feat: extract `has_false` and `has_true` from BooleanArray to `BooleanBuffer` and reuse for no nulls by rluvaton · Pull Request #9987 · apache/arrow-rs

rluvaton · 2026-05-17T10:54:55Z

Which issue does this PR close?

N/A

Rationale for this change

So we can use the useful helpers without creating temp BooleanArray

What changes are included in this PR?

Extract non null variants for computing has_false and has_true from BooleanArray to BooleanBuffer and call them instead, and copied the tests for not nullable

Are these changes tested?

Yes

Are there any user-facing changes?

2 new functions

Cc @alamb as talked in:

perf: reuse mask in truncate_list_nulls and avoid counting all true bits datafusion#22158 (comment)

`BooleanBuffer` and reuse for no nulls

alamb

Thank yoU @rluvaton -- looks like a nice refactor to me

alamb · 2026-05-18T19:48:32Z

        self.into_iter()
    }

+    /// Returns an [`UnalignedBitChunk`] over this buffer's values.


this is nice -- it just moves the code down a level (into BooleanBuffer out of BooleanArray)

alamb · 2026-05-18T19:50:26Z

run benchmark boolean_kernels

alamb · 2026-05-18T19:50:32Z

run benchmark boolean_kernels

alamb · 2026-05-18T19:52:12Z

CI test failure looks unrelated https://github.com/apache/arrow-rs/actions/runs/26001934862/job/76426635449?pr=9987

I see you filed Failure in CI: Archery test With other arrows - binary_view Rust producing, .NET consuming #9989 👍

adriangbot · 2026-05-18T19:53:31Z

🤖 Arrow criterion benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4481448653-188-2wks7 6.12.68+ #1 SMP Wed Apr 1 02:23:28 UTC 2026 aarch64 GNU/Linux

CPU Details (lscpu)

Architecture:                            aarch64
CPU op-mode(s):                          64-bit
Byte Order:                              Little Endian
CPU(s):                                  16
On-line CPU(s) list:                     0-15
Vendor ID:                               ARM
Model name:                              Neoverse-V2
Model:                                   1
Thread(s) per core:                      1
Core(s) per cluster:                     16
Socket(s):                               -
Cluster(s):                              1
Stepping:                                r0p1
BogoMIPS:                                2000.00
Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
L1d cache:                               1 MiB (16 instances)
L1i cache:                               1 MiB (16 instances)
L2 cache:                                32 MiB (16 instances)
L3 cache:                                80 MiB (1 instance)
NUMA node(s):                            1
NUMA node0 CPU(s):                       0-15
Vulnerability Gather data sampling:      Not affected
Vulnerability Indirect target selection: Not affected
Vulnerability Itlb multihit:             Not affected
Vulnerability L1tf:                      Not affected
Vulnerability Mds:                       Not affected
Vulnerability Meltdown:                  Not affected
Vulnerability Mmio stale data:           Not affected
Vulnerability Reg file data sampling:    Not affected
Vulnerability Retbleed:                  Not affected
Vulnerability Spec rstack overflow:      Not affected
Vulnerability Spec store bypass:         Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1:                Mitigation; __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; CSV2, BHB
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Not affected

Comparing move-some-func-to-boolean-buffer (273da35) to fd1c5b3 (merge-base) diff
BENCH_NAME=boolean_kernels
BENCH_COMMAND=cargo bench --features=arrow,async,test_common,experimental,object_store --bench boolean_kernels
BENCH_FILTER=
Results will be posted here when complete

File an issue against this benchmark runner

adriangbot · 2026-05-18T19:54:15Z

🤖 Arrow criterion benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4481449618-189-mh2j6 6.12.68+ #1 SMP Wed Apr 1 02:23:28 UTC 2026 aarch64 GNU/Linux

CPU Details (lscpu)

Architecture:                            aarch64
CPU op-mode(s):                          64-bit
Byte Order:                              Little Endian
CPU(s):                                  16
On-line CPU(s) list:                     0-15
Vendor ID:                               ARM
Model name:                              Neoverse-V2
Model:                                   1
Thread(s) per core:                      1
Core(s) per cluster:                     16
Socket(s):                               -
Cluster(s):                              1
Stepping:                                r0p1
BogoMIPS:                                2000.00
Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
L1d cache:                               1 MiB (16 instances)
L1i cache:                               1 MiB (16 instances)
L2 cache:                                32 MiB (16 instances)
L3 cache:                                80 MiB (1 instance)
NUMA node(s):                            1
NUMA node0 CPU(s):                       0-15
Vulnerability Gather data sampling:      Not affected
Vulnerability Indirect target selection: Not affected
Vulnerability Itlb multihit:             Not affected
Vulnerability L1tf:                      Not affected
Vulnerability Mds:                       Not affected
Vulnerability Meltdown:                  Not affected
Vulnerability Mmio stale data:           Not affected
Vulnerability Reg file data sampling:    Not affected
Vulnerability Retbleed:                  Not affected
Vulnerability Spec rstack overflow:      Not affected
Vulnerability Spec store bypass:         Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1:                Mitigation; __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; CSV2, BHB
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Not affected

