With this commit events created on multi root device contexts will
synchronize using signaled TagNodes instead of using taskCounts.
Signed-off-by: Maciej Plewka <maciej.plewka@intel.com>
Related-To: NEO-7105
Confirm the allocations used in an appendMemoryCopy operation
belong to the same context as the list.
Related-To: LOCI-1996
Resolves: NEO-6162
Signed-off-by: Jaime Arteaga <jaime.a.arteaga.molina@intel.com>
Confirm the allocations used in an appendMemoryCopy operation
belong to the same context as the list.
Related-To: LOCI-1996
Resolves: NEO-6162
Signed-off-by: Jaime Arteaga <jaime.a.arteaga.molina@intel.com>
By default, cooperative dispatch is not supported
for platforms not supporting cooperative engine.
Signed-off-by: Filip Hazubski <filip.hazubski@intel.com>
Enable resolving dependencies by pipecontrol on same CSR, IOQ on DG2 by
default.
Related-To: NEO-7321
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
Flag ResolveDependenciesViaPipeControls now removes only same csr
dependencies. Still enables pipe controls.
Works through hwInfoConfig method isResolveDependenciesByPipeControlsSupported
Related-To: NEO-7321
Signed-off-by: Dominik Dabek <dominik.dabek@intel.com>
Add flag for forcing execution of kernels on single tile
Force cooperative kernels to use only single tile
Related-to: NEO-6729
Signed-off-by: Naklicki, Mateusz <mateusz.naklicki@intel.com>
set include path to third_party/aub_stream
rename third_party/aub_stream/headers -> third_party/aub_stream/aubstream
Signed-off-by: Mateusz Jablonski <mateusz.jablonski@intel.com>
Related-To: NEO-7361
Currently additional command buffer is
preallocated for all CSRs, even for those which
won't be used by application. This PR changes that
Signed-off-by: Szymon Morek <szymon.morek@intel.com>
PVC platform with no support for atomic operations on system memory
must always allocate buffers in local memory to avoid atomic access violation.
Note: the feature is being implemented under the new registry key
AllocateBuffersInLocalMemoryForMultiRootDeviceContexts (disabled by default)
Related-To: NEO-7092
Signed-off-by: Milczarek, Slawomir <slawomir.milczarek@intel.com>
- cases with null lws should only fail when computed
lws sizes result in too big number of workgroups
Related-To: NEO-6976
Signed-off-by: Mateusz Hoppe <mateusz.hoppe@intel.com>
This change replaces mechanism of patching global constants and
variables in kernel per relocation to patching them only once. This
would improve linking time performance for kernels with multiple global
symbols.
Signed-off-by: Luzynski, Sebastian Jozef <sebastian.jozef.luzynski@intel.com>
Removes usage of precompiled binaries in debug program tests.
Related-To: NEO-7383
Signed-off-by: Krystian Chmielewski <krystian.chmielewski@intel.com>
This change fixes problem with memory locality.
When calculating work group size do not take into account
work group sizes where there's bigger number of elements in
higher dimensions namely: Y>X or Z>Y.
Related-To: NEO-5719
Signed-off-by: Krystian Chmielewski <krystian.chmielewski@intel.com>
