* @brief Tensor factory function to create a tensor (a Tensor type is simply * an Array with an N-dimensional Shape specification) on the GPU. The t

* @brief Converts NumType to string. */

* @brief A factory function to create a kernel on the GPU. The kernel is * created with the given WGSL code, input tensors, output tensor, and * opt

* @brief Copies data from a GPU buffer to CPU memory. * @param[in] ctx Context instance to manage the operation * @param[in] tensor Tensor instance

* @brief Ceiling division. */

* @brief Asynchronously submits a kernel to the GPU queue for execution. * It also sets up a callback to notify when the kernel has finished executin

* @brief Factory function to create a GPU context, which aggregates WebGPU API * handles to interact with the GPU including the instance, adapter, de

* @brief simple in-place string replacement helper function for substituting * placeholders in a WGSL string template. * * Note this is not meant t

* @brief Set the log level of the default logger. * @param level The log level to set. */

* @brief Converts a 16-bit half-precision float to a 32-bit float. * * Based on Mike Acton's half.c implementation. */

* Convenience function to check if a condition is true, if not log an error * message and exit. * * @param condition: The condition to check. * @p

* @brief Converts a 32-bit float to a 16-bit half-precision float. * * Based on Mike Acton's half.c implementation. */

* @brief Checks a condition and logs an error message if the condition is * false. * @param[in] condition The condition to check. * @param[in] mess

* @brief Populate the array with random integers. * @param a The array to populate. * @param N The number of elements in the array. * @param gen Th

* @brief Populate the array with a range of values. This is mostly for testing * purposes. * @param input The array to populate. * @param N The num

* @brief Determine if the values of two arrays are close to each other. * @param a The first array. * @param b The second array. * @param n The num

* @brief Returns the number of elements in a tensor with the given shape, * which is equal to the product of the dimensions. * @param[in] shape Shap

* @brief Populate the array with random floats, generated from a Gaussian distribution. * @param a The array to populate. * @param N The number of e

* @brief Resets the command buffer in preparation for a kernel dispatch. * Since command buffers are consumed upon submission, this function is used

* @brief Copies data from CPU memory to a GPU buffer. The toGPU overloads are * effectively a convenience wrapper around the WebGPU API call * wgpuQ

Loop-unrolling optimization with regex Note: Be cautious, as it does not correctly recognize comments or lexical tokens.

* @brief Transpose a matrix. * @param input The input matrix. * @param output The output matrix. * @param M The number of rows in the input matrix.

allocate memory for the parameters and point the individual tensors to the right places

* @brief Frees a tensor resource and updates the tensor pool. * * Only needed if the use case requires manually managing resource lifetimes of * GP

Generates KernelCode instance for all matmul kernels - pass in * the template code via `shaderRaw`. * * This is intended to be run ahead of time, s