d55b970ab6
Three stacked optimizations, each verified bit-exact against the CPU reference (qp-poseidon-core) by the dual-shader component suite and a new GPU/CPU parity example: - mining_u64.wgsl: native 64-bit Goldilocks arithmetic with plonky2-style lazy reduction, used automatically when the adapter supports SHADER_INT64 (all Apple Silicon, NVIDIA, modern AMD). mining.wgsl remains the 32-bit fallback. (+50%) - Midstate precompute: the first two of five sponge permutations absorb the header and high nonce half, both constant per batch; they are now computed once on the CPU (pow_core::mining_midstate) and resumed on the GPU. Batches are clamped so nonces never carry past 2^256. (+77%) - Lazy second squeeze: the first squeeze yields the most significant 256 bits of the hash, which decide hash-vs-target unless exactly equal to the target's high half, so the common reject path skips the final permutation. (+56%) Apple M4 throughput: 2.81 -> 11.4 MH/s at the default 1M batch (criterion large_range_1m/gpu: 355.8ms -> 86.3ms, -75.7%). Also: - Fix criterion GPU bench crash: thread-local worker resources are now tagged with an engine id so multiple GpuEngines per process never mix devices. - Fix stale end-to-end test harness (6-binding layout) and run the full component suite against both shader variants. - New examples: hashrate, gpu_cpu_parity (25 jobs incl. 2^256-boundary crossing), gpu_features. - Add Apple M5 family GPU tiers. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
53 lines
1.6 KiB
Rust
53 lines
1.6 KiB
Rust
use engine_cpu::{AtomicBoolCancelCheck, MinerEngine, Range};
|
|
use engine_gpu::GpuEngine;
|
|
use primitive_types::U512;
|
|
use std::sync::atomic::AtomicBool;
|
|
|
|
fn main() {
|
|
env_logger::init();
|
|
let args: Vec<String> = std::env::args().collect();
|
|
let total: u64 = args
|
|
.get(1)
|
|
.map(|s| s.parse().expect("total nonces"))
|
|
.unwrap_or(4_000_000);
|
|
let batch: u32 = args
|
|
.get(2)
|
|
.map(|s| s.parse().expect("batch size"))
|
|
.unwrap_or(1_000_000);
|
|
|
|
let engine = GpuEngine::try_new(batch, 0, false).expect("GPU init failed");
|
|
let cancel_flag = AtomicBool::new(false);
|
|
let cancel = AtomicBoolCancelCheck(&cancel_flag);
|
|
|
|
let header = [42u8; 32];
|
|
let ctx = engine.prepare_context(header, U512::from(u64::MAX));
|
|
|
|
let range = Range {
|
|
start: U512::from(1u64) << 200,
|
|
end: (U512::from(1u64) << 200) + U512::from(total - 1),
|
|
};
|
|
|
|
// Warmup
|
|
let warm = Range {
|
|
start: range.start,
|
|
end: range.start + U512::from(200_000u64),
|
|
};
|
|
engine.search_range(&ctx, warm, &cancel);
|
|
|
|
let start = std::time::Instant::now();
|
|
let status = engine.search_range(&ctx, range, &cancel);
|
|
let elapsed = start.elapsed().as_secs_f64();
|
|
|
|
let hashes = match status {
|
|
engine_cpu::EngineStatus::Exhausted { hash_count } => hash_count,
|
|
engine_cpu::EngineStatus::Found { hash_count, .. } => hash_count,
|
|
other => panic!("unexpected status: {other:?}"),
|
|
};
|
|
println!(
|
|
"{} hashes in {:.3}s = {:.3} MH/s",
|
|
hashes,
|
|
elapsed,
|
|
hashes as f64 / elapsed / 1e6
|
|
);
|
|
}
|