gf2121 edited a comment on pull request #2113:
URL: https://github.com/apache/lucene-solr/pull/2113#issuecomment-741520801
> You need to either return a value from the benchmark methods or call
blackhole.consume, otherwise the JVM will detect that everything is unused
outside of the scope and optimize it away. That should get you some different
results. Thank you for being thorough!
Thank you for the clue! Based on your guidance, I tried some more benchmark,
but find array val is alway faster... here are the codes and results (code is
used to show the way prevent jvm optimize, so only one method is enough here).
1. return an array result
```
public long[] decode0() {
for (int iter = 0, tmpIdx = 0, longsIdx = 30; iter < 2; ++iter,
tmpIdx += 15, longsIdx += 1) {
long l0 = (TMP[tmpIdx+0] & MASKS16_1[0]) << 14;
l0 |= (TMP[tmpIdx+1] & MASKS16_1[0]) << 13;
l0 |= (TMP[tmpIdx+2] & MASKS16_1[0]) << 12;
l0 |= (TMP[tmpIdx+3] & MASKS16_1[0]) << 11;
l0 |= (TMP[tmpIdx+4] & MASKS16_1[0]) << 10;
l0 |= (TMP[tmpIdx+5] & MASKS16_1[0]) << 9;
l0 |= (TMP[tmpIdx+6] & MASKS16_1[0]) << 8;
l0 |= (TMP[tmpIdx+7] & MASKS16_1[0]) << 7;
l0 |= (TMP[tmpIdx+8] & MASKS16_1[0]) << 6;
l0 |= (TMP[tmpIdx+9] & MASKS16_1[0]) << 5;
l0 |= (TMP[tmpIdx+10] & MASKS16_1[0]) << 4;
l0 |= (TMP[tmpIdx+11] & MASKS16_1[0]) << 3;
l0 |= (TMP[tmpIdx+12] & MASKS16_1[0]) << 2;
l0 |= (TMP[tmpIdx+13] & MASKS16_1[0]) << 1;
l0 |= (TMP[tmpIdx+14] & MASKS16_1[0]) << 0;
ARR[longsIdx+0] = l0;
}
return ARR;
}
```
method | speed (ops/s)
------------ | -------------
MyBenchmark.decode0 | 92215691.271 ± 1149229.830
MyBenchmark.decode1 | 62019521.428 ± 4268837.164
MyBenchmark.decode2 | 62595196.347 ± 1434012.058
2. return an long result
```
public long decode0() {
for (int iter = 0, tmpIdx = 0, longsIdx = 30; iter < 2; ++iter,
tmpIdx += 15, longsIdx += 1) {
long l0 = (TMP[tmpIdx+0] & MASKS16_1[0]) << 14;
l0 |= (TMP[tmpIdx+1] & MASKS16_1[0]) << 13;
l0 |= (TMP[tmpIdx+2] & MASKS16_1[0]) << 12;
l0 |= (TMP[tmpIdx+3] & MASKS16_1[0]) << 11;
l0 |= (TMP[tmpIdx+4] & MASKS16_1[0]) << 10;
l0 |= (TMP[tmpIdx+5] & MASKS16_1[0]) << 9;
l0 |= (TMP[tmpIdx+6] & MASKS16_1[0]) << 8;
l0 |= (TMP[tmpIdx+7] & MASKS16_1[0]) << 7;
l0 |= (TMP[tmpIdx+8] & MASKS16_1[0]) << 6;
l0 |= (TMP[tmpIdx+9] & MASKS16_1[0]) << 5;
l0 |= (TMP[tmpIdx+10] & MASKS16_1[0]) << 4;
l0 |= (TMP[tmpIdx+11] & MASKS16_1[0]) << 3;
l0 |= (TMP[tmpIdx+12] & MASKS16_1[0]) << 2;
l0 |= (TMP[tmpIdx+13] & MASKS16_1[0]) << 1;
l0 |= (TMP[tmpIdx+14] & MASKS16_1[0]) << 0;
ARR[longsIdx+0] = l0;
}
return ARR[31];
}
```
method | speed (ops/s)
