Congratulations, Gang!
On 12/4/24 11:55, Kevin Gurney wrote:
Congratulations, Gang!
From: Ruoxi Sun
Sent: Tuesday, December 3, 2024 7:57:45 PM
To: dev@arrow.apache.org
Subject: Re: [ANNOUNCE] New Arrow PMC member: Gang Wu
Congratulations Gang!
*Regards,*
*Ros
+1 (binding)
Verified cpp/python/go on ubuntu20.04, aarch64
TEST_DEFAULT=0 TEST_CPP=1 TEST_PYTHON=1 TEST_GO=1
dev/release/verify-release-candidate.sh 15.0.0 1
-Original Message-
From: Raúl Cumplido
Sent: Wednesday, January 17, 2024 18:58
To: dev@arrow.apache.org
Subject: [VOTE] Release
Congrats Andy!
On 11/28/23 06:03, L. C. Hsieh wrote:
Congrats Andy!
Thanks Andrew for the efforts to lead the Arrow project in the past year!
On Tue, Nov 28, 2023 at 3:51 AM Krisztián Szűcs
wrote:
Congrats Andy & Thanks Andrew!
On Mon, Nov 27, 2023 at 6:55 PM Chao Sun wrote:
Congratulat
+1
Verified cpp/python/go on Arm64 ubuntu-20.04. No blocking issue found.
TEST_DEFAULT=0 \
TEST_CPP=1 \
TEST_PYTHON=1 \
TEST_GO=1 \
dev/release/verify-release-candidate.sh 14.0.0 2
-Original Message-
From: Sutou Kouhei
Sent: Wednesday, October 25, 2023 14:03
To: dev@arrow.apache.org
Su
Congrats Xuwei!
-Original Message-
From: Gang Wu
Sent: Monday, October 23, 2023 13:29
To: dev@arrow.apache.org
Subject: Re: [ANNOUNCE] New Arrow committer: Xuwei Fu
Congrats Xuwei!
Best,
Gang
On Mon, Oct 23, 2023 at 12:56 PM Sutou Kouhei wrote:
> On behalf of the Arrow PMC, I'm happy
+1.
Verified c++/python/go source on Ubuntu-22.04 aarch64.
TEST_DEFAULT=0 TEST_CPP=1 TEST_PYTHON=1 TEST_GO=1 \
dev/release/verify-release-candidate.sh 13.0.0 0
Met with a non-blocking issue:
https://github.com/apache/arrow/issues/36860
On 7/21/23 17:49, Raúl Cumplido wrote:
Hi,
As discussed
Congrats Matt!
On 5/4/23 07:07, Krisztián Szűcs wrote:
Congrats Matt!
On Wed, May 3, 2023 at 11:44 PM Rok Mihevc wrote:
Congrats Matt. Well deserved!
Rok
On Wed, May 3, 2023 at 11:03 PM David Li wrote:
Congrats Matt!
On Wed, May 3, 2023, at 16:06, Neal Richardson wrote:
Congratulation
+1
I ran the followings on Ubuntu-22.04, aarch64.
TEST_DEFAULT=0 \
TEST_CPP=1 \
TEST_PYTHON=1 \
TEST_GO=1 \
dev/release/verify-release-candidate.sh 12.0.0 0
TEST_DEFAULT=0 \
TEST_WHEELS=1 \
dev/release/verify-release-candidate.sh 12.0.0 0
On 4/23/23 14:40, Sutou Kouhei wrote:
+1
+1 for title and description
For purely personal reason. I care about commit messages and often try
writing informative messages (even following pedantic rules like 72
chars length). It's a bit disappointed if the messages are not shown by
`git log`.
On 2/1/23 10:46, Jacob Wujciak wrote:
Y
Congratulations!
-Original Message-
From: Rok Mihevc
Sent: Tuesday, December 27, 2022 7:57 AM
To: dev@arrow.apache.org
Subject: Re: [ANNOUNCE] New Arrow PMC chair: Andrew Lamb
Congratulations Andrew!
