Age | Commit message (Collapse) | Author |
|
* Batch dimension is added to reduction operation.
- All the dimensions higher than the batch dimension are collapsed
so that the input and output tensors are always 3-4D.
- CL kernel is called once instead of being repeatedly called
to process each sliding window.
Resolves: COMPMID-6443
Signed-off-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Change-Id: Icd99939d52d3bb648f08537e5f52ef27e894061b
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/10456
Reviewed-by: Jakub Sujak <jakub.sujak@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
Code is formatted as per a revised clang format configuration
file(not part of this delivery). Version 14.0.6 is used.
Exclusion List:
- files with .cl extension
- files that are not strictly C/C++ (e.g. Android.bp, Sconscript ...)
And the following directories
- compute_kernel_writer/validation/
- tests/
- include/
- src/core/NEON/kernels/convolution/
- src/core/NEON/kernels/arm_gemm/
- src/core/NEON/kernels/arm_conv/
- data/
There will be a follow up for formatting of .cl files and the
files under tests/ and compute_kernel_writer/validation/.
Signed-off-by: Felix Thomasmathibalan <felixjohnny.thomasmathibalan@arm.com>
Change-Id: Ib7eb1fcf4e7537b9feaefcfc15098a804a3fde0a
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/10391
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
|
|
* Add public interfaces:
* OperatorGraph: Describe a workload that could contain fused kernels
* IWorkload: Generic interface for workloads built from OperatorGraph
* ClWorkload: OpenCL workloads built from OperatorGraph
* ClCompositeOperator: Runtime async operator to execute a ClWorkload
* DependencyGraph (will likely be deprecated in later iterations)
* Add example
* cl_fused_conv2d_elementwise_add.cpp to explain how to use the new
interfaces
* Add internal translation layer
* Refactor ClKernelBuildingAPI
* Remove non-tile based gemm native kernel component
* Minor interface changes
* Add integration tests
Resolves COMPMID-5161
Signed-off-by: SiCong Li <sicong.li@arm.com>
Change-Id: Ib987ed79289ab0bcbd3130d54f5793408d9f1240
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7510
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
|
|
When store the Tensor shape information, the size was clamped to 32bit, which cause the memory allocated is not big enough.
Signed-off-by: Sheri Zhang <sheri.zhang@arm.com>
Change-Id: I9f7dfcd5595a143b0ed4f6973e20bcd9d776b673
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/4331
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
|
|
preferred presentation
Change-Id: Ib7dcfcbb24b408999dfae366b9da396485aacf78
Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3525
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Tested-by: Georgios Pinitas <georgios.pinitas@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
If the total passed to split window did not fit
nicely into the selected Dimensions size then
the size of of the window return will vary considerably
for different ids
This change means that the amount of work each id
will vary by the minimal amount.
For example:
If total was 10 and a Dimensions size was 19
With then with the old code :
* id 0 - 8 would get back 1,
* id 9 would get 10
With the new code:
* id 0-8 would get 2
* id 9 would get 1
Change-Id: I6b74b81d7ddcea06db7aa9fbaf8cb47a659994c1
Signed-off-by: Joseph Dobson <joseph.dobson@arm.com>
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/c/VisualCompute/ComputeLibrary/+/224448
Tested-by: bsgcomp <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Comments-Addressed: bsgcomp <bsgcomp@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2961
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
|
|
Removed the following flags:
-Wno-format-nonliteral: This had a side effect on
Error.h that resulted in rewriting most of the macros. Since
I was at it I removed all the va_args in order to comply
with DCL50-CPP.
-Wno-deprecated-increment-bool
-Wno-vla-extension
-Wno-mismatched-tags
-Wno-redundant-move
Change-Id: I7c593854ecc3b7d595b8edcbd6a86d3c2563c6bd
Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com>
Reviewed-on: https://review.mlplatform.org/c/2069
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
|
|
Broadcast pixel-wise multiplication with 5D tensors is fixed
by adding information whether a dimension has been broadcasted
to compute correct start offset when adding 3D tensor argument.
The testcase that failed is added to the validation test suite.
Change-Id: I320876f507012c27b39daae1316f9b69138ed204
Signed-off-by: Sang-Hoon Park <sang-hoon.park@arm.com>
Reviewed-on: https://review.mlplatform.org/c/1994
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
|
|
-Remove FIXMEs and link to tickets.
-Pass large object by const reference.
-Implement copy assignment operator for Window.
Change-Id: I975223ac42ec424f153569a8c963f29e6b86ad29
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Reviewed-on: https://review.mlplatform.org/c/899
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
|
|
- WindowIterator: used to iterate over arbitrary positions of a window. (More flexible than execute_window_loop which only can iterate over entire dimensions)
- TensorAccessor: RSH's code uses pointers to specialised types and strides in element sizes, this helps interfacing with their code.
Change-Id: I8ded8758d345668804873409f949b8cec694d289
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/139082
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
|
|
- There used to be two problems with scale():
- The first argument of ceil_to_multiple was promoted to float
which broke the function (For example ceil_to_multiple( 24.0, 8 ) will return 31.
- "End - start" needs to be a multiple of step, not "end" (e.g start=1, end =5, step =4 is a valid dimension)
The reason it didn't break before is because Window::scale() was only
used on windows used by iterators, and therefore the "end" value is not
used in that context.
Change-Id: I1798db73014294ac82eed53c74eec3d4b8cb7d59
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/133967
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Pablo Tello <pablo.tello@arm.com>
|
|
Removed unnecessary collapse_if_possible() calls.
Change-Id: I6f3434bc4a26470c4de5bac4e3d90b4b019c2c9c
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/117993
Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com>
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
|
|
Also, added instrumentation to support generic tensor broadcasting for
NEON and CL backends.
Change-Id: I1bc5747a286e1a4b464c209067581e103d473b9a
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/114201
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Tested-by: Jenkins <bsgcomp@arm.com>
|
|
Change-Id: I6d97b649f1ebc289c9e6f8949e67740a6b3cbcb2
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/116636
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Pablo Tello <pablo.tello@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
Change-Id: I4e21ad98d029e360010c5927f04b716527700a00
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/88888
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
|
|
* Add tensorflow_data_extractor script.
* Incorporate 3rdparty npy reader libnpy.
* Port AlexNet system test to validation_new.
* Port LeNet5 system test to validation_new.
* Update 3rdparty/ and data/ submodules.
Change-Id: I156d060fe9185cd8db810b34bf524cbf5cb34f61
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/84914
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
|
|
Change-Id: Iebb50a88d017445b6b37a86563ebd4abd86c5cf5
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/86788
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
Change-Id: I5943235aff1bb6440e3ab08e818d53aa5d94143a
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/80349
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
|
|
Change-Id: I32f7b84daa560e460b77216add529c8fa8b327ae
|