aboutsummaryrefslogtreecommitdiff
path: root/src/core/CL
AgeCommit message (Collapse)Author
2019-03-29COMPMID-1995: Removed layout checks from Reduction opsPablo Tello
Change-Id: Icd8d153da63c53c51d3a2e3ea6bc7de5938934f2 Signed-off-by: Pablo Tello <pablo.tello@arm.com> Reviewed-on: https://review.mlplatform.org/c/913 Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2019-03-29COMPMID-1958: Implements 1D FFT in OpenCL.Georgios Pinitas
Forward complex FFT implementation. Change-Id: Ia0ba8740072e5adb06f8ead462a47abc8b5dd125 Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Reviewed-on: https://review.mlplatform.org/c/904 Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2019-03-28COMPMID-1318: Implementing Winograd 7x7 NHWC on OpenCL -- Part IMichele Di Giorgio
Change-Id: I94c3c886718076c6eee09be37a074a4bb0e54809 Signed-off-by: giuros01 <giuseppe.rossini@arm.com> Reviewed-on: https://review.mlplatform.org/c/868 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2019-03-27COMPMID-1995: Minor code fixes.Georgios Pinitas
-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>
2019-03-26COMPMID-2077 Optimise CLL2NormalizeLayerKernelUsama Arif
Change-Id: If3866d90f84d62578b7e26f524fa4d7757a5970c Signed-off-by: Usama Arif <usama.arif@arm.com> Reviewed-on: https://review.mlplatform.org/c/906 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
2019-03-22COMPMID-2056: Remove data layout check in NECopyLayerKernel and ↵Gian Marco Iodice
CLCopyLayerKernel Change-Id: I231ed704badf08107dcce9ad55eb217a0b5b119a Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Reviewed-on: https://review.mlplatform.org/c/859 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Pablo Marquez <pablo.tello@arm.com> Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2019-03-20COMPMID-1932: Implement CLHeightConcatenateLayer.Pablo Tello
Change-Id: I244ff2352c3c9620148dab6475aee62b218b96ef Signed-off-by: Pablo Tello <pablo.tello@arm.com> Reviewed-on: https://review.mlplatform.org/c/871 Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
2019-03-20COMPMID-2043: Add support for "dummy threads" in CLGEMMReshapedGian Marco Iodice
Change-Id: I89403b97503fbb99f6a32f5d62b8c535ab26a7be Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Reviewed-on: https://review.mlplatform.org/c/877 Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2019-03-15COMPMID-1694: Fuse offset contribution with the output stage when we use ↵George Wort
NEGEMMLowpMatrixMultiplyCore Change-Id: Ic1a681e4cc03e1eba3bf8485d9cdb17b3e926047 Signed-off-by: giuros01 <giuseppe.rossini@arm.com> Reviewed-on: https://review.mlplatform.org/c/561 Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2019-03-14COMPMID-1936: Add support for QASYMM8 in CLQuantizeLayer.Usama Arif
Change-Id: I9aa1f1f1753bcdee6a74ec15b4fb366f823788b4 Signed-off-by: Usama Arif <usama.arif@arm.com> Reviewed-on: https://review.mlplatform.org/c/850 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2019-03-13COMPMID-1844: Implement CLCropGeorge Wort
Change-Id: I8822c37adc45960705dc3f32a53214795ba3cf39 Signed-off-by: George Wort <george.wort@arm.com> Reviewed-on: https://review.mlplatform.org/c/789 Reviewed-by: Manuel Bottini <manuel.bottini@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Pablo Marquez <pablo.tello@arm.com>
2019-03-13COMPMID-1740: Fuse batch normalization with Convolution Layer at graph levelgiuros01
Change-Id: I77ca51c2c72783cc26a099a6a9c3210cdbbe822d Signed-off-by: giuros01 <giuseppe.rossini@arm.com> Reviewed-on: https://review.mlplatform.org/c/797 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2019-03-12COMPMID-1964: Implement CLGEMMMatrixMultiplyReshapedOnlyRHS - Not transposedGian Marco Iodice
Change-Id: I6b7f7a406fcb8d64adb221a24d7983e11bcb391e Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Reviewed-on: https://review.mlplatform.org/c/846 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
