Merge pull request 'optimized affine-relu #13' (#255) from Ljy123/GPUCodeForces:optimized_affine into main

S1/Ljy123_#13/cudacode.py

@@ -0,0 +1,55 @@
+import torch
+from torch.utils.cpp_extension import load_inline
+
+source = """
+#include <torch/extension.h>
+#include <cuda_runtime.h>
+
+__global__ void affine_relu6_kernel(const float* x, const float* scale, const float* bias, float* y, int dim, long long total) {
+    long long idx = blockIdx.x * blockDim.x + threadIdx.x;
+    long long stride = blockDim.x * gridDim.x;
+    for (long long i = idx; i < total; i += stride) {
+        int j = (int)(i % dim);
+        float v = __fmul_rn(x[i], scale[j]);
+        v = __fadd_rn(v, bias[j]);
+        v = fminf(fmaxf(v, 0.0f), 6.0f);
+        y[i] = v;
+    }
+}
+
+torch::Tensor affine_relu6_cuda(torch::Tensor x, torch::Tensor scale, torch::Tensor bias) {
+    auto x_contig = x.contiguous();
+    auto s_contig = scale.contiguous();
+    auto b_contig = bias.contiguous();
+    auto y = torch::empty_like(x_contig);
+    long long total = x_contig.numel();
+    int dim = (int)x_contig.size(-1);
+    int block = 512;
+    long long grid = (total + block - 1) / block;
+    grid = grid > 65535 ? 65535 : grid;
+    affine_relu6_kernel<<<(int)grid, block>>>(x_contig.data_ptr<float>(), s_contig.data_ptr<float>(), b_contig.data_ptr<float>(), y.data_ptr<float>(), dim, total);
+    return y;
+}
+"""
+
+cpp_source = """
+torch::Tensor affine_relu6_cuda(torch::Tensor x, torch::Tensor scale, torch::Tensor bias);
+"""
+
+ops = load_inline(
+    name="affine_relu6",
+    cpp_sources=cpp_source,
+    cuda_sources=source,
+    functions=["affine_relu6_cuda"],
+    verbose=True
+)
+
+class ModelNew(torch.nn.Module):
+    def __init__(self, scale: torch.Tensor, bias: torch.Tensor):
+        super(ModelNew, self).__init__()
+        self.ops = ops
+        self.register_buffer("scale", scale)
+        self.register_buffer("bias", bias)
+
+    def forward(self, x):
+        return self.ops.affine_relu6_cuda(x, self.scale, self.bias)

S1/Ljy123_#13/prompt.txt

@@ -0,0 +1,5 @@
+Affine+ReLU6 融合：一次内核完成仿射与 ReLU6（0..6）裁剪，减少内核与显存往返。
+
+torchcode.py：参考实现 `y = clamp(x * scale + bias, 0, 6)`。
+cudacode.py：`__global__ void affine_relu6_kernel(...)` 完成融合计算。
+run_code.py：比较精度与性能（100 次迭代，`rtol=1e-03`）。

S1/Ljy123_#13/run_code.py

@@ -0,0 +1,76 @@
+###########################################################
+# 性能和精度验证程序
+###########################################################
+import torch
+import torch.nn as nn
+import time
+from torchcode import Model,get_inputs,get_init_inputs
+from cudacode import ModelNew
+
+def run_benchmark():
+    if not torch.cuda.is_available():
+        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
+    else:
+        device = torch.device("cuda")
+
+    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():
+        output_torch = torch_model(*inputs)
+        output_cuda = cuda_model(*inputs)
+
+    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！")
+        diff = (output_torch - output_cuda).abs().max().item()
+        print(f"最大绝对误差: {diff}")
+        print(f"输出张量形状: torch={tuple(output_torch.shape)}, cuda={tuple(output_cuda.shape)}")
+        print(f"数据类型: torch={output_torch.dtype}, cuda={output_cuda.dtype}")
+        print(f"设备: torch={output_torch.device}, cuda={output_cuda.device}")
+
+    print("\n-------------------- 性能加速比测试 --------------------")
+    num_iterations = 100 
+
+    torch.cuda.synchronize()
+    start_time = time.time()
+    for _ in range(num_iterations):
+        _ = torch_model(*inputs)
+    torch.cuda.synchronize()
+    torch_time = (time.time() - start_time) / num_iterations
+
+    torch.cuda.synchronize()
+    start_time = time.time()
+    for _ in range(num_iterations):
+        _ = cuda_model(*inputs)
+    torch.cuda.synchronize()
+    cuda_time = (time.time() - start_time) / num_iterations
+
+    print(f"PyTorch Affine+ReLU6 平均执行时间: {torch_time:.6f} 秒")
+    print(f"自定义 CUDA 融合内核 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()

S1/Ljy123_#13/torchcode.py

@@ -0,0 +1,24 @@
+import torch
+import torch.nn as nn
+
+class Model(nn.Module):
+    def __init__(self, scale: torch.Tensor, bias: torch.Tensor):
+        super(Model, self).__init__()
+        self.register_buffer("scale", scale)
+        self.register_buffer("bias", bias)
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        y = x * self.scale + self.bias
+        return torch.clamp(y, 0.0, 6.0)
+
+batch_size = 16
+dim = 16384
+
+def get_inputs():
+    x = torch.randn(batch_size, dim)
+    return [x]
+
+def get_init_inputs():
+    scale = torch.randn(dim)
+    bias = torch.randn(dim)
+    return [scale, bias]