Skip to content
Merged
Show file tree
Hide file tree
Changes from 1 commit
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
Expand Up @@ -82,4 +82,13 @@ public void packAsBinaryLegacy(Blackhole bh) {
bh.consume(packed);
}
}

@Benchmark
@Fork(jvmArgsPrepend = { "--add-modules=jdk.incubator.vector" })
public void packAsBinaryPanama(Blackhole bh) {
for (int i = 0; i < numVectors; i++) {
BQVectorUtils.packAsBinary(qVectors[i], packed);
bh.consume(packed);
}
}
}
Original file line number Diff line number Diff line change
Expand Up @@ -368,4 +368,17 @@ public static void soarDistanceBulk(
}
IMPL.soarDistanceBulk(v1, c0, c1, c2, c3, originalResidual, soarLambda, rnorm, distances);
}

/**
* Packs the provided int array populated with "0" and "1" values into a byte array.
*
* @param vector the int array to pack, must contain only "0" and "1" values.
* @param packed the byte array to store the packed result, must be large enough to hold the packed data.
*/
public static void packAsBinary(int[] vector, byte[] packed) {
if (packed.length * Byte.SIZE < vector.length) {
throw new IllegalArgumentException("packed array is too small: " + packed.length * Byte.SIZE + " < " + vector.length);
}
IMPL.packAsBinary(vector, packed);
}
}
Original file line number Diff line number Diff line change
Expand Up @@ -320,4 +320,37 @@ public void soarDistanceBulk(
distances[2] = soarDistance(v1, c2, originalResidual, soarLambda, rnorm);
distances[3] = soarDistance(v1, c3, originalResidual, soarLambda, rnorm);
}

@Override
public void packAsBinary(int[] vector, byte[] packed) {
packAsBinaryImpl(vector, packed);
}

public static void packAsBinaryImpl(int[] vector, byte[] packed) {
int limit = vector.length - 7;
int i = 0;
int index = 0;
for (; i < limit; i += 8, index++) {
assert vector[i] == 0 || vector[i] == 1;
assert vector[i + 1] == 0 || vector[i + 1] == 1;
assert vector[i + 2] == 0 || vector[i + 2] == 1;
assert vector[i + 3] == 0 || vector[i + 3] == 1;
assert vector[i + 4] == 0 || vector[i + 4] == 1;
assert vector[i + 5] == 0 || vector[i + 5] == 1;
assert vector[i + 6] == 0 || vector[i + 6] == 1;
assert vector[i + 7] == 0 || vector[i + 7] == 1;
int result = vector[i] << 7 | (vector[i + 1] << 6) | (vector[i + 2] << 5) | (vector[i + 3] << 4) | (vector[i + 4] << 3)
| (vector[i + 5] << 2) | (vector[i + 6] << 1) | (vector[i + 7]);
packed[index] = (byte) result;
}
if (i == vector.length) {
return;
}
byte result = 0;
for (int j = 7; j >= 0 && i < vector.length; i++, j--) {
assert vector[i] == 0 || vector[i] == 1;
result |= (byte) ((vector[i] & 1) << j);
}
packed[index] = result;
}
}
Original file line number Diff line number Diff line change
Expand Up @@ -63,4 +63,6 @@ void soarDistanceBulk(
float rnorm,
float[] distances
);

void packAsBinary(int[] vector, byte[] packed);
}
Original file line number Diff line number Diff line change
Expand Up @@ -22,8 +22,10 @@
import org.apache.lucene.util.Constants;

import static jdk.incubator.vector.VectorOperators.ADD;
import static jdk.incubator.vector.VectorOperators.LSHL;
import static jdk.incubator.vector.VectorOperators.MAX;
import static jdk.incubator.vector.VectorOperators.MIN;
import static jdk.incubator.vector.VectorOperators.OR;

public final class PanamaESVectorUtilSupport implements ESVectorUtilSupport {

Expand Down Expand Up @@ -942,4 +944,69 @@ public void soarDistanceBulk(
distances[2] = dsq2 + soarLambda * proj2 * proj2 / rnorm;
distances[3] = dsq3 + soarLambda * proj3 * proj3 / rnorm;
}

private static final VectorSpecies<Integer> INT_SPECIES_128 = IntVector.SPECIES_128;
private static final int[] SHIFTS = new int[] { 7, 6, 5, 4, 3, 2, 1, 0 };