Rok
On Mon, Dec 26, 2022 at 11:26 PM Neal Richardson < neal.p.richard...@gmail.com>
w
+1
Verified C++/Python/Go source on ubuntu20.04, aarch64.
TEST_DEFAULT=0 TEST_CPP=1 TEST_PYTHON=1 TEST_GO=1 \
dev/release/verify-release-candidate.sh 10.0.0 0
On 10/21/22 14:06, Sutou Kouhei wrote:
Hi,
I would like to propose the following release candidate (RC0) of Apache
Arrow version 10.0
There are some nightly job failures [1].
Pasted some logs below, not sure if already reported.
osx related
---
https://github.com/ursacomputing/crossbow/actions/runs/3125303015/jobs/5069525838#step:7:747
https://github.com/ursacomputing/crossbow/actions/runs/3125257793/jobs/5069437237#ste
Congratulations Weston!
From: Andrew Lamb
Sent: Monday, September 5, 2022 9:18 PM
To: dev
Subject: Re: [ANNOUNCE] New Arrow PMC member: Weston Pace
Congratulations Weston!
On Mon, Sep 5, 2022 at 8:09 AM Rok Mihevc wrote:
> Congrats Weston!
>
> Rok
>
IMPORTANT
+1 (binding)
On 8/25/22 04:03, Mauricio Vargas Sepúlveda wrote:
+1
On 2022-08-24 12:50, Weston Pace wrote:
+1 (non-binding)
On Wed, Aug 24, 2022 at 9:24 AM Keith Kraus
wrote:
+1 (non-binding)
On Wed, Aug 24, 2022 at 12:12 PM David Li wrote:
+1 (binding)
On Wed, Aug 24, 2022, at 12:06,
+1 (binding)
Verified source (cpp/python/go) and wheels on ubuntu-20.04 aarch64.
TEST_DEFAULT=0 TEST_CPP=1 TEST_PYTHON=1 TEST_GO=1
dev/release/verify-release-candidate.sh 9.0.0 2
TEST_DEFAULT=0 TEST_WHEELS=1 dev/release/verify-release-candidate.sh 9.0.0 2
On 7/30/22 07:10, Krisztián Szűcs w
+1, verified on arm64
-Original Message-
From: Sutou Kouhei
Sent: Friday, July 15, 2022 5:11 AM
To: dev@arrow.apache.org
Subject: [VOTE] Release Apache Arrow 6.0.2 - RC0
Hi,
I would like to propose the following release candidate
(RC0) of Apache Arrow version 6.0.2. This is a release co
+1, verified on arm64
-Original Message-
From: Sutou Kouhei
Sent: Friday, July 15, 2022 5:11 AM
To: dev@arrow.apache.org
Subject: [VOTE] Release Apache Arrow 7.0.1 - RC0
Hi,
I would like to propose the following release candidate
(RC0) of Apache Arrow version 7.0.1. This is a release co
+1, verified on arm64
-Original Message-
From: Sutou Kouhei
Sent: Friday, July 15, 2022 5:11 AM
To: dev@arrow.apache.org
Subject: [VOTE] Release Apache Arrow 8.0.1 - RC0
Hi,
I would like to propose the following release candidate
(RC0) of Apache Arrow version 8.0.1. This is a release co
+1
On 7/1/22 04:20, David Li wrote:
Hello,
This vote is to determine if the Arrow PMC is in favor of accepting the
donation of the Flight SQL JDBC driver.
This process was deemed necessary since there was significant development prior
to opening the pull request. This was discussed in a pre
+1
-Original Message-
From: Sutou Kouhei
Sent: Wednesday, May 18, 2022 11:43 AM
To: dev@arrow.apache.org
Subject: Merge a pull request with GitHub API
Hi,
How about using GitHub API instead of local "git merge" to merge a pull request?
We use local "git merge" to merge a pull request
+1.
Verified cpp/python/go source and apt binaries on ubuntu20.04, aarch64.
