| #
3c9ab6eb |
| 17-Jul-2024 |
Saki Takamachi |
ext/bcmath: Moved macros and added a test
|
| #
90a5b871 |
| 07-May-2024 |
Niels Dossche <7771979+nielsdos@users.noreply.github.com> |
Simplify conversion in BCMath (#14157)
This simplifies the code, and also might indirectly improve performance
due to a decrease in instruction cache pressure. Although the latter is
Simplify conversion in BCMath (#14157)
This simplifies the code, and also might indirectly improve performance
due to a decrease in instruction cache pressure. Although the latter is
probably negligible.
This works because 0x30 has no overlapping bits with [0, 9].
show more ...
|
| #
02732007 |
| 07-May-2024 |
Saki Takamachi <34942839+SakiTakamachi@users.noreply.github.com> |
Refactor BCMath `_bc_do_sub` (#14132)
_bc_do_sub now uses SIMD to perform calculations at high speed.
Moved the macros used for SIMD to `private.h`, and added some constants
and
Refactor BCMath `_bc_do_sub` (#14132)
_bc_do_sub now uses SIMD to perform calculations at high speed.
Moved the macros used for SIMD to `private.h`, and added some constants
and macros.
show more ...
|
| #
a604d1d3 |
| 01-May-2024 |
Niels Dossche <7771979+nielsdos@users.noreply.github.com> |
Use SSE2 in bc_copy_and_shift_numbers() if possible
|
| #
0a3ccc0b |
| 01-May-2024 |
Niels Dossche <7771979+nielsdos@users.noreply.github.com> |
Use bulk conversion in BCMath of BCD/CHAR where possible (#14103)
On my i7-4790 with benchmark from #14076, on top of #14101 I obtain the
following results:
before (with #14101)
Use bulk conversion in BCMath of BCD/CHAR where possible (#14103)
On my i7-4790 with benchmark from #14076, on top of #14101 I obtain the
following results:
before (with #14101):
```
1.672737121582
2.3618471622467
2.3474779129028
```
after (with #14101 + this):
```
1.5878579616547
2.0568618774414
2.0204811096191
```
show more ...
|
