Skip to content

ext/standard: Remove useless _mm_movemask_epi8 check in rot13 #23795

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
LamentXU123 wants to merge 1 commit into
base: master
Choose a base branch
from
+9 −16
Open

ext/standard: Remove useless _mm_movemask_epi8 check in rot13 #23795

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions UPGRADING
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1145,6 +1145,7 @@ PHP 8.6 UPGRADE NOTES
. Improved performance of str_split().
. Improved performance of str_pad().
. Improved performance of str_repeat() when the multiplier is 1.
. Removed redundant branches from the SSE2 implementation of str_rot13().

- URI:
. Improved performance of Uri\WhatWg\Url::parse() when collecting
Expand Down
24 changes: 8 additions & 16 deletions ext/standard/string.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6037,34 +6037,26 @@ static zend_string *php_str_rot13(zend_string *str)
gt = _mm_cmpgt_epi8(in, a_minus_1);
lt = _mm_cmplt_epi8(in, m_plus_1);
cmp = _mm_and_si128(lt, gt);
if (_mm_movemask_epi8(cmp)) {
cmp = _mm_and_si128(cmp, add);
delta = _mm_or_si128(delta, cmp);
}
cmp = _mm_and_si128(cmp, add);
delta = _mm_or_si128(delta, cmp);

gt = _mm_cmpgt_epi8(in, n_minus_1);
lt = _mm_cmplt_epi8(in, z_plus_1);
cmp = _mm_and_si128(lt, gt);
if (_mm_movemask_epi8(cmp)) {
cmp = _mm_and_si128(cmp, sub);
delta = _mm_or_si128(delta, cmp);
}
cmp = _mm_and_si128(cmp, sub);
delta = _mm_or_si128(delta, cmp);

gt = _mm_cmpgt_epi8(in, A_minus_1);
lt = _mm_cmplt_epi8(in, M_plus_1);
cmp = _mm_and_si128(lt, gt);
if (_mm_movemask_epi8(cmp)) {
cmp = _mm_and_si128(cmp, add);
delta = _mm_or_si128(delta, cmp);
}
cmp = _mm_and_si128(cmp, add);
delta = _mm_or_si128(delta, cmp);

gt = _mm_cmpgt_epi8(in, N_minus_1);
lt = _mm_cmplt_epi8(in, Z_plus_1);
cmp = _mm_and_si128(lt, gt);
if (_mm_movemask_epi8(cmp)) {
cmp = _mm_and_si128(cmp, sub);
delta = _mm_or_si128(delta, cmp);
}
cmp = _mm_and_si128(cmp, sub);
delta = _mm_or_si128(delta, cmp);
Comment on lines 6037 to +6059

@iliaal iliaal Sep 20, 2026

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

c | 0x20 maps A-Z onto a-z and moves nothing else into that range (it only touches bit 5, and bytes >= 0x80 stay negative under the signed compare), so the four range tests collapse into one plus a midpoint test:

const __m128i lowbit = _mm_set1_epi8(0x20);
const __m128i a_minus_1 = _mm_set1_epi8('a' - 1);
const __m128i z_plus_1 = _mm_set1_epi8('z' + 1);
const __m128i n = _mm_set1_epi8('n');
const __m128i add = _mm_set1_epi8(13);
const __m128i sub = _mm_set1_epi8(-13);

do {
	__m128i in = _mm_loadu_si128((__m128i *)p);
	__m128i low = _mm_or_si128(in, lowbit);
	__m128i alpha = _mm_and_si128(_mm_cmpgt_epi8(low, a_minus_1), _mm_cmplt_epi8(low, z_plus_1));
	__m128i first = _mm_cmplt_epi8(low, n);
	__m128i delta = _mm_and_si128(_mm_or_si128(_mm_and_si128(first, add), _mm_andnot_si128(first, sub)), alpha);

	_mm_storeu_si128((__m128i *)target, _mm_add_epi8(in, delta));

	p += 16;
	target += 16;
} while (e - p > 15);

gcc 11.4 -O2: the compiled loop body goes from 28 SIMD instructions to 15, and the 4-deep serial OR chain on delta goes away. Best of 7 over 1 MiB against your version: 1.9x on all-lowercase, 1.9x on digits, 2.4x on mixed case. Byte-identical to the scalar fallback for every byte value in every lane.

Separately, for the description: 1.2-1.3x is the floor, not the typical case. Random bytes at 1 MiB measure 7.9x against master here, since the four branches mispredict. Small buffers hide that, the predictor just memorizes a short repeating pattern.


in = _mm_add_epi8(in, delta);
_mm_storeu_si128((__m128i *)target, in);
Expand Down
Loading