TEST_DEFAULT=0 TEST_CPP=1 TEST_PYTHON=1 TEST_GO=1
dev/release/verify-release-candidate.sh 8.0.0 3
TEST_DEFAULT=0 TEST_APT=1 dev/release/verify-release-candidate.sh 8.0.0 3
-Original Message-
From: Krisztián Szűc
Hi Sasha,
Thanks for the advice. I didn't quite catch the point. Would you explain a bit
the purpose of this proposal?
We do prefer compiler auto-vectorization to explicit simd code, even if the c++
code is slower than simd one (20% is acceptable IMO). And we do support runtime
dispatch kernel
Unfortunately the runner may not be available. Will update if things change.
Yibo
On 11/12/21 6:57 PM, Krisztián Szűcs wrote:
On Wed, Nov 10, 2021 at 2:55 AM Yibo Cai wrote:
Some updates, @kou, @kszucs
There are two kinds of runners provided. One is dynamic vm created on
demand like travis
+1.
Verified C++ and Python source on Arm64 ubuntu20.04.
CC=clang-12 CXX=clang++-12 TEST_SOURCE=1 TEST_DEFAULT=0 TEST_CPP=1
TEST_PYTHON=1 dev/release/verify-release-candidate.sh source 7.0.0 10
-Original Message-
From: Krisztián Szűcs
Sent: Saturday, January 29, 2022 7:29 PM
To: dev
Su
Gandiva unit test failed on Arm (TEST_SOURCE=1 TEST_CPP=1), but the bug is not
arch dependent, should be fixed in 7.0 release.
Details at https://issues.apache.org/jira/browse/ARROW-15493, PR is ready.
-Original Message-
From: Krisztián Szűcs
Sent: Wednesday, January 26, 2022 9:24 PM
To:
BitUtilTests.TestCopyAndReverseBitmapPreAllocated test failure is tracked at
https://issues.apache.org/jira/browse/ARROW-15461
It's due to clang-12 compiler bug. PR
https://github.com/apache/arrow/pull/12276 fixes the issue.
-Original Message-
From: Jonathan Keane
Sent: Friday, January
arrow-utility-test failed on both x86 and Arm if verify Arrow from source with
clang-12.
I believe it's a compiler bug and not a blocking issue.
Details at https://issues.apache.org/jira/browse/ARROW-15461
-Original Message-
From: Krisztián Szűcs
Sent: Tuesday, January 25, 2022 2:03 AM
T
when it's ready.
-David
On Wed, Dec 29, 2021, at 22:16, Yibo Cai wrote:
On 12/29/21 11:03 PM, David Li wrote:
Awesome, thanks for sharing this too!
The refactoring you have with DataClientStream what I would like to do as well
- I think much of the existing code can be adapted to be more
discussion.
-David
On Wed, Dec 29, 2021, at 04:37, Yibo Cai wrote:
Thanks David to initiate UCX integration, great work!
I think 5Gbps network is too limited for performance evaluation. I will try the
patch on 100Gb RDMA network, hopefully we can see some improvements.
I once benchmarked flight
Thanks David to initiate UCX integration, great work!
I think 5Gbps network is too limited for performance evaluation. I will try the
patch on 100Gb RDMA network, hopefully we can see some improvements.
I once benchmarked flight over 100Gb network [1], grpc based throughput is
2.4GB/s for one thr
+1.
Verified c++ and python source, on ubuntu 20.04, aarch64.
CC=clang-10 CXX=clang++-10 \
TEST_SOURCE=1 TEST_DEFAULT=0 TEST_CPP=1 TEST_PYTHON=1 \
dev/release/verify-release-candidate.sh source 6.0.1 1
On 11/11/21 10:39 AM, Sutou Kouhei wrote:
Hi,
I would like to propose the following releas
runner.
Please note for security reasons, the runner cannot be accessed directly
from internet. Inbound connection requests are rejected. It can initiate
connections to other hosts. Is it okay for crossbow? Any security
concern from crossbow side?
On 10/22/21 10:07 AM, Yibo Cai wrote:
Thanks
ou
& your colleagues can take a look there as well.
