Age | Commit message (Collapse) | Author |
|
DoD:
- Implement NEON kernel for quantizing down the gemmlowp result. The
result should be scaled by a fixedpoint number
- Implement OpenCL kernel for quantizing down the gemmlowp result. The
result should be scaled by a fixedpoint number
- Add test for validating the result
Required for:
- Integration of GEMMLowp in Android NN
- Convolution quantized
- Fully connected quantized
Change-Id: Ia963d25d695471e963961fb49a5600e78374ac4f
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/110981
Tested-by: BSG Visual Compute Jenkins server to access repositories on http://mpd-gerrit.cambridge.arm.com <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
Change-Id: I73a11ef3ff7265abce196b128413f54623d33cae
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/111294
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Reviewed-by: Pablo Tello <pablo.tello@arm.com>
Tested-by: BSG Visual Compute Jenkins server to access repositories on http://mpd-gerrit.cambridge.arm.com <bsgcomp@arm.com>
|
|
Change-Id: I70e04d3a175ba366432ada98e9ca893c9f81b260
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/111094
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Tested-by: BSG Visual Compute Jenkins server to access repositories on http://mpd-gerrit.cambridge.arm.com <bsgcomp@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
-Changes way of clamping in the kernel side.
-Fills padding with quantized values
Change-Id: I94d17c341fd637fbb24390722162b551b62d16cb
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/111114
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Tested-by: BSG Visual Compute Jenkins server to access repositories on http://mpd-gerrit.cambridge.arm.com <bsgcomp@arm.com>
|
|
Change-Id: I480eb8ad55b632c7d75b1a89e952e77b0ebbeda5
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/111158
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Tested-by: BSG Visual Compute Jenkins server to access repositories on http://mpd-gerrit.cambridge.arm.com <bsgcomp@arm.com>
|
|
Change-Id: I4b5150476839649e6c3005a54f01e0788519bfb1
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/111101
Tested-by: BSG Visual Compute Jenkins server to access repositories on http://mpd-gerrit.cambridge.arm.com <bsgcomp@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
Reworked the interface of GemmLowp in order to make easy the integration
in Android NN
- Added support for different output stage
- Added validation for both matrix multiplication and output stage
- Added bounded relu support in the output stage
- Added in32_t bias support
- Added optimized path for vector by matrix case
This rework is required for:
- Convolution quantized
- Fully connected quantized
Change-Id: I512283d406099cf8c614dd89d0a97ed411143afc
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/110625
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Tested-by: BSG Visual Compute Jenkins server to access repositories on http://mpd-gerrit.cambridge.arm.com <bsgcomp@arm.com>
|
|
Change-Id: I6f51ffe6c324d9da500716b52c97c344f2a2a164
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/110486
Tested-by: BSG Visual Compute Jenkins server to access repositories on http://mpd-gerrit.cambridge.arm.com <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
|
|
from occurring when an output value cannot be expressed in the output space
Change-Id: I4045a44ee257a829f6cfe708dcbad37bb91c0ee4
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/110393
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Tested-by: BSG Visual Compute Jenkins server to access repositories on http://mpd-gerrit.cambridge.arm.com <bsgcomp@arm.com>
|
|
Change-Id: If1dcca724e5e5f5ab363ffc16b0ef8c943e0b657
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/110105
Tested-by: BSG Visual Compute Jenkins server to access repositories on http://mpd-gerrit.cambridge.arm.com <bsgcomp@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
Change-Id: Ie56ac88dff5ff339572cec562e8cd62dc7f0aa8b
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/109805
Tested-by: BSG Visual Compute Jenkins server to access repositories on http://mpd-gerrit.cambridge.arm.com <bsgcomp@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
CLDepthwiseConvolution3x3 kernel (#28)
Change-Id: I51bebe74e3814c1245812ad575fe7854d460674f
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/109864
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Tested-by: BSG Visual Compute Jenkins server to access repositories on http://mpd-gerrit.cambridge.arm.com <bsgcomp@arm.com>
|
|
Biases were incorrectly passed as uchar8 in asymmetric quantized
calculations while they should be in int32.
Change-Id: I461f5e4ef6eb44374c1094378a1bfe9ade5e247d
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/96244
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
Changes in CL and reference in terms of border handling.
Change-Id: I5bed95b1f4c308629d7113455dc8a55d74500bcd
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/95742
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
|
|
The new common code of compute shader is in file helpers_cs.h
Rewrite the direct_convolution1x1.cs and softmax_layer.cs to use the new common code.
It will also remove the dependence of the token pasting operator (##).
We'll remove the "##" support after we rewrite all of the compute shader code.
Change-Id: Icd8553ef6b61ad484a8507590ac8ed499bd47061
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/95455
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Reviewed-by: Frank Lei <frank.lei@arm.com>
(cherry picked from commit 0a4f83570d261f839d9866b68979efe8d7a95883)
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/95601
Reviewed-by: Jim He <jim.he@arm.com>
|
|
-Extracts calculations from the CL kernel core loop.
-Changes the access elements for CROSS_MAP to reduce the applied
redundant padding.
Change-Id: If41c3adddd977be9386fe34940d055c301ccbb91
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/95917
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
Rounds output result of average pooling uint8 to match AndroidNN
reference.
