Skip to content
This repository was archived by the owner on Sep 1, 2020. It is now read-only.

Commit 9aae16a

Browse files
committed
Clean implementation of sorts for scala.util.Sorting.
Removed code based on Sun JDK sorts and implemented new (basic) sorts from scratch. Deferred to Java Arrays.sort whenever practical. Behavior of `scala.util.Sorting` should be unchanged, but changed documentation to specify when the Java methods are being used (as they're typically very fast). A JUnit test is provided. Performance is important for sorts. Everything is better with this patch, though it could be better yet, as described below. Below are sort times (in microseconds, SEM < 5%) for various 1024-element arrays of small case classes that compare on an int field (quickSort), or int arrays that use custom ordering (stableSort). Note: "degenerate" means there are only 16 values possible, so there are lots of ties. Times are all with fresh data (no re-using cache from run to run). Results: ``` random sorted reverse degenerate big:64k tiny:16 Old Sorting.quickSort 234 181 178 103 25,700 1.4 New Sorting.quickSort 170 27 115 74 18,600 0.8 Old Sorting.stableSort 321 234 236 282 32,600 2.1 New Sorting.stableSort 239 16 194 194 25,100 1.2 java.util.Arrays.sort 124 4 8 105 13,500 0.8 java.util.Arrays.sort|Box 126 15 13 112 13,200 0.9 ``` The new versions are uniformly faster, but uniformly slower than Java sorting. scala.util.Sorting has use cases that don't map easily in to Java unless everything is pre-boxed, but the overhead of pre-boxing is minimal compared to the sort. A snapshot of some of my benchmarking code is below. (Yes, lots of repeating myself--it's dangerous not to when trying to get somewhat accurate benchmarks.) ``` import java.util.Arrays import java.util.Comparator import math.Ordering import util.Sorting import reflect.ClassTag val th = ichi.bench.Thyme.warmed() case class N(i: Int, j: Int) {} val a = Array.fill(1024)( Array.tabulate(1024)(i => N(util.Random.nextInt, i)) ) var ai = 0 val b = Array.fill(1024)( Array.tabulate(1024)(i => N(i, i)) ) var bi = 0 val c = Array.fill(1024)( Array.tabulate(1024)(i => N(1024-i, i)) ) var ci = 0 val d = Array.fill(1024)( Array.tabulate(1024)(i => N(util.Random.nextInt(16), i)) ) var di = 0 val e = Array.fill(16)( Array.tabulate(65536)(i => N(util.Random.nextInt, i)) ) var ei = 0 val f = Array.fill(65535)( Array.tabulate(16)(i => N(util.Random.nextInt, i)) ) var fi = 0 val o = new Ordering[N]{ def compare(a: N, b: N) = if (a.i < b.i) -1 else if (a.i > b.i) 1 else 0 } for (s <- Seq("one", "two", "three")) { println(s) th.pbench{ val x = a(ai).clone; ai = (ai+1)%a.length; Sorting.quickSort(x)(o); x(x.length/3) } th.pbench{ val x = b(bi).clone; bi = (bi+1)%b.length; Sorting.quickSort(x)(o); x(x.length/3) } th.pbench{ val x = c(ci).clone; ci = (ci+1)%c.length; Sorting.quickSort(x)(o); x(x.length/3) } th.pbench{ val x = d(di).clone; di = (di+1)%d.length; Sorting.quickSort(x)(o); x(x.length/3) } th.pbench{ val x = e(ei).clone; ei = (ei+1)%e.length; Sorting.quickSort(x)(o); x(x.length/3) } th.pbench{ val x = f(fi).clone; fi = (fi+1)%f.length; Sorting.quickSort(x)(o); x(x.length/3) } } def ix(ns: Array[N]) = { val is = new Array[Int](ns.length) var i = 0 while (i < ns.length) { is(i) = ns(i).i i += 1 } is } val p = new Ordering[Int]{ def compare(a: Int, b: Int) = if (a > b) 1 else if (a < b) -1 else 0 } for (s <- Seq("one", "two", "three")) { println(s) val tag: ClassTag[Int] = implicitly[ClassTag[Int]] th.pbench{ val x = ix(a(ai)); ai = (ai+1)%a.length; Sorting.stableSort(x)(tag, p); x(x.length/3) } th.pbench{ val x = ix(b(bi)); bi = (bi+1)%b.length; Sorting.stableSort(x)(tag, p); x(x.length/3) } th.pbench{ val x = ix(c(ci)); ci = (ci+1)%c.length; Sorting.stableSort(x)(tag, p); x(x.length/3) } th.pbench{ val x = ix(d(di)); di = (di+1)%d.length; Sorting.stableSort(x)(tag, p); x(x.length/3) } th.pbench{ val x = ix(e(ei)); ei = (ei+1)%e.length; Sorting.stableSort(x)(tag, p); x(x.length/3) } th.pbench{ val x = ix(f(fi)); fi = (fi+1)%f.length; Sorting.stableSort(x)(tag, p); x(x.length/3) } } for (s <- Seq("one", "two", "three")) { println(s) th.pbench{ val x = a(ai).clone; ai = (ai+1)%a.length; Arrays.sort(x, o); x(x.length/3) } th.pbench{ val x = b(bi).clone; bi = (bi+1)%b.length; Arrays.sort(x, o); x(x.length/3) } th.pbench{ val x = c(ci).clone; ci = (ci+1)%c.length; Arrays.sort(x, o); x(x.length/3) } th.pbench{ val x = d(di).clone; di = (di+1)%d.length; Arrays.sort(x, o); x(x.length/3) } th.pbench{ val x = e(ei).clone; ei = (ei+1)%e.length; Arrays.sort(x, o); x(x.length/3) } th.pbench{ val x = f(fi).clone; fi = (fi+1)%f.length; Arrays.sort(x, o); x(x.length/3) } } def bx(is: Array[Int]): Array[java.lang.Integer] = { val Is = new Array[java.lang.Integer](is.length) var i = 0 while (i < is.length) { Is(i) = java.lang.Integer.valueOf(is(i)) i += 1 } Is } def xb(Is: Array[java.lang.Integer]): Array[Int] = { val is = new Array[Int](Is.length) var i = 0 while (i < is.length) { is(i) = Is(i).intValue i += 1 } is } val q = new Comparator[java.lang.Integer]{ def compare(a: java.lang.Integer, b: java.lang.Integer) = o.compare(a.intValue, b.intValue) } for (s <- Seq("one", "two", "three")) { println(s) val tag: ClassTag[Int] = implicitly[ClassTag[Int]] th.pbench{ val x = bx(ix(a(ai))); ai = (ai+1)%a.length; Arrays.sort(x, q); xb(x)(x.length/3) } th.pbench{ val x = bx(ix(b(bi))); bi = (bi+1)%b.length; Arrays.sort(x, q); xb(x)(x.length/3) } th.pbench{ val x = bx(ix(c(ci))); ci = (ci+1)%c.length; Arrays.sort(x, q); xb(x)(x.length/3) } th.pbench{ val x = bx(ix(d(di))); di = (di+1)%d.length; Arrays.sort(x, q); xb(x)(x.length/3) } th.pbench{ val x = bx(ix(e(ei))); ei = (ei+1)%e.length; Arrays.sort(x, q); xb(x)(x.length/3) } th.pbench{ val x = bx(ix(f(fi))); fi = (fi+1)%f.length; Arrays.sort(x, q); xb(x)(x.length/3) } } ```
1 parent 70f0b1d commit 9aae16a

