From 04af846156effe4f574b43239892b578970f23d6 Mon Sep 17 00:00:00 2001 From: hli28146 Date: Wed, 10 Dec 2025 12:57:17 +0800 Subject: [PATCH] finish NLReLU #78 --- S1/hli28146_#78/NLReLU_cuda.py | 109 ++++++++++++++++++++++++++++++++ S1/hli28146_#78/NLReLU_torch.py | 41 ++++++++++++ S1/hli28146_#78/prompt.txt | 69 ++++++++++++++++++++ S1/hli28146_#78/run_code.py | 74 ++++++++++++++++++++++ 4 files changed, 293 insertions(+) create mode 100644 S1/hli28146_#78/NLReLU_cuda.py create mode 100644 S1/hli28146_#78/NLReLU_torch.py create mode 100644 S1/hli28146_#78/prompt.txt create mode 100644 S1/hli28146_#78/run_code.py diff --git a/S1/hli28146_#78/NLReLU_cuda.py b/S1/hli28146_#78/NLReLU_cuda.py new file mode 100644 index 00000000..784f18f3 --- /dev/null +++ b/S1/hli28146_#78/NLReLU_cuda.py @@ -0,0 +1,109 @@ +import torch +import torch.nn as nn +from torch.utils.cpp_extension import load_inline + +# C++ 源代码 wrapper +cpp_source = """ +#include + +torch::Tensor nlrelu_cuda_forward(const torch::Tensor& input, float beta); +""" + +# CUDA 源代码 +cuda_source = """ +#include +#include +#include + +#define BLOCK_SIZE 256 + +struct __align__(16) Float4 { + float x, y, z, w; +}; + +// NLReLU Logic +__device__ __forceinline__ float compute_nlrelu(float x, float beta) { + if (x >= 0.0f) { + return __logf(beta * x + 1.0f); + } + return 0.0f; +} + +__global__ void nlrelu_kernel( + float* __restrict__ output, + const float* __restrict__ input, + const int n, + const float beta) +{ + const int idx = blockIdx.x * blockDim.x + threadIdx.x; + const int vec_n = n / 4; + + int i = idx; + const int stride = blockDim.x * gridDim.x; + + // 1. Vectorized Loop + for (; i < vec_n; i += stride) { + Float4 in_vec = reinterpret_cast(input)[i]; + Float4 out_vec; + + out_vec.x = compute_nlrelu(in_vec.x, beta); + out_vec.y = compute_nlrelu(in_vec.y, beta); + out_vec.z = compute_nlrelu(in_vec.z, beta); + out_vec.w = compute_nlrelu(in_vec.w, beta); + + reinterpret_cast(output)[i] = out_vec; + } + + // 2. Scalar Tail + int start_scalar = vec_n * 4; + int global_tid = blockIdx.x * blockDim.x + threadIdx.x; + int total_threads = gridDim.x * gridDim.x; + + int current_idx = start_scalar + global_tid; + while (current_idx < n) { + output[current_idx] = compute_nlrelu(input[current_idx], beta); + current_idx += total_threads; + } +} + +torch::Tensor nlrelu_cuda_forward(const torch::Tensor& input, float beta) { + TORCH_CHECK(input.is_cuda(), "Input must be a CUDA tensor"); + TORCH_CHECK(input.is_contiguous(), "Input must be contiguous"); + + const int n = input.numel(); + auto output = torch::empty_like(input); + + const int vec_n = n / 4; + const int grid_size = (vec_n + BLOCK_SIZE - 1) / BLOCK_SIZE; + + int final_grid = (grid_size < 1) ? 1 : grid_size; + if (final_grid > 65535) final_grid = 65535; + + nlrelu_kernel<<>>( + output.data_ptr(), + input.data_ptr(), + n, + beta + ); + + return output; +} +""" + +nlrelu_op_module = load_inline( + name='nlrelu_op', + cpp_sources=cpp_source, + cuda_sources=cuda_source, + functions=['nlrelu_cuda_forward'], + verbose=False, + extra_cuda_cflags=['-O3', '--use_fast_math'] +) + +class ModelNew(nn.Module): + def __init__(self, beta=1.0): + super(ModelNew, self).__init__() + self.beta = beta + self.op = nlrelu_op_module + + def forward(self, input_tensor: torch.Tensor) -> torch.Tensor: + return self.op.nlrelu_cuda_forward(input_tensor.contiguous(), self.beta) \ No newline at end of file diff --git a/S1/hli28146_#78/NLReLU_torch.py b/S1/hli28146_#78/NLReLU_torch.py new file mode 100644 index 00000000..9bc9f92f --- /dev/null +++ b/S1/hli28146_#78/NLReLU_torch.py @@ -0,0 +1,41 @@ +import torch +import torch.nn as nn +import torch.nn.functional as F + +BATCH_SIZE = 4096 +HIDDEN_DIM = 4096 +SHAPE = (BATCH_SIZE, HIDDEN_DIM) + +# NLReLU 超参数 beta ，论文中建议范围 0.7-1.1 +BETA_VALUE = 1.0 + +class NLReLU(nn.Module): + """ + "Natural-Logarithm-Rectified Activation Function in Convolutional Neural Networks" + Formula: + f(x) = log(beta * x + 1.0) if x >= 0 + f(x) = 0 if x < 0 + """ + def __init__(self, beta=1.0): + super(NLReLU, self).