Comparing move-some-func-to-boolean-buffer (273da35) to fd1c5b3 (merge-base) diff
BENCH_NAME=boolean_kernels
BENCH_COMMAND=cargo bench --features=arrow,async,test_common,experimental,object_store --bench boolean_kernels
BENCH_FILTER=
Results will be posted here when complete

File an issue against this benchmark runner

adriangbot · 2026-05-18T19:57:44Z

🤖 Arrow criterion benchmark completed (GKE) | trigger

Instance: c4a-highmem-16 (12 vCPU / 65 GiB)

CPU Details (lscpu)

Architecture:                            aarch64
CPU op-mode(s):                          64-bit
Byte Order:                              Little Endian
CPU(s):                                  16
On-line CPU(s) list:                     0-15
Vendor ID:                               ARM
Model name:                              Neoverse-V2
Model:                                   1
Thread(s) per core:                      1
Core(s) per cluster:                     16
Socket(s):                               -
Cluster(s):                              1
Stepping:                                r0p1
BogoMIPS:                                2000.00
Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
L1d cache:                               1 MiB (16 instances)
L1i cache:                               1 MiB (16 instances)
L2 cache:                                32 MiB (16 instances)
L3 cache:                                80 MiB (1 instance)
NUMA node(s):                            1
NUMA node0 CPU(s):                       0-15
Vulnerability Gather data sampling:      Not affected
Vulnerability Indirect target selection: Not affected
Vulnerability Itlb multihit:             Not affected
Vulnerability L1tf:                      Not affected
Vulnerability Mds:                       Not affected
Vulnerability Meltdown:                  Not affected
Vulnerability Mmio stale data:           Not affected
Vulnerability Reg file data sampling:    Not affected
Vulnerability Retbleed:                  Not affected
Vulnerability Spec rstack overflow:      Not affected
Vulnerability Spec store bypass:         Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1:                Mitigation; __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; CSV2, BHB
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Not affected

Details

group            main                                   move-some-func-to-boolean-buffer
-----            ----                                   --------------------------------
and              1.00    150.7±0.76ns        ? ?/sec    1.02    154.3±2.49ns        ? ?/sec
and_sliced_1     1.00    550.2±1.19ns        ? ?/sec    1.02    559.8±1.36ns        ? ?/sec
and_sliced_24    1.00    152.4±0.64ns        ? ?/sec    1.02    155.0±2.07ns        ? ?/sec
not              1.03    112.1±0.63ns        ? ?/sec    1.00    108.8±1.61ns        ? ?/sec
not_slice_24     1.02    110.8±0.56ns        ? ?/sec    1.00    108.9±1.38ns        ? ?/sec
not_sliced_1     1.03    111.6±0.60ns        ? ?/sec    1.00    108.9±1.57ns        ? ?/sec
or               1.05    161.7±0.37ns        ? ?/sec    1.00    153.4±3.42ns        ? ?/sec
or_sliced_1      1.01    563.0±0.93ns        ? ?/sec    1.00    558.8±2.16ns        ? ?/sec
or_sliced_24     1.07    164.6±0.40ns        ? ?/sec    1.00    153.9±2.18ns        ? ?/sec

Resource Usage

base (merge-base)

Metric	Value
Wall time	95.0s
Peak memory	3.0 GiB
Avg memory	3.0 GiB
CPU user	89.4s
CPU sys	0.7s
Peak spill	0 B

branch

Metric	Value
Wall time	90.0s
Peak memory	3.0 GiB
Avg memory	3.0 GiB
CPU user	88.3s
CPU sys	0.1s
Peak spill	0 B

File an issue against this benchmark runner

adriangbot · 2026-05-18T19:57:45Z

🤖 Arrow criterion benchmark completed (GKE) | trigger

Instance: c4a-highmem-16 (12 vCPU / 65 GiB)

CPU Details (lscpu)

Architecture:                            aarch64
CPU op-mode(s):                          64-bit
Byte Order:                              Little Endian
CPU(s):                                  16
On-line CPU(s) list:                     0-15
Vendor ID:                               ARM
Model name:                              Neoverse-V2
Model:                                   1
Thread(s) per core:                      1
Core(s) per cluster:                     16
Socket(s):                               -
Cluster(s):                              1
Stepping:                                r0p1
BogoMIPS:                                2000.00
Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
L1d cache:                               1 MiB (16 instances)
L1i cache:                               1 MiB (16 instances)
L2 cache:                                32 MiB (16 instances)
L3 cache:                                80 MiB (1 instance)
NUMA node(s):                            1
NUMA node0 CPU(s):                       0-15
Vulnerability Gather data sampling:      Not affected
Vulnerability Indirect target selection: Not affected
Vulnerability Itlb multihit:             Not affected
Vulnerability L1tf:                      Not affected
Vulnerability Mds:                       Not affected
Vulnerability Meltdown:                  Not affected
Vulnerability Mmio stale data:           Not affected
Vulnerability Reg file data sampling:    Not affected
Vulnerability Retbleed:                  Not affected
Vulnerability Spec rstack overflow:      Not affected
Vulnerability Spec store bypass:         Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1:                Mitigation; __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; CSV2, BHB
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Not affected

