diff options
Diffstat (limited to 'Android.bp')
| -rw-r--r-- | Android.bp | 27 |
1 files changed, 11 insertions, 16 deletions
diff --git a/Android.bp b/Android.bp index 2983e2e21..6cc85f192 100644 --- a/Android.bp +++ b/Android.bp @@ -172,6 +172,7 @@ cc_library_static { proprietary: true, local_include_dirs: ["build/android-arm64v8a/src/core", "build/android-arm64v8a/src/core/CL", + "compute_kernel_writer/include", "src/core/common", "src/core/helpers", "src/core/NEON/kernels/arm_gemm", @@ -323,14 +324,17 @@ cc_library_static { "src/core/NEON/kernels/arm_conv/pooling/pooling_u8.cpp", "src/core/NEON/kernels/arm_conv/pooling/pooling_u8q.cpp", "src/core/NEON/kernels/arm_gemm/gemm_bf16.cpp", + "src/core/NEON/kernels/arm_gemm/gemm_bf16bf16.cpp", "src/core/NEON/kernels/arm_gemm/gemm_fp16.cpp", "src/core/NEON/kernels/arm_gemm/gemm_fp32.cpp", "src/core/NEON/kernels/arm_gemm/gemm_int16.cpp", "src/core/NEON/kernels/arm_gemm/gemm_int8.cpp", "src/core/NEON/kernels/arm_gemm/gemm_qint8.cpp", "src/core/NEON/kernels/arm_gemm/gemm_quint8.cpp", + "src/core/NEON/kernels/arm_gemm/gemm_s8fp32.cpp", "src/core/NEON/kernels/arm_gemm/gemm_uint16.cpp", "src/core/NEON/kernels/arm_gemm/gemm_uint8.cpp", + "src/core/NEON/kernels/arm_gemm/interleave-8way.cpp", "src/core/NEON/kernels/arm_gemm/interleave_indirect-sve.cpp", "src/core/NEON/kernels/arm_gemm/interleave_indirect.cpp", "src/core/NEON/kernels/arm_gemm/mergeresults-fp16.cpp", @@ -621,7 +625,6 @@ cc_library_static { "src/dynamic_fusion/sketch/attributes/ReshapeAttributes.cpp", "src/dynamic_fusion/sketch/attributes/ResizeAttributes.cpp", "src/dynamic_fusion/sketch/attributes/SoftmaxAttributes.cpp", - "src/dynamic_fusion/sketch/gpu/GpuKernelArgument.cpp", "src/dynamic_fusion/sketch/gpu/GpuKernelComponentGraph.cpp", "src/dynamic_fusion/sketch/gpu/GpuKernelComponentGroup.cpp", "src/dynamic_fusion/sketch/gpu/GpuKernelComponentStream.cpp", @@ -634,8 +637,6 @@ cc_library_static { "src/dynamic_fusion/sketch/gpu/components/cl/ClComponentDepthwiseConv2d.cpp", "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/ClComponentMatMul.cpp", "src/dynamic_fusion/sketch/gpu/components/cl/ClComponentPool2d.cpp", "src/dynamic_fusion/sketch/gpu/components/cl/ClComponentReshape.cpp", @@ -657,19 +658,6 @@ cc_library_static { "src/dynamic_fusion/sketch/gpu/operators/GpuSub.cpp", "src/dynamic_fusion/sketch/gpu/operators/GpuTanh.