#include <cuda_bf16.h>
#include <math.h>

// GELU (tanh approximation):
// gelu(x) = 0.5 * x * (1 + tanh(sqrt(2/pi) * (x + 0.044715 * x^3)))
__device__ __forceinline__ float gelu_f(float x) {
    const float SQRT_2_OVER_PI = 0.7978845608f;
    float cube = x * x * x;
    float inner = SQRT_2_OVER_PI * (x + 0.044715f * cube);
    return 0.5f * x * (1.0f + tanhf(inner));
}

// SiLU (Swish): silu(x) = x * sigmoid(x) = x / (1 + exp(-x))
__device__ __forceinline__ float silu_f(float x) {
    return x / (1.0f + expf(-x));
}

__global__ void gelu_f32(const float* x, float* out, int n) {
    int idx = blockIdx.x * blockDim.x + threadIdx.x;
    if (idx < n) out[idx] = gelu_f(x[idx]);
}

__global__ void gelu_bf16(const __nv_bfloat16* x, __nv_bfloat16* out, int n) {
    int idx = blockIdx.x * blockDim.x + threadIdx.x;
    if (idx < n) out[idx] = __float2bfloat16(gelu_f(__bfloat162float(x[idx])));
}

__global__ void silu_f32(const float* x, float* out, int n) {
    int idx = blockIdx.x * blockDim.x + threadIdx.x;
    if (idx < n) out[idx] = silu_f(x[idx]);
}

__global__ void silu_bf16(const __nv_bfloat16* x, __nv_bfloat16* out, int n) {
    int idx = blockIdx.x * blockDim.x + threadIdx.x;
    if (idx < n) out[idx] = __float2bfloat16(silu_f(__bfloat162float(x[idx])));
}

__global__ void scale_f32_kernel(const float* x, float* out, float scale, int n) {
    int idx = blockIdx.x * blockDim.x + threadIdx.x;
    if (idx < n) out[idx] = x[idx] * scale;
}

__global__ void scale_bf16_kernel(const __nv_bfloat16* x, __nv_bfloat16* out, float scale, int n) {
    int idx = blockIdx.x * blockDim.x + threadIdx.x;
    if (idx < n) out[idx] = __float2bfloat16(__bfloat162float(x[idx]) * scale);
}

// Element-wise add: out = a + b
__global__ void add_f32_kernel(const float* a, const float* b, float* out, int n) {
    int idx = blockIdx.x * blockDim.x + threadIdx.x;
    if (idx < n) out[idx] = a[idx] + b[idx];
}
__global__ void add_bf16_kernel(const __nv_bfloat16* a, const __nv_bfloat16* b, __nv_bfloat16* out, int n) {
    int idx = blockIdx.x * blockDim.x + threadIdx.x;
    if (idx < n) out[idx] = __float2bfloat16(__bfloat162float(a[idx]) + __bfloat162float(b[idx]));
}

// Element-wise mul: out = a * b
__global__ void mul_f32_kernel(const float* a, const float* b, float* out, int n) {
    int idx = blockIdx.x * blockDim.x + threadIdx.x;
    if (idx < n) out[idx] = a[idx] * b[idx];
}
__global__ void mul_bf16_kernel(const __nv_bfloat16* a, const __nv_bfloat16* b, __nv_bfloat16* out, int n) {
    int idx = blockIdx.x * blockDim.x + threadIdx.x;
    if (idx < n) out[idx] = __float2bfloat16(__bfloat162float(a[idx]) * __bfloat162float(b[idx]));
}

extern "C" {

void launch_gelu_f32(const void* x, void* out, int n, void* stream) {
    int block = 256;
    int grid = (n + block - 1) / block;
    gelu_f32<<<grid, block, 0, (cudaStream_t)stream>>>((const float*)x, (float*)out, n);
}

void launch_gelu_bf16(const void* x, void* out, int n, void* stream) {
    int block = 256;
    int grid = (n + block - 1) / block;
    gelu_bf16<<<grid, block, 0, (cudaStream_t)stream>>>(
        (const __nv_bfloat16*)x, (__nv_bfloat16*)out, n);
}

void launch_silu_f32(const void* x, void* out, int n, void* stream) {
    int block = 256;
    int grid = (n + block - 1) / block;
    silu_f32<<<grid, block, 0, (cudaStream_t)stream>>>((const float*)x, (float*)out, n);
}

void launch_silu_bf16(const void* x, void* out, int n, void* stream) {
    int block = 256;
    int grid = (n + block - 1) / block;
    silu_bf16<<<grid, block, 0, (cudaStream_t)stream>>>(
        (const __nv_bfloat16*)x, (__nv_bfloat16*)out, n);
}

void launch_scale_f32(const void* x, void* out, float scale, int n, void* stream) {
    int block = 256;
    int grid = (n + block - 1) / block;
    scale_f32_kernel<<<grid, block, 0, (cudaStream_t)stream>>>(
        (const float*)x, (float*)out, scale, n);
}

void launch_scale_bf16(const void* x, void* out, float scale, int n, void* stream) {
    int block = 256;
    int grid = (n + block - 1) / block;
    scale_bf16_kernel<<<grid, block, 0, (cudaStream_t)stream>>>(
        (const __nv_bfloat16*)x, (__nv_bfloat16*)out, scale, n);
}

void launch_add_f32(const void* a, const void* b, void* out, int n, void* stream) {
    int block = 256;
    int grid = (n + block - 1) / block;
    add_f32_kernel<<<grid, block, 0, (cudaStream_t)stream>>>(
        (const float*)a, (const float*)b, (float*)out, n);
}
void launch_add_bf16(const void* a, const void* b, void* out, int n, void* stream) {
    int block = 256;
    int grid = (n + block - 1) / block;
    add_bf16_kernel<<<grid, block, 0, (cudaStream_t)stream>>>(
        (const __nv_bfloat16*)a, (const __nv_bfloat16*)b, (__nv_bfloat16*)out, n);
}
void launch_mul_f32(const void* a, const void* b, void* out, int n, void* stream) {
    int block = 256;
    int grid = (n + block - 1) / block;
    mul_f32_kernel<<<grid, block, 0, (cudaStream_t)stream>>>(
        (const float*)a, (const float*)b, (float*)out, n);
}
void launch_mul_bf16(const void* a, const void* b, void* out, int n, void* stream) {
    int block = 256;
    int grid = (n + block - 1) / block;
    mul_bf16_kernel<<<grid, block, 0, (cudaStream_t)stream>>>(
        (const __nv_bfloat16*)a, (const __nv_bfloat16*)b, (__nv_bfloat16*)out, n);
}

}