Fix Or/Xor dropping bits when combining bitmaps of different lengths (#51)

* fix: union/xor of different-sized bitmaps drops bits in variadic path

Or and Xor with extra bitmaps used _or_many/_xor_many, which apply a single
word count to every input. The count came from pointersOf, whose length is
the maximum over the extra slice only and ignores other, so a longer other
lost its tail words. More generally a uniform count cannot combine operands
of different lengths: a longer source is truncated and a shorter one is read
past its end.

Fold each source in with the single-operand SIMD primitive over its own
length, matching the scalar reference in simd_generic.go. Fixes the amd64
accelerated and AVX-512 branches and the arm64 branch.

* Keep the _many primitives for equal-sized operands, fold only ragged ones

* test: cover longer ragged bitmap extras

---------

Co-authored-by: Roman <roman.atachiants@gmail.com>
This commit is contained in:
dualfrozandRoman committed 2026-09-23 15:30:32 +04:00
1 parent 58b05bdfdd
commit 47698fd8b9
4 files changed
+146 -12

No files matched your search

+16 -4
View File
@@ -67,8 +67,14 @@ func (dst *Bitmap) Or(other Bitmap, extra ...Bitmap) {
case 0:
_or(unsafe.Pointer(&(*dst)[0]), unsafe.Pointer(&other[0]), uint64(len(other)))
default:
vx, max := pointersOf(other, extra)
_or_many(unsafe.Pointer(&(*dst)[0]), vx, dimensionsOf(max, len(extra)+1))
// _or_many applies one word count to every input, so it only fits
// sources that share a length; ragged ones are folded in one by one.
if n := uniformLen(other, extra); n > 0 {
vx, _ := pointersOf(other, extra)
_or_many(unsafe.Pointer(&(*dst)[0]), vx, dimensionsOf(n, len(extra)+1))
} else {
foldEach(dst, _or, other, extra)
}
}
default:
or(*dst, other, extra)
@@ -89,8 +95,14 @@ func (dst *Bitmap) Xor(other Bitmap, extra ...Bitmap) {
case 0:
_xor(unsafe.Pointer(&(*dst)[0]), unsafe.Pointer(&other[0]), uint64(len(other)))
default:
vx, max := pointersOf(other, extra)
_xor_many(unsafe.Pointer(&(*dst)[0]), vx, dimensionsOf(max, len(extra)+1))
// _xor_many applies one word count to every input, so it only fits
// sources that share a length; ragged ones are folded in one by one.
if n := uniformLen(other, extra); n > 0 {
vx, _ := pointersOf(other, extra)
_xor_many(unsafe.Pointer(&(*dst)[0]), vx, dimensionsOf(n, len(extra)+1))
} else {
foldEach(dst, _xor, other, extra)
}
}
default:
xor(*dst, other, extra)