kaivalnp commented on code in PR #16790:
URL: https://github.com/apache/lucene/pull/16790#discussion_r4447066163
##########
lucene/core/src/java/org/apache/lucene/internal/vectorization/DefaultVectorUtilSupport.java:
##########
@@ -459,6 +459,80 @@ private float quantizeFloat(float v, byte[] dest, int
destIndex) {
}
}
+ @Override
+ public void osqCenter(float[] vector, float[] centroid, float[] stats) {
+ float dot = 0;
+ float min = Float.MAX_VALUE;
+ float max = -Float.MAX_VALUE;
+ float sumSq = 0;
+ float sum = 0;
+ for (int i = 0; i < vector.length; i++) {
+ dot += vector[i] * centroid[i];
+ float x = vector[i] - centroid[i];
+ vector[i] = x;
+ min = Math.min(min, x);
+ max = Math.max(max, x);
+ sumSq += x * x;
+ sum += x;
+ }
+ stats[0] = dot;
+ stats[1] = min;
+ stats[2] = max;
+ stats[3] = sumSq;
+ stats[4] = sum;
+ }
+
+ @Override
+ public void osqGridStats(float[] vector, float lower, float upper, int
points, double[] stats) {
+ osqGridStatsImpl(vector, lower, upper, points, stats);
+ }
+
+ static void osqGridStatsImpl(
+ float[] vector, float lower, float upper, int points, double[] stats) {
+ float stepInv = (points - 1f) / (upper - lower);
+ float step = (upper - lower) / (points - 1f);
+ long sumK = 0;
+ long sumKK = 0;
+ double sumXK = 0;
+ double sumXD = 0;
+ double sumDD = 0;
+ double sumX = 0;
+ for (float x : vector) {
+ // Adds 0.5 and truncates, as Math.round is costly to match in the
Panama version.
+ int k = (int) ((Math.min(Math.max(x, lower), upper) - lower) * stepInv +
0.5f);
+ float d = x - (lower + k * step);
+ sumK += k;
+ sumKK += (long) k * k;
+ sumXK += x * k;
+ sumXD += x * d;
+ sumDD += d * d;
+ sumX += x;
+ }
+ stats[0] = sumK;
+ stats[1] = sumKK;
+ stats[2] = sumXK;
+ stats[3] = sumXD;
+ stats[4] = sumDD;
+ stats[5] = sumX;
+ }
+
+ @Override
+ public int osqAssign(float[] vector, float lower, float upper, float step,
byte[] dest) {
+ return osqAssignImpl(vector, 0, lower, upper, step, dest);
+ }
+
+ // The Panama version calls this for its tail, with start where its vector
loop stopped.
+ static int osqAssignImpl(
+ float[] vector, int start, float lower, float upper, float step, byte[]
dest) {
+ int sum = 0;
+ for (int i = start; i < vector.length; i++) {
+ int k = Math.round((Math.min(Math.max(vector[i], lower), upper) - lower)
/ step);
Review Comment:
Ah nice catch! So if `lower = +0f` and `upper = -0f`, the assertions won't
be triggered, but `Math.clamp` will throw -- in that case keeping it as
`min(max(...))` looks okay to me.
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
