| Age | Commit message (Collapse) | Author |
|---|
|
* Generalises ConstCpuTensorHandle and inherited
classes by removing 'Cpu' from aliases.
* New renamed classes: ConstTensorHandle, TensorHandle,
ScopedTensorHandle, PassthroughTensorHandle,
ConstPassthroughTensorHandle.
Signed-off-by: James Conroy <james.conroy@arm.com>
Change-Id: I1824e0e134202735fb77051f20a7252f161dfe16
|
|
Make it easier for backends to traverse the subgraph during optimization
Change-Id: I140cb11f78bab5f19c801a5b55efffb38c63837f
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
* Replaced with armnn/utility/NumericCast.hpp
* Exclusions in TypeUtils.cpp and QuantizerVisitor.cpp
* Excluded as requires float implementation in NumericCast.hpp
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I5c4c60e7028e1a51bf9379457278d253fd37bc70
|
|
Signed-off-by: Matthew Bentham <Matthew.Bentham@arm.com>
Change-Id: Idb583f8de4470eefb47c90189cd3c90e74e0440a
|
|
Change-Id: I6003d2f82ca02d926dd95abee712337783eacfc7
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
|
|
The current algorithm in SubgraphViewSelector has a bug that can lead to
it producing subgraphs which have a dependency cycle (see the newly
added test case 'ValidMerge' for a repro). It also fails to merge
subgraphs in some cases where it could, which leads to smaller subgraphs.
In the case of FSRCNN, the NPU cannot support these smaller subgraphs and
so this is blocking us from supporting that network.
This commit changes the algorithm to fix the dependency bug and
also make it so that subgraphs are merged in the cases that were missed
before. It also adds some unit tests to cover cases that were problematic
before, and to extend coverage for the new algorithm.
The new algorithm has two downsides compared to the previous one:
1. Disjoint subgraphs are not merged. This can never lead to a failed
compilation by the NPU and so I believe this is less of an issue than
the previous algorithm's "missed merges". This could however lead to a
runtime performance loss in some cases as the NPU will be unable
to parallelise as many operations. There are some unit tests that cover
this which I have disabled.
2. The performance is worse. I have spent some time analysing this and
for a graph with ~1000 layers the new algorithm takes 20ms vs. the
old algorithm's 4ms (on my desktop PC). I believe the performance is
still within acceptable limits. I also compared inception V3 (which was
the network which caused performance issues with the original version of
the splitting algorithm) and this new algorithm has not regressed there
(200-300us in both cases).
Change-Id: I1dd64a779f272723621e04d203b5a2752a6af2ef
Signed-off-by: Robert Hughes <robert.hughes@arm.com>
|
|
!android-nn-driver:1210
Change-Id: I940b3b9e421c92bfd55ae996f7bc54ac077f2604
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
|
|
now works when substituting layers from another Graph
Signed-off-by: David Monahan <david.monahan@arm.com>
Change-Id: Iebd21a4975dd0ea1fc9d62708555dae4b1809623
|
|
Change-Id: I9b93bc81b97f3d89fa046ba001854f732040e63a
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
Change-Id: I45f81aa4ca8a964e423594fe271825c4a52b21f4
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
* Removed the reference to the parent graph in SubgraphView
* Removed the AddLayer method in SubgraphView
* Updated the code where necessary to adapt to the new changes in
SubgraphView
* Fixed a check in the CreatePreCompiledWorkloadTest test function
Change-Id: I4d3af87f11ec3cd8f18a21b250a2d295da56e1a0
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
|
|
Change-Id: Ie50aeccf053c20c3a01a75042bbc3acd824375af
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
|
