- remove method allocateGraphicsMemory(size_t size)
- pass allocation type in allocation properties
- set allocation type in allocateGraphicsMemoryInPreferredPool
Change-Id: Ia9296d0ab2f711b7d78aff615cb56b3a246b60ec
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
- make AllocationData a protected structure
- use AllocationProperties instead of AllocationFlags
- refactor methods: allocateGraphicsMemory64kb, allocateGraphicsMemoryForSVM
- call AllocateGraphicsMemoryInPreferredPool in AllocateGraphicsMemory
where there is no host ptr
Change-Id: Ie9ca47b1bccacd00f8486e7d1bf6fb3985e5cb12
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
Move:
- getEngineIndexFromInstance
- getEngineIndex
to common CSR
Unification of arguments of some AUB/TBX methods
Change-Id: I46f25e16aa9fbad10ffc3890cc31915fa5edb1d9
pass struct with properties to allocate graphics memory methods:
for protected methods use AllocationData
for public methods use AllocationProperties
Change-Id: Ie1c3cb6b5e330bc4adac2ca8b0bf02d30ec76065
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
- Store inspectionId for each osContext in GraphicsAllocation
- Pass osContextId to aggregateCommandBuffer and use it to select inspectionId
Change-Id: I2c377ad7577a8c882cc89c1205430cb581c2c0d5
Signed-off-by: Maciej Dziuban <maciej.dziuban@intel.com>
Move code related to batch buffer submission from flush to dedicated function
Add parameter to pass aub file name from AubCenter to AubManager
Change-Id: I20abb3c8bd92114b3bc9caa2a6291dc1bbddad2a
Move definitions of objectNotUsed and objectNotResident to GraphicsAllocation
Change-Id: I2aec604a865cc6c975e9d1121028cbdd35c0b18a
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
- When queue is created with throttle hint low it should be power conservative
- With this change whenever queues with low throttle setting requests wait
for GPU completion, such wait will be handled in power conservative manner.
- Whenever GPU is not completed, waiting thread will be put to sleep and will
for GPU completion that triggers the wake up interrupt.
Change-Id: I9f34872a38ab9f5952f9d9623ea43503fc3dd587
- pass hwInfo and localMemoryEnabled to AubCenter ctor
- initialize AubCenter in Platform:intialize() when Device is
created - only when CSR is not CsrHw
- move aub_center files to runtime/aub directory
Change-Id: Iceb4bf1cb2bb55b42d438502cca667a449f11411
Move definition of allocations list method to internal_allocation_storage.cpp
Change-Id: I4c6038df8fd1b9335e8a74edbab33b78f9293d8f
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
Remove not needed includes from command_queue.h
Change-Id: I45963bf005471bd7716d55471474299a15e27b62
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
- AUB and TBX use this method and it was duplicated,
- moving to common base class allows to remove duplicates
Change-Id: Ia9f08dfb0967de1b5968ac0e531733c5b868e504
OsContext has to propagate through following calls first:
- WddmCommandStreamReceiver<GfxFamily>::processEviction
- CommandStreamReceiver::makeSurfacePackNonResident
Change-Id: I7559c7406b2860c51905c9961cec251fac231b08
Signed-off-by: Maciej Dziuban <maciej.dziuban@intel.com>
Ensures that each submit of LRCA be serialized through the simulator
like it is for AUBs captured in the standalone mode.
Change-Id: I1e3ad500012dce960d0e64b56af1cb60142772da
This commit moves address mapper from CSR to execution environment
in order to generate unique GTT VA for LRCA, HWSP and ring buffer
between different CSRs.
Additionally, moved the rest of AUB file stream tests to separate module.
Change-Id: I02ae44202c0255277a7ac17532485419e0c403ab
AUB CSR can implement additional actions to be taken on makeNonResident
such as dumping buffer and image resources.
Change-Id: Iab76081116011e0882de3c902db74a5dc4dd0b36
- fixture is creating AUBCsr or TBXWithAubCsr only and sets
executionEnvironment used by Device
- this sequence ensures correct initialization without redundant
objects creation
- adding new AUB test: AubWriteCopyReadBufferTest
Change-Id: I678410585c91c008fc53a44b13e885e970fd315b
This commit introduces AUB stream provider class to produce
a single file stream in multi device scenarios with multiple AUB CSRs.