@Override
public void packAsBinary(int[] vector, byte[] packed) {
// 128 / 32 == 4
if (vector.length >= 8 && HAS_FAST_INTEGER_VECTORS) {
// TODO: can we optimize for >= 512?
if (VECTOR_BITSIZE >= 256) {
packAsBinary256(vector, packed);
return;
} else if (VECTOR_BITSIZE == 128) {
packAsBinary128(vector, packed);
return;
}
}
DefaultESVectorUtilSupport.packAsBinaryImpl(vector, packed);
}

private void packAsBinary256(int[] vector, byte[] packed) {
final int limit = INT_SPECIES_256.loopBound(vector.length);
int i = 0;
int index = 0;
IntVector shifts = IntVector.fromArray(INT_SPECIES_256, SHIFTS, 0);
for (; i < limit; i += INT_SPECIES_256.length(), index++) {
IntVector v = IntVector.fromArray(INT_SPECIES_256, vector, i);
int result = v.lanewise(LSHL, shifts).reduceLanes(OR);
packed[index] = (byte) result;
}
if (i == vector.length) {
return; // all done
}
byte result = 0;
for (int j = 7; j >= 0 && i < vector.length; i++, j--) {
assert vector[i] == 0 || vector[i] == 1;
result |= (byte) ((vector[i] & 1) << j);
}
packed[index] = result;
}

private void packAsBinary128(int[] vector, byte[] packed) {
final int limit = INT_SPECIES_128.loopBound(vector.length) - INT_SPECIES_128.length();
int i = 0;
int index = 0;
IntVector highShifts = IntVector.fromArray(INT_SPECIES_128, SHIFTS, 0);
IntVector lowShifts = IntVector.fromArray(INT_SPECIES_128, SHIFTS, INT_SPECIES_128.length());
for (; i < limit; i += 2 * INT_SPECIES_128.length(), index++) {
IntVector v = IntVector.fromArray(INT_SPECIES_128, vector, i);
var v1 = v.lanewise(LSHL, highShifts);
v = IntVector.fromArray(INT_SPECIES_128, vector, i + INT_SPECIES_128.length());
var v2 = v.lanewise(LSHL, lowShifts);
int result = v1.lanewise(OR, v2).reduceLanes(OR);
packed[index] = (byte) result;
}
if (i == vector.length) {
return; // all done
}
byte result = 0;
for (int j = 7; j >= 0 && i < vector.length; i++, j--) {
assert vector[i] == 0 || vector[i] == 1;
result |= (byte) ((vector[i] & 1) << j);
}
packed[index] = result;
}
}
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,7 @@

package org.elasticsearch.simdvec;

import org.elasticsearch.index.codec.vectors.BQVectorUtils;
import org.elasticsearch.index.codec.vectors.OptimizedScalarQuantizer;
import org.elasticsearch.simdvec.internal.vectorization.BaseVectorizationTests;
import org.elasticsearch.simdvec.internal.vectorization.ESVectorizationProvider;
Expand Down Expand Up @@ -355,6 +356,20 @@ public void testSoarDistanceBulk() {
assertArrayEquals(expectedDistances, panamaDistances, deltaEps);
}

public void testPackAsBinary() {
int dims = randomIntBetween(16, 2048);
int[] toPack = new int[dims];
for (int i = 0; i < dims; i++) {
toPack[i] = randomInt(1);
}
int length = BQVectorUtils.discretize(dims, 64) / 8;
byte[] packed = new byte[length];
byte[] packedLegacy = new byte[length];
defaultedProvider.getVectorUtilSupport().packAsBinary(toPack, packedLegacy);
defOrPanamaProvider.getVectorUtilSupport().packAsBinary(toPack, packed);
assertArrayEquals(packedLegacy, packed);
}

private float[] generateRandomVector(int size) {
float[] vector = new float[size];
for (int i = 0; i < size; ++i) {
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,7 @@
import org.apache.lucene.util.ArrayUtil;
import org.apache.lucene.util.BitUtil;
import org.apache.lucene.util.VectorUtil;
import org.elasticsearch.simdvec.ESVectorUtil;

/** Utility class for vector quantization calculations */
public class BQVectorUtils {
Expand Down Expand Up @@ -55,31 +56,7 @@ public static void packAsBinaryLegacy(int[] vector, byte[] packed) {
}

public static void packAsBinary(int[] vector, byte[] packed) {
int limit = vector.length - 7;
int i = 0;
int index = 0;
for (; i < limit; i += 8, index++) {
assert vector[i] == 0 || vector[i] == 1;
assert vector[i + 1] == 0 || vector[i + 1] == 1;
assert vector[i + 2] == 0 || vector[i + 2] == 1;
assert vector[i + 3] == 0 || vector[i + 3] == 1;
assert vector[i + 4] == 0 || vector[i + 4] == 1;
assert vector[i + 5] == 0 || vector[i + 5] == 1;
assert vector[i + 6] == 0 || vector[i + 6] == 1;
assert vector[i + 7] == 0 || vector[i + 7] == 1;
int result = vector[i] << 7 | (vector[i + 1] << 6) | (vector[i + 2] << 5) | (vector[i + 3] << 4) | (vector[i + 4] << 3)
| (vector[i + 5] << 2) | (vector[i + 6] << 1) | (vector[i + 7]);
packed[index] = (byte) result;
}
if (i == vector.length) {
return;
}
byte result = 0;
for (int j = 7; j >= 0 && i < vector.length; i++, j--) {
assert vector[i] == 0 || vector[i] == 1;
result |= (byte) ((vector[i] & 1) << j);
}
packed[index] = result;
ESVectorUtil.packAsBinary(vector, packed);
}

public static int discretize(int value, int bucket) {
Expand Down