diff options
| author | Ramy Elgammal <ramelg01@e129512.arm.com> | 2023-01-11 18:48:04 +0000 |
|---|---|---|
| committer | Ramy Elgammal <ramy.elgammal@arm.com> | 2023-01-25 10:24:23 +0000 |
| commit | 002e6530f6218b00a28aef9be8b21efb08cf3602 (patch) | |
| tree | f3e2f9d064b985ffe283512825b34cdd59f29f50 /Android.bp | |
| parent | cc2877368d5e15d9ea89d31c84ec651fc0fffd13 (diff) | |
| download | ComputeLibrary-002e6530f6218b00a28aef9be8b21efb08cf3602.tar.gz | |
Implement dynamic fusion softmax operator
- Return aux tensorInfo by get_aux_tensors() at runtime to init the aux
tensor with the right size.
- Keep softmax unfusable for this commit
- Hence, added Tensor3D to template writer arguments declaration, for sake of
keeping dynamic fusion softmax componenets' kernels matching their cl
counterparts.
Resolves: COMPMID-5523
Change-Id: I667f39545db925f667036ef448302c79a0330373
Signed-off-by: Ramy Elgammal <ramy.elgammal@arm.com>
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/c/VisualCompute/ComputeLibrary/+/483924
Tested-by: bsgcomp <bsgcomp@arm.com>
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Comments-Addressed: bsgcomp <bsgcomp@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8986
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Jakub Sujak <jakub.sujak@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'Android.bp')
| -rw-r--r-- | Android.bp | 3 |
1 files changed, 3 insertions, 0 deletions
diff --git a/Android.bp b/Android.bp index f426f2fbc2..34f722f6fe 100644 --- a/Android.bp +++ b/Android.bp @@ -609,6 +609,7 @@ cc_library_static { "src/dynamic_fusion/sketch/gpu/components/cl/ClComponentDirectConv2d.cpp", "src/dynamic_fusion/sketch/gpu/components/cl/ClComponentElementwiseBinary.cpp", "src/dynamic_fusion/sketch/gpu/components/cl/ClComponentLogits1DMaxShiftExpSum.cpp", + "src/dynamic_fusion/sketch/gpu/components/cl/ClComponentLogits1DNorm.cpp", "src/dynamic_fusion/sketch/gpu/components/cl/ClComponentPool2d.cpp", "src/dynamic_fusion/sketch/gpu/components/cl/ClComponentReshape.cpp", "src/dynamic_fusion/sketch/gpu/components/cl/ClComponentResize.cpp", @@ -622,6 +623,7 @@ cc_library_static { "src/dynamic_fusion/sketch/gpu/operators/GpuPool2d.cpp", "src/dynamic_fusion/sketch/gpu/operators/GpuReshape.cpp", "src/dynamic_fusion/sketch/gpu/operators/GpuResize.cpp", + "src/dynamic_fusion/sketch/gpu/operators/GpuSoftmax.cpp", "src/dynamic_fusion/sketch/gpu/operators/internal/GpuElementwiseBinaryCommon.cpp", "src/dynamic_fusion/sketch/gpu/template_writer/GpuKernelVariableTable.cpp", "src/dynamic_fusion/sketch/gpu/template_writer/cl/ClTemplateActivation.cpp", @@ -630,6 +632,7 @@ cc_library_static { "src/dynamic_fusion/sketch/gpu/template_writer/cl/ClTemplateDirectConv2d.cpp", "src/dynamic_fusion/sketch/gpu/template_writer/cl/ClTemplateElementwiseBinary.cpp", "src/dynamic_fusion/sketch/gpu/template_writer/cl/ClTemplateLogits1DMaxShiftExpSum.cpp", + "src/dynamic_fusion/sketch/gpu/template_writer/cl/ClTemplateLogits1DNorm.cpp", "src/dynamic_fusion/sketch/gpu/template_writer/cl/ClTemplatePool2d.cpp", "src/dynamic_fusion/sketch/gpu/template_writer/cl/ClTemplateReshape.cpp", "src/dynamic_fusion/sketch/gpu/template_writer/cl/ClTemplateResize.cpp", |