• H
    [Core][XPU] Add XPU op kernels (#3274) · 2b80bab6
    hong19860320 提交于
    * [LITE][XPU] bind xpu resnet50 kernels
    
    * [LITE][XPU] fuse resnet50 and encoder
    
    * [LITE][XPU] bind xpu bert kernels
    
    * [LITE][XPU] refine xpu_resnet_fuse_pass.cc
    
    * [LITE][XPU] add xpu stack kernel
    
    * [LITE][XPU] add xpu slice/tanh kernel
    
    * [LITE][XPU] refine resnet50 and encoder fusor
    
    * [LITE][XPU] split resnet50 and multi_encoder op from subgraph_op.h
    
    * [LITE][XPU] clean workspace
    
    * [LITE][XPU] add build script
    
    * [LITE][XPU] fix compilation errors
    
    * [LITE][XPU] fix kernel matmul
    
    * [LITE][XPU] fix kernel ewadd ewsub
    
    * [LITE][XPU] add xpu cast kernel
    
    * [LITE][XPU] fix kernel slice
    
    * [LITE][XPU] switch dev by LITE_XPU_DEV env
    
    * [LITE][XPU] eliminate useless cast op
    
    * [LITE][XPU] add PerThread Ops
    
    * [LITE][X86] add SequenceUnpad op and kernel
    
    * [LITE][XPU] add LITE_WITH_XTCL option
    
    * [LITE][X86] add SequenceConv kernel
    
    * [LITE][XPU] fix cmake dependency
    
    * [LITE][XPU] add xpu sigmoid kernel
    
    * [XPU] Remove the dependencies of framework.pb.h
    test=develop
    
    Change-Id: Icfb44efb0482a6369b365b5c09017765328fc10d
    
    * [XPU] Fix the precision of cast kernel
    test=develop
    
    Change-Id: Icb18be47d7ab490de9fb9c92eae1165f49dbf492
    
    * [Core] Fix the compiling error when build for the target that disable XPU
    test=develop
    
    Change-Id: I38ec53f222391d3bf06b70512e6c3ad1282e4683
    
    * [XPU] Add io_copy kernel for xpu<->arm
    test=develop
    
    Change-Id: Iec7ea066f040534285557f9948b73e6a1970aed7
    
    * fix
    test=develop
    
    Change-Id: I4db1c93df48e22afbba904ce6c3b0babd9fda4c3
    
    * fix target matching of type_target_cast_pass and remove the unnecessary registration of io_copy kernel
    test=develop
    
    Change-Id: I432c10c9d1064e778d43fd0d12d8cf0599252f7a
    
    * [X86] Add the keyword 'template' to avoid the compiling errors
    test=develop
    
    Change-Id: I015d5d323adafb3884029c8287ced66c90ad931e
    
    * Fix the build.sh for XPU and x86
    test=develop
    
    Change-Id: I7d9575243669ce02af69a8ddbd6421db31902bd6
    
    * [XPU] Add the keyword 'template' to avoid the compiling errors
    test=develop
    
    Change-Id: I46d0b3b6861286a73ee2999934b8e185e453e749
    
    * [XPU] Add XTCL compiling option in build.sh
    test=develop
    
    Change-Id: I8b3fd998ca5f898d5bd2e665646e3874b3b73c80
    
    * fix namespace conflicts, test=develop
    
    * [API][XPU] Move the XPU related APIs into CxxConfig
    test=develop
    
    Change-Id: I75ac35e8bae96bcb835683f413f01b9db45afbf9
    
    * [API][XPU] Remove the LITE_WITH_XPU in paddle_api.h
    test=develop
    
    Change-Id: Idbd64013bdf331ad876919511c1c349332d46f93
    
    * [API][XPU] Remove XPUSetWorkspaceL3SizePerThread and XPUSetDevPerThread
    test=develop
    
    Change-Id: I515958f56f8e129280bae61c923513cc91fb9728
    
    * [API][Core][XPU] Refine the test case and remove the necessary modifications
    test=develop
    
    Change-Id: I1e0e2957a2f9d5f4207b06c0bc98a5ab611fee56
    
    * [Core] Remove useless code
    test=develop
    
    Change-Id: I6293faa10424aea2836d09d85ddb6a30f7811678
    
    * [XPU] Refine the test cases
    test=develop
    
    Change-Id: I6818fc3addf1bca5b96a7d66ee99263242e3374f
    
    * [XPU] Remove useless scripts and code
    test=develop
    
    Change-Id: I965ba6712d3cf881d0038f0473fec27d4c1bc684
    
    * [XPU] Use InferShapeImpl in sequence_unpad, resnet50 and multi_encoder op
    test=develop
    
    Change-Id: I5375f524d36836a394d426b4b2bc9fb44be0b59c
    
    * test=develop
    
    Change-Id: I42ee68c8a5e891dd0f3e95d6cfbc498be7cf1519
    
    * test=develop
    
    Change-Id: If679e5aa73e1368e0ee5bd5f286d2e1b4c2f354e
    
    * [XPU] Add __xpu__ prefix to the op and graph pass name of resnet50 and multi_encoder
    test=develop
    
    Change-Id: Idb61c99b4b8429cb87665bfd6835ab4d7d263be2
    
    * [XPU] Fix and refine the xpu fuse pass
    test=develop
    
    Change-Id: If1c5b6788d994e2809c1a00d9384685a89440907
    
    * test=develop
    
    Change-Id: Icfa333e322fc4351700103692c46cfcb3d4f9a89
    
    * [XPU] Remove the dependency on xpu api for xpu fuse passes
    test=develop
    
    Change-Id: I6094b5536f58ae18bab068284b32f9bd10a2ab92
    
    * [XPU] Move unit tests from lite/api to lite/tests/api
    test=develop
    
    Change-Id: I7ba27abb23abeffb0c95fdbbefec7ac16cdbd250
    
    * test=develop
    
    Change-Id: I33230c84d6c4e61bf19f46668bae2baa3ef68794
    
    * [XPU] Refine code
    test=develop
    
    Change-Id: I37bc5b948b4927e44cd3ea2594ebe3fd7671be06
    
    * [XPU] Add env XPU_ENABLE_XTCL to enable xpu_subgraph_pass
    test=develop
    
    Change-Id: Ifb8e07e86f307f562adaca3ce792015a6f2a2204
    
    * [XPU] refine code
    test=develop
    
    Change-Id: I1380654b930d51ae704dbc0cd855464d9c3b5b79
    
    * [XPU] Refine code
    test=develop
    
    Change-Id: I73285c2718ccd3612490eb2635bef4fd608c9bde
    
    * [XPU] Add comments for the XPU APIs
    test=develop
    
    Change-Id: Ieb5015f37984f8869b90c4c625c5894bb26164fd
    Co-authored-by: Nmiaotianxiang <miaotianxiang@baidu.com>
    Co-authored-by: NShixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
    2b80bab6
context.h 13.3 KB