simd int and string parsing on aarch64

.github/workflows/ci.yml

@@ -9,15 +9,19 @@ on:
   pull_request: {}
 
 jobs:
-  test:
-    name: test rust-${{ matrix.rust-version }}
+  test-linux:
+    name: test rust-${{ matrix.rust-version }} on linux
     strategy:
       fail-fast: false
       matrix:
         rust-version: [stable, nightly]
 
     runs-on: ubuntu-latest
 
+    env:
+      RUNS_ON: ubuntu-latest
+      RUST_VERSION: ${{ matrix.rust-version }}
+
     steps:
     - uses: actions/checkout@v3
 
@@ -30,6 +34,55 @@ jobs:
       with:
         toolchain: ${{ matrix.rust-version }}
 
+    - id: cache-rust
+      uses: Swatinem/rust-cache@v2
+      with:
+        prefix-key: "v1-rust"
+
+    - run: cargo install rustfilt coverage-prepare cargo-careful
+      if: steps.cache-rust.outputs.cache-hit != 'true'
+
+    - run: rustup component add llvm-tools-preview
+
+    - run: cargo test -F python
+      env:
+        RUST_BACKTRACE: 1
+        RUSTFLAGS: '-C instrument-coverage'
+
+    - run: coverage-prepare --ignore-filename-regex '/tests/' lcov $(find target/debug/deps -regex '.*/main[^.]*')
+
+    - run: cargo test --doc
+
+    - run: cargo careful t -F python
+      if: matrix.rust-version == 'nightly'
+
+    - uses: codecov/codecov-action@v3
+      with:
+        env_vars: RUNS_ON,RUST_VERSION
+
+  test-macos:
+    name: test on ${{ matrix.runs-on }}
+    strategy:
+      fail-fast: false
+      matrix:
+        runs-on: [macos-latest, macos-latest-xlarge]
+
+    runs-on: ${{ matrix.runs-on }}
+
+    env:
+      RUNS_ON: ${{ matrix.runs-on }}
+      RUST_VERSION: stable
+
+    steps:
+    - uses: actions/checkout@v3
+
+    - name: set up python
+      uses: actions/setup-python@v4
+      with:
+        python-version: '3.11'
+
+    - uses: dtolnay/rust-toolchain@stable
+
     - id: cache-rust
       uses: Swatinem/rust-cache@v2
 
@@ -48,13 +101,15 @@ jobs:
     - run: cargo test --doc
 
     - uses: codecov/codecov-action@v3
+      with:
+        env_vars: RUNS_ON,RUST_VERSION
 
   bench:
     runs-on: ubuntu-latest
     steps:
     - uses: actions/checkout@v3
 
-    - uses: moonrepo/setup-rust@v0
+    - uses: moonrepo/setup-rust@v1
       with:
         channel: stable
         cache-target: release
@@ -70,11 +125,18 @@ jobs:
         token: ${{ secrets.CODSPEED_TOKEN }}
 
   fuzz:
-    runs-on: ubuntu-latest
+    name: fuzz on ${{ matrix.runs-on }}
+    strategy:
+      fail-fast: false
+      matrix:
+        runs-on: [ubuntu-latest, macos-latest-xlarge]
+
+    runs-on: ${{ matrix.runs-on }}
+
     steps:
     - uses: actions/checkout@v3
 
-    - uses: moonrepo/setup-rust@v0
+    - uses: moonrepo/setup-rust@v1
       with:
         channel: nightly
         cache-target: release
@@ -88,7 +150,7 @@ jobs:
     steps:
     - uses: actions/checkout@v3
 
-    - uses: moonrepo/setup-rust@v0
+    - uses: moonrepo/setup-rust@v1
       with:
         channel: stable
         components: rustfmt, clippy
@@ -105,7 +167,7 @@ jobs:
   # https://github.com/marketplace/actions/alls-green#why used for branch protection checks
   check:
     if: always()
-    needs: [test, bench, fuzz, lint]
+    needs: [test-linux, test-macos, bench, fuzz, lint]
     runs-on: ubuntu-latest
     steps:
       - name: Decide whether the needed jobs succeeded or failed

benches/main.rs

@@ -239,6 +239,7 @@ test_cases!(medium_response);
 test_cases!(x100);
 test_cases!(sentence);
 test_cases!(unicode);
+test_cases!(short_numbers);
 
 fn string_array_jiter_value_owned(bench: &mut Bencher) {
     let json = read_file("./benches/string_array.json");
@@ -336,5 +337,8 @@ benchmark_group!(
     lazy_map_lookup_1_10,
     lazy_map_lookup_2_20,
     lazy_map_lookup_3_50,
+    short_numbers_jiter_iter,
+    short_numbers_jiter_value,
+    short_numbers_serde_value,
 );
 benchmark_main!(benches);

benches/python.rs

@@ -51,6 +51,10 @@ fn _python_parse_file(path: &str, bench: &mut Bencher, cache_mode: StringCacheMo
     })
 }
 
+fn python_parse_massive_ints_array(bench: &mut Bencher) {
+    _python_parse_file("./benches/massive_ints_array.json", bench, StringCacheMode::All);
+}
+
 fn python_parse_medium_response_not_cached(bench: &mut Bencher) {
     _python_parse_file("./benches/medium_response.json", bench, StringCacheMode::None);
 }
@@ -111,5 +115,6 @@ benchmark_group!(
     python_parse_x100,
     python_parse_true_object,
     python_parse_true_array,
+    python_parse_massive_ints_array,
 );
 benchmark_main!(benches);

benches/short_numbers.json

@@ -0,0 +1 @@
+[0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942, 0, 142, 242, 342, 442, 542, 642, 742, 842, 942]

src/lazy_index_map.rs

@@ -1,5 +1,4 @@
 use std::borrow::{Borrow, Cow};
-use std::cmp::{Eq, PartialEq};
 use std::fmt;
 use std::hash::Hash;
 use std::slice::Iter as SliceIter;

src/lib.rs

@@ -9,6 +9,8 @@ mod parse;
 mod py_string_cache;
 #[cfg(feature = "python")]
 mod python;
+#[cfg(target_arch = "aarch64")]
+mod simd_aarch64;
 mod string_decoder;
 mod value;