Age | Commit message (Collapse) | Author |
|
Change-Id: I9dd26b80025ea3a4c66f5f0bf41b7a98dd0d3aa4
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/152549
Tested-by: bsgcomp <bsgcomp@arm.com>
Reviewed-by: Pablo Tello <pablo.tello@arm.com>
|
|
Change-Id: I4920e43059a713126f15493f38fe50f07d0a8c7f
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/151087
Tested-by: bsgcomp <bsgcomp@arm.com>
Reviewed-by: Pablo Tello <pablo.tello@arm.com>
|
|
Change-Id: I637add70310d2da4d82b236a6352af9d33be17a1
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/149706
Reviewed-by: Isabella Gottardi <isabella.gottardi@arm.com>
Reviewed-by: Michele DiGiorgio <michele.digiorgio@arm.com>
Tested-by: bsgcomp <bsgcomp@arm.com>
|
|
Change-Id: I4d06eca9404ea6d3df9d0ca52f5d6f5421ab7116
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/150117
Tested-by: bsgcomp <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
|
|
Change-Id: I47033fa70881fd32b13266adb6ccbf10c202aabc
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/150344
Tested-by: bsgcomp <bsgcomp@arm.com>
Reviewed-by: Pablo Tello <pablo.tello@arm.com>
|
|
Change-Id: I82d95c4f1c5fed13b213a2591cc2b4e0d0e02a54
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/149676
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Reviewed-by: Pablo Tello <pablo.tello@arm.com>
Tested-by: bsgcomp <bsgcomp@arm.com>
|
|
Change-Id: Ice28996959dc666fff5e8ae486c1ff8093db083f
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/148367
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Tested-by: bsgcomp <bsgcomp@arm.com>
|
|
Change-Id: I61e7d39d09a9936b1128ec04038fa2d8dfe6a2c8
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/149211
Reviewed-by: Isabella Gottardi <isabella.gottardi@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Tested-by: bsgcomp <bsgcomp@arm.com>
|
|
Restore window step across width to 4 for FP32 instead of the whole row
as the kernel code was inconsistent with this decision.
Change-Id: I7c4dcdf960b8cbc970a36fa1df39df2c6f000c86
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/148908
Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Tested-by: bsgcomp <bsgcomp@arm.com>
|
|
Change-Id: I1f55508af6f220e5f41df7b56daffb4761ed0591
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/148253
Tested-by: bsgcomp <bsgcomp@arm.com>
Reviewed-by: Isabella Gottardi <isabella.gottardi@arm.com>
|
|
Change-Id: I780970f317b979b3230e2b471ac01df7fda9ee14
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/148168
Tested-by: bsgcomp <bsgcomp@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
Change-Id: I5f868091cae7bd86eeeb7216d44f32c190c5a604
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/147804
Tested-by: bsgcomp <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
|
|
Change-Id: I05d21f9a92013ecfd1128d12cf1561cfd6e5c5e9
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/147983
Tested-by: bsgcomp <bsgcomp@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
The 32bit version of AlexNet seems to require ~1.4 GB of memory to run (got this
result via valgrind's massif tool).
The problem is a miscalculation of the shape of the _transformed_b tensor, which
should not be multiplied by the size of the data type, but rather represent only
the size of the dimensions.
Change-Id: I55dfb538b31772afc4ce0ce0ccd31fdeb1585cfb
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/147666
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Tested-by: Jenkins <bsgcomp@arm.com>
|
|
Refactored the validate method to make it easier to maintain in the future when
adding support for new kernels sizes
Change-Id: I12d9fe7af15ceb0e655cef61ca94407558fb29e8
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/146713
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
Change-Id: I88793688e4175d409a022db1c2b6db6783d7feeb
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/147682
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Tested-by: Jenkins <bsgcomp@arm.com>
|
|
Change-Id: I50c13b5808f3cceec36b92e7afc027f47ebbdea4
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/147369
Reviewed-by: Michele DiGiorgio <michele.digiorgio@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Tested-by: Jenkins <bsgcomp@arm.com>
|
|
Change-Id: I1fe346a360b2d9ddd8576a1d24ff66e78c95c1f2
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/147049
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
Also extended tests on NEON
Change-Id: Icb0eced534e904ef807972dd3a31988f501bb02e
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/147095
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Tested-by: Jenkins <bsgcomp@arm.com>
|
|
Removes FP16 from HarrisCorners and CannyEdge.
Change-Id: I5e4f9205fdbe4de85f04f55ecf1568c837e56cc0
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/146247
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele DiGiorgio <michele.digiorgio@arm.com>
|
|
Change-Id: I44369b4a716767163e2233b7d87bff300c523383
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/146314
Reviewed-by: Pablo Tello <pablo.tello@arm.com>
Tested-by: Jenkins <bsgcomp@arm.com>
|
|
Refactors the transforms to make use of partial specialization.