-David
On Thu, Sep 9, 2021, at 11:24, Jed Brown wrote:
Yibo Cai writes:
HPC infrastructure normally leverages RDMA for fast data transfer
among
storage nodes and compute nodes. Computation tasks are dispatched to
compute nodes with b
+1
Verified c++/python source on ubuntu 20.04, aarch64
ARROW_CMAKE_OPTIONS="-DCMAKE_CXX_COMPILER=/usr/bin/clang++-10
-DCMAKE_C_COMPILER=/usr/bin/clang-10" TEST_DEFAULT=0 TEST_SOURCE=1
TEST_CPP=1 TEST_PYTHON=1 dev/release/verify-release-candidate.sh source
6.0.0 3
On 10/22/21 7:30 AM, Kriszt
;Arm64 github runner" on Wed, 20 Oct 2021 12:43:16 +0800,
Yibo Cai wrote:
Hi,
We have free Arm64 instances (maintained by Arm) as github action
self-hosted runners for open source projects.
Arrow Arm CI is currently running on Travis. Is an additional Arm64
runner useful? I think we can bu
Hi,
We have free Arm64 instances (maintained by Arm) as github action
self-hosted runners for open source projects.
Arrow Arm CI is currently running on Travis. Is an additional Arm64
runner useful? I think we can build and verify Arm64 Linux releases on it.
Yibo
Hi,
We have some rough ideas of applying Flight in HPC (High Performance
Computation). Would like to hear comments.
HPC infrastructure normally leverages RDMA for fast data transfer among
storage nodes and compute nodes. Computation tasks are dispatched to
compute nodes with best fit resourc
d the alignment does not impact the benches.
Best,
Jorge
[1] https://stackoverflow.com/a/27184001/931303
On Tue, Sep 7, 2021 at 4:29 AM Yibo Cai wrote:
Did a quick bench of accessing long buffer not 8 bytes aligned. Giving
enough conditions, looks it does shows unaligned access has some penalty
Did a quick bench of accessing long buffer not 8 bytes aligned. Giving
enough conditions, looks it does shows unaligned access has some penalty
over aligned access. But I don't think this is an issue in practice.
Please be very skeptical to this benchmark. It's hard to get it right
given the c
Did a quick review. Listed error positions. Removed duplicated failures.
*-osx-*
https://dev.azure.com/ursacomputing/crossbow/_build/results?buildId=10372&view=logs&j=cf796865-97b7-5cd1-be8e-6e00ce4fd8cf&t=9f7de14c-8ff0-55c4-a998-d852f888262c&l=15
test-conda-python-3.6-pandas-0.23 (I remember the
+1
Verified C++ and Python on Arm64 Linux (Ubuntu 20.04, aarch64).
ARROW_CMAKE_OPTIONS="-DCMAKE_CXX_COMPILER=/usr/bin/clang++-10
-DCMAKE_C_COMPILER=/usr/bin/clang-10" TEST_DEFAULT=0 TEST_SOURCE=1
TEST_CPP=1 TEST_PYTHON=1 dev/release/verify-release-candidate.sh source
5.0.0 1
On 7/23/21 11:2
On 7/17/21 12:08 AM, Wes McKinney wrote:
hi folks,
I had a conversation with the developers of xsimd last week in Paris
and was made aware that they are working on a substantial refactor of
xsimd to improve its usability for cross-compilation and
dynamic-dispatch based on runtime processor ca
Congrats Weston!
From: Wes McKinney
Sent: Friday, July 9, 2021 8:47 PM
To: dev
Subject: [ANNOUNCE] New Arrow committer: Weston Pace
On behalf of the Arrow PMC, I'm happy to announce that Weston has accepted an
invitation to become a committer on Apache Arrow. We
k with benchmark results
https://issues.apache.org/jira/browse/ARROW-13170
On Thu, Jun 24, 2021 at 12:27 AM Yibo Cai wrote:
Did a quick test. For random bitmaps and my trivial test code, the
branch-less code is 3.5x faster than branch one.
https://quick-bench.com/q/UD22IIdMgKO9HU1PsPezj05
Did a quick test. For random bitmaps and my trivial test code, the
branch-less code is 3.5x faster than branch one.
https://quick-bench.com/q/UD22IIdMgKO9HU1PsPezj05Kkro
On 6/23/21 11:21 PM, Wes McKinney wrote:
One project I was interested in getting to but haven't had the time
was introducing
Congrats David!
