wumeibanfa commented on PR #59426:
URL: https://github.com/apache/doris/pull/59426#issuecomment-3694532699
use simd + handle 16 byte one time
```text
Running ./be/output/lib/benchmark_test
Run on (16 X 200 MHz CPU s)
CPU Caches:
L1 Data 64 KiB (x16)
L1 Instruction 64 KiB (x16)
L2 Unified 512 KiB (x16)
L3 Unified 32768 KiB (x1)
Load Average: 1.46, 1.21, 3.47
---------------------------------------------------------------------------------------------------------------
Benchmark Time
CPU Iterations UserCounters...
---------------------------------------------------------------------------------------------------------------
BM_bytes32_mask_to_bits32_mask/32/repeats:5_mean 2.77 ns
2.77 ns 5 bytes_per_second=10.7547G/s
BM_bytes32_mask_to_bits32_mask/32/repeats:5_median 2.77 ns
2.77 ns 5 bytes_per_second=10.7616G/s
BM_bytes32_mask_to_bits32_mask/32/repeats:5_stddev 0.005 ns
0.005 ns 5 bytes_per_second=18.5077M/s
BM_bytes32_mask_to_bits32_mask/32/repeats:5_cv 0.17 %
0.17 % 5 bytes_per_second=0.17%
BM_bytes32_mask_to_bits32_mask/64/repeats:5_mean 5.54 ns
5.54 ns 5 bytes_per_second=10.7593G/s
BM_bytes32_mask_to_bits32_mask/64/repeats:5_median 5.54 ns
5.54 ns 5 bytes_per_second=10.7676G/s
BM_bytes32_mask_to_bits32_mask/64/repeats:5_stddev 0.010 ns
0.010 ns 5 bytes_per_second=20.5456M/s
BM_bytes32_mask_to_bits32_mask/64/repeats:5_cv 0.19 %
0.19 % 5 bytes_per_second=0.19%
BM_bytes32_mask_to_bits32_mask/256/repeats:5_mean 22.2 ns
22.2 ns 5 bytes_per_second=10.7202G/s
BM_bytes32_mask_to_bits32_mask/256/repeats:5_median 22.2 ns
22.2 ns 5 bytes_per_second=10.7226G/s
BM_bytes32_mask_to_bits32_mask/256/repeats:5_stddev 0.012 ns
0.012 ns 5 bytes_per_second=5.81638M/s
BM_bytes32_mask_to_bits32_mask/256/repeats:5_cv 0.05 %
0.05 % 5 bytes_per_second=0.05%
BM_bytes32_mask_to_bits32_mask/1024/repeats:5_mean 88.8 ns
88.8 ns 5 bytes_per_second=10.7428G/s
BM_bytes32_mask_to_bits32_mask/1024/repeats:5_median 88.8 ns
88.8 ns 5 bytes_per_second=10.7441G/s
BM_bytes32_mask_to_bits32_mask/1024/repeats:5_stddev 0.050 ns
0.051 ns 5 bytes_per_second=6.29135M/s
BM_bytes32_mask_to_bits32_mask/1024/repeats:5_cv 0.06 %
0.06 % 5 bytes_per_second=0.06%
```
--
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]
