import assert from 'node:assert/strict';
import {conv2d, im2col, dot, requantize, maxPool2x2} from './model.mjs';
const x = [Array.from({length: 4}, (_, r) => Array.from({length: 4}, (_, c) => r * 4 + c + 1))];
const kernel = [[1, 0, -1], [1, 0, -1], [1, 0, -1]];
const weights = [[kernel]], bias = [8];
const reference = conv2d(x, weights, {bias});
const flattenedWeights = kernel.flat();
const rows = im2col(x, 3, 3);
const accumulators = rows.map(row => dot(row, flattenedWeights) + bias[0]);
assert.deepEqual(accumulators, reference[0].flat());
assert.deepEqual(accumulators, [2, 2, 2, 2]);
const activated = reference[0].map(row => row.map(v => Math.max(0, requantize(v, 0.5))));
const pooled = maxPool2x2(activated);
assert.deepEqual(activated, [[1, 1], [1, 1]]);
assert.deepEqual(pooled, [[1]]);
// Cycle estimate with explicit assumptions: all MAC operands local, no stalls,
// one output at a time, K=9, two single-MAC PEs, no overlap with output write.
const macs = rows.length * flattenedWeights.length;
const peCount = 2, macCyclesPerOutput = Math.ceil(flattenedWeights.length / peCount);
const modelCycles = rows.length * (macCyclesPerOutput + 1);
const usefulSlots = macs, scheduledSlots = rows.length * macCyclesPerOutput * peCount;
assert.equal(macs, 36);
assert.equal(modelCycles, 24);
assert.equal(usefulSlots / scheduledSlots, 0.9);
const report = {shape:[1, 2, 2], accumulators, activated, pooled, macs, peCount,
  modelCycles, macSlotUtilization:usefulSlots / scheduledSlots,
  uniqueInputBytes:16, weightBytes:9, outputBytes:4, biasBytes:4,
  scope:'Software reference and schedule estimate only; no synthesis or DDS run'};
console.log(JSON.stringify(report, null, 2));