On 6/22/21 8:56 PM, David Li wrote:
Thanks everyone!
I've learned a lot and had a great time contributing here, and I look
forward to continuing to work with everybody.
Best,
David
On 2021/06/22 10:54:08, Krisztián Szűcs wrote:
Congrats David!
On Tue, Jun 22, 2021 at 11:19
arrow/adapters/arrow-rados-cls/docs/deploy.md
On 2021/06/07 10:36:08, Yibo Cai wrote:
Hi Jayjeet,
It is exciting to see a real world computational storage solution built
upon Arrow and Ceph. Amazing work!
We are interesting in this project (I'm from Arm open source software
team focusing on stora
Hi Jayjeet,
It is exciting to see a real world computational storage solution built
upon Arrow and Ceph. Amazing work!
We are interesting in this project (I'm from Arm open source software
team focusing on storage and big data OSS), and would like to reproduce
your works first, then evaluate per
n on each of the columns as soon as you create the
RecordBatch (from one thread) which will force the boxed columns to
materialize.
-Weston
On Thu, May 20, 2021 at 11:40 AM Wes McKinney wrote:
Also, is it possible that the field is not an Int64Array?
On Wed, May 19, 2021 at 10:19 PM Yibo Cai
On 5/20/21 4:15 AM, Rares Vernica wrote:
Hello,
I'm using Arrow for accessing data outside the SciDB database engine. It
generally works fine but we are running into Segmentation Faults in a
corner multi-threaded case. I identified two threads that work on the same
Record Batch. I wonder if ther
Yes, these soft-float math (in libm.so) makes Arm binary extremely slow.
-Original Message-
From: Antoine Pitrou
Sent: Thursday, April 22, 2021 17:20
To: dev@arrow.apache.org
Subject: Re: [C++] Indeterminate poor performance of random number generator
Le 22/04/2021 à 03:38, Yibo Cai a
On 4/22/21 9:38 AM, Yibo Cai wrote:
On 4/21/21 6:07 PM, Antoine Pitrou wrote:
Le 21/04/2021 à 11:41, Yibo Cai a écrit :
On 4/21/21 5:17 PM, Antoine Pitrou wrote:
Le 21/04/2021 à 11:14, Yibo Cai a écrit :
When running benchmarks on Arm64 servers, I find some benchmarks are extremely
slow
+1
Verified C++ and Python on Arm64 Linux (Ubuntu-18.04).
TEST_DEFAULT=0 TEST_SOURCE=1 TEST_CPP=1 TEST_PYTHON=1
dev/release/verify-release-candidate.sh source 4.0.0 3
On 4/22/21 5:30 AM, Krisztián Szűcs wrote:
Hi,
I would like to propose the following release candidate (RC3) of Apache
Arrow v
On 4/21/21 6:07 PM, Antoine Pitrou wrote:
Le 21/04/2021 à 11:41, Yibo Cai a écrit :
On 4/21/21 5:17 PM, Antoine Pitrou wrote:
Le 21/04/2021 à 11:14, Yibo Cai a écrit :
When running benchmarks on Arm64 servers, I find some benchmarks are extremely
slow when built with clang.
E.g
On 4/21/21 5:17 PM, Antoine Pitrou wrote:
Le 21/04/2021 à 11:14, Yibo Cai a écrit :
When running benchmarks on Arm64 servers, I find some benchmarks are extremely
slow when built with clang.
E.g., "ModeKernelNarrow/1048576/1" costs 90s to finish.
I find almost all the time i
When running benchmarks on Arm64 servers, I find some benchmarks are extremely
slow when built with clang.
E.g., "ModeKernelNarrow/1048576/1" costs 90s to finish.
I find almost all the time is spent in generating random bits (prepare test
data)[1], not the test itself.
Below sample code is
'gandiva-decimal-test' hangs on my machine, not sure if it's a blocker issue.
