslaw
f275eea6ec
Cleanup includes 14
...
Cleaned up files:
shared/source/device/device.h
Related-To: NEO-5548
Signed-off-by: Warchulski, Jaroslaw <jaroslaw.warchulski@intel.com >
2022-12-23 10:46:34 +01:00
Yates, Brandon
43ddabd8e6
L0 Debug - Change interrupt return code to match linux
...
Signed-off-by: Yates, Brandon <brandon.yates@intel.com >
2022-12-08 09:42:08 +01:00
Yates, Brandon
668149ab81
[L0 Debug] Add additional log messages to gfxmem r/w
...
Signed-off-by: Yates, Brandon <brandon.yates@intel.com >
2022-12-07 21:08:10 +01:00
Kamil Kopryk
73b2104183
Rename L0HwHelper -> L0GfxCoreHelper
...
Related-To: NEO-6853
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com >
2022-12-05 11:26:05 +01:00
Matias Cabral
467119931c
Add SIP version check
...
Make SLM access a single template function
Resolves: NEO-7335
Signed-off-by: Matias Cabral <matias.a.cabral@intel.com >
2022-12-01 00:55:04 +01:00
Igor Venevtsev
271a50d48e
L0Debug Win: Fix process hang on exit in L0 debugger tests
...
Some L0 debug CTSs intentionnally written to exit w/o proper
resource clenup, f.e do not call zetDebugDetach() etc.
On windows it could be the situation when cleanup of DebugSession is
called in context of DllMain(DLL_PROCESS_DETACH).
At this point all threads other then main already terminated by Windows,
see remarks for DLL_PROCESS_DETACH in
https://learn.microsoft.com/en-us/windows/win32/dlls/dllmain
In this case worker thread object still exists, handle and Id are not
null but corresponding Windows thread does not exist any more and
application waits forever for threadFinished variable. We can safely
omit this waiting since join() will either return immediately in case of
thread was killed by Windows or wait until thread is terminated in normal way.
Signed-off-by: Igor Venevtsev <igor.venevtsev@intel.com >
2022-11-18 17:34:11 +01:00
Mateusz Hoppe
5c23d05312
L0Debug - add support for blocking VM BIND on fence
...
Related-To: NEO-7454
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com >
2022-11-18 12:00:23 +01:00
Yates, Brandon
c95d40ccdd
L0 debug- Windows - Add gpuVA to log for r/w gfx mem
...
Signed-off-by: Yates, Brandon <brandon.yates@intel.com >
2022-11-17 19:08:50 +01:00
Kamil Kopryk
88ed486f6b
Move L0HwHelper ownership to RootDeviceEnvironment 3/n
...
Related-To: NEO-6853
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com >
Use RootDeviceEnvironment getHelper<L0CoreHelper> for
- getAttentionBitmaskForSingleThreads
- getThreadsFromAttentionBitmask
2022-11-15 17:30:15 +01:00
Yates, Brandon
99ef6c499b
L0 debug - fix windows bitmask decode
...
Keep threads created in EU range (0,7)
Signed-off-by: Yates, Brandon <brandon.yates@intel.com >
2022-11-07 14:41:29 +01:00
Igor Venevtsev
f47e1306f2
L0Debug: do not set acknowledge flag for MODULE_UNLOAD event
...
Signed-off-by: Igor Venevtsev <igor.venevtsev@intel.com >
2022-11-07 14:01:29 +01:00
Matias Cabral
0772d32a76
Windows debugger access to SLM
...
Resolves: NEO-7382
Signed-off-by: Matias Cabral <matias.a.cabral@intel.com >
2022-11-02 10:58:09 +01:00
Yates, Brandon
789a53e8f8
L0 Debug - Don't pollute debug log with event timeouts
...
Signed-off-by: Yates, Brandon <brandon.yates@intel.com >
2022-10-19 17:26:31 +02:00
Igor Venevtsev
5a0dd8048b
L0Debug Win: fix bitmap reading for EU_ATTN_BIT_SET event
...
Signed-off-by: Igor Venevtsev <igor.venevtsev@intel.com >
2022-10-06 15:41:14 +02:00
Matias Cabral
c012034c19
Debugger access to SLM
...
Resolves: NEO-5998
Signed-off-by: Matias Cabral <matias.a.cabral@intel.com >
2022-09-30 11:31:19 +02:00
Mateusz Hoppe
7ff258fc92
L0Debug - Enable attaching to Root or Subdevices
...
- enable tile attach mode by default
- both root device and subdevice may be attached to
Related-To: NEO-7347
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com >
2022-09-26 16:03:54 +02:00
Yates, Brandon
12c7f32679
L0 Win Debugger - implement thread control
...
Resolves: NEO-6722
Signed-off-by: Yates, Brandon <brandon.yates@intel.com >
Signed-off-by: Igor Venevtsev <igor.venevtsev@intel.com >
2022-09-05 19:26:14 +02:00
Jitendra Sharma
3212a71760
Debugger L0 Win: Attention event handling from UMD
...
Related-To: NEO-7261
Signed-off-by: Jitendra Sharma <jitendra.sharma@intel.com >
2022-09-02 18:22:41 +02:00
Igor Venevtsev
d40173e47a
L0Debug Win: Always generate module create/destroy events
...
We have to always generate module create/destroy events to give
debugger a chance to insert bp, read/write debuggee memory etc
even there is no debug data was generated. In this case ELF will not be
reported to debugger, just ISA GpuVA
Related-To: NEO-6723
Signed-off-by: Igor Venevtsev <igor.venevtsev@intel.com >
2022-08-24 14:58:30 +02:00
Yates, Brandon
dbf955c1f2
L0 win debugger - implement read elf
...
Signed-off-by: Yates, Brandon <brandon.yates@intel.com >
2022-08-11 16:16:21 +02:00
Igor Venevtsev
4cb9ad5d55
Debugger L0 Win: implement module destroy event
...
Related-To: NEO-6723
Signed-off-by: Igor Venevtsev <igor.venevtsev@intel.com >
2022-07-28 15:55:40 +02:00
Kamil Kopryk
d4d54f5093
Cleanup includes
...
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com >
2022-07-25 09:58:38 +02:00
Igor Venevtsev
d79e799bea
Debugger L0 win: implement zetAcknowledgeEvent API
...
Related-To: NEO-6723
Signed-off-by: Igor Venevtsev <igor.venevtsev@intel.com >
2022-07-22 16:46:27 +02:00
Igor Venevtsev
547dd59272
Debugger L0 Win: Implement CREATE_DEBUG_DATA/MODULE_CREATE events handling
...
Related-To: NEO-6723
Signed-off-by: Igor Venevtsev <igor.venevtsev@intel.com >
2022-07-20 13:20:50 +02:00
Jitendra Sharma
4a8a93af96
Debugger L0 Win - Generate Proc Entry/Exit events
...
Related-To: NEO-7117
Signed-off-by: Jitendra Sharma <jitendra.sharma@intel.com >
2022-07-18 12:32:57 +02:00
Mateusz Hoppe
bd07b3ec97
L0Debug refactor: Replace ze_device_thread_t with EuThread::ThreadId
...
- ThreadId is preferred beacuse it uniquely identifies thread and is
not related to device topology
Related-To: NEO-5784
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com >
2022-07-14 20:01:56 +02:00