add gemv gemm int8 neon impl (no test)

add empty conv kernel

paddle/fluid/lite/arm/math/CMakeLists.txt

@@ -35,6 +35,8 @@ cc_library(math_arm SRCS
     split.cc
     activation.cc
     dropout.cc
+    gemm_prepacked_int8.cc
+    gemv_arm_int8.cc
     DEPS ${lite_kernel_deps} eigen3 framework_proto_lite)
   # TODO(TJ): fix me do not deps proto
  

paddle/fluid/lite/core/target_wrapper.h

@@ -38,6 +38,7 @@ enum class PrecisionType : int {
   kUnk = 0,
   kFloat,
   kInt8,
+  kInt32,
   kAny,  // any precision
   NUM,   // number of fields.
 };
@@ -48,6 +49,17 @@ enum class DataLayoutType : int {
   NUM,   // number of fields.
 };
 
+static size_t PrecisionTypeLength(PrecisionType type) {
+  switch (type) {
+    case PrecisionType::kFloat:
+      return 4;
+    case PrecisionType::kInt8:
+      return 1;
+    default:
+      return 4;
+  }
+}
+
 // Some helper macro to get a specific TargetType.
 #define TARGET(item__) paddle::lite::TargetType::item__
 // Some helper macro to get a specific PrecisionType.

paddle/fluid/lite/kernels/arm/conv_compute.cc

@@ -94,6 +94,9 @@ void ConvCompute::Run() {
   // }
 }
 
+void ConvComputeInt8::PrepareForRun() {}
+void ConvComputeInt8::Run() {}
+
 }  // namespace arm
 }  // namespace kernels
 }  // namespace lite
@@ -114,3 +117,23 @@ REGISTER_LITE_KERNEL(depthwise_conv2d, kARM, kFloat, kNCHW,
     .BindInput("Filter", {LiteType::GetTensorTy(TARGET(kARM))})
     .BindOutput("Output", {LiteType::GetTensorTy(TARGET(kARM))})
     .Finalize();
+
+REGISTER_LITE_KERNEL(conv2d, kARM, kInt8, kNCHW,
+                     paddle::lite::kernels::arm::ConvComputeInt8, def)
+    .BindInput("Input", {LiteType::GetTensorTy(TARGET(kARM), PRECISION(kInt8))})
+    .BindInput("Bias", {LiteType::GetTensorTy(TARGET(kARM), PRECISION(kInt32))})
+    .BindInput("Filter",
+               {LiteType::GetTensorTy(TARGET(kARM), PRECISION(kInt8))})
+    .BindOutput("Output",
+                {LiteType::GetTensorTy(TARGET(kARM), PRECISION(kInt8))})
+    .Finalize();
+
+REGISTER_LITE_KERNEL(depthwise_conv2d, kARM, kInt8, kNCHW,
+                     paddle::lite::kernels::arm::ConvComputeInt8, def)
+    .BindInput("Input", {LiteType::GetTensorTy(TARGET(kARM), PRECISION(kInt8))})
+    .BindInput("Bias", {LiteType::GetTensorTy(TARGET(kARM), PRECISION(kInt32))})
+    .BindInput("Filter",
+               {LiteType::GetTensorTy(TARGET(kARM), PRECISION(kInt8))})
+    .BindOutput("Output",
+                {LiteType::GetTensorTy(TARGET(kARM), PRECISION(kInt8))})
+    .Finalize();

paddle/fluid/lite/kernels/arm/conv_compute.h

@@ -41,6 +41,25 @@ class ConvCompute : public KernelLite<TARGET(kARM), PRECISION(kFloat)> {
       nullptr};
 };
 
+class ConvComputeInt8 : public KernelLite<TARGET(kARM), PRECISION(kInt8)> {
+ public:
+  using param_t = operators::ConvParam;
+
+  void PrepareForRun() override;
+
+  void Run() override;
+
+  ~ConvComputeInt8() {
+    if (impl_ != nullptr) {
+      delete impl_;
+    }
+  }
+
+ private:
+  lite::arm::math::ImplBase<TARGET(kARM), PRECISION(kInt8), param_t>* impl_{
+      nullptr};
+};
+
 }  // namespace arm
 }  // namespace kernels
 }  // namespace lite