------------ | -------------
MyBenchmark.decode0 | 92470935.234 ± 3525240.576
MyBenchmark.decode1 | 62389057.277 ± 567747.489
MyBenchmark.decode2 | 62141559.925 ± 1012364.417
3. blackwhole consume last
```
public void decode0(Blackhole blackhole) {
for (int iter = 0, tmpIdx = 0, longsIdx = 30; iter < 2; ++iter,
tmpIdx += 15, longsIdx += 1) {
long l0 = (TMP[tmpIdx+0] & MASKS16_1[0]) << 14;
l0 |= (TMP[tmpIdx+1] & MASKS16_1[0]) << 13;
l0 |= (TMP[tmpIdx+2] & MASKS16_1[0]) << 12;
l0 |= (TMP[tmpIdx+3] & MASKS16_1[0]) << 11;
l0 |= (TMP[tmpIdx+4] & MASKS16_1[0]) << 10;
l0 |= (TMP[tmpIdx+5] & MASKS16_1[0]) << 9;
l0 |= (TMP[tmpIdx+6] & MASKS16_1[0]) << 8;
l0 |= (TMP[tmpIdx+7] & MASKS16_1[0]) << 7;
l0 |= (TMP[tmpIdx+8] & MASKS16_1[0]) << 6;
l0 |= (TMP[tmpIdx+9] & MASKS16_1[0]) << 5;
l0 |= (TMP[tmpIdx+10] & MASKS16_1[0]) << 4;
l0 |= (TMP[tmpIdx+11] & MASKS16_1[0]) << 3;
l0 |= (TMP[tmpIdx+12] & MASKS16_1[0]) << 2;
l0 |= (TMP[tmpIdx+13] & MASKS16_1[0]) << 1;
l0 |= (TMP[tmpIdx+14] & MASKS16_1[0]) << 0;
ARR[longsIdx+0] = l0;
}
blackhole.consume(ARR[30]);
blackhole.consume(ARR[31]);
}
```
method | speed (ops/s)
------------ | -------------
MyBenchmark.decode0 | 79570016.826 ± 1210338.335
MyBenchmark.decode1 | 58225242.201 ± 905039.184
MyBenchmark.decode2 | 58524381.688 ± 585220.494
4. blackwhole consume in loop
```
public void decode0(Blackhole blackhole) {
for (int iter = 0, tmpIdx = 0, longsIdx = 30; iter < 2; ++iter,
tmpIdx += 15, longsIdx += 1) {
long l0 = (TMP[tmpIdx+0] & MASKS16_1[0]) << 14;
l0 |= (TMP[tmpIdx+1] & MASKS16_1[0]) << 13;
l0 |= (TMP[tmpIdx+2] & MASKS16_1[0]) << 12;
l0 |= (TMP[tmpIdx+3] & MASKS16_1[0]) << 11;
l0 |= (TMP[tmpIdx+4] & MASKS16_1[0]) << 10;
l0 |= (TMP[tmpIdx+5] & MASKS16_1[0]) << 9;
l0 |= (TMP[tmpIdx+6] & MASKS16_1[0]) << 8;
l0 |= (TMP[tmpIdx+7] & MASKS16_1[0]) << 7;
l0 |= (TMP[tmpIdx+8] & MASKS16_1[0]) << 6;
l0 |= (TMP[tmpIdx+9] & MASKS16_1[0]) << 5;
l0 |= (TMP[tmpIdx+10] & MASKS16_1[0]) << 4;
l0 |= (TMP[tmpIdx+11] & MASKS16_1[0]) << 3;
l0 |= (TMP[tmpIdx+12] & MASKS16_1[0]) << 2;
l0 |= (TMP[tmpIdx+13] & MASKS16_1[0]) << 1;
l0 |= (TMP[tmpIdx+14] & MASKS16_1[0]) << 0;
blackhole.consume(l0);
ARR[longsIdx+0] = l0;
}
}
```
method | speed (ops/s)
------------ | -------------
MyBenchmark.decode0 | 62292723.905 ± 185021.358
MyBenchmark.decode1 | 43453980.399 ± 645575.911
MyBenchmark.decode2 | 43369008.884 ± 751782.611
----------------------------------------------------------------
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.
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
