misc optimizations

Cargo.toml

@@ -9,3 +9,8 @@ edition = "2021"
 anyhow = "1.0"
 cached = "0.26.2"
 itertools = "0.10.1"
+
+[profile.release]
+lto = true
+codegen-units = 1
+panic = "abort"

flamegraph.svg

@@ -0,0 +1,414 @@
+<?xml version="1.0" standalone="no"?><!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd"><svg version="1.1" width="1200" height="294" onload="init(evt)" viewBox="0 0 1200 294" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:fg="http://github.com/jonhoo/inferno"><!--Flame graph stack visualization. See https://github.com/brendangregg/FlameGraph for latest version, and http://www.brendangregg.com/flamegraphs.html for examples.--><!--NOTES: --><defs><linearGradient id="background" y1="0" y2="1" x1="0" x2="0"><stop stop-color="#eeeeee" offset="5%"/><stop stop-color="#eeeeb0" offset="95%"/></linearGradient></defs><style type="text/css">
+text { font-family:"Verdana"; font-size:12px; fill:rgb(0,0,0); }
+#title { text-anchor:middle; font-size:17px; }
+#search { opacity:0.1; cursor:pointer; }
+#search:hover, #search.show { opacity:1; }
+#subtitle { text-anchor:middle; font-color:rgb(160,160,160); }
+#unzoom { cursor:pointer; }
+#frames > *:hover { stroke:black; stroke-width:0.5; cursor:pointer; }
+.hide { display:none; }
+.parent { opacity:0.5; }
+</style><script type="text/ecmascript"><![CDATA[
+        var nametype = 'Function:';
+        var fontsize = 12;
+        var fontwidth = 0.59;
+        var xpad = 10;
+        var inverted = false;
+        var searchcolor = 'rgb(230,0,230)';
+        var fluiddrawing = true;
+        var truncate_text_right = false;
+    ]]><![CDATA["use strict";
+var details, searchbtn, unzoombtn, matchedtxt, svg, searching, frames;
+function init(evt) {
+    details = document.getElementById("details").firstChild;
+    searchbtn = document.getElementById("search");
+    unzoombtn = document.getElementById("unzoom");
+    matchedtxt = document.getElementById("matched");
+    svg = document.getElementsByTagName("svg")[0];
+    frames = document.getElementById("frames");
+    total_samples = parseInt(frames.attributes.total_samples.value);
+    searching = 0;
+
+    // Use GET parameters to restore a flamegraph's state.
+    var restore_state = function() {
+        var params = get_params();
+        if (params.x && params.y)
+            zoom(find_group(document.querySelector('[*|x="' + params.x + '"][y="' + params.y + '"]')));
+        if (params.s)
+            search(params.s);
+    };
+
+    if (fluiddrawing) {
+        // Make width dynamic so the SVG fits its parent's width.
+        svg.removeAttribute("width");
+        // Edge requires us to have a viewBox that gets updated with size changes.
+        var isEdge = /Edge\/\d./i.test(navigator.userAgent);
+        if (!isEdge) {
+          svg.removeAttribute("viewBox");
+        }
+        var update_for_width_change = function() {
+            if (isEdge) {
+                svg.attributes.viewBox.value = "0 0 " + svg.width.baseVal.value + " " + svg.height.baseVal.value;
+            }
+
+            // Keep consistent padding on left and right of frames container.
+            frames.attributes.width.value = svg.width.baseVal.value - xpad * 2;
+
+            // Text truncation needs to be adjusted for the current width.
+            var el = frames.children;
+            for(var i = 0; i < el.length; i++) {
+                update_text(el[i]);
+            }
+
+            // Keep search elements at a fixed distance from right edge.
+            var svgWidth = svg.width.baseVal.value;
+            searchbtn.attributes.x.value = svgWidth - xpad - 100;
+            matchedtxt.attributes.x.value = svgWidth - xpad - 100;
+        };
+        window.addEventListener('resize', function() {
+            update_for_width_change();
+        });
+        // This needs to be done asynchronously for Safari to work.
+        setTimeout(function() {
+            unzoom();
+            update_for_width_change();
+            restore_state();
+        }, 0);
+    } else {
+        restore_state();
+    }
+}
+// event listeners