2019-03-11COMPMID-1882: Improve memory coalescence when reshaping the weights for ↵Pablo Tello
CLDepthwiseConvolution Change-Id: Ib226fd3e7d2715847594eb5bafa46c938672cf9b Signed-off-by: giuros01 <giuseppe.rossini@arm.com> Reviewed-on: https://review.mlplatform.org/c/839 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2019-03-08COMPMID-1882: Improve memory coalescence when reshaping the weights for ↵Pablo Tello
CLDepthwiseConvolution Change-Id: I97788d9e349f37fcd818d588d668e2d5e22fd568 Signed-off-by: giuros01 <giuseppe.rossini@arm.com> Reviewed-on: https://review.mlplatform.org/c/818 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
2019-03-08COMPMID-2000: Implement CLGEMMMatrixMultiplyReshapedOnlyRHS - TransposedGian Marco Iodice
Change-Id: I364c7ec5a43ad391a73429489802b0e679ee0c6e Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Reviewed-on: https://review.mlplatform.org/c/732 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2019-03-05COMPMID-1937: Adds support for DequantizationLayer for NEON/CL.Georgios Pinitas
Change-Id: I4b73edd176a277294e0e42e642460bc61210778a Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Reviewed-on: https://review.mlplatform.org/c/744 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Giuseppe Rossini <giuseppe.rossini@arm.com>
2019-02-27COMPMID-1995: Fix output quantization CLDeptwiseConv3x3 when activation is fusedIsabella Gottardi
When quantization is fused in the optimazed Deptwise Convolution 3x3, we quatized twice the output. Change-Id: I1cae1f646045a456d6e2754917ddef0cda0679f4 Signed-off-by: Isabella Gottardi <isabella.gottardi@arm.com> Reviewed-on: https://review.mlplatform.org/c/796 Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2019-02-22COMPMID-1710: Add FP16 support checks.Georgios Pinitas
Change-Id: I6291847935996859ab245160714f9fbefb03b5be Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Reviewed-on: https://review.mlplatform.org/761 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
2019-02-18COMPMID-1999: Add support for GenerateProposals operator in CLManuel Bottini
Change-Id: Ie08a6874347085f96b00f25bdb605eee7d683c25 Signed-off-by: giuros01 <giuseppe.rossini@arm.com> Reviewed-on: https://review.mlplatform.org/719 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com>
2019-02-15COMPMID-1710: Add check on different input/output quantization info were not ↵Isabella Gottardi
supported Change-Id: Id64dab5e2de341316238506d4fb3ab82b992753d Signed-off-by: Isabella Gottardi <isabella.gottardi@arm.com> Reviewed-on: https://review.mlplatform.org/697 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2019-02-15COMPMID-1710: Fix CL logistic activation for QASYMM8Michele Di Giorgio
Logistic activation in QASYMM8 is performed in floating point and then converting back to QASYMM8. However, if input and output have different quantization information, a double conversion is done leading to loss in accuracy. This patch creates a special case kernel for logistic activation. Change-Id: Ia18ee0b2f84701674f88785bcd13753b50d64a08 Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-on: https://review.mlplatform.org/696 Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2019-02-15Revert "COMPMID-1329: Add support for GenerateProposals operator in CL"Giuseppe Rossini
This reverts commit cd96a26f67bfbb9b0efe6e0e2b229d0b46b4e3e6. Change-Id: I1d46f37095c94968ad4f3b781269adaa03e2e410 Signed-off-by: giuros01 <giuseppe.rossini@arm.com> Reviewed-on: https://review.mlplatform.org/706 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2019-02-13COMPMID-1996: Update documenation for doxgen 1.8.15Manuel Bottini
Change-Id: I763edb3dabf401459dbbf2512e415a6e1e258bfc Signed-off-by: Manuel Bottini <manuel.bottini@arm.com> Reviewed-on: https://review.mlplatform.org/681 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
