Add data generator (#20)

2023-06-03 20:04:13 +01:00
parent c2d09452b3
commit c80e6b6b1e
12 changed files with 472 additions and 112 deletions
--- a/.gitignore
+++ b/.gitignore
@@ -4,3 +4,6 @@ target/
 .vscode/
 .profile*
 .DS_Store
+
+data_*_flex.json
+data_*_haveranswer.f64
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -4,42 +4,51 @@ version = 3

 [[package]]
 name = "anstream"
-version = "0.2.6"
+version = "0.3.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "342258dd14006105c2b75ab1bd7543a03bdf0cfc94383303ac212a04939dff6f"
+checksum = "0ca84f3628370c59db74ee214b3263d58f9aadd9b4fe7e711fd87dc452b7f163"
 dependencies = [
 "anstyle",
 "anstyle-parse",
+ "anstyle-query",
 "anstyle-wincon",
- "concolor-override",
- "concolor-query",
+ "colorchoice",
 "is-terminal",
 "utf8parse",
 ]

 [[package]]
 name = "anstyle"
-version = "0.3.5"
+version = "1.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "23ea9e81bd02e310c216d080f6223c179012256e5151c41db88d12c88a1684d2"
+checksum = "41ed9a86bf92ae6580e0a31281f65a1b1d867c0cc68d5346e2ae128dddfa6a7d"

 [[package]]
 name = "anstyle-parse"
-version = "0.1.1"
+version = "0.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a7d1bb534e9efed14f3e5f44e7dd1a4f709384023a4165199a4241e18dff0116"
+checksum = "e765fd216e48e067936442276d1d57399e37bce53c264d6fefbe298080cb57ee"
 dependencies = [
 "utf8parse",
 ]

 [[package]]
-name = "anstyle-wincon"
-version = "0.2.0"
+name = "anstyle-query"
+version = "1.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c3127af6145b149f3287bb9a0d10ad9c5692dba8c53ad48285e5bec4063834fa"
+checksum = "5ca11d4be1bab0c8bc8734a9aa7bf4ee8316d462a08c6ac5052f888fef5b494b"
+dependencies = [
+ "windows-sys",
+]
+
+[[package]]
+name = "anstyle-wincon"
+version = "1.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "180abfa45703aebe0093f79badacc01b8fd4ea2e35118747e5811127f926e188"
 dependencies = [
 "anstyle",
- "windows-sys 0.45.0",
+ "windows-sys",
 ]

 [[package]]
@@ -66,6 +75,12 @@ version = "1.3.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "bef38d45163c2f1dde094a7dfd33ccf595c92905c8f8f4fdc18d06fb1037718a"

+[[package]]
+name = "byteorder"
+version = "1.4.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "14c189c53d098945499cdfa7ecc63567cf3886b3332b312a5b4585d8d3a6a610"
+
 [[package]]
 name = "cc"
 version = "1.0.79"
@@ -73,10 +88,16 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "50d30906286121d95be3d479533b458f87493b30a4b5f79a607db8f5d11aa91f"

 [[package]]
-name = "clap"
-version = "4.2.1"
+name = "cfg-if"
+version = "1.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "046ae530c528f252094e4a77886ee1374437744b2bff1497aa898bbddbbb29b3"
+checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
+
+[[package]]
+name = "clap"
+version = "4.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b4ed2379f8603fa2b7509891660e802b88c70a79a6427a70abb5968054de2c28"
 dependencies = [
 "clap_builder",
 "clap_derive",
@@ -85,9 +106,9 @@ dependencies = [

 [[package]]
 name = "clap_builder"
-version = "4.2.1"
+version = "4.3.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "223163f58c9a40c3b0a43e1c4b50a9ce09f007ea2cb1ec258a687945b4b7929f"
+checksum = "72394f3339a76daf211e57d4bcb374410f3965dcc606dd0e03738c7888766980"
 dependencies = [
 "anstream",
 "anstyle",
@@ -98,9 +119,9 @@ dependencies = [

 [[package]]
 name = "clap_derive"
-version = "4.2.0"
+version = "4.3.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3f9644cd56d6b87dbe899ef8b053e331c0637664e9e21a33dfcdc36093f5c5c4"
+checksum = "59e9ef9a08ee1c0e1f2e162121665ac45ac3783b0f897db7244ae75ad9a8f65b"
 dependencies = [
 "heck",
 "proc-macro2",
@@ -110,24 +131,15 @@ dependencies = [

