Optimizations of not-matthias

.github/workflows/codspeed.yml

@@ -1,9 +1,5 @@
 name: CodSpeed Benchmarks
 
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
-  cancel-in-progress: true
-
 on:
   push:
     branches:
@@ -18,21 +14,9 @@ jobs:
     strategy:
       matrix:
         include:
-          - runner: ubuntu-latest
-            mode: instrumentation
-            bench: [hello_world, bfs]
           - runner: codspeed-macro
             mode: walltime
-            bench:
-              [
-                dna_matcher,
-                lut_grayscale_bench,
-                lut_filters_bench,
-                simd_brightness_bench,
-                simd_filters_bench,
-                blob_corruption_checker,
-                blob_corruption_checker,
-              ]
+            bench: [dna_matcher]
     steps:
       - uses: actions/checkout@v4
         with:

Cargo.toml

@@ -11,6 +11,9 @@ path = "src/lib.rs"
 rand = "0.8"
 image = "0.25"
 image-compare = "0.5.0"
+rayon = "1.10"
+memmap2 = "0.9"
+memchr = "2.7.6"
 
 [dev-dependencies]
 divan = { version = "4.0.2", package = "codspeed-divan-compat" }

benches/blob_corruption_checker.rs

@@ -1,14 +1,95 @@
 use divan::Bencher;
-use eurorust_2025_workshop::blob_corruption_checker::find_corruptions_sequential;
+use eurorust_2025_workshop::blob_corruption_checker::{find_corruptions_parallel, find_corruptions_simd, find_corruptions_simd_parallel};
 
 fn main() {
     divan::main();
 }
 
 #[divan::bench(sample_count = 3, sample_size = 5)]
-fn corruption_check(bencher: Bencher) {
+fn corruption_check_sequential(bencher: Bencher) {
     bencher.bench_local(|| {
-        let corruptions = divan::black_box(find_corruptions_sequential(
+        let corruptions = divan::black_box(find_corruptions_simd_parallel(
+            "reference.bin",
+            "corrupted.bin",
+            1024, // 1KB chunks
+        ));
+
+        assert_eq!(corruptions.len(), 50, "Should find 50 corruptions");
+
+        // All corruptions should be 1KB aligned
+        for corruption in &corruptions {
+            assert_eq!(corruption.offset % 1024, 0, "Corruption offset should be 1KB aligned");
+            assert_eq!(corruption.length % 1024, 0, "Corruption length should be multiple of 1KB");
+        }
+
+        // Check specific corruptions
+        assert_eq!(corruptions[0].offset, 14801920, "First corruption offset");
+        assert_eq!(corruptions[0].length, 2048, "First corruption length");
+        assert_eq!(corruptions[25].offset, 243891200, "Middle corruption offset");
+        assert_eq!(corruptions[25].length, 4096, "Middle corruption length");
+        assert_eq!(corruptions[49].offset, 507871232, "Last corruption offset");
+        assert_eq!(corruptions[49].length, 5120, "Last corruption length");
+    });
+}
+
+#[divan::bench(sample_count = 3, sample_size = 5)]
+fn corruption_check_parallel(bencher: Bencher) {
+    bencher.bench_local(|| {
+        let corruptions = divan::black_box(find_corruptions_parallel(
+            "reference.bin",
+            "corrupted.bin",
+            1024, // 1KB chunks
+        ));
+
+        assert_eq!(corruptions.len(), 50, "Should find 50 corruptions");
+
+        // All corruptions should be 1KB aligned
+        for corruption in &corruptions {
+            assert_eq!(corruption.offset % 1024, 0, "Corruption offset should be 1KB aligned");
+            assert_eq!(corruption.length % 1024, 0, "Corruption length should be multiple of 1KB");
+        }
+
+        // Check specific corruptions
+        assert_eq!(corruptions[0].offset, 14801920, "First corruption offset");
+        assert_eq!(corruptions[0].length, 2048, "First corruption length");
+        assert_eq!(corruptions[25].offset, 243891200, "Middle corruption offset");
+        assert_eq!(corruptions[25].length, 4096, "Middle corruption length");
+        assert_eq!(corruptions[49].offset, 507871232, "Last corruption offset");
+        assert_eq!(corruptions[49].length, 5120, "Last corruption length");
+    });
+}
+
+#[divan::bench(sample_count = 3, sample_size = 5)]
+fn corruption_check_simd(bencher: Bencher) {
+    bencher.bench_local(|| {
+        let corruptions = divan::black_box(find_corruptions_simd(
+            "reference.bin",
+            "corrupted.bin",
+            1024, // 1KB chunks
+        ));
+
+        assert_eq!(corruptions.len(), 50, "Should find 50 corruptions");
+
+        // All corruptions should be 1KB aligned
+        for corruption in &corruptions {
+            assert_eq!(corruption.offset % 1024, 0, "Corruption offset should be 1KB aligned");
+            assert_eq!(corruption.length % 1024, 0, "Corruption length should be multiple of 1KB");
+        }
+
+        // Check specific corruptions
+        assert_eq!(corruptions[0].offset, 14801920, "First corruption offset");
+        assert_eq!(corruptions[0].length, 2048, "First corruption length");
+        assert_eq!(corruptions[25].offset, 243891200, "Middle corruption offset");
+        assert_eq!(corruptions[25].length, 4096, "Middle corruption length");
+        assert_eq!(corruptions[49].offset, 507871232, "Last corruption offset");
+        assert_eq!(corruptions[49].length, 5120, "Last corruption length");
+    });
+}
+
+#[divan::bench(sample_count = 3, sample_size = 5)]
+fn corruption_check_simd_parallel(bencher: Bencher) {
+    bencher.bench_local(|| {
+        let corruptions = divan::black_box(find_corruptions_simd_parallel(
             "reference.bin",
             "corrupted.bin",
             1024, // 1KB chunks

