Method Compute

mllm/backends/ascend/kernels/vec_add.cpp:48–56

    inQueueY.EnQue(yLocal);
  }
  __aicore__ inline void Compute(int32_t progress) {
    AscendC::LocalTensor<half> xLocal = inQueueX.DeQue<half>();
    AscendC::LocalTensor<half> yLocal = inQueueY.DeQue<half>();
    AscendC::LocalTensor<half> zLocal = outQueueZ.AllocTensor<half>();
    AscendC::Add(zLocal, xLocal, yLocal, TILE_LENGTH);
    outQueueZ.EnQue<half>(zLocal);
    inQueueX.FreeTensor(xLocal);
    inQueueY.FreeTensor(yLocal);
  }
  __aicore__ inline void CopyOut(int32_t progress) {
    AscendC::LocalTensor<half> zLocal = outQueueZ.DeQue<half>();
    AscendC::DataCopy(zGm[progress * TILE_LENGTH], zLocal, TILE_LENGTH);