 [[package]]
 name = "clap_lex"
-version = "0.4.1"
+version = "0.5.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8a2dd5a6fe8c6e3502f568a6353e5273bbb15193ad9a89e457b9970798efbea1"
+checksum = "2da6da31387c7e4ef160ffab6d5e7f00c42626fe39aea70a7b0f1773f7dd6c1b"

 [[package]]
-name = "concolor-override"
+name = "colorchoice"
 version = "1.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a855d4a1978dc52fb0536a04d384c2c0c1aa273597f08b77c8c4d3b2eec6037f"
-
-[[package]]
-name = "concolor-query"
-version = "0.3.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "88d11d52c3d7ca2e6d0040212be9e4dbbcd78b6447f535b6b561f449427944cf"
-dependencies = [
- "windows-sys 0.45.0",
-]
+checksum = "acbf1af155f9b9ef647e42cdc158db4b64a1b61f743629225fde6f3e0be2a7c7"

 [[package]]
 name = "const_panic"
@@ -157,7 +169,7 @@ checksum = "4bcfec3a70f97c962c307b2d2c56e358cf1d00b558d74262b5f929ee8cc7e73a"
 dependencies = [
 "errno-dragonfly",
 "libc",
- "windows-sys 0.48.0",
+ "windows-sys",
 ]

 [[package]]
@@ -170,6 +182,36 @@ dependencies = [
 "libc",
 ]

+[[package]]
+name = "generator"
+version = "0.1.0"
+dependencies = [
+ "byteorder",
+ "clap",
+ "haversine",
+ "rand",
+ "serde",
+ "serde_json",
+]
+
+[[package]]
+name = "getrandom"
+version = "0.2.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c85e1d9ab2eadba7e5040d4e09cbd6d072b76a557ad64e797c2cb9d4da21d7e4"
+dependencies = [
+ "cfg-if",
+ "libc",
+ "wasi",
+]
+
+[[package]]
+name = "haversine"
+version = "0.1.0"
+dependencies = [
+ "serde",
+]
+
 [[package]]
 name = "heck"
 version = "0.4.1"
@@ -190,7 +232,7 @@ checksum = "9c66c74d2ae7e79a5a8f7ac924adbe38ee42a859c6539ad869eb51f0b52dc220"
 dependencies = [
 "hermit-abi",
 "libc",
- "windows-sys 0.48.0",
+ "windows-sys",
 ]

 [[package]]
@@ -202,9 +244,15 @@ dependencies = [
 "hermit-abi",
 "io-lifetimes",
 "rustix",
- "windows-sys 0.48.0",
+ "windows-sys",
 ]

+[[package]]
+name = "itoa"
+version = "1.0.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "453ad9f582a441959e5f0d088b02ce04cfe8d51a8eaf077f12ac6d3e94164ca6"
+
 [[package]]
 name = "konst_kernel"
 version = "0.3.4"
@@ -251,6 +299,12 @@ version = "1.17.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b7e5500299e16ebb147ae15a00a942af264cf3688f47923b8fc2cd5858f23ad3"

+[[package]]
+name = "ppv-lite86"
+version = "0.2.17"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5b40af805b3121feab8a3c29f04d8ad262fa8e0561883e7653e024ae4479e6de"
+
 [[package]]
 name = "proc-macro2"
 version = "1.0.56"
@@ -269,6 +323,36 @@ dependencies = [
 "proc-macro2",
 ]

