finish ItakuraSaitoDistanceLoss #93

S1/uucoco_#93/ItakuraSaitoDistanceLoss_cuda.py

@@ -0,0 +1,85 @@
+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 itakura_saito_kernel(
+    const float* __restrict__ input,
+    const float* __restrict__ target,
+    float* __restrict__ output,
+    int n,
+    float eps
+) {
+    extern __shared__ float sdata[];
+    int tid = threadIdx.x;
+    int idx = blockIdx.x * blockDim.x + threadIdx.x;
+
+    float local_sum = 0.0f;
+    for (int i = idx; i < n; i += blockDim.x * gridDim.x) {
+        float x = input[i];
+        float y = target[i];
+
+        float ratio = y / (x + eps);
+        float term = ratio - logf(ratio + eps) - 1.0f;
+
+        local_sum += term;
+    }
+
+    sdata[tid] = local_sum;
+    __syncthreads();
+
+    for (int s = blockDim.x / 2; s > 0; s >>= 1) {
+        if (tid < s) {
+            sdata[tid] += sdata[tid + s];
+        }
+        __syncthreads();
+    }
+
+    if (tid == 0) {
+        atomicAdd(output, sdata[0]);
+    }
+}
+
+torch::Tensor itakura_saito_cuda(torch::Tensor input, torch::Tensor target, float eps) {
+    int n = input.numel();
+    auto output = at::zeros({1}, input.options());
+
+    int threads = 256;
+    int blocks = 128;
+    int shared_mem = threads * sizeof(float);
+
+    itakura_saito_kernel<<<blocks, threads, shared_mem>>>(
+        input.data_ptr<float>(),
+        target.data_ptr<float>(),
+        output.data_ptr<float>(),
+        n,
+        eps
+    );
+
+    return output / n;
+}
+"""
+
+cpp_source = """
+torch::Tensor itakura_saito_cuda(torch::Tensor input, torch::Tensor target, float eps);
+"""
+
+itakura_saito_loss = load_inline(
+    name="itakura_saito_loss",
+    cpp_sources=cpp_source,
+    cuda_sources=cuda_source,
+    functions=["itakura_saito_cuda"],
+    verbose=False
+)
+
+
+class ModelNew(nn.Module):
+    def __init__(self, eps=1e-8):
+        super(ModelNew, self).__init__()
+        self.eps = eps
+
+    def forward(self, input, target):
+        return itakura_saito_loss.itakura_saito_cuda(input, target, self.eps)

S1/uucoco_#93/ItakuraSaitoDistanceLoss_torch.py

@@ -0,0 +1,23 @@
+import torch
+import torch.nn as nn
+
+class Model(nn.Module):
+    def __init__(self, eps=1e-8):
+        super(Model, self).__init__()
+        self.eps = eps
+
+    def forward(self, input, target):
+        ratio = target / (input + self.eps)
+        loss = ratio - torch.log(ratio + self.eps) - 1.0
+        return loss.mean()
+
+batch_size = 32
+input_dim = 1024
+
+def get_inputs():
+    input = torch.abs(torch.randn(batch_size, input_dim, requires_grad=True)) + 0.1
+    target = torch.abs(torch.randn(batch_size, input_dim)) + 0.1
+    return [input, target]
+
+def get_init_inputs():
+    return [1e-8]

S1/uucoco_#93/prompt.txt

@@ -0,0 +1,131 @@
+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 & Frameworks
+PyTorch: Deep learning framework
+
+CUDA: NVIDIA's parallel computing platform for GPU acceleration
+
+C++: For high-performance kernel implementation
+
+PyTorch Specific Components
+torch.nn.Module: Base class for neural network modules
+
+torch.utils.cpp_extension.load_inline: For inline compilation of CUDA/C++ extensions
+
+PyTorch Tensors: Multi-dimensional arrays with automatic differentiation
+
+Tensor.numel(): Method to get total number of elements
+
+CUDA/C++ Implementation Details
+CUDA Kernels: Custom GPU kernel (itakura_saito_kernel)
+
+CUDA Math Functions: logf() for logarithmic computations
+
+Parallel Reduction: Tree-based reduction using shared memory
+
+Shared Memory: Using __shared__ for inter-thread communication
+
+Atomic Operations: atomicAdd for thread-safe global updates
+
+Grid-Stride Loops: Efficient memory access pattern
+
+Mathematical Components
+Itakura-Saito Distance: Spectral distance measure for signals/spectra
+
+Ratio Computation: y/(x+eps) ratio calculation
+
+Logarithmic Term: log(ratio+eps) component
+
+Three-Term Formula: ratio - log(ratio) - 1 formulation
+
+Numerical Stability: Epsilon (eps) to prevent division by zero and log(0)
+
+Signal Processing/Spectral Analysis Components
+Spectral Distance: Originally designed for power spectra comparison
+
+Scale Invariance: Property of Itakura-Saito distance
+
+Non-Negative Inputs: Typically used with power spectra (non-negative values)
+
+Element-Wise Computation: Independent computation across frequency bins
+
+Optimization Techniques
+Shared Memory Reduction: Parallel tree reduction within thread blocks
+
+Grid-Stride Loops: Efficient handling of arbitrary tensor sizes
+
+Numerical Stability: Dual epsilon usage for division and log operations
+
+Fused Computation: Complete distance calculation in single kernel
+
+Element-Wise Parallelism: Massive parallelism across all tensor elements
+
+Performance Features
+Massive Parallelization: GPU acceleration for distance computation
+
+Memory Efficiency: Shared memory for intermediate reduction results
+
+Atomic Accumulation: Safe parallel sum across thread blocks
+
+Scalable Design: Efficient for any tensor shape/size
+
+Mean Normalization: Final division by total number of elements
+
+Unique Implementation Aspects
+Dual Epsilon Protection: Prevents both division by zero and log(0)
+
+Ratio-Based Computation: Core of Itakura-Saito formulation
+
+Element-Wise Metric: Unlike matrix-based distances, operates element-wise
+
+Signal Processing Focus: Specialized for spectral/power distribution comparison
+
+Scale Invariant: Important property preserved in implementation
+
+Applications & Use Cases
+Speech Processing: Originally for speech spectrum comparison
+
+Audio Signal Analysis: Power spectrum distance measurement
+
+Non-Negative Matrix Factorization: Common divergence measure in NMF
+
+Spectral Data: Suitable for any non-negative spectral/power data
+
+Numerical Considerations
+Non-Negative Inputs: Expects non-negative values (typical for spectra)
+
+Epsilon Selection: Small but non-zero to ensure numerical stability
+
+Ratio Stability: Protected against both numerator and denominator extremes
+
+Mean Computation: Averages across all elements (not batch mean)
+
+
+
+
+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, eps=1e-8):
+        super(Model, self).__init__()
+        self.eps = eps
+
+    def forward(self, input, target):
+        ratio = target / (input + self.eps)
+        loss = ratio - torch.log(ratio + self.eps) - 1.0
+        return loss.mean()
+
+batch_size = 32
+input_dim = 1024
+
+def get_inputs():
+    input = torch.abs(torch.randn(batch_size, input_dim, requires_grad=True)) + 0.1
+    target = torch.abs(torch.randn(batch_size, input_dim)) + 0.1
+    return [input, target]
+
+def get_init_inputs():
+    return [1e-8]

S1/uucoco_#93/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 ItakuraSaitoDistanceLoss_torch import Model, get_inputs, get_init_inputs
+from ItakuraSaitoDistanceLoss_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()