Merge pull request 'please check before PR #13' (#84) from Kuohais/GPUCodeForces:fix1 into main

S1/Example/run_code.py

@@ -4,7 +4,7 @@
 import torch
 import torch.nn as nn
 import time
-from example_torchcode import Model, get_inputs, get_init_inputs
+from example_torchcode import Model,get_inputs,get_init_inputs
 from example_cudacode import ModelNew
 
 def run_benchmark():
@@ -33,30 +33,17 @@ def run_benchmark():
 
     print("-------------------- 精度对齐验证 --------------------")
     with torch.no_grad():
-        output_torch = torch_model(*inputs)
+        output_torch = torch_model( *inputs)
         output_cuda = cuda_model(*inputs)
 
-    # 更严格的精度检查
-    abs_diff = (output_torch - output_cuda).abs()
-    max_diff = abs_diff.max().item()
-    mean_diff = abs_diff.mean().item()
-    
-    print(f"最大差异: {max_diff:.6f}")
-    print(f"平均差异: {mean_diff:.6f}")
-    
-    precision_flag = torch.allclose(output_torch, output_cuda, rtol=1e-05, atol=1e-05)
+    precision_flag = torch.allclose(output_torch, output_cuda,rtol=1e-03)
     if precision_flag:
         print("✅ 精度对齐：两个模型的输出结果非常接近。")
     else:
         print("❌ 精度不一致！")
         
     print("\n-------------------- 性能加速比测试 --------------------")
-    num_iterations = 1000  # 增加迭代次数以获得更准确的时间测量
-    
-    # Warm up
-    for _ in range(100):
-        _ = torch_model(*inputs)
-        _ = cuda_model(*inputs)
+    num_iterations = 100 
     
     # PyTorch 模型计时
     torch.cuda.synchronize()
@@ -74,15 +61,14 @@ def run_benchmark():
     torch.cuda.synchronize()
     cuda_time = (time.time() - start_time) / num_iterations
     
-    print(f"PyTorch (matmul + relu) 平均执行时间: {torch_time:.6f} 秒")
-    print(f"自定义 CUDA ReLU 平均执行时间: {cuda_time:.6f} 秒")
+    print(f"PyTorch torch.relu 平均执行时间: {torch_time:.6f} 秒")
+    print(f"自定义 CUDA 内核 平均执行时间: {cuda_time:.6f} 秒")
     speedup = 0
     if cuda_time > 0:
         speedup = torch_time / cuda_time
         print(f"加速比 (Speedup): {speedup:.2f}x")
     else:
         print("CUDA 内核执行时间为0，无法计算加速比。")
-    return precision_flag, speedup
-
+    return precision_flag,speedup
 if __name__ == "__main__":
-    precision_flag, speedup = run_benchmark()
+    precision_flag,speedup = run_benchmark()

S1/README.md

@@ -0,0 +1,5 @@
+# 提交前的注意事项
+
+- 确保已经阅读了[赛题入门](https://www.gitlink.org.cn/ccf-ai-infra/GPUCodeForces/tree/main/GPUCodeForces%E8%B5%9B%E9%A2%98%E5%85%A5%E9%97%A8.md)、[代码解读](https://www.gitlink.org.cn/ccf-ai-infra/GPUCodeForces/tree/main/GPUCodeForces%E4%BB%A3%E7%A0%81%E8%A7%A3%E8%AF%BB.md)的内容
+- 你的提交包含S1/Example下的四份完整文件
+- **提交时请不要更改原S1/Example/run_code.py的文件内容**