__init__() + self.beta = beta + + def forward(self, x: torch.Tensor) -> torch.Tensor: + x_relu = F.relu(x) + inner = self.beta * x_relu + 1.0 + return torch.log(inner) + +class Model(nn.Module): + def __init__(self, beta=1.0): + super(Model, self).__init__() + self.act = NLReLU(beta=beta) + + def forward(self, x): + return self.act(x) + +def get_inputs(): + input_tensor = torch.randn(SHAPE, dtype=torch.float32) * 5.0 + return [input_tensor.contiguous()] + +def get_init_inputs(): + return [BETA_VALUE] \ No newline at end of file diff --git a/S1/hli28146_#78/prompt.txt b/S1/hli28146_#78/prompt.txt new file mode 100644 index 00000000..61872e46 --- /dev/null +++ b/S1/hli28146_#78/prompt.txt @@ -0,0 +1,69 @@ +Write a custom CUDA kernel to optimize `NLReLU` (Natural-Logarithm-Rectified Linear Unit). + +Formula: + f(x) = log(beta * x + 1.0) if x >= 0 + f(x) = 0 if x < 0 + +This is equivalent to `log(beta * max(0, x) + 1.0)`. + +Problem Analysis: +1. Memory Bound: As a point-wise activation, its performance is strictly limited by memory bandwidth. +2. Operator Chaining: The PyTorch implementation `torch.log(beta * F.relu(x) + 1.0)` chains multiple kernels (`relu`, `mul`, `add`, `log`), creating high memory traffic. + +Optimization Strategy: Fused Element-wise Kernel with Vectorization + +1. One-Thread-per-Element: Map each element to a CUDA thread. + +2. Vectorized Loads (float4): Use `float4` to process 128 bits per memory transaction to maximize throughput. + +3. Fused Branching Logic: + - For each element `x`, check `if (x >= 0)`. + - If true, compute `__logf(beta * x + 1.0f)`. + - If false, the result is `0.0f`. + +4. One-Pass: Fuse all steps into a single read-compute-write kernel. + +Here's an example to show you the syntax of inline embedding custom CUDA operators in torch: The example given architecture is: + +```python +import torch +import torch.nn as nn +import torch.nn.functional as F + +BATCH_SIZE = 4096 +HIDDEN_DIM = 4096 +SHAPE = (BATCH_SIZE, HIDDEN_DIM) + +# NLReLU 超参数 beta ，论文中建议范围 0.7-1.1 +BETA_VALUE = 1.0 + +class NLReLU(nn.Module): + """ + "Natural-Logarithm-Rectified Activation Function in Convolutional Neural Networks" + Formula: + f(x) = log(beta * x + 1.0) if x >= 0 + f(x) = 0 if x < 0 + """ + def __init__(self, beta=1.0): + super(NLReLU, self).__init__() + self.beta = beta + + def forward(self, x: torch.Tensor) -> torch.Tensor: + x_relu = F.relu(x) + inner = self.beta * x_relu + 1.0 + return torch.log(inner) + +class Model(nn.Module): + def __init__(self, beta=1.0): + super(Model, self).__init__() + self.act = NLReLU(beta=beta) + + def forward(self, x): + return self.act(x) + +def get_inputs(): + input_tensor = torch.randn(SHAPE, dtype=torch.float32) * 5.0 + return [input_tensor.contiguous()] + +def get_init_inputs(): + return [BETA_VALUE] \ No newline at end of file diff --git a/S1/hli28146_#78/run_code.py b/S1/hli28146_#78/run_code.py new file mode 100644 index 00000000..b18f6aa6 --- /dev/null +++ b/S1/hli28146_#78/run_code.py @@ -0,0 +1,74 @@ +########################################################### +# 性能和精度验证程序 +########################################################### +import torch +import torch.nn as nn +import time +from NLReLU_torch import Model,get_inputs,get_init_inputs +from NLReLU_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() \ No newline at end of file