2019-02-13COMPMID-1918: Different qinfos support in CLConcatLayerPablo Tello
Added support in CLDepthConcatenateLayerKernel and CLWidthConcatenateLayer for different quantization arguments both for the input and output. If input's quantization infos are not homogeneous the input values are requantized using the output's quantization info. Change-Id: Ib5446d0c6790c2fe6e7172e87e4f2833247436db Signed-off-by: Pablo Tello <pablo.tello@arm.com> Reviewed-on: https://review.mlplatform.org/650 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
2019-02-12COMPMID-1934: Doxygen online documentation errors on FirefoxManuel Bottini
Change-Id: I669d57380d95760399cd7fd28c58d0e636d706dd Signed-off-by: Manuel Bottini <manuel.bottini@arm.com> Reviewed-on: https://review.mlplatform.org/647 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Pablo Marquez <pablo.tello@arm.com>
2019-02-08COMPMID-1859: Avoid unnecessary padding in CLWidthConcatenate[2,4]TensorsKernelMichele Di Giorgio
Change-Id: I827f3fe0f013089ee930806c5273089a878435da Reviewed-on: https://review.mlplatform.org/438 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
2019-02-07COMPMID-1706: Fuse the bias addition within CLGEMMMichele Di Giorgio
Change-Id: I378f2023f4fa010f195f76716ac07aa86279bfae Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-on: https://review.mlplatform.org/280 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
2019-02-06COMPMID-1924: Validate quantization info in pooling layer.Georgios Pinitas
Validates if the quantization info of the input matches the ones of the output. If not an error is raised. Change-Id: I9406cf67ae31cc45b024d56078d52c61d29e4f8c Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Reviewed-on: https://review.mlplatform.org/630 Reviewed-by: Pablo Marquez <pablo.tello@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com>
2019-01-30COMPMID-1691: Optimize CLDepthwiseConvolutionKernel (QASYMM8/NHWC) for 3x3 ↵giuros01
kernels (stride=1 and stride=2) Change-Id: I7d0d2dc350feeb40d253d17f9ffd5051a8fb42ef Reviewed-on: https://review.mlplatform.org/511 Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2019-01-25COMPMID-1698: Implementing CLGEMMLowpMatrixMultiplyReshapedKernelGian Marco Iodice
Change-Id: Ia4db21b394a0b9235393202ce3c00b11cceb94ea Reviewed-on: https://review.mlplatform.org/568 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
2019-01-25COMPMID-1866: Revisit padding and window on CLDepthwiseConvolutionNHWCMichele Di Giorgio
Change-Id: I1fd20ebb5f3295722c833a599ea82798ceff6e01 Reviewed-on: https://review.mlplatform.org/471 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
2019-01-24COMPMID-1900: Nightly issue with GEMMReshapeLHSMatrixGian Marco Iodice
Change-Id: I01656785fe58e6157469f6c6e66bb7eec53380f1 Reviewed-on: https://review.mlplatform.org/563 Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2019-01-21COMPMID-1899: Fix NaN issue in CLGEMMMatrixMultiplyReshapedKernelGian Marco Iodice
Change-Id: Ide950b46c4d41de230c272c7044a03f4f9f237ed Reviewed-on: https://review.mlplatform.org/548 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Reviewed-by: Giuseppe Rossini <giuseppe.rossini@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2019-01-21COMPMID-1898: (Nightly) Many CLGEMM tests failgiuros01
Change-Id: Ie9086098acbbb2d561051f102700e64c9bea05b0 Reviewed-on: https://review.mlplatform.org/545 Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2019-01-21COMPMID-1727: CL: Implement Gather - support S32 indicesManuel Bottini
Change-Id: Ib0298dc75d25acf8db2262c0ab73ecaa6fec636c Reviewed-on: https://review.mlplatform.org/522 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2019-01-18COMPMID-1710: Fix address space issueGeorge Wort
Change-Id: I72ca4245b4732f304aa12e58cb0093773917cdf1 Reviewed-on: https://review.mlplatform.org/539 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Giuseppe Rossini <giuseppe.rossini@arm.com>