Details at https://issues.apache.org/jira/browse/ARROW-12476
Test command "TEST_DEFAULT=0 TEST_SOURCE=1 TEST_CPP=1
dev/release/verify-release-candidate.sh source 4.0.0 1"
On 4/19/21 10:50 PM, Krisztián Szűcs wrote:
Hi
Beside reporting errors, maybe a kernel wants to allocate memory through
KernelContext::memory_pool [1] in Kernel::init?
I'm not quite sure if this is a valid case. Would like to hear other comments.
[1]
https://github.com/apache/arrow/blob/master/cpp/src/arrow/compute/kernel.h#L95
Yibo
On 3/
Sent from my iPhone
On 06-Mar-2021, at 12:48 AM, Antoine Pitrou wrote:
Hello,
The Project Management Committee (PMC) for Apache Arrow has invited Yibo
Cai to become a committer and we are pleased to announce that he has
accepted. Yibo is a frequent contributor to the C++ Arrow implementation
Hi Ivan,
I guess you didn't log in Jira? Otherwise you will see "Assign to me" link at
the right pane.
You can click "Log In" at the upper right corner, maybe "Sign up" an account if
you don’t have.
Yibo
-Original Message-
From: Ivan Vankov
Sent: Wednesday, March 3, 2021 16:41
To: de
I prefer keeping Jira. Simply because I'm familiar with it and use it in daily
work.
I will log detailed progresses, findings and todos for non-trivial tasks in
Jira comments. It does helps me.
Yibo
From: Sutou Kouhei
Sent: Tuesday, March 2, 2021 9:47 AM
To: de
This topic was talked in an earlier thread [1], but not landed yet.
PR https://github.com/apache/arrow/pull/9424 optimizes ByteStreamSplit with
Arm64 NEON, maybe it's a good chance to evaluate possibility of simplifying
arch dependent SIMD code with an SIMD library.
I did a quick comparison of
Current kernel framework divides inputs (e.g. arrays, chunked arrays) into
batches and feeds to kernel code.
Does it make sense to pass input args directly to kernel?
I'm writing quantile kernel, need to allocate buffer to record all inputs and
find nth at last. For chunked array, input is recei
edia.org/wiki/Algorithms_for_calculating_variance#Computing_shifted_data
[2] https://github.com/tdunning/t-digest
On Thu, Sep 17, 2020 at 8:17 PM Yibo Cai wrote:
Thanks Andrew. The link gives a cool method to calculate variance
incrementally. I think the problem is that it's computationally too
expensive
DAF's
interface requires `update` and `merge`
On Wed, Sep 16, 2020 at 12:12 PM Yibo Cai wrote:
Hi,
I have a question about aggregate kernel implementation. Any help is
appreciated.
Aggregate kernel implements "consume" and "merge" interfaces. For a
chunked array, &qu
/ count(x))/(count(x)-1)))
(loosely translated from
https://math.stackexchange.com/questions/102978/incremental-computation-of-standard-deviation
)
On Wed, Sep 16, 2020 at 6:12 AM Yibo Cai wrote:
Hi,
I have a question about aggregate kernel implementation. Any help is
appreciated.
Aggreg
Hi,
I have a question about aggregate kernel implementation. Any help is
appreciated.
Aggregate kernel implements "consume" and "merge" interfaces. For a chunked array, "consume" is
called for each array to get a temporary aggregated result, then "merge" it with previously consumed result. For
On 6/22/20 5:07 PM, Antoine Pitrou wrote:
Le 22/06/2020 à 06:27, Micah Kornfield a écrit :
There has been significant effort recently trying to optimize our C++
code. One thing that seems to come up frequently is different benchmark
results between GCC and Clang. Even different versions of t
quot;Optimizing Data Throughput over gRPC"
in https://arrow.apache.org/blog/2019/10/13/introducing-arrow-flight/
Kind Regards
Chengxin
Sent with ProtonMail Secure Email.
