Sparse Matrix-Vector Multiplication

题面

Implement a GPU program that performs sparse matrix-vector multiplication. 给定稀疏矩阵 A∈R^{M×N} 与稠密向量 x∈R^{N}，计算 y = A x（长度 M）。

Implementation Requirements

• Use only GPU native features (external libraries are not permitted)
• The solve function signature must remain unchanged
• The final result must be stored in vector y

Examples

Example: A (3×4), x=[1,2,3,4] → y=[9,13,16]

Constraints

• 1 ≤ M, N ≤ 10,000
• A 约 60–70% 稀疏（零元素占比 60–70%）
• Performance is measured with M = 1,000, N = 10,000