2019-01-17COMPMID-1652 CL Cleanup and add missing testsMichalis Spyrou
Change-Id: I359cc0fd0c3fa42ab10a770e59d58704403889b2 Reviewed-on: https://review.mlplatform.org/498 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-by: Isabella Gottardi <isabella.gottardi@arm.com>
2019-01-16COMPMID-1794: Add support for NHWC in CLROIAlignLayerGeorge Wort
Change-Id: If1df8f6c0549c986e607cbceb0977c80b2891b75 Reviewed-on: https://review.mlplatform.org/493 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Isabella Gottardi <isabella.gottardi@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
2019-01-16COMPMID-1710 Move some Util functions to core/UtilsMichalis Spyrou
Building with exceptions=0 was failing Change-Id: I6f264dc859dedc66d12d522652134508e18d5740 Reviewed-on: https://review.mlplatform.org/526 Reviewed-by: Isabella Gottardi <isabella.gottardi@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2019-01-15COMPMID-1886 : Enable CLTuner for CLScaleVidhya Sudhan Loganathan
Change-Id: If92dc7fc46accdef5e67f96a91a8428c18db2028 Reviewed-on: https://review.mlplatform.org/517 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2019-01-15COMPMID-1687: Optimize CLGEMMMatrixMultiplyKernel (part 1)Gian Marco Iodice
Extended CLGEMMMatrixMultiplyReshapedKernel to support more parameters Change-Id: I4a27f986e3fe2dd071a4ccba5cfa0565f3db39ad Reviewed-on: https://review.mlplatform.org/495 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
2019-01-14COMPMID-1758: NEON: Implement RangeManuel Bottini
Change-Id: I56dff9462b85760fbed6db43224cadb90d283810 Reviewed-on: https://review.mlplatform.org/472 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2019-01-14COMPMID-1724: CL Implement ProdManuel Bottini
Change-Id: I17e51f25064b53a8f7e13d6fcbecc14a192de103 Reviewed-on: https://review.mlplatform.org/387 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2019-01-14Issue COMPMID-1835: Remove CLGEMMInterleave4x4Kernel and replace with ↵giuros01
CLGEMMReshapeLHSMatrixKernel Change-Id: Id6a1bd78f9b1698b64a004e4adebc41002b15745 Reviewed-on: https://review.mlplatform.org/496 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
2019-01-11COMPMID-1677: Change ROIPooling layer interface to accept ROIs as tensorsManuel Bottini
Change-Id: If16b572a4d906187b77f32133a72a44316fa74e4 Reviewed-on: https://review.mlplatform.org/490 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2019-01-11COMPMID-1761: NEON: Implement PackIsabella Gottardi
Change-Id: Icc3392494b1e3361e8fd925da200827c494351b3 Reviewed-on: https://review.mlplatform.org/430 Reviewed-by: Manuel Bottini <manuel.bottini@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Giuseppe Rossini <giuseppe.rossini@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
2019-01-09COMPMID-1710: Collapse window in CLDepthConvertKernelGeorgios Pinitas
Change-Id: I16589a2b3beb18e20b56059fdabccc61e26e3944 Reviewed-on: https://review.mlplatform.org/481 Reviewed-by: Isabella Gottardi <isabella.gottardi@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2019-01-09COMPMID-1837 : Implement REPEAT utility macro on OpenCLVidhya Sudhan Loganathan
Change-Id: I2b0dbfe7d430a8d0f62eb906f0334b16cde9e45b Reviewed-on: https://review.mlplatform.org/457 Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2019-01-08Implementation of Permute CL kernel to handle all permutationsshubham
This patch will add a generic permute cl-kernel to handle all permutations available for tensors having rank upto 4. Change-Id: I50eb555d9d45d5ad5f7fa9b0a3862dd17551d458 Signed-off-by: shubham <shub98.gupta@samsung.com> Reviewed-on: https://review.mlplatform.org/449 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Manuel Bottini <manuel.bottini@arm.com> Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com>