Method onExecute

source/backend/cpu/CPURaster.cpp:882–1200

    }

    virtual ErrorCode onExecute(const std::vector<Tensor *> &originInputs, const std::vector<Tensor *> &originOutputs) override {
        auto cpubackend = static_cast<CPUBackend*>(backend());
        auto precision = cpubackend->precisionMode();
        auto threadNumber = cpubackend->threadNumber();
        if (mLoop->initCommand() != nullptr) {
            for (int i=0; i<mLoop->initCommand()->size(); ++i) {
                auto cmd = mLoop->initCommand()->GetAs<RegionCommand>(i);
                if (cmd->op() == nullptr) {
                    auto output = mStack[cmd->indexes()->data()[0]];
                    ::memset(output->host<void>(), 0, cpubackend->getTensorSize(output) * cpubackend->functions()->bytes);
                } else {
                    Tensor::InsideDescribe::Region reg;
                    auto srcView = cmd->view()->GetAs<View>(1);
                    auto dstView = cmd->view()->GetAs<View>(0);
                    ::memcpy(reg.size, cmd->size()->data(), 3 * sizeof(int32_t));
                    ::memcpy(reg.src.stride, srcView->stride()->data(), 3 * sizeof(int32_t));
                    ::memcpy(reg.dst.stride, dstView->stride()->data(), 3 * sizeof(int32_t));
                    auto input = mStack[cmd->indexes()->data()[1]];
                    auto inputSize = input->elementSize();
                    auto output = mStack[cmd->indexes()->data()[0]];
                    auto bytes = input->getType().bytes();
                    if (halide_type_float == input->getType().code) {
                        bytes = cpubackend->functions()->bytes;
                    }
                    _blit(reg, bytes, input->host<uint8_t>(), output->host<uint8_t>(), false);
                }

            }
        }
        if (1 == mLoop->commands()->size()) {
            auto cmd = mLoop->commands()->GetAs<RegionCommand>(0);
            auto op = cmd->op();
            if (OpType_UnaryOp == op->type() && nullptr == op->main() && cmd->fuse() < 0) {
                // For Gather / Single Unary
                auto index0 = cmd->iterIndexes()->data()[0];
                auto index1 = cmd->iterIndexes()->data()[1];
                int32_t iter = 0;
                int32_t* iter0 = &iter;
                int32_t* iter1 = &iter;
                int32_t iter0Stride = 0;
                int32_t iter1Stride = 0;
                if (index0 >= 0) {
                    iter0 = originInputs[index0]->host<int32_t>();
                    iter0Stride = 1;
                }
                if (index1 >= 0) {
                    iter1 = originInputs[index1]->host<int32_t>();
                    iter1Stride = 1;
                }
                Tensor::InsideDescribe::Region reg;
                auto srcView = cmd->view()->GetAs<View>(1);
                auto dstView = cmd->view()->GetAs<View>(0);
                ::memcpy(reg.size, cmd->size()->data(), 3 * sizeof(int32_t));
                ::memcpy(reg.src.stride, srcView->stride()->data(), 3 * sizeof(int32_t));
                ::memcpy(reg.dst.stride, dstView->stride()->data(), 3 * sizeof(int32_t));
                auto input = mStack[cmd->indexes()->data()[1]];
                auto inputSize = input->usize() / input->buffer().type.bytes();
                auto output = mStack[cmd->indexes()->data()[0]];