Workflow for quantized neural networks:
// 1. Load quantized weights and scales
int8_t *weights_q = load_quantized_weights();
float *scales = load_scales();
// 2. Set up quantization post-ops
aocl_post_op post_ops;
setup_quantization_post_ops(&post_ops, scales, zero_points);
// 3. Process quantized inputs
aocl_gemm_u8s8s32os8(
'R', 'N', 'N', m, n, k,
1, input_q, k, 'N',
weights_q, n, 'N',
0, output_q, n,
&post_ops
);