Function toCPU

gpu.hpp:997–1025

* @brief Copies data from a GPU buffer to CPU memory. * @param[in] ctx Context instance to manage the operation * @param[in] tensor Tensor instance representing the GPU buffer to copy from * @param[out] data Pointer to the CPU memory to copy the data to * @param[in] bufferSize Size of the data buffer in bytes * @param[in] op StagingBuffer instance to manage the operation * * @code * toCPU(

 * @endcode
 */
inline void toCPU(Context &ctx, Tensor &tensor, void *data, size_t bufferSize,
                  CopyData &op) {
  wgpuQueueSubmit(ctx.queue, 1, &op.commandBuffer);
  CallbackData callbackData = {op.readbackBuffer, bufferSize, data, &op.promise,
                               &op.future};
  wgpuQueueOnSubmittedWorkDone(
      ctx.queue,
      [](WGPUQueueWorkDoneStatus status, void *callbackData) {
        check(status == WGPUQueueWorkDoneStatus_Success, "Queue work done",
              __FILE__, __LINE__);
        const auto *data = static_cast<CallbackData *>(callbackData);
        wgpuBufferMapAsync(
            data->buffer, WGPUMapMode_Read, 0, data->bufferSize,
            [](WGPUBufferMapAsyncStatus status, void *captureData) {
              const auto *data = static_cast<CallbackData *>(captureData);
              check(status == WGPUBufferMapAsyncStatus_Success,
                    "Map readbackBuffer", __FILE__, __LINE__);
              const void *mappedData = wgpuBufferGetConstMappedRange(
                  data->buffer, /*offset=*/0, data->bufferSize);
              check(mappedData, "Get mapped range", __FILE__, __LINE__);
              memcpy(data->output, mappedData, data->bufferSize);
              wgpuBufferUnmap(data->buffer);
              data->promise->set_value();
            },
            callbackData);
      },
      &callbackData);
  wait(ctx, op.future);
}

/**
 * @brief Overload of the toCPU function to copy data from a GPU buffer to CPU