+[[package]]
+name = "rand"
+version = "0.8.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "34af8d1a0e25924bc5b7c43c079c942339d8f0a8b57c39049bef581b46327404"
+dependencies = [
+ "libc",
+ "rand_chacha",
+ "rand_core",
+]
+
+[[package]]
+name = "rand_chacha"
+version = "0.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e6c10a63a0fa32252be49d21e7709d4d4baf8d231c2dbce1eaa8141b9b127d88"
+dependencies = [
+ "ppv-lite86",
+ "rand_core",
+]
+
+[[package]]
+name = "rand_core"
+version = "0.6.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ec0be4795e2f6a28069bec0b5ff3e2ac9bafc99e6a9a7dc3547996c5c816922c"
+dependencies = [
+ "getrandom",
+]
+
 [[package]]
 name = "rustix"
 version = "0.37.11"
@@ -280,7 +364,44 @@ dependencies = [
 "io-lifetimes",
 "libc",
 "linux-raw-sys",
- "windows-sys 0.48.0",
+ "windows-sys",
+]
+
+[[package]]
+name = "ryu"
+version = "1.0.13"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f91339c0467de62360649f8d3e185ca8de4224ff281f66000de5eb2a77a79041"
+
+[[package]]
+name = "serde"
+version = "1.0.163"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2113ab51b87a539ae008b5c6c02dc020ffa39afd2d83cffcb3f4eb2722cebec2"
+dependencies = [
+ "serde_derive",
+]
+
+[[package]]
+name = "serde_derive"
+version = "1.0.163"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8c805777e3930c8883389c602315a24224bcc738b63905ef87cd1420353ea93e"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.14",
+]
+
+[[package]]
+name = "serde_json"
+version = "1.0.96"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "057d394a50403bcac12672b2b18fb387ab6d289d957dab67dd201875391e52f1"
+dependencies = [
+ "itoa",
+ "ryu",
+ "serde",
 ]

 [[package]]
@@ -334,13 +455,10 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "711b9620af191e0cdc7468a8d14e709c3dcdb115b36f838e601583af800a370a"

 [[package]]
-name = "windows-sys"
-version = "0.45.0"
+name = "wasi"
+version = "0.11.0+wasi-snapshot-preview1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "75283be5efb2831d37ea142365f009c02ec203cd29a3ebecbc093d52315b66d0"
-dependencies = [
- "windows-targets 0.42.2",
-]
+checksum = "9c8d87e72b64a3b4db28d11ce29237c246188f4f51057d65a7eab63b7987e423"

 [[package]]
 name = "windows-sys"
@@ -348,22 +466,7 @@ version = "0.48.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "677d2418bec65e3338edb076e806bc1ec15693c5d0104683f2efe857f61056a9"
 dependencies = [
- "windows-targets 0.48.0",
-]
-
-[[package]]
-name = "windows-targets"
-version = "0.42.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8e5180c00cd44c9b1c88adb3693291f1cd93605ded80c250a75d472756b4d071"
-dependencies = [
- "windows_aarch64_gnullvm 0.42.2",
- "windows_aarch64_msvc 0.42.2",
- "windows_i686_gnu 0.42.2",
- "windows_i686_msvc 0.42.2",
- "windows_x86_64_gnu 0.42.2",
- "windows_x86_64_gnullvm 0.42.2",
- "windows_x86_64_msvc 0.42.2",
+ "windows-targets",
 ]

 [[package]]
@@ -372,93 +475,51 @@ version = "0.48.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7b1eb6f0cd7c80c79759c929114ef071b87354ce476d9d94271031c0497adfd5"
 dependencies = [
- "windows_aarch64_gnullvm 0.48.0",
- "windows_aarch64_msvc 0.48.0",
- "windows_i686_gnu 0.48.0",
- "windows_i686_msvc 0.48.0",
- "windows_x86_64_gnu 0.48.0",
- "windows_x86_64_gnullvm 0.48.0",
- "windows_x86_64_msvc 0.48.0",
+ "windows_aarch64_gnullvm",
+ "windows_aarch64_msvc",
+ "windows_i686_gnu",
+ "windows_i686_msvc",
+ "windows_x86_64_gnu",
+ "windows_x86_64_gnullvm",
+ "windows_x86_64_msvc",
 ]

-[[package]]
-name = "windows_aarch64_gnullvm"
-version = "0.42.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "597a5118570b68bc08d8d59125332c54f1ba9d9adeedeef5b99b02ba2b0698f8"
-
 [[package]]
 name = "windows_aarch64_gnullvm"
 version = "0.48.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "91ae572e1b79dba883e0d315474df7305d12f569b400fcf90581b06062f7e1bc"

-[[package]]
-name = "windows_aarch64_msvc"
-version = "0.42.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e08e8864a60f06ef0d0ff4ba04124db8b0fb3be5776a5cd47641e942e58c4d43"
-
 [[package]]
 name = "windows_aarch64_msvc"
 version = "0.48.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b2ef27e0d7bdfcfc7b868b317c1d32c641a6fe4629c171b8928c7b08d98d7cf3"

