Use faster hash map implementation

Cargo.toml

@@ -10,6 +10,7 @@ threadpool = "1.7"
 lazy_static = "1.1"
 rand = "0.5.5"
 itertools = "0.7.8"
+hashbrown = "0.1"
 
 [dependencies.nix]
 version = "0.9"

LICENSE-THIRD-PARTY.txt

@@ -198,6 +198,7 @@ Library.
 ** lazy_static
 ** rand
 ** itertools
+** hashbrown
                              Apache License
                         Version 2.0, January 2004
                      http://www.apache.org/licenses/

README.md

@@ -41,7 +41,7 @@ git clone https://github.com/awslabs/fast-pseudoprimes.git
 cd fast-pseudoprimes
 cargo +nightly run --features numa,unstable --release
 ```
-The code takes about 24 seconds to run from start to finish.
+The code takes about 21.9 seconds to run from start to finish.
 
 ## Status of this code
 This code is released as-is, and we have no plans to maintain it. We are happy to accept pull requests.

src/bloomfilter/mod.rs

@@ -7,7 +7,7 @@ use numa_threadpool::ThreadPool;
 
 use std::sync::{Mutex, Arc, mpsc::channel};
 use std::sync::atomic::{Ordering, AtomicUsize};
-use std::collections::HashMap;
+use hashbrown::HashMap;
 use std::time::Instant;
 
 mod conc_bloom;
@@ -230,6 +230,7 @@ pub fn final_sieve(
     t1: &[u64],
     t2: &[u64]
 ) -> Vec<Pseudoprime> {
+    let total = Instant::now();
     let t2map = Arc::new(t2map);
     let pool = ThreadPool::new(|_| ());
     let t1_product_set = Arc::new(ProductSet::new(t1_forward, MODULUS));
@@ -264,6 +265,8 @@ pub fn final_sieve(
 
     let t3_misses = t3_misses.load(Ordering::SeqCst);
 
+    println!("[final_sieve] Completed in {}ms", total.elapsed().as_millis());
+
     println!("Found {} pseudoprimes, with {} T3 misses, {} T2 false positives",
         results.len(), t3_misses, t2map.len() - t3_misses - results.len());
 

src/lib.rs

@@ -2,6 +2,7 @@
 // SPDX-License-Identifier: Apache-2.0
 
 #![allow(dead_code)]
+#![cfg_attr(feature = "unstable", feature(duration_as_u128))]
 #![cfg_attr(feature = "unstable", feature(asm))]
 #![cfg_attr(feature = "unstable", feature(core_intrinsics))]
 #![cfg_attr(feature = "unstable", feature(avx512_target_feature))]
@@ -11,6 +12,8 @@ extern crate lazy_static;
 extern crate modinverse;
 extern crate rug;
 extern crate threadpool;
+extern crate hashbrown;
+
 #[cfg(feature="unstable")]
 extern crate libc;
 extern crate itertools;

src/main.rs

@@ -2,6 +2,7 @@
 // SPDX-License-Identifier: Apache-2.0
 
 #![cfg_attr(feature = "unstable", feature(asm))]
+#![cfg_attr(feature = "unstable", feature(duration_as_u128))]
 
 extern crate pseudoprimes;
 extern crate rug;
@@ -21,6 +22,7 @@ fn main() {
 
     // fp p<=0.001, 32GiB, k=2
     let filter = bloom_t1(&T1_INVERSE);
+    println!("[timing]: bloom_t1 {} milliseconds", total.elapsed().as_millis());
 
     let t2_map = build_t2(filter, &T2);
 
@@ -32,5 +34,6 @@ fn main() {
         println!("Found passing prime {}, vector {:?}", result.pseudoprime, result.factors);
     }
 
+    println!("[total]: Completed in {}ms", total.elapsed().as_millis());
     println!("Total time: {} seconds, primes found: {}", total.elapsed().as_secs(), results.len());
 }

src/progress.rs

@@ -27,8 +27,8 @@ impl<'a> Drop for ProgressHandle<'a> {
 
 impl<'a> Drop for ProgressReporter {
     fn drop(&mut self) {
-        println!("[{}] Completed {} in {}s", self.desc, self.counter.load(Ordering::SeqCst),
-            self.start_time.elapsed().as_secs());
+        println!("[{}] Completed {} in {}ms", self.desc, self.counter.load(Ordering::SeqCst),
+            self.start_time.elapsed().as_millis());
     }
 }