FP16 Dot Product

题面

计算两个 FP16 向量的点积，乘加过程中使用 FP32 累加，最终结果转回 FP16 存入输出。

Implementation Requirements

• External libraries are not permitted
• The solve function signature must remain unchanged
• FP32 累加后写回 half

Examples

同 FP32 点积示例：A=[1,2,3,4], B=[5,6,7,8] → 70.0；A=[0.5,1.5,2.5], B=[2,3,4] → 15.5

Constraints

• A 与 B 等长
• 1 ≤ N ≤ 100,000,000
• Performance: N = 100,000,000