finish Relu6 #44

S1/uucoco_#44/Relu6_cuda.py

@@ -0,0 +1,84 @@
+import torch
+import torch.nn as nn
+from torch.utils.cpp_extension import load_inline
+
+class ModelNew(nn.Module):
+    def __init__(self):
+        super().__init__()
+        self._compile_cuda_kernel()
+
+    def _compile_cuda_kernel(self):
+        cpp_source = """
+        torch::Tensor relu6_cuda(torch::Tensor x);
+        """
+
+        cuda_source = """
+        #include <torch/extension.h>
+        #include <cuda_runtime.h>
+        #include <math.h>
+
+        __device__ __forceinline__ float relu6_op(float x) {
+            // f(x) = min(6, max(0, x))
+            return fminf(6.0f, fmaxf(0.0f, x));
+        }
+
+        __global__ void relu6_kernel(
+            const float* __restrict__ x,
+            float* __restrict__ output,
+            const int n_elements) 
+        {
+            const int tid = blockIdx.x * blockDim.x + threadIdx.x;
+            const int stride = blockDim.x * gridDim.x;
+
+            const int vec_loops = n_elements >> 2;
+            const float4* x_vec = reinterpret_cast<const float4*>(x);
+            float4* out_vec = reinterpret_cast<float4*>(output);
+
+            for (int i = tid; i < vec_loops; i += stride) {
+                float4 v = __ldg(&x_vec[i]);
+                float4 r;
+
+                r.x = relu6_op(v.x);
+                r.y = relu6_op(v.y);
+                r.z = relu6_op(v.z);
+                r.w = relu6_op(v.w);
+
+                out_vec[i] = r;
+            }
+
+            const int tail_start = vec_loops << 2;
+            for (int i = tail_start + tid; i < n_elements; i += stride) {
+                output[i] = relu6_op(x[i]);
+            }
+        }
+
+        torch::Tensor relu6_cuda(torch::Tensor x) {
+            auto x_c = x.contiguous();
+            const int n_elements = x_c.numel();
+            auto output = torch::empty_like(x_c);
+
+            const int threads = 256;
+            const int max_blocks = 65535;
+            const int blocks = std::min((n_elements + threads * 4 - 1) / (threads * 4), max_blocks);
+
+            relu6_kernel<<<blocks, threads>>>(
+                x_c.data_ptr<float>(),
+                output.data_ptr<float>(),
+                n_elements
+            );
+
+            return output;
+        }
+        """
+
+        self.op = load_inline(
+            name="relu6_v1",
+            cpp_sources=cpp_source,
+            cuda_sources=cuda_source,
+            functions=["relu6_cuda"],
+            extra_cuda_cflags=["-O3", "--use_fast_math"],
+            verbose=False
+        )
+
+    def forward(self, x):
+        return self.op.relu6_cuda(x)

S1/uucoco_#44/Relu6_torch.py

@@ -0,0 +1,25 @@
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+
+class Model(nn.Module):
+    def __init__(self):
+        super().__init__()
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        # 直接使用 PyTorch 內建的優化函式 F.relu6
+        return F.relu6(x)
+
+
+batch_size = 128
+feature_dim = 512
+
+
+def get_inputs():
+    x = torch.randn(batch_size, feature_dim, dtype=torch.float32)
+    return [x]
+
+
+def get_init_inputs():
+    return []

S1/uucoco_#44/prompt.txt

@@ -0,0 +1,39 @@
+You write custom CUDA kernels to replace the pytorch operators in the given GeGLU architecture to get speedups.
+
+You have complete freedom to choose the set of operators you want to replace. You may make the decision to replace some operators with custom CUDA kernels and leave others unchanged. You may replace multiple operators with custom implementations, consider operator fusion opportunities (combining multiple operators into a single kernel, for example, combining chunk+gelu+elementwise_mul), or algorithmic changes (such as optimized memory access patterns). You are only limited by your imagination.
+
+This CUDA kernel implements several key optimizations for the ReLU6 activation function:
+Vectorization: Uses float4memory operations to process 4 elements per thread, increasing memory throughput.
+Memory Coalescing: Accesses contiguous memory blocks through vector loads/stores, optimizing GPU memory bandwidth.
+Grid-Stride Loop: Handles arbitrary-sized tensors efficiently by having threads process multiple elements with strided indexing.
+Fast Math: Uses CUDA's fminf/fmaxfintrinsics and --use_fast_mathcompiler flag for optimized mathematical operations.
+Occupancy Optimization: Employs 256 threads per block and calculates optimal grid size to maximize GPU utilization.
+Tail Processing: Handles non-multiple-of-4 elements separately after vectorized operations.
+
+
+Here's an example to show you the syntax of inline embedding custom CUDA operators in torch: The example given architecture is:
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+
+class Model(nn.Module):
+    def __init__(self):
+        super().__init__()
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        # 直接使用 PyTorch 內建的優化函式 F.relu6
+        return F.relu6(x)
+
+
+batch_size = 128
+feature_dim = 512
+
+
+def get_inputs():
+    x = torch.randn(batch_size, feature_dim, dtype=torch.float32)
+    return [x]
+
+
+def get_init_inputs():
+    return []

S1/uucoco_#44/run_code.py

@@ -0,0 +1,77 @@
+###########################################################
+# 性能和精度验证程序
+###########################################################
+import torch
+import torch.nn as nn
+import time
+from Relu6_torch import Model, get_inputs, get_init_inputs
+from Relu6_cuda  import ModelNew
+
+
+def run_benchmark():
+    # 检查 CUDA 是否可用
+    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")
+
+    # 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():
+        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！")
+
+    print("\n-------------------- 性能加速比测试 --------------------")
+    num_iterations = 100
+
+    # PyTorch 模型计时
+    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
+
+    # 自定义 CUDA 内核计时
+    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 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()