mechanism for freeing allocations saved for reuse that have not been
used in a given time
Related-To: NEO-13425
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
Addresses regressions from the reverted merge
of the tbx fault manager for host memory.
Recursive locking of mutex caused deadlock.
To fix, separate tbx fault data from base
cpu fault data, allowing separate mutexes
for each, eliminating recursive locks on
the same mutex.
By separating, we also help ensure that tbx-related
changes don't affect the original cpu fault manager code
paths.
As an added safe guard preventing critical regressions
and avoiding another auto-revert, the tbx fault manager
is hidden behind a new debug flag which is disabled by default.
Related-To: NEO-12268
Signed-off-by: Jack Myers <jack.myers@intel.com>
Addresses regressions from the reverted merge
of the tbx fault manager for host memory.
This fixes attempts by the tbx fault manager
to protect/unprotect host buffer memory, even
if the host ptr was not driver-allocated.
In the case of the smoke test that triggered
the critical regression, clCreateBuffer was
called with the CL_MEM_USE_HOST_PTR flag.
The subsequent `mprotect` calls on the
provided host ptr then failed.
Related-To: NEO-12268
Signed-off-by: Jack Myers <jack.myers@intel.com>
Related-To: NEO-11908
There is overhead when submission method is used for
zeDeviceGetGlobalTimestamps. This fixes it.
Signed-off-by: Chandio, Bibrak Qamar <bibrak.qamar.chandio@intel.com>
-Add AbortHostSyncOnNonHostVisibleEvent which abort when waiting for non
host visible event from host
-Add ForceHostSignalScope which forces add or clear of host scope to
event's signal scope
Related-To: NEO-13441
Signed-off-by: Lukasz Jobczyk <lukasz.jobczyk@intel.com>
In TBX mode, the host could not write to host buffers after access from device
code due to the lack of a migration mechanism post-initial TBX upload.
Migration is unnecessary with real hardware, but required for TBX.
This patch introduces a new page fault manager type that extends the original
CPU fault manager, enabling automatic migration of host buffers in TBX mode.
Refactoring was necessary to avoid diamond inheritance, achieved by using a
template parameter as the base class for OS-specific fault managers.
Related-To: NEO-12268
Signed-off-by: Jack Myers <jack.myers@intel.com>
Refactors the STATE_BASE_ADDRESS to align with the latest specification.
Removes redundant functionality for multiple GPU partial writes and
atomics.
Related-To: NEO-13147
Signed-off-by: Vysochyn, Illia <illia.vysochyn@intel.com>
Related-To: GSD-10253, GSD-9467, GSD-9381, NEO-11908
When EnableGlobalTimestampViaSubmission is set then
zeDeviceGetGlobalTimestamp uses immediate cmd submission
method to get GPU time.
Signed-off-by: Chandio, Bibrak Qamar <bibrak.qamar.chandio@intel.com>
Add flag to log information for indirect detection debugging.
Add flag to disable indirect detection by kernel name.
Add flag to force indirect detection enable/disable for CM kernels.
Related-To: NEO-13372
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
PrintCalculatedTimestamps - print ts in level zero paths
PrintTimestampPacketContents - add logging also to level zero paths
ForceUseOnlyGlobalTimestamps - force using a global ts
Related-To: HSD-14023527252
Signed-off-by: Katarzyna Cencelewska <katarzyna.cencelewska@intel.com>
When debug flag ForceZeroCopyForUseHostPtr is set, add
CL_MEM_FORCE_HOST_MEMORY_INTEL flag to buffers created with
CL_MEM_USE_HOST_PTR.
This makes the buffers use zero copy.
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
- EnableCompatibilityMode flag added
- validateTergetDevice func modified to take into account the flag
Related-To: NEO-11568
Signed-off-by: Wojciech Konior <wojciech.konior@intel.com>
This adds abbility to load different versions of the backend
compiler based on underlying device.
Related-To: NEO-12747
Signed-off-by: Chodor, Jaroslaw <jaroslaw.chodor@intel.com>
Up till now, NEO ignored uknown attributes in zeinfo
which could lead to undefined behavior. With this change
NEO will emit an error whenever an unknown attribute is
encountered.
Note : old behavior can be restored using new
IgnoreZebinUnknownAttributes debug environment variable
Resolves: NEO-11762
Signed-off-by: Chodor, Jaroslaw <jaroslaw.chodor@intel.com>
This adds abbility to load different versions of the backend
compiler based on underlying device.
Related-To: NEO-12747
Signed-off-by: Chodor, Jaroslaw <jaroslaw.chodor@intel.com>
Recorded multiple page fault handlers by using vector in
cpu_page_fault_manager_linux.
Added a static handlerIndex in order to track the depth of
handler logic to call appropriate previous handlers.
Related-To: NEO-11563
Signed-off-by: Young Jin Yoon <young.jin.yoon@intel.com>
Dedicated pools for different allocations size ranges.
Additional reused allocations will create their own pools.
Do not reuse allocations >256MB.
Related-To: NEO-6893, NEO-12299, NEO-12349
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
Recorded multiple page fault handlers by using vector in
cpu_page_fault_manager_linux.
Added a static handlerIndex in order to track the depth of
handler logic to call appropriate previous handlers.
Related-To: NEO-11563
Signed-off-by: Young Jin Yoon <young.jin.yoon@intel.com>
Up till now, NEO ignored uknown attributes in zeinfo
which could lead to undefined behavior. With this change
NEO will emit an error whenever an unknown attribute is
encountered.
Note : old behavior can be restored using new
IgnoreZebinUnknownAttributes debug environment variable
Resolves: NEO-11762
Signed-off-by: Chodor, Jaroslaw <jaroslaw.chodor@intel.com>
Related-To: NEO-12197
Currently for new resources user thread must wait before submitting
actual workload. With this commit, instead of waiting on user thread,
request is sent to background ULLS controller thread and additional
semaphore is programmed. ULLS controller will perform actual wait
and signal semaphore when paging fence reaches required value.
Signed-off-by: Szymon Morek <szymon.morek@intel.com>
Dominik Dabek