‐‐‐ Original Message ‐‐‐
On Wednesday, June 17, 2020 8:35 AM, Yibo Cai wrote:
Find a way to achieve reasonable b
Find a way to achieve reasonable benchmark result with multiple threads. Diff
pasted below for a quick review or try.
Tested on E5-2650, with this change:
num_threads = 1, speed = 1996
num_threads = 2, speed = 3555
num_threads = 4, speed = 5828
When running `arrow_flight_benchmark`, I find there
I'm evaluating flight benchmark [1] on single host. Met with one problem. Would
like to seek for help.
Flight benchmark has a "num_threads" parameter [1] to set "number of current gets".
Counter-intuitively, setting it to larger values drops performance, "arrow-flight-benchmark --num_threads=1"
On 6/12/20 2:30 PM, Micah Kornfield wrote:
Hi Frank,
Are the performance numbers you published for the baseline directly from
master? I'd like to look at this over the next few days to see if I can
figure out what is going on.
To all:
I'd like to make sure we flush out things to consider in gen
} pair, it may lead to a globally
suboptimal situation (that is, unless the number of full-time developers
and maintainers on Arrow C++ inflates significantly).
Personally, I would like interested developers and contributors (such as
Micah, Frank, Yibo Cai) to hash out the various possible approaches, a
Yibo Cai created ARROW-9038:
---
Summary: [C++] Improve BitBlockCounter
Key: ARROW-9038
URL: https://issues.apache.org/jira/browse/ARROW-9038
Project: Apache Arrow
Issue Type: Improvement
Yibo Cai created ARROW-8979:
---
Summary: [C++] Implement bitmap word reader and writer
Key: ARROW-8979
URL: https://issues.apache.org/jira/browse/ARROW-8979
Project: Apache Arrow
Issue Type
Yibo Cai created ARROW-8974:
---
Summary: [C++] Refine TransferBitmap template parameters
Key: ARROW-8974
URL: https://issues.apache.org/jira/browse/ARROW-8974
Project: Apache Arrow
Issue Type
Yibo Cai created ARROW-8844:
---
Summary: [C++] Optimize TransferBitmap unaligned case
Key: ARROW-8844
URL: https://issues.apache.org/jira/browse/ARROW-8844
Project: Apache Arrow
Issue Type
Yibo Cai created ARROW-8843:
---
Summary: [C++] Optimize BItmapEquals unaligned case
Key: ARROW-8843
URL: https://issues.apache.org/jira/browse/ARROW-8843
Project: Apache Arrow
Issue Type
Thanks Wes, I'm glad to see this feature coming.
From history talks, the main concern is runtime dispatcher may cause
performance issue.
Personally, I don't think it's a big problem. If we're using SIMD, it must be
targeting some time consuming code.
But we do need to take care some issues. E.
Yibo Cai created ARROW-8728:
---
Summary: [C++] Bitmap operation may cause buffer overflow
Key: ARROW-8728
URL: https://issues.apache.org/jira/browse/ARROW-8728
Project: Apache Arrow
Issue Type: Bug
Yibo Cai created ARROW-8537:
---
Summary: [C++] Performance regression from ARROW-8523
Key: ARROW-8537
URL: https://issues.apache.org/jira/browse/ARROW-8537
Project: Apache Arrow
Issue Type: Bug
Yibo Cai created ARROW-8523:
---
Summary: [C++] Optimize BitmapReader
Key: ARROW-8523
URL: https://issues.apache.org/jira/browse/ARROW-8523
Project: Apache Arrow
Issue Type: Improvement
Yibo Cai created ARROW-8496:
---
Summary: [C++] Refine ByteStreamSplitDecodeScalar
Key: ARROW-8496
URL: https://issues.apache.org/jira/browse/ARROW-8496
Project: Apache Arrow
Issue Type: Improvement
Yibo Cai created ARROW-8440:
---
Summary: Refine simd header files
Key: ARROW-8440
URL: https://issues.apache.org/jira/browse/ARROW-8440
Project: Apache Arrow
Issue Type: Improvement
Yibo Cai created ARROW-8438:
---
Summary: [C++] arrow-io-memory-benchmark crashes
Key: ARROW-8438
URL: https://issues.apache.org/jira/browse/ARROW-8438
Project: Apache Arrow
Issue Type: Bug
Yibo Cai created ARROW-8238:
---
Summary: [C++][Compute] Failed to build compute tests on windows
with msvc2015
Key: ARROW-8238
URL: https://issues.apache.org/jira/browse/ARROW-8238
Project: Apache Arrow
Yibo Cai created ARROW-8227:
---
Summary: [C++] Propose refining SIMD code framework
Key: ARROW-8227
URL: https://issues.apache.org/jira/browse/ARROW-8227
Project: Apache Arrow
Issue Type
s
On Thu, Mar 19, 2020 at 9:57 PM Yibo Cai wrote:
I'm revisiting this old thread as I see some avx512 code merged recently[1].
