finish signmuladd #108

S1/uucoco_#108/prompt.txt

@@ -0,0 +1,61 @@
+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.
+
+Technologies Used in This Code
+Core Libraries
+PyTorch: Deep learning framework
+
+CUDA: GPU parallel computing
+
+C++: Kernel implementation
+
+CUDA Components
+CUDA kernel: sign_mul_add_kernel
+
+Element-wise parallelism: One thread per element
+
+Simple branching: Sign extraction logic
+
+Mathematical Operations
+Sign function: Extract sign of tensor a (1, 0, or -1)
+
+Element-wise multiplication: sign(a) × b
+
+Element-wise addition: (sign(a) × b) + c
+
+Three-input operation: Combines three tensors
+
+Architecture
+Standard CUDA pattern: 1D grid/block configuration
+
+Three tensor inputs: a, b, c of same shape
+
+Conditional logic: Branching for sign extraction
+
+
+
+
+
+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
+
+class Model(nn.Module):
+    def __init__(self):
+        super(Model, self).__init__()
+
+    def forward(self, a, b, c):
+        return torch.sign(a) * b + c
+
+batch_size = 4096
+dim = 1024
+
+def get_inputs():
+    a = torch.randn(batch_size, dim)
+    b = torch.randn(batch_size, dim)
+    c = torch.randn(batch_size, dim)
+    return [a, b, c]
+
+def get_init_inputs():
+    return []

S1/uucoco_#108/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 signmuladd_torch import Model, get_inputs, get_init_inputs
+from signmuladd_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()

S1/uucoco_#108/signmuladd_cuda.py

@@ -0,0 +1,73 @@
+import torch
+import torch.nn as nn
+from torch.utils.cpp_extension import load_inline
+
+cuda_source = """
+#include <torch/extension.h>
+#include <cuda_runtime.h>
+
+__global__ void sign_mul_add_kernel(
+    const float* __restrict__ a,
+    const float* __restrict__ b,
+    const float* __restrict__ c,
+    float* __restrict__ output,
+    int size
+) {
+    int idx = blockIdx.x * blockDim.x + threadIdx.x;
+    if (idx < size) {
+        float a_val = a[idx];
+        float b_val = b[idx];
+        float c_val = c[idx];
+
+        float sign_val;
+        if (a_val > 0.0f) {
+            sign_val = 1.0f;
+        } else if (a_val < 0.0f) {
+            sign_val = -1.0f;
+        } else {
+            sign_val = 0.0f;
+        }
+
+        output[idx] = sign_val * b_val + c_val;
+    }
+}
+
+torch::Tensor sign_mul_add_cuda(torch::Tensor a, torch::Tensor b, torch::Tensor c) {
+    auto output = torch::empty_like(a);
+    int size = a.numel();
+
+    const int block_size = 256;
+    int num_blocks = (size + block_size - 1) / block_size;
+
+    sign_mul_add_kernel<<<num_blocks, block_size>>>(
+        a.data_ptr<float>(),
+        b.data_ptr<float>(),
+        c.data_ptr<float>(),
+        output.data_ptr<float>(),
+        size
+    );
+
+    return output;
+}
+"""
+
+cpp_source = """
+torch::Tensor sign_mul_add_cuda(torch::Tensor a, torch::Tensor b, torch::Tensor c);
+"""
+
+module = load_inline(
+    name="sign_mul_add",
+    cpp_sources=cpp_source,
+    cuda_sources=cuda_source,
+    functions=["sign_mul_add_cuda"],
+    verbose=True
+)
+
+
+class ModelNew(nn.Module):
+    def __init__(self):
+        super(ModelNew, self).__init__()
+        self.module = module
+
+    def forward(self, a, b, c):
+        return self.module.sign_mul_add_cuda(a, b, c)

S1/uucoco_#108/signmuladd_torch.py

@@ -0,0 +1,21 @@
+import torch
+import torch.nn as nn
+
+class Model(nn.Module):
+    def __init__(self):
+        super(Model, self).__init__()
+
+    def forward(self, a, b, c):
+        return torch.sign(a) * b + c
+
+batch_size = 4096
+dim = 1024
+
+def get_inputs():
+    a = torch.randn(batch_size, dim)
+    b = torch.randn(batch_size, dim)
+    c = torch.randn(batch_size, dim)
+    return [a, b, c]
+
+def get_init_inputs():
+    return []