Method constructor

tfjs-backend-webgl/src/top_k_gpu.ts:113–151

* @param shape desired output shape (must be half of the input size)

(shape: number[])

   * @param shape desired output shape (must be half of the input size)
   */
  constructor(shape: number[]) {
    this.outputShape = shape;

    this.userCode = `
    void main() {
         // Takes max of indices (0, k), (1, k + 1), (2, k + 2) ...
         ivec2 coords = getOutputCoords();
         int batch = coords[0];
         int elemIdx = coords[1];

         // The output size is half of the previous size.
         // If the previous sequence is | | | | _ _ _ _  | | | |  _ _ _ _ (k=4),
         // we only need to output the indices at positions |, the indices at
         // positions _ can be thrown away, see Figure5(b) After Phase 2
         // (Merge phase) in the Bitonic Top K paper referenced above.
         // For example, the paper shows we only need to output the orange bars.
         // The output sequence should look like this | | | | | | | |.
         // Because the sequence is halved, to map the output index back
         // to the previous sequence to find the corresponding value,
         // we need to double the index. When we double the index,
         // we basically interpolate a position, so 2i looks like
         // | _ | _ | _ | _ | _ | _ | _. We move the | to the first k position
         // of each 2k positions by - elemIdx % k. E.g. for output at
         // index 4,5,6,7, we want to get the corresponding element at
         // original index 8,9,10,11, for output at index 8,9,10,11,
         // we want to get the corresponding element at original index
         // 16,17,18,19, so on and so forth.

         int i = elemIdx < k ? elemIdx : (elemIdx * 2 - imod(elemIdx, k));
         int i0 = firstPass == 1 ? i : int(getIndices(batch, i));
         int i1 = firstPass == 1 ? i + k : int(getIndices(batch, i + k));

         float x0 = getX(batch, i0);
         float x1 = i1 < n ? getX(batch, i1) : x0;

         setOutput(x0 >= x1 ? float(i0) : float(i1));
       }
     `;
  }
}