+window.addEventListener("click", function(e) {
+    var target = find_group(e.target);
+    if (target) {
+        if (target.nodeName == "a") {
+            if (e.ctrlKey === false) return;
+            e.preventDefault();
+        }
+        if (target.classList.contains("parent")) unzoom();
+        zoom(target);
+
+        // set parameters for zoom state
+        var el = target.querySelector("rect");
+        if (el && el.attributes && el.attributes.y && el.attributes["fg:x"]) {
+            var params = get_params()
+            params.x = el.attributes["fg:x"].value;
+            params.y = el.attributes.y.value;
+            history.replaceState(null, null, parse_params(params));
+        }
+    }
+    else if (e.target.id == "unzoom") {
+        unzoom();
+
+        // remove zoom state
+        var params = get_params();
+        if (params.x) delete params.x;
+        if (params.y) delete params.y;
+        history.replaceState(null, null, parse_params(params));
+    }
+    else if (e.target.id == "search") search_prompt();
+}, false)
+// mouse-over for info
+// show
+window.addEventListener("mouseover", function(e) {
+    var target = find_group(e.target);
+    if (target) details.nodeValue = nametype + " " + g_to_text(target);
+}, false)
+// clear
+window.addEventListener("mouseout", function(e) {
+    var target = find_group(e.target);
+    if (target) details.nodeValue = ' ';
+}, false)
+// ctrl-F for search
+window.addEventListener("keydown",function (e) {
+    if (e.keyCode === 114 || (e.ctrlKey && e.keyCode === 70)) {
+        e.preventDefault();
+        search_prompt();
+    }
+}, false)
+// functions
+function get_params() {
+    var params = {};
+    var paramsarr = window.location.search.substr(1).split('&');
+    for (var i = 0; i < paramsarr.length; ++i) {
+        var tmp = paramsarr[i].split("=");
+        if (!tmp[0] || !tmp[1]) continue;
+        params[tmp[0]]  = decodeURIComponent(tmp[1]);
+    }
+    return params;
+}
+function parse_params(params) {
+    var uri = "?";
+    for (var key in params) {
+        uri += key + '=' + encodeURIComponent(params[key]) + '&';
+    }
+    if (uri.slice(-1) == "&")
+        uri = uri.substring(0, uri.length - 1);
+    if (uri == '?')
+        uri = window.location.href.split('?')[0];
+    return uri;
+}
+function find_child(node, selector) {
+    var children = node.querySelectorAll(selector);
+    if (children.length) return children[0];
+    return;
+}
+function find_group(node) {
+    var parent = node.parentElement;
+    if (!parent) return;
+    if (parent.id == "frames") return node;
+    return find_group(parent);
+}
+function orig_save(e, attr, val) {
+    if (e.attributes["fg:orig_" + attr] != undefined) return;
+    if (e.attributes[attr] == undefined) return;
+    if (val == undefined) val = e.attributes[attr].value;
+    e.setAttribute("fg:orig_" + attr, val);
+}
+function orig_load(e, attr) {
+    if (e.attributes["fg:orig_"+attr] == undefined) return;
+    e.attributes[attr].value = e.attributes["fg:orig_" + attr].value;
+    e.removeAttribute("fg:orig_" + attr);
+}
+function g_to_text(e) {
+    var text = find_child(e, "title").firstChild.nodeValue;
+    return (text)
+}
+function g_to_func(e) {
+    var func = g_to_text(e);
+    // if there's any manipulation we want to do to the function
+    // name before it's searched, do it here before returning.
+    return (func);
+}
+function update_text(e) {
+    var r = find_child(e, "rect");
+    var t = find_child(e, "text");
+    var w = parseFloat(r.attributes.width.value) * frames.attributes.width.value / 100 - 3;
+    var txt = find_child(e, "title").textContent.replace(/\([^(]*\)$/,"");
+    t.attributes.x.value = format_percent((parseFloat(r.attributes.x.value) + (100 * 3 / frames.attributes.width.value)));
+    // Smaller than this size won't fit anything
+    if (w < 2 * fontsize * fontwidth) {
+        t.textContent = "";
+        return;
+    }
+    t.textContent = txt;
+    // Fit in full text width
+    if (/^ *\$/.test(txt) || t.getComputedTextLength() < w)
+        return;
