jpountz commented on code in PR #14896:
URL: https://github.com/apache/lucene/pull/14896#discussion_r2186790341
##########
lucene/core/src/java/org/apache/lucene/util/VectorUtil.java:
##########
@@ -376,4 +376,25 @@ public static float recalculateOffset(
return IMPL.recalculateScalarQuantizationOffset(
vector, oldAlpha, oldMinQuantile, scale, alpha, minQuantile,
maxQuantile);
}
+
+ /**
+ * filter both {@code docBuffer} and {@code scoreBuffer} with {@code
minScoreInclusive}, each
+ * {@code docBuffer} and {@code scoreBuffer} of the same index forms a pair,
pairs with score less
+ * than {@code minScoreInclusive} will be filtered out from the array.
Review Comment:
nit: maybe say "not greater than or equal to" rather than "les than" because
of Double.NaN (which is not less than `minScoreInclusive` but would still be
filtered out)
(It's really a nitpick since NaN is not a legal score value.)
##########
lucene/benchmark-jmh/src/java/org/apache/lucene/benchmark/jmh/CompetitiveBenchmark.java:
##########
@@ -0,0 +1,127 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.lucene.benchmark.jmh;
+
+import java.util.Arrays;
+import java.util.Random;
+import java.util.concurrent.TimeUnit;
+import org.apache.lucene.util.ArrayUtil;
+import org.apache.lucene.util.VectorUtil;
+import org.openjdk.jmh.annotations.Benchmark;
+import org.openjdk.jmh.annotations.BenchmarkMode;
+import org.openjdk.jmh.annotations.Fork;
+import org.openjdk.jmh.annotations.Level;
+import org.openjdk.jmh.annotations.Measurement;
+import org.openjdk.jmh.annotations.Mode;
+import org.openjdk.jmh.annotations.OutputTimeUnit;
+import org.openjdk.jmh.annotations.Param;
+import org.openjdk.jmh.annotations.Scope;
+import org.openjdk.jmh.annotations.Setup;
+import org.openjdk.jmh.annotations.State;
+import org.openjdk.jmh.annotations.Warmup;
+
+@BenchmarkMode(Mode.Throughput)
+@OutputTimeUnit(TimeUnit.MILLISECONDS)
+@State(Scope.Benchmark)
+@Warmup(iterations = 3, time = 1)
+@Measurement(iterations = 5, time = 1)
+@Fork(
+ value = 1,
+ jvmArgsAppend = {
+ "-Xmx1g",
+ "-Xms1g",
+ "-XX:+AlwaysPreTouch",
+ "--add-modules",
+ "jdk.incubator.vector"
+ })
+public class CompetitiveBenchmark {
+
+ private Random R = new Random(0);
+
+ @Param("128")
+ int size;
+
+ double[] scores;
+ int[] docs;
+ double minScoreInclusive;
Review Comment:
I'd suggest making it a configuration parameter, e.g. by annotating it with
`@Param("0.2")` or something along these lines. Since scores are uniform in
0..1, we could then see how performance changes depending on how selective the
filter is.
##########
lucene/benchmark-jmh/src/java/org/apache/lucene/benchmark/jmh/CompetitiveBenchmark.java:
##########
@@ -0,0 +1,127 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.lucene.benchmark.jmh;
+
+import java.util.Arrays;
+import java.util.Random;
+import java.util.concurrent.TimeUnit;
+import org.apache.lucene.util.ArrayUtil;
+import org.apache.lucene.util.VectorUtil;
+import org.openjdk.jmh.annotations.Benchmark;
+import org.openjdk.jmh.annotations.BenchmarkMode;
+import org.openjdk.jmh.annotations.Fork;
+import org.openjdk.jmh.annotations.Level;
+import org.openjdk.jmh.annotations.Measurement;
+import org.openjdk.jmh.annotations.Mode;
+import org.openjdk.jmh.annotations.OutputTimeUnit;
+import org.openjdk.jmh.annotations.Param;
+import org.openjdk.jmh.annotations.Scope;
+import org.openjdk.jmh.annotations.Setup;
+import org.openjdk.jmh.annotations.State;
+import org.openjdk.jmh.annotations.Warmup;
+
+@BenchmarkMode(Mode.Throughput)
+@OutputTimeUnit(TimeUnit.MILLISECONDS)
+@State(Scope.Benchmark)
+@Warmup(iterations = 3, time = 1)
+@Measurement(iterations = 5, time = 1)
+@Fork(
+ value = 1,
+ jvmArgsAppend = {
+ "-Xmx1g",
+ "-Xms1g",
+ "-XX:+AlwaysPreTouch",
+ "--add-modules",
+ "jdk.incubator.vector"
+ })
+public class CompetitiveBenchmark {
+
+ private Random R = new Random(0);
+
+ @Param("128")
+ int size;
+
+ double[] scores;
+ int[] docs;
+ double minScoreInclusive;
+
+ @Setup(Level.Trial)
+ public void setUpTrial() {
+ scores = new double[size];
+ docs = new int[size];
+ R = new Random(System.currentTimeMillis());
+ }
+
+ @Setup(Level.Invocation)
+ public void setUpInvocation() {
+ for (int i = 0; i < size; i++) {
+ docs[i] = R.nextInt(Integer.MAX_VALUE);
+ scores[i] = R.nextDouble();
+ }
Review Comment:
I wonder if we should generate arrays only once in `setupTrial` and then
`arraycopy` them here.
##########
lucene/benchmark-jmh/src/java/org/apache/lucene/benchmark/jmh/CompetitiveBenchmark.java:
##########
@@ -0,0 +1,127 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.lucene.benchmark.jmh;
+
+import java.util.Arrays;
+import java.util.Random;
+import java.util.concurrent.TimeUnit;
+import org.apache.lucene.util.ArrayUtil;
+import org.apache.lucene.util.VectorUtil;
+import org.openjdk.jmh.annotations.Benchmark;
+import org.openjdk.jmh.annotations.BenchmarkMode;
+import org.openjdk.jmh.annotations.Fork;
+import org.openjdk.jmh.annotations.Level;
+import org.openjdk.jmh.annotations.Measurement;
+import org.openjdk.jmh.annotations.Mode;
+import org.openjdk.jmh.annotations.OutputTimeUnit;
+import org.openjdk.jmh.annotations.Param;
+import org.openjdk.jmh.annotations.Scope;
+import org.openjdk.jmh.annotations.Setup;
+import org.openjdk.jmh.annotations.State;
+import org.openjdk.jmh.annotations.Warmup;
+
+@BenchmarkMode(Mode.Throughput)
+@OutputTimeUnit(TimeUnit.MILLISECONDS)
+@State(Scope.Benchmark)
+@Warmup(iterations = 3, time = 1)
+@Measurement(iterations = 5, time = 1)
+@Fork(
+ value = 1,
+ jvmArgsAppend = {
+ "-Xmx1g",
+ "-Xms1g",
+ "-XX:+AlwaysPreTouch",
+ "--add-modules",
+ "jdk.incubator.vector"
+ })
+public class CompetitiveBenchmark {
+
+ private Random R = new Random(0);
+
+ @Param("128")
+ int size;
+
+ double[] scores;
+ int[] docs;
+ double minScoreInclusive;
+
+ @Setup(Level.Trial)
+ public void setUpTrial() {
+ scores = new double[size];
+ docs = new int[size];
+ R = new Random(System.currentTimeMillis());
Review Comment:
I'd avoid relying on the current timestamp. `new Random(0)` should be good
enough?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org
For additional commands, e-mail: issues-h...@lucene.apache.org