-[[package]]
-name = "windows_i686_gnu"
-version = "0.42.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c61d927d8da41da96a81f029489353e68739737d3beca43145c8afec9a31a84f"
-
 [[package]]
 name = "windows_i686_gnu"
 version = "0.48.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "622a1962a7db830d6fd0a69683c80a18fda201879f0f447f065a3b7467daa241"

-[[package]]
-name = "windows_i686_msvc"
-version = "0.42.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "44d840b6ec649f480a41c8d80f9c65108b92d89345dd94027bfe06ac444d1060"
-
 [[package]]
 name = "windows_i686_msvc"
 version = "0.48.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "4542c6e364ce21bf45d69fdd2a8e455fa38d316158cfd43b3ac1c5b1b19f8e00"

-[[package]]
-name = "windows_x86_64_gnu"
-version = "0.42.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8de912b8b8feb55c064867cf047dda097f92d51efad5b491dfb98f6bbb70cb36"
-
 [[package]]
 name = "windows_x86_64_gnu"
 version = "0.48.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ca2b8a661f7628cbd23440e50b05d705db3686f894fc9580820623656af974b1"

-[[package]]
-name = "windows_x86_64_gnullvm"
-version = "0.42.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "26d41b46a36d453748aedef1486d5c7a85db22e56aff34643984ea85514e94a3"
-
 [[package]]
 name = "windows_x86_64_gnullvm"
 version = "0.48.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7896dbc1f41e08872e9d5e8f8baa8fdd2677f29468c4e156210174edc7f7b953"

-[[package]]
-name = "windows_x86_64_msvc"
-version = "0.42.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9aec5da331524158c6d1a4ac0ab1541149c0b9505fde06423b02f5ef0106b9f0"
-
 [[package]]
 name = "windows_x86_64_msvc"
 version = "0.48.0"
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -1,10 +1,12 @@
 [workspace]
 members = [
    "sim_8086",
-    "wrapper"
+    "wrapper",
+    "generator",
+    "haversine"
 ]