+    if (truncate_text_right) {
+        // Truncate the right side of the text.
+        for (var x = txt.length - 2; x > 0; x--) {
+            if (t.getSubStringLength(0, x + 2) <= w) {
+                t.textContent = txt.substring(0, x) + "..";
+                return;
+            }
+        }
+    } else {
+        // Truncate the left side of the text.
+        for (var x = 2; x < txt.length; x++) {
+            if (t.getSubStringLength(x - 2, txt.length) <= w) {
+                t.textContent = ".." + txt.substring(x, txt.length);
+                return;
+            }
+        }
+    }
+    t.textContent = "";
+}
+// zoom
+function zoom_reset(e) {
+    if (e.tagName == "rect") {
+        e.attributes.x.value = format_percent(100 * parseInt(e.attributes["fg:x"].value) / total_samples);
+        e.attributes.width.value = format_percent(100 * parseInt(e.attributes["fg:w"].value) / total_samples);
+    }
+    if (e.childNodes == undefined) return;
+    for(var i = 0, c = e.childNodes; i < c.length; i++) {
+        zoom_reset(c[i]);
+    }
+}
+function zoom_child(e, x, zoomed_width_samples) {
+    if (e.tagName == "text") {
+        var parent_x = parseFloat(find_child(e.parentNode, "rect[x]").attributes.x.value);
+        e.attributes.x.value = format_percent(parent_x + (100 * 3 / frames.attributes.width.value));
+    } else if (e.tagName == "rect") {
+        e.attributes.x.value = format_percent(100 * (parseInt(e.attributes["fg:x"].value) - x) / zoomed_width_samples);
+        e.attributes.width.value = format_percent(100 * parseInt(e.attributes["fg:w"].value) / zoomed_width_samples);
+    }
+    if (e.childNodes == undefined) return;
+    for(var i = 0, c = e.childNodes; i < c.length; i++) {
+        zoom_child(c[i], x, zoomed_width_samples);
+    }
+}
+function zoom_parent(e) {
+    if (e.attributes) {
+        if (e.attributes.x != undefined) {
+            e.attributes.x.value = "0.0%";
+        }
+        if (e.attributes.width != undefined) {
+            e.attributes.width.value = "100.0%";
+        }
+    }
+    if (e.childNodes == undefined) return;
+    for(var i = 0, c = e.childNodes; i < c.length; i++) {
+        zoom_parent(c[i]);
+    }
+}
+function zoom(node) {
+    var attr = find_child(node, "rect").attributes;
+    var width = parseInt(attr["fg:w"].value);
+    var xmin = parseInt(attr["fg:x"].value);
+    var xmax = xmin + width;
+    var ymin = parseFloat(attr.y.value);
+    unzoombtn.classList.remove("hide");
+    var el = frames.children;
+    for (var i = 0; i < el.length; i++) {
+        var e = el[i];
+        var a = find_child(e, "rect").attributes;
+        var ex = parseInt(a["fg:x"].value);
+        var ew = parseInt(a["fg:w"].value);
+        // Is it an ancestor
+        if (!inverted) {
+            var upstack = parseFloat(a.y.value) > ymin;
+        } else {
+            var upstack = parseFloat(a.y.value) < ymin;
+        }
+        if (upstack) {
+            // Direct ancestor
+            if (ex <= xmin && (ex+ew) >= xmax) {
+                e.classList.add("parent");
+                zoom_parent(e);
+                update_text(e);
+            }
+            // not in current path
+            else
+                e.classList.add("hide");
+        }
+        // Children maybe
+        else {
+            // no common path
+            if (ex < xmin || ex >= xmax) {
+                e.classList.add("hide");
+            }
+            else {
+                zoom_child(e, xmin, width);
+                update_text(e);
+            }
+        }
+    }
+}
+function unzoom() {
+    unzoombtn.classList.add("hide");
+    var el = frames.children;
+    for(var i = 0; i < el.length; i++) {
+        el[i].classList.remove("parent");
+        el[i].classList.remove("hide");
+        zoom_reset(el[i]);
+        update_text(el[i]);
+    }
+}
+// search
+function reset_search() {
+    var el = document.querySelectorAll("#frames rect");
+    for (var i = 0; i < el.length; i++) {
+        orig_load(el[i], "fill")
+    }
+    var params = get_params();
+    delete params.s;