Change-Id: Id70e0d680459d34f4291b9e56aa39d960f025ac6
Updating files modified in 2018 only. Older files remain with old style
copyright header
Change-Id: Ic99f2e190ad74b4b7f2bd79dd7b9fa5fbe36ec92
Signed-off-by: Artur Harasimiuk <artur.harasimiuk@intel.com>
This commit adds a capability for a driver to generate multiple devices
and hwinfo in AUB and TBX CSR modes.
Change-Id: Icc0eac7c16760d3d4ae6ef08cd0be950b45d35e7
- get PageTable entry data hints and address space from AubHelper
based on local memory flag
- add enableLocalMemory flag in CSR HW
Change-Id: I061bda62be8da55d52cff48ecddcf26c4212dc67
This prepares for moving this method from MemoryManager to CSR.
Change-Id: I82393289c48990f26ed3ac922bcd64e2b6c11f28
Signed-off-by: Maciej Dziuban <maciej.dziuban@intel.com>
This commit introduces new controls to define start/end indexes
that apply only to the kernel specified by name for a sub-capture
Change-Id: I7ad7674d115f9addd35c44d824aee0731060881e
This commit adds a helper function to get Page Table entry bits
and control a configuration of first levels page walks (non-PTE).
Change-Id: I85666ffae8e89a193d1ac4a065c2b84b814d47ec
- extend constructor to take new flag
- extend ExecutionEnvironment createMemoryManager with new flag
- only OsAgnosticMemoryManager changes in this step
Change-Id: I1dae4fd79fe28fd87e42b237600dc216c94b597e
- remove Wddm parameter from WddmCommandStreamReceiver
and pass it via ExecutionEnvironment
- remove drm parameter from DrmCommandStreamReceiver
and pass it via ExecutionEnvironment
- remove void parametr from TbxCommandStreamReceiverHw
Change-Id: Ib76332f1341339426e86e0ce2b6ce96919219881
This commit ensures that AUB CSR be using make resident of the base CSR class
hence the task count of the graphics allocation be updated properly.
Change-Id: I33b5ed86a463eeeee00a4094cefda8add316af73
This commit adds the AUBDumpCaptureFileName control to configure from outside
a file name with an optional path where to save the AUB capture into.
Change-Id: Ibf2f7663e23ad9e1001896b0c5b7030f9979dae2
This commit adds a new callback to be called by GMM library
when it allocates/deallocates compressed resources to collect data
about their addresses and sizes and handle their AUB residency.
Change-Id: I075d3ff4cb049cfe626da82892069c4460ea585c
- OsInterface is now a part of execution environment
- it is created when getDevice is being called
- move ownership of wddm from Wddm Memory manager to OSInterface
- reuse osInterface on Linux in Command Stream Receiver
- currently OsInterface is not reused upon command stream receiver creation
on Windows this will change in further commits.
- make enumAdapters non static function
Change-Id: I10f36c01e6729f48653e3b5c11cbc32e811ce754
Fix for clang tidy warning: Call to virtual function
during destruction will not dispatch to derived class
Change-Id: I000dacdbdfb486d2e35795d18ea9f5e4a00b7d6a
- Command Stream Receiver should be used instead for locking.
- Remove not needed synchronization in clSetUserEventStatus
Change-Id: I17050dc70cb0be03b2003043a9666ba8df1a83c9
- resources are dumped in make non resident call
- in order to dump correct data we need to be sure that GPU is done processing
- waiting needs to be unconditional to handle all cases
- remove not needed parameter to makeSurfacePackNonResident
Change-Id: Ib2b065d486cd3a5d86e599c51b24f3c958c3a10b
- remove not needed method in mock device.
- remove duplication from aub tests.
- tag allocation now have desired value
Change-Id: Ib3161cce6753eae27c60fddb63054fd2e12f7dac
- in VA sharing scenarios driver needs to be as power efficient as possible
- Added new mode to KMD notify helper called maxPowerSavingMode
- in this mode, whenever GPU is not busy, driver will choose non busy wait
path.
Change-Id: I7e4079be995107bea543ffda774ca161ce483944
- new ExtendableEnum struct that serves as enum but can
be extended with values
- decrease dependencies on graphics_allocation.h header -
use forward class declaration when possible
- memoryPool indicates what kind of memory is allocated
for a given GraphicsAllocation
Change-Id: I7a707c28dc4544cc73abc5f0ed5263ba5be17452
- remove other explicit resets, no longer needed.
- change the order of destruction, command stream receiver needs to be
destroyed prior to memory manager.
Change-Id: I3c5db46db15a2cb7dc9f6fdb0e06441806fbd9f2
Add a capability for AUB subcapture feature to dump into several files
and read file name from the outside (via regkey and env variable).
Change-Id: I2d5f7945cfbc740b0316fe23b8c5ae9fd698ac57
This code is an infrastructure for special debug purpose that allow measure
execution time of any hardware command.
Change-Id: Id12a7979d204734a0c4a6c4700e427b65ac2397f
- replace createGraphicsAllocationWithRequiredBitness with more general
methodallocateGraphicsMemoryInPreferredPool based on passed
AllocationData
- proper flags for allocation selected based on AllocationType
- remove allocateGraphicsMemory(size_t size, size_t alignment)
and use allocateGraphicsMemory(size_t size) instead where default
alignment is sufficient, otherwise use full options version:
allocateGraphicsMemory(size_t size, size_t alignment,
bool forcePin, bool uncacheable)
Change-Id: I2da891f372ee181253cb840568a61b33c0d71fc9
- change GraphicsAllocatoin::AllocationType to scoped enumeration
so that ALLOCATION_TYPE_ prefix in every enum value can be removed
- all accesses are typed (example AllocationType::IMAGE)
- Rename allocationType to AllocationUsage to eliminate confusion
with multiple AllocationType enums / types
Change-Id: I16003297ecfcb0aaa5779ad00706c5d983914bbe
- makeCoherent should be called after TBX finished processing
- this is when tagAddress is updated with taskCount
makeCoherent is called from makeNonResident which is invoked just
after flush and may happen before TBX server finished processing
leading to invalid data to be read back to CPU accessible memory
- this fix adds waiting for taskCount to blocking calls for TBX CSR
before calling makeNonResident on surfaces to guarantee correct data
from TBX server is ready.
Change-Id: I498a5454e0826eec2a5413a08880af40268550e1
- move AUBDumpToggleCaptureOnOff from HKLM to HKCU without admin rights
- fix AUB subcapture in toggle mode to call make resident in standalone mode
Change-Id: Ia6971921f33bb9ca63112790af870217da8a1585
This commit adds a capability to selectively enable/disable AUB capture,
i.e. by toggling the registry key from the outside or specifying the filter
with a kernel name and/or kernel start index and kernel end index.
Change-Id: Ib5d39c21863fbc4a95aa73c949b9779ff993de0f
- when CSR is set to AUB or TBX (with AubDump) Device should
return true in isSimulation(). This method is used to set flag
m_IsSimulation in deviceQueue which is used by scheduler kernel
Change-Id: Ibdf07d4c940335fb0bb8448071b66d47e9391d71
when SLD is active:
- make Sip Kernel Resident
- program GPGPU_CSR_BASE_ADDRESS
- Disable Preemption
- adjust getDebuggerOption input param,
value passed has to be at least 2 bytes in size
change unit test behaviour accordingly
Change-Id: I4ec87d0e8dfcf02437fdeeffc5363314eea5dd07
- Rename misnamed test function
- Adjust 2 tests, so they use CSR size getters instead of hardcoded values
- Move getSizeRequiredPreambleCS() into CommandStreamReceiverHw class
- Improve PreambleHelper size estimating
Change-Id: I3f292d50e08f3d10d190c9f8722e1f0498481154
- This allows applications to force the N:1 aggregation by creating out
of order queue.
- That switches csr to N:1 submission model where commands from multiple
command streams may be aggregated.
- That forces scenarios returning an event to be aggregated as well.
Change-Id: I8fd8d7f88bb2665234ee90870133120b206710a8
-This is required to enable N:1 submission model.
-If heaps are coming from different command queues that always
mean that STATE_BASE_ADDRESS needs to be reloaded
-In order to not emit any non pipelined state in CSR, this change
moves the ownership of IndirectHeap to one centralized place which is
CommandStreamReceiver
-This way when there are submissions from multiple command queues then
they reuse the same heaps, therefore preventing SBA reload
Change-Id: I5caf5dc5cb05d7a2d8766883d9bc51c29062e980
- Internal allocations may now coexists with non internal on reusable list.
- Caller now specifies if internal allocation is needed.
- If criteria are not met , then allocation is not returned.
Change-Id: I7da3a4f944768b7c8a873e44fd47248f1d76bf9e
- program SIP_STATE when either MidThread preemption is enabled
or kernel debugging is active
- device creates correct sip based on preemption mode and
active kernel debugging
Change-Id: I3e43b66ad00d24c2389fa4fc766dd47044b6af80
- This is to improve battery usage while waiting in busy loop on CPU
- New Kmd Notify helper to maintain dynamic parameters
- Ask OS about battery status on longer waits
- Pick different timeout when using battery and optimization is disabled
Change-Id: I5f9c8c5a9c635652aac27c707f2b55933947a7fb
- Decission about timeout enabling and value moved out of CSR
- Timeout multiplier is no longer Linux specific
Change-Id: I6858fe2f811ef13802b95e0470e310210a9dea8b
- cpu virtual address was used instead of gpu va
- this caused incorrect behaviour of TBX server when
special heap allocator assigning GPU addresses was used
Change-Id: I2328cf2441be797311fd6a3c7b331b0fff79d4fc
Any CPU related updates such as clEnqueueMapBuffer or similar
need to trigger a re-dump of memory prior to the next clEnqueue call.
Change-Id: I7b31e559278e92ff55b6ebab8ef4190caef1ebc0
- Align SIP kernel & STATE_SIP programming.
- on Linux address may be non 0
- on Windows address is expected to be always 0
Change-Id: I385ed59ef652382f3f17d1afe55f6050d07ed1f4
- Switch to internal heap for kernel ISA allocations.
- remove IH from various functions
- remove IHState from CSR , IH is never dirty
- ISA is no longer copied on enqueue calls.
Change-Id: I0099cf2a9ebab6192ea03a74dd35f7da963fd5a5
-This is to make sure those functions are not called when gtpin is not used
-This preserves CPU instruction cache pollution.
-Our enqueue path needs to be as thin as possible, even with this small change
there is visible gain in ULT execution time.
Change-Id: I44cc2144754cda95ca1fe058184cd8a151b8d35c
- Measure time between wait calls. If delay is exeeded use QuickKmdSleep
- Kmd Notify helper functions
- Refactor overriding from debug variables
- Refactor Kmd Notify tests
Change-Id: I123c31f492d98fd304184f99ee0bf7d733d06f04
- KmdNotifyProperties struct for CapabilityTable that can be extended by
incoming KmdNotify related optimizations
- Quick KMD sleep optimization that is called from async events handler
- Optimization makes a taskCount check in busy loop with much smaller
delay than basic version of KMD Notify optimization
Change-Id: I60c851c59895f0cf9de1e1f21e755a8b4c2fe900
This commit introduces a software controlled HW Tag
in the configuration of AUB CSR in standalone mode
(i.e. with no execution on real HW).
Change-Id: Ic470957d58e6568b13dda3d61cb230498d8f2691
New debug option FlattenBatchBufferForAUBDump has been added. When set it
modifies AUB dump in such way that commands from main and chained batch
buffer are dumped as single allocation. Commands from chained batch buffer are
dumped directly after commands from main batch buffer without
MI_BATCH_BUFFER_START. This feature also requires ImmediateDispatch mode which
can be forced using debug option CsrDispatchMode = 1.
Change-Id: I730760791693a748e7f4e1463ce8e7af94287b93
Add macro to add all subdirectories
Add macro to create project source tree based on target sources
Small cleanup runtime/CMakeLists.txt
Change-Id: I9b99145c544f648c4c3fe7421752d0c5d9504edf
This commit eliminates redundancy in calling processResidency() for AUB CSR
twice in the HW CSR with AUB dump configuration.
Change-Id: Ib49c80fa9d81a495dfb7261ff76e0b9b1422e42d
- Microseconds offer better precision.
- Some workloads require threshold less then 1 millisecond to work
efficiently.
Change-Id: I1a565049340fb6eeebe5c0a61ededae9959daca8
This commit enables AUB dumps in scenarios with images with no host ptr
when resource lock is required to get CPU address and dump image contents.
Change-Id: I996efc5f520d0ac7b470870f7b4eeb9d2ef7b25b
-If out of order flag was disabled then pipe control was not having dc flush.
-This could led to a batch buffer that doesn't end with dc flush.
-This change adds differentiation between pipe controls that may be erased and
pipe controls that are used as a part of epilogue command
Change-Id: Ic9c970c75c89ff524a0e40506eff6dd097760145
-Do not flush dc for every command in batched mode
-Do that only in immediate mode
-For commands that needs DC do not noop pipe controls
-Ensure that each command buffer in batching mode ends with dc flush.
Change-Id: I3cd9d1831c19b69c66092687922f20df7e330245
- account for initial setting (when set mode was equal to initial(Disabled))
estimate size in cmdStreamCS, program MMIO
Change-Id: Ice218ae986583c8f3bab4f4f6979e38f03e30d7e
Milczarek, Slawomir