avx512-peel-first-iteration.patch
text/x-patch
Filename: avx512-peel-first-iteration.patch
Type: text/x-patch
Part: 0
Patch
Same data as JSON:
GET /api/v1/attachments/:id/patch
the parsed metadata as JSON — format, series position, per-file stats; never the diff bytes.
API reference →
Format: unified
| File | + | − |
|---|---|---|
| src/port/pg_popcount_avx512.c | 9 | 1 |
diff --git a/src/port/pg_popcount_avx512.c b/src/port/pg_popcount_avx512.c
index dacc7553d29..f6e718b86e9 100644
--- a/src/port/pg_popcount_avx512.c
+++ b/src/port/pg_popcount_avx512.c
@@ -52,13 +52,21 @@ pg_popcount_avx512(const char *buf, int bytes)
* Iterate through all but the final iteration. Starting from second
* iteration, the start index mask is ignored.
*/
- for (; buf < final; buf += sizeof(__m512i))
+ if (buf < final)
{
val = _mm512_maskz_loadu_epi8(mask, (const __m512i *) buf);
cnt = _mm512_popcnt_epi64(val);
accum = _mm512_add_epi64(accum, cnt);
+ buf += sizeof(__m512i);
mask = ~UINT64CONST(0);
+
+ for (; buf < final; buf += sizeof(__m512i))
+ {
+ val = _mm512_load_si512((const __m512i *) buf);
+ cnt = _mm512_popcnt_epi64(val);
+ accum = _mm512_add_epi64(accum, cnt);
+ }
}
/* Final iteration needs to ignore bytes that are not within the length */