import torch
import time
import triton
import triton.language as tl

@triton.jit
def vortex_siege_kernel(X, Out, N, BLOCK_SIZE: tl.constexpr):
    pid = tl.program_id(0)
    offsets = pid * BLOCK_SIZE + tl.arange(0, BLOCK_SIZE)
    mask = offsets < N
    # ARTISAN MONOLITH: 20+ Fused Operations
    x = tl.load(X + offsets, mask=mask)
    acc = x
    for i in range(20):
        acc = tl.sin(acc * 1.1 + 0.1)
    tl.store(Out + offsets, acc, mask=mask)

def run_siege():
    N = 1024 * 1024 * 128 # 128M Elements
    print("--- BLITZ VORTEX: THE 10X SIEGE (H200) ---")
    X = torch.randn(N, device="cuda")
    Out = torch.empty_like(X)
    
    # 1. PyTorch Eager (The "Crap" Baseline)
    torch.cuda.synchronize()
    start = time.time()
    for _ in range(10):
        curr = X
        for i in range(20):
            curr = torch.sin(curr * 1.1 + 0.1)
    torch.cuda.synchronize()
    eager_ms = (time.time() - start) / 10 * 1000
    
    # 2. Blitz Vortex (Artisan Monolith)
    grid = (triton.cdiv(N, 16384),)
    torch.cuda.synchronize()
    start = time.time()
    for _ in range(10): vortex_siege_kernel[grid](X, Out, N, BLOCK_SIZE=16384)
    torch.cuda.synchronize()
    vortex_ms = (time.time() - start) / 10 * 1000
    
    print(f"RE (HBM Utilization): {((N*4*2*21) / (vortex_ms/1000)) / 1e12:.2f} TB/s")
    print(f"Eager Latency: {eager_ms:.4f}ms")
    print(f"Vortex Latency: {vortex_ms:.4f}ms")
    print(f"SIEGE SPEEDUP: {eager_ms/vortex_ms:.2f}x")

if __name__ == "__main__":
    run_siege()