finish lppool1d #6

S1/hli28146_#6/run_code.py

@@ -1,76 +1,74 @@
+###########################################################
+# 性能和精度验证程序
+###########################################################
 import torch
+import torch.nn as nn
 import time
-from lppool1d_torch import Model, get_inputs, get_init_inputs
+from lppool1d_torch import Model,get_inputs,get_init_inputs
 from lppool1d_cuda import ModelNew
- 
+
 def run_benchmark():
+    # 检查 CUDA 是否可用
     if not torch.cuda.is_available():
-        print("CUDA 不可用")
+        print("CUDA 不可用，请确保您有可用的 NVIDIA GPU 并已正确安装 PyTorch CUDA 版本。")
         return
-    
-    device = torch.device("cuda")
-    
-    # 准备输入数据
-    inputs = [x.cuda(device=device) for x in get_inputs()]
-    init_inputs = [x.cuda(device=device) if isinstance(x, torch.Tensor) else x for x in get_init_inputs()]
+    else:
+        device = torch.device("cuda")
+
     # 初始化模型
+    init_inputs = get_init_inputs()
+    init_inputs = [
+        x.cuda(device=device) if isinstance(x, torch.Tensor) else x for x in init_inputs
+    ]
+    inputs = get_inputs()
+    inputs = [
+        x.cuda(device=device) if isinstance(x, torch.Tensor) else x for x in inputs
+    ]
+
     torch_model = Model(*init_inputs).cuda()
     cuda_model = ModelNew(*init_inputs).cuda()
-    
+
     torch_model.eval()
     cuda_model.eval()
-    
+
     print("-------------------- 精度对齐验证 --------------------")
     with torch.no_grad():
-        # 预热GPU
-        _ = torch_model(*inputs)
-        _ = cuda_model(*inputs)
-        
-        # 正式测试
-        output_torch = torch_model(*inputs)
+        output_torch = torch_model( *inputs)
         output_cuda = cuda_model(*inputs)
 
-    # 精度验证
-    abs_diff = torch.abs(output_torch - output_cuda)
-    max_diff = torch.max(abs_diff).item()
-    mean_diff = torch.mean(abs_diff).item()
-    
-    if max_diff < 1e-4 and mean_diff < 1e-5:
-        print(f"✅ 精度对齐：最大误差 {max_diff:.6f}，平均误差 {mean_diff:.6f}")
-        precision_flag = True
+    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(f"❌ 精度不一致：最大误差 {max_diff:.6f}，平均误差 {mean_diff:.6f}")
-        precision_flag = False
-
+        print("❌ 精度不一致！")
+        
     print("\n-------------------- 性能加速比测试 --------------------")
     num_iterations = 100 
     
-    # 预热GPU
-    for _ in range(10):
-        _ = torch_model(*inputs)
-        _ = cuda_model(*inputs)
-    
-    # PyTorch模型计时
+    # PyTorch 模型计时
     torch.cuda.synchronize()
     start_time = time.time()
     for _ in range(num_iterations):
-     _ = torch_model(*inputs)
+        _ = torch_model(*inputs)
     torch.cuda.synchronize()
     torch_time = (time.time() - start_time) / num_iterations
     
-    # 自定义CUDA内核计时
+    # 自定义 CUDA 内核计时
     torch.cuda.synchronize()
     start_time = time.time()
     for _ in range(num_iterations):
-     _ = cuda_model(*inputs)
+        _ = cuda_model(*inputs)
     torch.cuda.synchronize()
     cuda_time = (time.time() - start_time) / num_iterations
     
-    print(f"PyTorch内置Swish平均执行时间: {torch_time:.6f}秒")
-    print(f"自定义CUDA Swish平均执行时间: {cuda_time:.6f}秒")
-    speedup = torch_time / cuda_time if cuda_time > 0 else 0
-    print(f"加速比 (Speedup): {speedup:.2f}x")
-    
-    return precision_flag, speedup
+    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
 if __name__ == "__main__":
-    precision_flag, speedup = run_benchmark()
+    precision_flag,speedup = run_benchmark()