+    history.replaceState(null, null, parse_params(params));
+}
+function search_prompt() {
+    if (!searching) {
+        var term = prompt("Enter a search term (regexp " +
+            "allowed, eg: ^ext4_)", "");
+        if (term != null) {
+            search(term)
+        }
+    } else {
+        reset_search();
+        searching = 0;
+        searchbtn.classList.remove("show");
+        searchbtn.firstChild.nodeValue = "Search"
+        matchedtxt.classList.add("hide");
+        matchedtxt.firstChild.nodeValue = ""
+    }
+}
+function search(term) {
+    var re = new RegExp(term);
+    var el = frames.children;
+    var matches = new Object();
+    var maxwidth = 0;
+    for (var i = 0; i < el.length; i++) {
+        var e = el[i];
+        // Skip over frames which are either not visible, or below the zoomed-to frame
+        if (e.classList.contains("hide") || e.classList.contains("parent")) {
+            continue;
+        }
+        var func = g_to_func(e);
+        var rect = find_child(e, "rect");
+        if (func == null || rect == null)
+            continue;
+        // Save max width. Only works as we have a root frame
+        var w = parseInt(rect.attributes["fg:w"].value);
+        if (w > maxwidth)
+            maxwidth = w;
+        if (func.match(re)) {
+            // highlight
+            var x = parseInt(rect.attributes["fg:x"].value);
+            orig_save(rect, "fill");
+            rect.attributes.fill.value = searchcolor;
+            // remember matches
+            if (matches[x] == undefined) {
+                matches[x] = w;
+            } else {
+                if (w > matches[x]) {
+                    // overwrite with parent
+                    matches[x] = w;
+                }
+            }
+            searching = 1;
+        }
+    }
+    if (!searching)
+        return;
+    var params = get_params();
+    params.s = term;
+    history.replaceState(null, null, parse_params(params));
+
+    searchbtn.classList.add("show");
+    searchbtn.firstChild.nodeValue = "Reset Search";
+    // calculate percent matched, excluding vertical overlap
+    var count = 0;
+    var lastx = -1;
+    var lastw = 0;
+    var keys = Array();
+    for (k in matches) {
+        if (matches.hasOwnProperty(k))
+            keys.push(k);
+    }
+    // sort the matched frames by their x location
+    // ascending, then width descending
+    keys.sort(function(a, b){
+        return a - b;
+    });
+    // Step through frames saving only the biggest bottom-up frames
+    // thanks to the sort order. This relies on the tree property
+    // where children are always smaller than their parents.
+    for (var k in keys) {
+        var x = parseInt(keys[k]);
+        var w = matches[keys[k]];
+        if (x >= lastx + lastw) {
+            count += w;
+            lastx = x;
+            lastw = w;
+        }
+    }
+    // display matched percent
+    matchedtxt.classList.remove("hide");
+    var pct = 100 * count / maxwidth;
+    if (pct != 100) pct = pct.toFixed(1);
+    matchedtxt.firstChild.nodeValue = "Matched: " + pct + "%";
+}
+function format_percent(n) {
+    return n.toFixed(4) + "%";
+}
+]]></script><rect x="0" y="0" width="100%" height="294" fill="url(#background)"/><text id="title" x="50.0000%" y="24.00">Flame Graph</text><text id="details" x="10" y="277.00"> </text><text id="unzoom" class="hide" x="10" y="24.00">Reset Zoom</text><text id="search" x="1090" y="24.00">Search</text><text id="matched" x="1090" y="277.00"> </text><svg id="frames" x="10" width="1180" total_samples="37403"><g><title>aoc2021`&lt;core::iter::adapters::flatten::Flatten&lt;I&gt; as core::iter::traits::iterator::Iterator&gt;::next (17 samples, 0.05%)</title><rect x="0.0107%" y="149" width="0.0455%" height="15" fill="rgb(227,0,7)" fg:x="4" fg:w="17"/><text x="0.2607%" y="159.50"></text></g><g><title>libsystem_malloc.dylib`malloc_zone_realloc (7 samples, 0.02%)</title><rect x="0.5080%" y="85" width="0.0187%" height="15" fill="rgb(217,0,24)" fg:x="190" fg:w="7"/><text x="0.7580%" y="95.50"></text></g><g><title>libsystem_malloc.dylib`szone_realloc (5 samples, 0.01%)</title><rect x="0.5133%" y="69" width="0.0134%" height="15" fill="rgb(221,193,54)" fg:x="192" fg:w="5"/><text x="0.7633%" y="79.50"></text></g><g><title>aoc2021`alloc::raw_vec::RawVec&lt;T,A&gt;::reserve::do_reserve_and_handle (9 samples, 0.02%)</title><rect x="0.5053%" y="133" width="0.0241%" height="15" fill="rgb(248,212,6)" fg:x="189" fg:w="9"/><text x="0.7553%" y="143.50"></text></g><g><title>aoc2021`alloc::raw_vec::finish_grow (9 samples, 0.02%)</title><rect x="0.5053%" y="117" width="0.0241%" height="15" fill="rgb(208,68,35)" fg:x="189" fg:w="9"/><text x="0.7553%" y="127.50"></text></g><g><title>libsystem_malloc.dylib`realloc (8 samples, 0.02%)</title><rect x="0.5080%" y="101" width="0.0214%" height="15" fill="rgb(232,128,0)" fg:x="190" fg:w="8"/><text x="0.7580%" y="111.50"></text></g><g><title>aoc2021`core::str::iter::SplitInternal&lt;P&gt;::next (205 samples, 0.55%)</title><rect x="0.5294%" y="133" width="0.5481%" height="15" fill="rgb(207,160,47)" fg:x="198" fg:w="205"/><text x="0.7794%" y="143.50"></text></g><g><title>libsystem_platform.dylib`_platform_memcmp (24 samples, 0.06%)</title><rect x="1.0133%" y="117" width="0.0642%" height="15" fill="rgb(228,23,34)" fg:x="379" fg:w="24"/><text x="1.2633%" y="127.50"></text></g><g><title>aoc2021`aoc2021::day01::run (391 samples, 1.05%)</title><rect x="0.0722%" y="149" width="1.0454%" height="15" fill="rgb(218,30,26)" fg:x="27" fg:w="391"/><text x="0.3222%" y="159.50"></text></g><g><title>libsystem_platform.dylib`_platform_memcmp (15 samples, 0.04%)</title><rect x="1.0775%" y="133" width="0.0401%" height="15" fill="rgb(220,122,19)" fg:x="403" fg:w="15"/><text x="1.3275%" y="143.50"></text></g><g><title>aoc2021`aoc2021::day02::parse_line (22 samples, 0.06%)</title><rect x="1.1176%" y="149" width="0.0588%" height="15" fill="rgb(250,228,42)" fg:x="418" fg:w="22"/><text x="1.3676%" y="159.50"></text></g><g><title>aoc2021`DYLD-STUB$$memcmp (7 samples, 0.02%)</title><rect x="1.2940%" y="133" width="0.0187%" height="15" fill="rgb(240,193,28)" fg:x="484" fg:w="7"/><text x="1.5440%" y="143.50"></text></g><g><title>aoc2021`aoc2021::day02::parse_line (173 samples, 0.46%)</title><rect x="1.3127%" y="133" width="0.4625%" height="15" fill="rgb(216,20,37)" fg:x="491" fg:w="173"/><text x="1.5627%" y="143.50"></text></g><g><title>aoc2021`core::str::iter::SplitInternal&lt;P&gt;::next (411 samples, 1.10%)</title><rect x="1.7753%" y="133" width="1.0988%" height="15" fill="rgb(206,188,39)" fg:x="664" fg:w="411"/><text x="2.0253%" y="143.50"></text></g><g><title>libsystem_platform.dylib`_platform_memcmp (20 samples, 0.05%)</title><rect x="2.8206%" y="117" width="0.0535%" height="15" fill="rgb(217,207,13)" fg:x="1055" fg:w="20"/><text x="3.0706%" y="127.50"></text></g><g><title>aoc2021`aoc2021::day02::run (649 samples, 1.74%)</title><rect x="1.1764%" y="149" width="1.7352%" height="15" fill="rgb(231,73,38)" fg:x="440" fg:w="649"/><text x="1.4264%" y="159.50"></text></g><g><title>libsystem_platform.dylib`_platform_memcmp (14 samples, 0.04%)</title><rect x="2.8741%" y="133" width="0.0374%" height="15" fill="rgb(225,20,46)" fg:x="1075" fg:w="14"/><text x="3.1241%" y="143.50"></text></g><g><title>aoc2021`DYLD-STUB$$memcmp (13 samples, 0.03%)</title><rect x="4.2136%" y="133" width="0.0348%" height="15" fill="rgb(210,31,41)" fg:x="1576" fg:w="13"/><text x="4.4636%" y="143.50"></text></g><g><title>libsystem_malloc.dylib`tiny_try_realloc_in_place (6 samples, 0.02%)</title><rect x="5.4087%" y="37" width="0.0160%" height="15" fill="rgb(221,200,47)" fg:x="2023" fg:w="6"/><text x="5.6587%" y="47.50"></text></g><g><title>libsystem_malloc.dylib`malloc_zone_realloc (14 samples, 0.04%)</title><rect x="5.3899%" y="69" width="0.0374%" height="15" fill="rgb(226,26,5)" fg:x="2016" fg:w="14"/><text x="5.6399%" y="79.50"></text></g><g><title>libsystem_malloc.dylib`szone_realloc (13 samples, 0.03%)</title><rect x="5.3926%" y="53" width="0.0348%" height="15" fill="rgb(249,33,26)" fg:x="2017" fg:w="13"/><text x="5.6426%" y="63.50"></text></g><g><title>Line truncated

src/day02.rs

@@ -1,18 +1,23 @@
 use anyhow::Result;
 
-fn parse_line(s: &str) -> (&str, i32) {
+fn parse_line(s: &str) -> (char, i32) {
-    let parsed: Vec<&str> = s.splitn(2, ' ').collect();
+    let mut parsed = s.split_ascii_whitespace();
-    let instruction = parsed[0];
+    let instruction = match parsed.next().unwrap() {
-    let quantity = parsed[1].parse::<i32>().unwrap();
+        "forward" => 'f',
+        "down" => 'd',
+        "up" => 'u',
+        _ => unreachable!(),
+    };
+    let quantity = parsed.next().unwrap().parse::<i32>().unwrap();
     (instruction, quantity)
 }
 
 fn follow_course(s: &str) -> i32 {
     let (mut pos, mut depth) = (0, 0);
     s.lines().for_each(|line| match parse_line(line) {
-        ("forward", d) => pos += d,
+        ('f', d) => pos += d,
-        ("down", d) => depth += d,
+        ('d', d) => depth += d,
-        ("up", d) => depth -= d,
+        ('u', d) => depth -= d,
         _ => unreachable!(),
     });
     pos * depth
@@ -21,12 +26,12 @@ fn follow_course(s: &str) -> i32 {
 fn follow_course_better(s: &str) -> i32 {
     let (mut pos, mut depth, mut aim) = (0, 0, 0);
     s.lines().for_each(|line| match parse_line(line) {
-        ("forward", d) => {
+        ('f', d) => {
             pos += d;
             depth += aim * d;
         }
-        ("down", d) => aim += d,
+        ('d', d) => aim += d,
-        ("up", d) => aim -= d,
+        ('u', d) => aim -= d,
         _ => unreachable!(),
     });
     pos * depth

src/day03.rs

@@ -39,8 +39,8 @@ fn find_oxygen_or_co2(s: &str, oxygen: bool) -> usize {
             .rev()
             .map(|bit| {
                 // split current set into ones/zeroes for current bit
-                let mut ones = vec![];
+                let mut ones = Vec::with_capacity(kept.len());
-                let mut zeroes = vec![];
+                let mut zeroes = Vec::with_capacity(kept.len());
                 kept.iter().for_each(|x| {
                     if x & (1 << bit) != 0 {
                         ones.push(*x);

src/day05.rs

@@ -12,17 +12,40 @@ impl LineSegment {
         self.start.0 == self.end.0 || self.start.1 == self.end.1
     }
 
-    fn rasterize(&self) -> Vec<(isize, isize)> {
+    fn rasterize(&self) -> LineSegmentPixelIter {
-        let xstep = (self.end.0 - self.start.0).signum();
+        let dx = self.end.0 - self.start.0;
-        let ystep = (self.end.1 - self.start.1).signum();
+        let dy = self.end.1 - self.start.1;
-        let mut ret = vec![self.start];
+        LineSegmentPixelIter {
-        let (mut x, mut y) = self.start;
+            x: self.start.0,
-        while (x, y) != self.end {
+            y: self.start.1,
-            x += xstep;
+            xstep: dx.signum(),
-            y += ystep;
+            ystep: dy.signum(),
-            ret.push((x, y));
+            length: dx.abs().max(dy.abs()) + 1,
+            i: 0,
+        }
+    }
+}
+
+struct LineSegmentPixelIter {
+    x: isize,
+    y: isize,
+    xstep: isize,
+    ystep: isize,
+    length: isize,
+    i: isize,
+}
+
+impl Iterator for LineSegmentPixelIter {
+    type Item = (isize, isize);
+
+    fn next(&mut self) -> Option<Self::Item> {
+        if self.i < self.length {
+            let ret = (self.x + self.i * self.xstep, self.y + self.i * self.ystep);
+            self.i += 1;
+            Some(ret)
+        } else {
+            None
         }
-        ret
     }
 }
 
@@ -50,21 +73,23 @@ fn parse_lines(input: &str) -> Vec<LineSegment> {
 }
 
 fn count_overlapped_cells(segments: &[LineSegment], includ_diag: bool) -> usize {
-    let mut marks: Vec<(isize, isize)> = segments
+    let mut cells: Vec<Vec<usize>> = vec![vec![0; 1000]; 1000];
+    segments
         .iter()
         .filter(|s| s.is_horizontal_or_vertical() || includ_diag)
-        .map(|s| s.rasterize())
+        .map(|s| {
-        .flatten()
+            s.rasterize()
-        .collect();
+                .map(|(x, y)| -> usize {
-    // sort so we can find duplicates
+                    cells[x as usize][y as usize] += 1;
-    // **NOTE** IterTools has `.duplicates()` but it's significantly slower (more than 2x) than this
+                    if cells[x as usize][y as usize] == 2 {
-    marks.sort_unstable();
+                        1
-    marks[..]
+                    } else {
-        .iter()
+                        0
-        .zip(&marks[1..])
+                    }
-        .filter(|(a, b)| a == b)
+                })
-        .unique()
+                .sum::<usize>()
-        .count()
+        })
+        .sum::<usize>()
 }
 
 pub(crate) fn run() -> Result<(usize, usize)> {

src/day07.rs

@@ -24,7 +24,8 @@ fn compute_fuel(positions: &[isize], target: isize, cheap_fuel: bool) -> usize {
 
 fn find_cheapest_location(positions: &[isize], cheap_fuel: bool) -> usize {
     // find start point
-    let mut position = get_median(positions);
+    let start = get_median(positions);
+    let mut position = start;
     let mut fuel = compute_fuel(positions, position, cheap_fuel);
 
     // search up
@@ -36,6 +37,9 @@ fn find_cheapest_location(positions: &[isize], cheap_fuel: bool) -> usize {
         position += 1;
         fuel = new_fuel;
     }
+    if position != start {
+        return fuel;
+    }
 
     // search down
     loop {

src/main.rs

@@ -1,3 +1,5 @@
+use std::env;
+
 use anyhow::Result;
 
 mod day01;
@@ -9,19 +11,32 @@ mod day06;
 mod day07;
 mod utils;
 
-fn main() -> Result<()> {
+// used to generate more runs when profiling
-    let dayfns = [
+const RUNS: usize = 1;
-        day01::run,
-        day02::run,
-        day03::run,
-        day04::run,
-        day05::run,
-        day06::run,
-        day07::run,
-    ];
 
-    for (i, f) in dayfns.iter().enumerate() {
+fn main() -> Result<()> {
-        println!("Day {:02} -> {:?}", i, f()?);
+    let args: Vec<String> = env::args().collect();
+
+    for _ in 0..RUNS {
+        for (i, f) in [
+            day01::run,
+            day02::run,
+            day03::run,
+            day04::run,
+            day05::run,
+            day06::run,
+            day07::run,
+        ]
+        .iter()
+        .enumerate()
+        {
+            if args.len() == 1 || args.contains(&(i + 1).to_string()) {
+                let result = f()?;
+                if RUNS == 1 {
+                    println!("Day {:02} -> {:?}", i + 1, result);
+                }
+            }
+        }
     }
 
     Ok(())