 [profile.release]
 lto = true
 strip = true
-panic = 'abort'
+panic = 'abort'
--- a/2
+++ b/2
--- a/generator/Cargo.toml
+++ b/generator/Cargo.toml
@@ -0,0 +1,15 @@
+[package]
+name = "generator"
+version = "0.1.0"
+edition = "2021"
+
+# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
+
+
+[dependencies]
+clap = { version = "4.3.1", features = [ "derive" ] }
+rand = "0.8.5"
+haversine = { path = "../haversine" }
+serde_json = "1.0.96"
+serde = "1.0.163"
+byteorder = "1.4.3"
--- a/generator/src/main.rs
+++ b/generator/src/main.rs
@@ -0,0 +1,227 @@
+use byteorder::{ByteOrder, LittleEndian};
+use clap::{builder::PossibleValue, Parser, ValueEnum};
+use haversine::haversine::{CoordinatePair, HaversineData};
+use haversine::{distance, earth};
+use rand::distributions::Distribution;
+use rand::rngs::StdRng;
+use rand::{Rng, SeedableRng};
+use std::fmt::{Display, Formatter};
+use std::fs::File;
+use std::io::{BufWriter, Read, Write};
+use std::str::FromStr;
+
+#[derive(Clone, Debug)]
+enum SelectionAlgorithm {
+    Cluster,
+    Uniform,
+}
+
+impl Display for SelectionAlgorithm {
+    fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
+        match self {
+            Self::Cluster => f.write_str("cluster"),
+            Self::Uniform => f.write_str("uniform"),
+        }
+    }
+}
+
+impl FromStr for SelectionAlgorithm {
+    type Err = ();
+
+    fn from_str(s: &str) -> Result<Self, Self::Err> {
+        match s.to_ascii_lowercase().as_str() {
+            "cluster" => Ok(SelectionAlgorithm::Cluster),
+            "uniform" => Ok(SelectionAlgorithm::Uniform),
+            _ => Err(()),
+        }
+    }
+}
+
+impl ValueEnum for SelectionAlgorithm {
+    fn value_variants<'a>() -> &'a [Self] {
+        &[SelectionAlgorithm::Cluster, SelectionAlgorithm::Uniform]
+    }
+    fn to_possible_value(&self) -> Option<PossibleValue> {
+        match self {
+            SelectionAlgorithm::Cluster => Some(PossibleValue::new("cluster")),
+            SelectionAlgorithm::Uniform => Some(PossibleValue::new("uniform")),
+        }
+    }
+}
+
+#[derive(Parser, Debug)]
+struct Args {
+    #[arg(value_name = "RANDOM_SEED", required = true)]
+    seed: u64,
+    #[arg(value_name = "COUNT", required = true)]
+    count: usize,
+    #[arg(default_value_t = SelectionAlgorithm::Cluster, long)]
+    algorithm: SelectionAlgorithm,
+}
+
+fn write_json(data: &HaversineData, json_filename: &str) {
+    let output_file = File::create(json_filename).unwrap();
+    let mut writer = BufWriter::new(output_file);
+
+    serde_json::to_writer(&mut writer, &data).unwrap();
+    writer.flush().unwrap();
+}
+
+fn write_answer(data: &HaversineData, binary_filename: &str) {
+    let output_file = File::create(binary_filename).unwrap();
+    let mut writer = BufWriter::new(output_file);
+
+    let mut expected_sum: f64 = 0.0;
+
+    let mut buf = [0u8; 8];
+    for point in &data.pairs {
+        let distance = distance::naive(point, earth::RADIUS);
+        LittleEndian::write_f64(&mut buf, distance);
+
+        let written = writer.write(&buf).unwrap();
+        if written < buf.len() {
+            panic!("Failed to write everything")
+        }
+
+        expected_sum += distance;
+    }
+
+    println!("Expected sum: {}", expected_sum);
+
+    LittleEndian::write_f64(&mut buf, expected_sum);
+    let written = writer.write(&buf).unwrap();
+    if written < buf.len() {
+        panic!("Failed to write everything")
+    }
+
+    writer.flush().unwrap();
+}
+
+#[allow(dead_code)]
+fn read_answer(binary_filename: &str) -> (Vec<f64>, f64) {
+    let mut file = File::create(binary_filename).unwrap();
+    let file_size = file.metadata().unwrap().len();
+    if file_size % 8 != 0 {
+        panic!(
+            "Malformed input file of size {} is not a multiple of 8",
+            file_size
+        )
+    }
+    let num_floats = file_size / 8;
+    assert_ne!(num_floats, 0, "Empty file");
+    let num_bytes = num_floats - 1;
+
+    let mut data = Vec::with_capacity(num_bytes as usize);
+    let mut buf = [0u8, 8];
+
+    for _ in 0..num_floats {
+        let bytes_read = file.read(&mut buf).unwrap();
+        if bytes_read < 8 {
+            panic!("Not enough bytes read")
+        }
+
+        data.push(LittleEndian::read_f64(&buf));
+    }
+
+    let bytes_read = file.read(&mut buf).unwrap();
+    if bytes_read < 8 {
+        panic!("Not enough bytes read")
+    }
+
+    (data, LittleEndian::read_f64(&buf))
+}
+
+fn point_within(
+    point: &CoordinatePair,
+    cluster_centre_x: f64,
+    cluster_centre_y: f64,
+    cluster_radius: f64,
+) -> bool {
+    let mut distance = CoordinatePair {
+        x0: point.x0,
+        y0: point.y0,
+        x1: cluster_centre_x,
+        y1: cluster_centre_y,
+    };
+    if distance::naive(&distance, 1.0) > cluster_radius {