Details

group            main                                   move-some-func-to-boolean-buffer
-----            ----                                   --------------------------------
and              1.02    153.1±2.01ns        ? ?/sec    1.00    150.2±0.50ns        ? ?/sec
and_sliced_1     1.00    551.2±1.36ns        ? ?/sec    1.01    557.8±1.21ns        ? ?/sec
and_sliced_24    1.00    151.9±0.84ns        ? ?/sec    1.01    152.7±0.72ns        ? ?/sec
not              1.06    113.0±1.72ns        ? ?/sec    1.00    106.5±0.52ns        ? ?/sec
not_slice_24     1.03    110.1±0.41ns        ? ?/sec    1.00    106.6±0.44ns        ? ?/sec
not_sliced_1     1.04    110.2±0.45ns        ? ?/sec    1.00    106.5±0.52ns        ? ?/sec
or               1.10    163.9±2.20ns        ? ?/sec    1.00    148.8±0.88ns        ? ?/sec
or_sliced_1      1.02    563.5±1.28ns        ? ?/sec    1.00    554.9±1.29ns        ? ?/sec
or_sliced_24     1.08    164.0±0.49ns        ? ?/sec    1.00    151.8±0.80ns        ? ?/sec

Resource Usage

base (merge-base)

Metric	Value
Wall time	95.0s
Peak memory	3.0 GiB
Avg memory	3.0 GiB
CPU user	89.3s
CPU sys	0.7s
Peak spill	0 B

branch

Metric	Value
Wall time	90.0s
Peak memory	3.0 GiB
Avg memory	3.0 GiB
CPU user	87.6s
CPU sys	0.1s
Peak spill	0 B

File an issue against this benchmark runner

alamb · 2026-05-20T17:57:09Z

Merging up to pick up CI fix

alamb · 2026-05-20T18:44:46Z

Thanks again @rluvaton

rluvaton added 2 commits May 17, 2026 13:14

feat: extract has_false, has_true from BooleanArray to

96f06ff

`BooleanBuffer` and reuse for no nulls

format and lint

dc70c49

github-actions Bot added the arrow Changes to the arrow crate label May 17, 2026

rluvaton mentioned this pull request May 17, 2026

Failure in CI: Archery test With other arrows - binary_view Rust producing, .NET consuming #9989

Closed

Merge branch 'main' into move-some-func-to-boolean-buffer

273da35

alamb approved these changes May 18, 2026

View reviewed changes

Merge branch 'main' into move-some-func-to-boolean-buffer

db73223

alamb merged commit 39c8814 into apache:main May 20, 2026
26 checks passed

rluvaton deleted the move-some-func-to-boolean-buffer branch May 20, 2026 18:45

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

feat: extract `has_false` and `has_true` from BooleanArray to `BooleanBuffer` and reuse for no nulls#9987

feat: extract `has_false` and `has_true` from BooleanArray to `BooleanBuffer` and reuse for no nulls#9987
alamb merged 4 commits into
apache:mainfrom
rluvaton:move-some-func-to-boolean-buffer

rluvaton commented May 17, 2026

Uh oh!

alamb left a comment

Uh oh!

alamb May 18, 2026

Uh oh!

alamb commented May 18, 2026

Uh oh!

alamb commented May 18, 2026

Uh oh!

alamb commented May 18, 2026

Uh oh!

adriangbot commented May 18, 2026

Uh oh!

adriangbot commented May 18, 2026

Uh oh!

adriangbot commented May 18, 2026

Uh oh!

adriangbot commented May 18, 2026

Uh oh!

alamb commented May 20, 2026

Uh oh!

Uh oh!

alamb commented May 20, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Conversation

rluvaton commented May 17, 2026

Which issue does this PR close?

Rationale for this change

What changes are included in this PR?

Are these changes tested?

Are there any user-facing changes?

Uh oh!

alamb left a comment

Choose a reason for hiding this comment

Uh oh!

alamb May 18, 2026

Choose a reason for hiding this comment

Uh oh!

alamb commented May 18, 2026

Uh oh!

alamb commented May 18, 2026

Uh oh!

alamb commented May 18, 2026

Uh oh!

adriangbot commented May 18, 2026

Uh oh!

adriangbot commented May 18, 2026

Uh oh!

adriangbot commented May 18, 2026

Uh oh!

adriangbot commented May 18, 2026

Uh oh!

alamb commented May 20, 2026

Uh oh!

Uh oh!

alamb commented May 20, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants