Another step towards cleaner callers of
StateBaseAddressHelper<>::programStateBaseAddress.
Export programming state base address into a separate function to
improve code reuse and reduce copy-pasted fragments, which make code
modifications or maintenance more and more difficult over time. Use
specialization for gen-specific variations.
Related-To: NEO-6774
Signed-off-by: Maciej Bielski <maciej.bielski@intel.com>
- Do not iterate when all devices are parsed
- Early continue if given device not present in context
200ns (+10%) in below scenario from compute-benchmarks
ZE_AFFINITY_MASK=0.0 PrintDebugSettings=1 ./api_overhead_benchmark_l0
--test=ExecuteCommandListImmediate --api=l0 --UseProfiling=0
--CallsCount=1 --MeasureCompletionTime=0 --useBarrierSynchronization=0
--KernelExecutionTime=1 --iterations=1000
Signed-off-by: Michal Mrozek <michal.mrozek@intel.com>
This change prepares infrastructure for pipeline select handling in
command lists and queues by optimization of number of commands dispatched.
State is synchronized between flush-task immediate and regular command lists.
Next step is to add optimization itself which disables legacy hw command
dispatch algorithm.
This change corrects ADL-P support for systolic mode changes.
Related-To: NEO-5019
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
With this change, module's data sections will be allocated in USM device pool
instead of SVM or USM shared.
Signed-off-by: Sebastian Luzynski <sebastian.jozef.luzynski@intel.com>
Adding new interface to cooperate with hw context state
Simplify programming removing unnecessary functions
Code optimization that stop using expensive call and instead
stores configuration parameter
Related-To: NEO-5019
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
So far captureStateBaseAddress() was a wrapper around
programSbaTrackingCommands(), doing an additional checking before
calling the latter. The checking is apparently no longer relevant, so
unify the distinction and remove part of the code which is no longer
needed.
In practice, keep the captureStateBaseAddress() while moving the body of
programSbaTrackingCommands() into it. This imposes lower diff-impact
onto the class hierarchy. Remove the second function. Simplify the
caller which had to distinct these two functions previously.
Related-To: NEO-6774
Signed-off-by: Maciej Bielski <maciej.bielski@intel.com>
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
Related-To: NEO-6075
Binding table entry count was zeroed even when
ForceBtpPrefetchMode debug flag was enabled
Fixes found out while working on the StateBaseAddress adaptation to
StreamProperties. Removing unused parameters, improving code reuse
(further improvements come with following commits).
Related-To: NEO-6774
Signed-off-by: Maciej Bielski <maciej.bielski@intel.com>
When pointer type differs from the type, which was obtained
via new[] operator, then delete[] is undefined behavior.
Signed-off-by: Patryk Wrobel <patryk.wrobel@intel.com>
Signed-off-by: Kamil Kopryk <kamil.kopryk@intel.com>
Related-To: NEO-7156
Additional pipeline select is required only on specific
gen12lp products. That check was missing only in cmdstream size
estimation path, hence we had an overestimation.
Automatically add "-s" (source path) option if -g flag is present.
This applies only to non-spirv input.
Related-To: NEO-7285
Signed-off-by: Kacper Nowak <kacper.nowak@intel.com>
This commits add support for relocating
symbols with local binding and of functional type
(STB_LOCAL, STT_FUNC).
Related-To: NEO-7299
Signed-off-by: Kacper Nowak <kacper.nowak@intel.com>
It was only needed for LOAD_BALANCED scenarios, so with recent disabling
of this feature in KMD, it is no longer required.
Signed-off-by: Michal Mrozek <michal.mrozek@intel.com>
With compiler LSC WAs this gives better performance.
If debugger is active, policy will not be changed ie.
will be WBP.
Related-To: NEO-7003
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
This commit adds parsing of "user_attributes" section of zeInfo
containing kernel's language attributes.
Signed-off-by: Krystian Chmielewski <krystian.chmielewski@intel.com>
Generated instructions writing to printf buffer require destination
address to be DWORD aligned. Because of that values of type BYTE (1B)
and SHORT (2B) need to be written as 4B value.
This change adds support for this. When trying to read value of type
BYTE or SHORT four bytes are actually read to be aligned with compiler
implementation.
Signed-off-by: Krystian Chmielewski <krystian.chmielewski@intel.com>
This change gives fine grain control over front end configuration for each
kernel.
As it gives possible to inject FE command in command queue and return to exact
place in command list.
Programming commands in queue makes patching commands in command lists
not needed as that operation is costly.
And it allows to program context information for each command list too.
Related-To: NEO-5019
Signed-off-by: Zbigniew Zdanowicz <zbigniew.zdanowicz@intel.com>
