Thousands of GPUs. No cloud bill.

@group(0) @binding(0) var<uniform> params: Params;
@group(0) @binding(1) var<storage, read_write> hits: atomic<u32>;

struct Params {
  seed_start:         u32,
  num_samples:        u32,
  samples_per_thread: u32,
}

// PCG hash — fast, good statistical properties
fn pcg(x: u32) -> u32 {
  var s = x * 747796405u + 2891336453u;
  var w = ((s >> ((s >> 28u) + 4u)) ^ s) * 277803737u;
  return (w >> 22u) ^ w;
}

@compute @workgroup_size(256)
fn main(@builtin(global_invocation_id) gid: vec3<u32>) {
  let tid = gid.x;
  var state = pcg(pcg(params.seed_start + tid));
  var local_hits: u32 = 0u;
  for (var i: u32 = 0u; i < params.samples_per_thread; i = i + 1u) {
    state = pcg(state);
    let x = f32(state) / 4294967296.0;
    state = pcg(state);
    let y = f32(state) / 4294967296.0;
    if (x*x + y*y < 1.0) { local_hits = local_hits + 1u; }
  }
  atomicAdd(&hits, local_hits);
}

# 1. Upload the kernel
$ curl https://warppool.tech/api/kernels \
    -F "src=@monte_carlo_pi.wgsl"
> { "kernel_id": "wgsl-pi-7f3" }

# 2. Build a chunk manifest — 100 chunks of
# 100M samples each, distinct seed ranges
$ python -c "
import json
print(json.dumps({
  'chunks': [
    {'seed_start': i * (1<<24),
     'num_samples': 100_000_000,
     'samples_per_thread': 256}
    for i in range(100)
  ],
}))" > manifest.json

# 3. Submit the job
$ curl https://warppool.tech/api/jobs \
    -H "Authorization: Bearer $WARPPOOL_TOKEN" \
    -F "kernel_id=wgsl-pi-7f3" \
    -F "manifest=@manifest.json" \
    -F "reducer=sum" \
    -F "redundancy=2"
> { "job_id": "job-9a2c",
    "queued_at": "2026-05-27T14:02:11Z",
    "chunks": 100, "est_seconds": 38 }

# 4. Stream results back
$ curl https://warppool.tech/api/jobs/job-9a2c/stream
event: chunk_done
data: {"chunk":0,"hits":78539701,"by":["w-3f1a","w-92e0"]}
event: chunk_done
data: {"chunk":1,"hits":78540234,"by":["w-441e","w-2bf8"]}
...
event: job_done
data: {"pi":3.14159265,"hits":7853981633}