+        return false;
+    }
+
+    distance.x0 = point.x1;
+    distance.y0 = point.y1;
+
+    distance::naive(&distance, 1.0) <= cluster_radius
+}
+
+const CLUSTER_COUNT: usize = 20;
+
+fn main() {
+    let args = Args::parse();
+    println!("Method: {}", args.algorithm);
+    println!("Random seed: {}", args.seed);
+    println!("Pair count: {}", args.count);
+
+    let mut v = Vec::with_capacity(args.count);
+    let mut rng = StdRng::seed_from_u64(args.seed);
+
+    let x_range = rand::distributions::Uniform::from(-180.0..180.0);
+    let y_range = rand::distributions::Uniform::from(-90.0..90.0);
+
+    match args.algorithm {
+        SelectionAlgorithm::Uniform => {
+            for _ in 0usize..args.count {
+                let point = CoordinatePair {
+                    x0: x_range.sample(&mut rng),
+                    y0: y_range.sample(&mut rng),
+                    x1: x_range.sample(&mut rng),
+                    y1: y_range.sample(&mut rng),
+                };
+
+                v.push(point);
+            }
+        }
+        SelectionAlgorithm::Cluster => {
+            if args.count % CLUSTER_COUNT != 0 {
+                panic!(
+                    "Number of points {} is not a multiple of cluster count {CLUSTER_COUNT}",
+                    args.count
+                );
+            }
+
+            for _ in 0..CLUSTER_COUNT {
+                // Uniformly sampling over lat/long pairs is dumb and biased towards the poles,
+                // but :shrug: we'll just bias it away a bit by hand.
+                let cluster_centre_x = x_range.sample(&mut rng);
+                // Bias a bit away from the pole by shrinking it
+                let cluster_centre_y = y_range.sample(&mut rng) * 0.9;
+                let cluster_radius = rng.gen_range(0.1..0.4);
+
+                for _ in 0..args.count / CLUSTER_COUNT {
+                    let mut point = CoordinatePair {
+                        x0: 0.0,
+                        y0: 0.0,
+                        x1: 0.0,
+                        // too big to ever be in the right place, so a suitable uninitialised value
+                        y1: 1000.0,
+                    };
+                    while !point_within(&point, cluster_centre_x, cluster_centre_y, cluster_radius)
+                    {
+                        point.x0 = x_range.sample(&mut rng);
+                        point.y0 = y_range.sample(&mut rng);
+                        point.x1 = x_range.sample(&mut rng);
+                        point.y1 = y_range.sample(&mut rng);
+                    }
+
+                    v.push(point);
+                }
+            }
+        }
+    }
+
+    let data = HaversineData { pairs: v };
+    let json_filename = format!("data_{}_flex.json", args.count);
+    write_json(&data, &json_filename);
+
+    let answer_filename = format!("data_{}_haveranswer.f64", args.count);
+    write_answer(&data, &answer_filename);
+}
--- a/haversine/Cargo.toml
+++ b/haversine/Cargo.toml
@@ -0,0 +1,11 @@
+[package]
+name = "haversine"
+version = "0.1.0"
+edition = "2021"
+
+[lib]
+
+# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
+
+[dependencies]
+serde = { version = "1.0.163", features = [ "derive" ] }
--- a/haversine/src/distance.rs
+++ b/haversine/src/distance.rs
@@ -0,0 +1,23 @@
+use crate::haversine::CoordinatePair;
+
+fn square(x: f64) -> f64 {
+    x * x
+}
+
+pub fn naive(point: &CoordinatePair, earth_radius: f64) -> f64 {
+    let lat1 = point.y0;
+    let lat2 = point.y1;
+    let lon1 = point.x0;
+    let lon2 = point.x1;
+
+    let lat_deg = (lat2 - lat1).to_radians();
+    let lon_deg = (lon2 - lon1).to_radians();
+    let lat1 = lat1.to_radians();
+    let lat2 = lat2.to_radians();
+
+    let a = square(f64::sin(lat_deg / 2.0))
+        + f64::cos(lat1) * f64::cos(lat2) * square(f64::sin(lon_deg / 2.0));
+    let c = 2.0 * f64::asin(f64::sqrt(a));
+
+    earth_radius * c
+}
--- a/haversine/src/earth.rs
+++ b/haversine/src/earth.rs
@@ -0,0 +1 @@
+pub const RADIUS: f64 = 6372.8;
--- a/haversine/src/haversine.rs
+++ b/haversine/src/haversine.rs
@@ -0,0 +1,14 @@
+use serde::Serialize;
+
+#[derive(Serialize)]
+pub struct CoordinatePair {
+    pub x0: f64,
+    pub y0: f64,
+    pub x1: f64,
+    pub y1: f64,
+}
+
+#[derive(Serialize)]
+pub struct HaversineData {
+    pub pairs: Vec<CoordinatePair>,
+}
--- a/haversine/src/lib.rs
+++ b/haversine/src/lib.rs
@@ -0,0 +1,3 @@
+pub mod distance;
+pub mod earth;
+pub mod haversine;
--- a/wrapper/Cargo.toml
+++ b/wrapper/Cargo.toml
@@ -6,5 +6,5 @@ edition = "2021"
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html

 [dependencies]
-clap = { version = "4.2.1", features = [ "derive" ] }
-sim_8086 = { path = "../sim_8086" }
+clap = { version = "4.3.1", features = [ "derive" ] }
+sim_8086 = { path = "../sim_8086" }