Change-Id: Idff68d22817a00a7ee9eef5351a5a9fd33147540
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/146635
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
|
|
COMPMID-1515: Add FP16 support to NEFloor and CLFloor
Change-Id: Ib63a62c7681056ee13be99ce081b4d3949da4217
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/146547
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Pablo Tello <pablo.tello@arm.com>
|
|
Change-Id: I6fe198881230e49864c841a3b2366ccf2a9247f9
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/145210
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
|
|
Change-Id: I68f65b6dea7889d71b4a10021f59e6f0ab82903b
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/145590
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
Change-Id: I228e2503eb40c12869fbd7e834ac1309aa613480
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/145878
Reviewed-by: Giorgio Arena <giorgio.arena@arm.com>
Tested-by: Jenkins <bsgcomp@arm.com>
|
|
+ validate() function
Change-Id: I12e4696a454744f6d493ab3a53520d3acf3a1a26
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/145719
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
|
|
Change-Id: Idc3b15f2421858bbf726cd9da82487ff2e1f2910
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/145335
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
The output of NECol2Im is already auto-initialized.
This patch is about calling ShapeCalculator instead of computing the shape inside the kernel, adding validate_and_configure_window, and standardize the way convolved dims are passed (now NEON uses Size2D, while CL passes a pair of uint values: using Size2D for both implementations)
Change-Id: I795696e1b6532f57847c3186c1b532c09f5a25da
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/145345
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele DiGiorgio <michele.digiorgio@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
|
|
Change-Id: Ib85e5cc203d6c71f83c6021c776ccdc0eef82acf
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/145165
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
Change-Id: I99ebae61024a7bce9d17292a02c28626ae6c29d5
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/144872
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
|
|
Change-Id: I1dd6df9bd4a96cb7cbacce939a89c3a7ccee71c8
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/145397
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
On GEMM we had accuracy issue
On Magnitude we have disabled the fp16 acceleration since we do not have feature parity with CL
and this function is not used for ML
Change-Id: Iaebe3bbbd2a9f45db0c714aa5ebaf48eb0b65741
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/145467
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
GCC (>=8) yields warning w/ -Wignored-qualifers (enabled by -Wextra) on
such usage.
Change-Id: Ib3284b60cec0ec4faf8c6e6c1e2980cbf5731973
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/145384
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
|
|
Implemented vinvq_f16 with fp32 data type in order to avoid accuracy issue.
Change-Id: Ibfffd12e4a941c1388a982fc7bbe3e1832351feb
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/145416
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Tested-by: Jenkins <bsgcomp@arm.com>
|
|
Change-Id: Icaf45cad826bb0966a6c663ecb7e828f5fe5e5db
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/145336
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Tested-by: Jenkins <bsgcomp@arm.com>
|
|
- Fixed GEMMConvolutionLayer test. The issue was related to the tolerance
- Fixed DirectConvolutioNLayer test. The issue was in the convolver_3x3
Change-Id: I9d5b906d7e5e32a0a34300d529d6edb804ac1c4e
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/145377
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
Simulates exp function in FP32
Change-Id: Ieffceeab64fda6f466f212b56f794cc44d477afa
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/145367
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
Simulates Logistic, Tanh and SoftRelu in FP32
Change-Id: I9950f7636b8ff2f3e054937e5ef414e45dfe06f5
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/145357
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
Change-Id: I1e206574dac6433218db6e138adb7bf5f66a536d
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/145222
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
Change-Id: I80f3aaadc8cae8c9ca1a5a239e79bda302b89bd8
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/144813
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
|
|
Change-Id: I183e4b7081bf12de3546293a00da68b4f4a0dd5e
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/143987
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Tested-by: Jenkins <bsgcomp@arm.com>
|
|
Change-Id: I7cd15e9115b5c6f544005528d69061751286be11
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/143708
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele DiGiorgio <michele.digiorgio@arm.com>
|
|
Change-Id: I57bbfb79090fd57c57fdedd24a26736b272ea2f5
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/143893
Reviewed-by: Giorgio Arena <giorgio.arena@arm.com>
Tested-by: Jenkins <bsgcomp@arm.com>
|
|
Change-Id: I4afb19751520a90fee27fb49b775cd10e92a94f5
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/140476
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Tested-by: Jenkins <bsgcomp@arm.com>
|
|
This changes help to prevent errors like passing a matrix
with less elements than required into the warp functions.
Change-Id: I863f933a5e0568258717cffed3a20788d3d03083
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/143044
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
This patch includes:
- Im2Col optimizations for NHWC using a new data layout
- Refactoring of CLIm2ColKernel adding validation method and auto-init
- Removed im2col_reduced from CLIm2ColKernel and created a new kernel CLFlattenLayerKernel
Change-Id: I1620640b6796baa268324b33ae92cdd8de53e27c
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/141241
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Giorgio Arena <giorgio.arena@arm.com>
|
|
- Ported PrepareB kernel from gemm_interleave
- Ported TransformA feature from gemm_interleave
- Allocate reshaped a and b buffers
- Added memory_manager / memory_group
- MatrixMultiply kernel
- Interleave kernels execution.
- Fixed a few bugs: all nightly Convolution tests passing for threads=1
and threads=4
- Added Doxygen documentations and comments in the code
- Added support for all data types supported
Change-Id: Iffa1c09fda0bb9c61213bb83524d5a48e7ecb03c
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/141281
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
|
|
Change-Id: I55f0018ac7214775ebbca63f58a3bf5c93732fec
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/142632
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
Apply offsets and strides to winograd transform functions in NEON.
Change-Id: Ia4f44d22244203a5f9d93d2fed73570396b0d28c
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/141803
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|