Code maintenance will be non-trivial if we want to cover more
hardware(sse/avx/avx512/neon/sve/...) and optimize more code in the future.
#ifdef is obviously no-g
>
> >>
> > Hi,>
> >>
> > I would recommend against reinventing the wheel. It would be possible>
> > to reuse an existing C++ SIMD library. There are several of them (Vc,>
> > xsimd, libsimdpp...). Of course, "just use Gandiva"
Yibo Cai created ARROW-8129:
---
Summary: [C++][Compute] Refine compare sorting kernel
Key: ARROW-8129
URL: https://issues.apache.org/jira/browse/ARROW-8129
Project: Apache Arrow
Issue Type
Yibo Cai created ARROW-8126:
---
Summary: [C++][Compute] Add Top-K kernel benchmark
Key: ARROW-8126
URL: https://issues.apache.org/jira/browse/ARROW-8126
Project: Apache Arrow
Issue Type: Improvement
Yibo Cai created ARROW-7587:
---
Summary: [C++][Compute] Add Top-k kernel
Key: ARROW-7587
URL: https://issues.apache.org/jira/browse/ARROW-7587
Project: Apache Arrow
Issue Type: New Feature
Yibo Cai created ARROW-7557:
---
Summary: [C++][Compute] Validate sorting stability in random test
Key: ARROW-7557
URL: https://issues.apache.org/jira/browse/ARROW-7557
Project: Apache Arrow
Issue
Yibo Cai created ARROW-7526:
---
Summary: [C++][Compute]: Optimize small integer sorting
Key: ARROW-7526
URL: https://issues.apache.org/jira/browse/ARROW-7526
Project: Apache Arrow
Issue Type
Maybe just install protobuf dev package is the simplest solution.
On 1/2/20 1:55 PM, Yibo Cai wrote:
I noticed a fresh build always stuck at compiling protobuf for a long time.
We've decided to use single job building for each third party module [1],
partly because different thirty
I noticed a fresh build always stuck at compiling protobuf for a long time.
We've decided to use single job building for each third party module [1],
partly because different thirty party modules are built concurrently (protobuf
is built concurrently with jemalloc, but protobuf itself is built
Yibo Cai created ARROW-7464:
---
Summary: [C++][util]: Refine CpuInfo singleton with std::call_once
Key: ARROW-7464
URL: https://issues.apache.org/jira/browse/ARROW-7464
Project: Apache Arrow
Issue
Hi,
I'm investigating SIMD support to C++ compute kernel(not gandiva).
A typical case is the sum kernel[1]. Below tight loop can be easily optimized
with SIMD.
for (int64_t i = 0; i < length; i++) {
local.sum += values[i];
}
Compiler already does loop vectorization. But it's done at compile
Yibo Cai created ARROW-7404:
---
Summary: [C++][Gandiva] Fix utf8 char length error on Arm64
Key: ARROW-7404
URL: https://issues.apache.org/jira/browse/ARROW-7404
Project: Apache Arrow
Issue Type
Yibo Cai created ARROW-7403:
---
Summary: [C++][JSON] Enable Rapidjson on Arm64 Neon
Key: ARROW-7403
URL: https://issues.apache.org/jira/browse/ARROW-7403
Project: Apache Arrow
Issue Type
1 - 100 of 109 matches
Mail list logo