File tree

3 files changed

+357
-477
lines changed

3 files changed

+357
-477
lines changed

bincompat-forward.whitelist.conf

Lines changed: 53 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -319,6 +319,59 @@ filter {
319319
{
320320
matchName="scala.util.Random.scala$util$Random$$nextAlphaNum$1"
321321
problemName=MissingMethodProblem
322+
},
323+
// Nominally private but in practice JVM-visible methods for reworked scala.util.Sorting
324+
{
325+
matchName="scala.util.Sorting.scala$util$Sorting$$mergeSort$default$5"
326+
problemName=MissingMethodProblem
327+
},
328+
{
329+
matchName="scala.util.Sorting.scala$util$Sorting$$mergeSort$mBc$sp"
330+
problemName=MissingMethodProblem
331+
},
332+
{
333+
matchName="scala.util.Sorting.scala$util$Sorting$$mergeSort$mFc$sp"
334+
problemName=MissingMethodProblem
335+
},
336+
{
337+
matchName="scala.util.Sorting.scala$util$Sorting$$mergeSort$mJc$sp"
338+
problemName=MissingMethodProblem
339+
},
340+
{
341+
matchName="scala.util.Sorting.scala$util$Sorting$$mergeSort"
342+
problemName=MissingMethodProblem
343+
},
344+
{
345+
matchName="scala.util.Sorting.scala$util$Sorting$$mergeSort$mCc$sp"
346+
problemName=MissingMethodProblem
347+
},
348+
{
349+
matchName="scala.util.Sorting.scala$util$Sorting$$mergeSort$mSc$sp"
350+
problemName=MissingMethodProblem
351+
},
352+
{
353+
matchName="scala.util.Sorting.scala$util$Sorting$$insertionSort"
354+
problemName=MissingMethodProblem
355+
},
356+
{
357+
matchName="scala.util.Sorting.scala$util$Sorting$$mergeSort$mZc$sp"
358+
problemName=MissingMethodProblem
359+
},
360+
{
361+
matchName="scala.util.Sorting.scala$util$Sorting$$mergeSort$mDc$sp"
362+
problemName=MissingMethodProblem
363+
},
364+
{
365+
matchName="scala.util.Sorting.scala$util$Sorting$$mergeSort$mIc$sp"
366+
problemName=MissingMethodProblem
367+
},
368+
{
369+
matchName="scala.util.Sorting.scala$util$Sorting$$mergeSorted"
370+
problemName=MissingMethodProblem
371+
},
372+
{
373+
matchName="scala.util.Sorting.scala$util$Sorting$$booleanSort"
374+
problemName=MissingMethodProblem
322375
}
323376
]
324377
}

0 commit comments

Comments
 (0)