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", - "src/dynamic_fusion/sketch/gpu/template_writer/cl/ClTemplateCast.cpp", - "src/dynamic_fusion/sketch/gpu/template_writer/cl/ClTemplateDepthwiseConv2d.cpp", - "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", - "src/dynamic_fusion/sketch/gpu/template_writer/cl/ClTemplateStore.cpp", - "src/dynamic_fusion/sketch/gpu/template_writer/cl/ClTemplateWriter.cpp", "src/gpu/cl/ClContext.cpp", "src/gpu/cl/ClKernelLibrary.cpp", "src/gpu/cl/ClQueue.cpp", @@ -720,6 +708,7 @@ cc_library_static { "src/gpu/cl/kernels/ClQuantizeKernel.cpp", "src/gpu/cl/kernels/ClReshapeKernel.cpp", "src/gpu/cl/kernels/ClScaleKernel.cpp", + "src/gpu/cl/kernels/ClScatterKernel.cpp", "src/gpu/cl/kernels/ClSoftmaxKernel.cpp", "src/gpu/cl/kernels/ClTransposeKernel.cpp", "src/gpu/cl/kernels/ClTransposedConvolutionKernel.cpp", @@ -771,6 +760,7 @@ cc_library_static { "src/gpu/cl/operators/ClQuantize.cpp", "src/gpu/cl/operators/ClReshape.cpp", "src/gpu/cl/operators/ClScale.cpp", + "src/gpu/cl/operators/ClScatter.cpp", "src/gpu/cl/operators/ClSoftmax.cpp", "src/gpu/cl/operators/ClSub.cpp", "src/gpu/cl/operators/ClTranspose.cpp", @@ -869,6 +859,7 @@ cc_library_static { "src/runtime/CL/functions/CLReshapeLayer.cpp", "src/runtime/CL/functions/CLReverse.cpp", "src/runtime/CL/functions/CLScale.cpp", + "src/runtime/CL/functions/CLScatter.cpp", "src/runtime/CL/functions/CLSelect.cpp", "src/runtime/CL/functions/CLSlice.cpp", "src/runtime/CL/functions/CLSoftmaxLayer.cpp", @@ -1224,6 +1215,7 @@ cc_library_static { "src/core/NEON/kernels/arm_gemm/kernels/a64_ffhybrid_fp16_mla_6x32/generic.cpp", "src/core/NEON/kernels/arm_gemm/kernels/a64_ffhybrid_fp32_mla_6x16/generic.cpp", "src/core/NEON/kernels/arm_gemm/kernels/a64_ffhybrid_fp32bf16fp32_mmla_4x24/generic.cpp", + "src/core/NEON/kernels/arm_gemm/kernels/a64_ffhybrid_fp32bf16fp32_mmla_6x16/generic.cpp", "src/core/NEON/kernels/arm_gemm/kernels/a64_ffinterleaved_bf16fp32_dot_8x12/generic.cpp", "src/core/NEON/kernels/arm_gemm/kernels/a64_ffinterleaved_bf16fp32_mmla_8x12/generic.cpp", "src/core/NEON/kernels/arm_gemm/kernels/a64_ffinterleaved_fp16_mla_8x24/generic.cpp", @@ -1311,6 +1303,9 @@ cc_library_static { "src/core/NEON/kernels/arm_gemm/kernels/sme2_interleaved_nomerge_s8q_mopa_1VLx4VL/generic.cpp", "src/core/NEON/kernels/arm_gemm/kernels/sme2_interleaved_nomerge_s8q_mopa_2VLx2VL/generic.cpp", "src/core/NEON/kernels/arm_gemm/kernels/sme2_interleaved_nomerge_s8q_mopa_4VLx1VL/generic.cpp", + "src/core/NEON/kernels/arm_gemm/kernels/sme2_interleaved_nomerge_s8qfp32_mopa_1VLx4VL/generic.cpp", + "src/core/NEON/kernels/arm_gemm/kernels/sme2_interleaved_nomerge_s8qfp32_mopa_2VLx2VL/generic.cpp", + "src/core/NEON/kernels/arm_gemm/kernels/sme2_interleaved_nomerge_s8qfp32_mopa_4VLx1VL/generic.cpp", "src/core/NEON/kernels/arm_gemm/kernels/sme2_interleaved_nomerge_s8s32_mopa_1VLx4VL/generic.cpp", "src/core/NEON/kernels/arm_gemm/kernels/sme2_interleaved_nomerge_s8s32_mopa_2VLx2VL/generic.cpp", "src/core/NEON/kernels/arm_gemm/kernels/sme2_interleaved_nomerge_s8s32_mopa_4VLx1VL/generic.cpp", |