Commit Graph

22 Commits

Author SHA1 Message Date
Alexey Milovidov
decdb62cef
Merge pull request #58800 from ZhiguoZh/20240115-combine-filter-bmi2
Optimize DB::combineFilters with BMI2/SSE intrinsics
2024-01-19 16:50:04 +01:00
Zhiguo Zhou
83f0c3bb99 Enable BMI2 attribute when AVX2 is supported
The BMI2/AVX2 features were introduced with the same architectures
(Haswell from Intel and Excavator from AMD). The enabling of BMI2
attribute should be safe for the AVX2 specific code.
2024-01-15 09:53:29 +08:00
Roman Glinskikh
96033cb0e4 add instructions everywhere 2024-01-10 12:29:14 +03:00
Raúl Marín
2fdb56bb4b Merge remote-tracking branch 'blessed/master' into speedup_numbers 2023-12-28 11:26:16 +01:00
Raúl Marín
76abd32196 Speedup MIN and MAX for native types 2023-12-26 20:23:55 +01:00
Alexey Milovidov
a22f0eee2a
Merge branch 'master' into Aggregate_Sum_AVX512 2023-02-19 04:03:45 +03:00
Guo Wangyang
4e294b9bfc
ColumnVector: re-enable AVX512_VBMI/AVX512_VBMI2 optimized filter and index (#41765)
* Revert "Merge pull request #41752 from ClickHouse/revert-revert-revert"

This reverts commit 7bb245720a, reversing
changes made to 78002dc248.

* Revert "Merge pull request #41797 from ClickHouse/revert-41247"

This reverts commit 69b13d9f31, reversing
changes made to 1719e000ea.

* AVX512VBMI::vectorIndexImpl: Fix heap buffer overflow when limit == 0

* use SIMD_ELEMENTS instead of SIMD_BYTES to avoid confusing
2022-10-24 23:11:46 +02:00
Alexey Milovidov
e3a6f2381b Revert "Merge pull request #40033 from ClickHouse/reenable-avx512-vbmi-columnvector-filter"
This reverts commit 70f63d2aae, reversing
changes made to a0693c3a84.
2022-09-25 17:03:52 +02:00
Robert Schulze
05ea33c897
Revert "Revert "ColumnVector: optimize filter with AVX512VBMI2 compress store""
This reverts commit 5524706b78.
2022-08-09 17:00:13 +00:00
Alexey Milovidov
5524706b78
Revert "ColumnVector: optimize filter with AVX512VBMI2 compress store" 2022-08-08 05:03:15 +03:00
Wangyang Guo
b05be56eef ColumnVector: naming style fix 2022-08-01 10:16:15 +08:00
Wangyang Guo
e6752d687f TargetSpecific: add AVX512VBMI2 support 2022-07-27 13:30:43 +08:00
Wangyang Guo
c07c65615d fix ENABLE_MULTITARGET_CODE not defined warning in some builds 2022-07-17 12:21:10 +08:00
Wangyang Guo
397a4ac888 TargetSpecific: add AVX512VBMI support 2022-07-15 15:07:09 +08:00
zhao zhou
cd2911d635 Add avx512 support for Aggregate Sum, function unary arithmetic, function comparison 2022-06-06 09:29:47 +08:00
Alexander Gololobov
6433fd6113 Added macros for AVX512BW target 2022-06-02 11:19:46 +02:00
Alexander Gololobov
a0cf902d49
Merge pull request #37588 from yaqi-zhao/avx512_tail_zero
add avx512 support for mergetree reader
2022-06-02 08:51:52 +03:00
yaqi-zhao
a2857491c4 add avx512 support for mergetreereader 2022-05-30 20:53:00 -04:00
Maksim Kita
e6e4b2826d Dynamic dispatch infrastructure style fixes 2022-05-24 14:25:29 +02:00
Maksim Kita
31a29d8315 Fixed dynamic dispatch macro 2022-05-17 16:59:11 +02:00
Maksim Kita
032b5d3fc3 Dynamic dispatch infrastructure for class member functions 2022-05-16 17:05:16 +02:00
Maksim Kita
47528de78b Fix build 2022-04-04 14:07:05 +02:00