benches/dna_matcher.rs

@@ -5,7 +5,7 @@ fn main() {
 }
 
 #[divan::bench(sample_count = 2, sample_size = 3)]
-fn dna_matcher() {
+fn dna_matcher_old() {
     let genome = std::fs::read_to_string("genome.fasta").expect(
         "Failed to read genome.fasta\n\n Make sure to run 'cargo run --release --bin generate_fasta'",
     );
@@ -22,3 +22,62 @@ fn dna_matcher() {
         matches.len()
     );
 }
+
+#[divan::bench(sample_count = 2, sample_size = 3)]
+fn dna_matcher_memchr() {
+    let genome = std::fs::read_to_string("genome.fasta").expect(
+        "Failed to read genome.fasta\n\n Make sure to run 'cargo run --release --bin generate_fasta'",
+    );
+    let pattern = "AGTCCGTA";
+
+    let matches = divan::black_box(memchr_search(
+        divan::black_box(&genome),
+        divan::black_box(pattern),
+    ));
+
+    assert!(
+        matches.len() == 4927,
+        "Expected 4927 matches, found {}",
+        matches.len()
+    );
+}
+
+#[divan::bench(sample_count = 2, sample_size = 3)]
+fn dna_matcher_mmap() {
+    let file = std::fs::File::open("genome.fasta").expect(
+        "Failed to read genome.fasta\n\n Make sure to run 'cargo run --release --bin generate_fasta'",
+    );
+    let mmap = unsafe { memmap2::Mmap::map(&file).expect("Failed to mmap genome.fasta") };
+    let pattern = b"AGTCCGTA";
+
+    let matches = divan::black_box(memchr_search_bytes(
+        divan::black_box(&mmap),
+        divan::black_box(pattern),
+    ));
+
+    assert!(
+        matches.len() == 4927,
+        "Expected 4927 matches, found {}",
+        matches.len()
+    );
+}
+
+#[divan::bench(sample_count = 2, sample_size = 3)]
+fn dna_matcher() {
+    let file = std::fs::File::open("genome.fasta").expect(
+        "Failed to read genome.fasta\n\n Make sure to run 'cargo run --release --bin generate_fasta'",
+    );
+    let mmap = unsafe { memmap2::Mmap::map(&file).expect("Failed to mmap genome.fasta") };
+    let pattern = b"AGTCCGTA";
+
+    let matches = divan::black_box(memchr_search_bytes_parallel(
+        divan::black_box(&mmap),
+        divan::black_box(pattern),
+    ));
+
+    assert!(
+        matches.len() == 4927,
+        "Expected 4927 matches, found {}",
+        matches.len()
+    );
+}