Method KernelCode

gpu.hpp:308–318

* @brief Constructor to create a code object from a template * string and optional workgroup size and precision. * * @param[in] pData Shader template string with placeholders * @param[in] workgroupSize Shape of the workgroup. Unlike tensor shapes which * can be of arbitrary rank, workgroup size is always of rank 3 corresponding * to x y and z. workgroupSize is stored as a field i

   * @endcode
   */
  inline KernelCode(const std::string &pData = "", size_t workgroupSize = 256,
                    NumType precision = kf32)
      : data(pData), workgroupSize({workgroupSize, 1, 1}),
        precision(precision) {
    if (precision == kf16) {
      data = "enable f16;\n" + data;
    }
    replaceAll(data, "{{workgroupSize}}", toString({workgroupSize, 1, 1}));
    replaceAll(data, "{{precision}}", toString(precision));
    LOG(kDefLog, kTrace, "Shader code:\n%s", data.c_str());
  }

  /**
   * @brief Overload of the constructor to create a code object from a template