Change-Id: If739086bbc5d2f0776cadae5b2312744bd7ce588
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/95349
Reviewed-by: Robert Hughes <robert.hughes@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
|
|
Change-Id: Iad11ce70a8a0878a48e445a092035c49c926cece
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/94855
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
Last commit:
commit b25c5f68042b0c81bf611d59a1bb8535e1c42497
Author: Xinghang Zhou <xinghang.zhou@arm.com>
Date: Wed Oct 25 18:48:10 2017 +0800
Synced validation's tolerances of GCSoftmax from cl side
Change-Id: Ibe72054205c1c8721845d679a31af7ed0a7c5cf6
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/93283
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
|
|
Change-Id: Iebb01c9e3d87ed17fa7991e157cfd15d795a53f1
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/95281
Reviewed-by: Robert Hughes <robert.hughes@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
|
|
Change-Id: I32ba6afbac6694ffa053dd16f03a1b3d14627a19
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/94857
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
Change-Id: I2007af1ed9dcf68065cf412aa50f73a2025b31a6
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/94605
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
|
|
Change-Id: I84f7a1ce3658be0d3c91e65096467258af48f0b6
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/94341
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
Change-Id: I0f5396c8f32acc28914e2ff9fe953f977a3077b9
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/93405
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
|
|
Adds support for excluding the padding pixels from the average scaling
factor calculation.
Change-Id: Ia13fbfeae235aff564db74191613921848231a01
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/93715
Reviewed-by: Robert Hughes <robert.hughes@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
|
|
Change-Id: I3c39ecbd36f06d5376c35ed4eb38dd73533ef97e
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/93686
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
Initial value was set two times for QS type in the generic case in pooling_layer.cl
Change-Id: Iddaad0bb48852388cf5e92d764150404454ac46e
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/93238
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
|
|
Change-Id: Ibfe7b8c1172d10cbcae7971fe86b82090519d31d
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/92798
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
Reviewed-by: Jaroslaw Rzepecki <jaroslaw.rzepecki@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
Change-Id: Idd830cff054114123229c189e423b753b8064146
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/92623
Reviewed-by: Robert Hughes <robert.hughes@arm.com>
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
Change-Id: Ib76554adf00fb3c1943da634dc948089843f0e78
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/92439
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
Change-Id: I5c6c95091ae77dba96459c0640f9f6167a988c8c
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/91700
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
|
|
Change-Id: I21da48d2f40aa900301235eaced54b7eb644b0b2
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/91307
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
Added volatile to the for loop counter in direct_convolution1x1.cl, direct_convolution3x3.cl and direct_convolution5x5.cl
This fix seems to solve the problem on Samsung S8 about the mismatches and clEnqueueMapBuffer.
Change-Id: I51687ec94bb897af2698ceab1133c988821e4c4e
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/90601
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
|
|
Change-Id: If70bba00bb4451251cbc21058dfecff2c0d106de
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/89641
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
Change-Id: I685a68e7bc8d2cdff19851d839f244206b3d5790
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/89391
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
Change-Id: Icc6194a311af0e96978e6be2cc4c5da9d7fb0bcc
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/89493
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com>
Reviewed-by: Steven Niu <steven.niu@arm.com>
|
|
Change-Id: I4924ab1de17adc3b880a5cc22f2497abbc8e221b
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/85820
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
Reviewed-by: Steven Niu <steven.niu@arm.com>
|
|
Change-Id: If2c90f7352bff64abbf2faec7f33340e6873b5cd
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/89020
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
|
|
Change-Id: Ie17e3f14c428553d433da2a564e016bfac7749a9
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/88881
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com>
|
|
Change-Id: I43641fa672f5905ca62edd1f63fc93e0cf7ea382
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/85963
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
|
|
This patch also fix the scale kernel issue where it was calcuated the
scale factor inside the gpu but now in the CPU. The GPU and CPU gave
different result for simple float division operation
Change-Id: Ib6709cb6c41dcf4fc0fa4eb79e481430695bf40e
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/87266
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
Reviewed-by: Moritz Pflanzer <moritz.pflanzer@arm.com>
|
|
Change-Id: I115e48fe6ce5e281f3791aa5d80fdc754cdd2b5e
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/85082
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
|
|
CLFlattening for 3D tensor
Change-Id: Ifc7db1e4d4af322a4dcbfeb3e132e5c326596872
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/86618
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
|
|
CLNonLinearFilter 5x5 was reading out-of-bounds for cross and disk
masks. Makes sure that read is in bounds and elements are shifted after.
Change-Id: I57a611e24cc9cadd50a36881e408a5a0d4ea5a3d
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/88056
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
Reviewed-by: Moritz Pflanzer <moritz.pflanzer@arm.com>
|
|
Change-Id: I11b39c2ceca26ade73822e29a384ef866ae05729
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/87707
Reviewed-by: Pablo Tello <pablo.tello@arm.com>
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
|
|
Change-Id: Id002e23a2ac48af3d245416dc6411d9a04a1e513
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/81827
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
|
|
- Fixed bug in CLDirectConvolution3x3
Change-Id: Iaf34ef44f0b7bc02e66f3eb4452ff7a90ef83523
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/86725
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Reviewed-by: Moritz Pflanzer <moritz.pflanzer@arm.com>
|
|
* Fix ROIPooling in NEON, CL and Reference.
Change-Id: Id5066625e5073e0bfebe69391f7941e993003296
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/87435
Reviewed-by: Moritz Pflanzer <moritz.pflanzer@arm.com>
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
Change-Id: I7b16216ac59c899a33942bf17757b54535256d7a
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/86172
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|
|
and validation tests (NEON and CL) for Scale
Change-Id: I056fa3588b807a97cacf0b8afaec56e37ffc92af
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/83872
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
|