weaselab/conflict-set
1
Fork 1
Code Issues 5 Pull Requests 1 Actions 4 Packages Releases 13 Activity

Merge pull request 'Fix ARM NEON scan helpers truncating 64-bit versions' (#75) from weaselbot/conflict-set:weaselbot/issue-69 into main
CI / pre-commit (push) Successful in 2m1s
Details
CI / release (arm64, , ubuntu-latest-arm64) (push) Successful in 3m24s
Details
CI / test (-DCMAKE_BUILD_TYPE=Debug -DMSAN_TOOLCHAIN_PATH=/opt/msan, debug) (push) Successful in 3m52s
Details
CI / test (-DCMAKE_CXX_FLAGS=-DUSE_64_BIT=1, 64-bit-versions) (push) Successful in 3m20s
Details
CI / test (-DCMAKE_C_COMPILER=gcc -DCMAKE_CXX_COMPILER=g++, gcc) (push) Successful in 3m15s
Details
CI / test (-DUSE_SIMD_FALLBACK=ON, simd-fallback) (push) Successful in 3m20s
Details
CI / release (amd64, -DMSAN_TOOLCHAIN_PATH=/opt/msan, ubuntu-latest-amd64) (push) Successful in 5m36s
Details
CI / coverage (push) Successful in 3m49s
Details

Browse Source 
Reviewed-on: #75
This commit was merged in pull request #75.
This commit is contained in:
andrew
2026-08-03 12:26:03 +00:00
parent bdbac1556d 6b1f597d77
commit 1179c1f56e
1 changed files with 56 additions and 57 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ConflictSet.cpp
+56 -57
View File
@@ -2057,6 +2057,52 @@ compare16_avx512(const InternalVersionT *vs, InternalVersionT rv) {
}
#endif
#ifdef HAS_ARM_NEON
// Returns a uint8x16_t whose byte i is 0xff if vs[i] > readVersion and 0
// otherwise. When USE_64_BIT is set the comparison uses the full 64-bit value
// (via vcgtq_s64); otherwise it falls back to the 32-bit subtract-and-compare
// used by the original NEON fast path. The caller narrows this 16-byte vector
// into the nibble-packed (4 bits per version) mask expected by scan16 and
// checkMaxBetweenExclusiveImpl.
inline uint8x16_t conflictMask16(const InternalVersionT *vs,
InternalVersionT readVersion) {
#if USE_64_BIT
int64_t rv;
memcpy(&rv, &readVersion, sizeof(rv));
const auto rvVec = vdupq_n_s64(rv);
int32x2_t r32[8];
const auto *vsp = reinterpret_cast<const int64_t *>(vs);
for (int j = 0; j < 8; ++j) {
r32[j] = vmovn_s64(vcgtq_s64(vld1q_s64(vsp + 2 * j), rvVec));
}
uint32x4_t w4[4];
for (int k = 0; k < 4; ++k) {
w4[k] = vreinterpretq_u32_s32(vcombine_s32(r32[2 * k], r32[2 * k + 1]));
}
return vcombine_u8(
vmovn_u16(vcombine_u16(vmovn_u32(w4[0]), vmovn_u32(w4[1]))),
vmovn_u16(vcombine_u16(vmovn_u32(w4[2]), vmovn_u32(w4[3]))));
#else
uint32x4_t w4[4];
memcpy(w4, vs, sizeof(w4));
uint32_t rv;
memcpy(&rv, &readVersion, sizeof(rv));
const auto rvVec = vdupq_n_u32(rv);
int32x4_t z;
memset(&z, 0, sizeof(z));
uint16x4_t conflicting[4];
for (int i = 0; i < 4; ++i) {
conflicting[i] =
vmovn_u32(vcgtq_s32(vreinterpretq_s32_u32(vsubq_u32(w4[i], rvVec)), z));
}
return vcombine_u8(vmovn_u16(vcombine_u16(conflicting[0], conflicting[1])),
vmovn_u16(vcombine_u16(conflicting[2], conflicting[3])));
#endif
}
#endif
// Returns true if v[i] <= readVersion for all i such that begin <= is[i] < end
// Preconditions: begin <= end, end - begin < 256
template <bool kAVX512>
@@ -2077,26 +2123,10 @@ bool scan16(const InternalVersionT *vs, const uint8_t *is, int begin, int end,
uint64_t mask = vget_lane_u64(
vreinterpret_u64_u8(vshrn_n_u16(vreinterpretq_u16_u8(results), 4)), 0);
uint32x4_t w4[4];
memcpy(w4, vs, sizeof(w4));
uint32_t rv;
memcpy(&rv, &readVersion, sizeof(rv));
const auto rvVec = vdupq_n_u32(rv);
int32x4_t z;
memset(&z, 0, sizeof(z));
uint16x4_t conflicting[4];
for (int i = 0; i < 4; ++i) {
conflicting[i] =
vmovn_u32(vcgtq_s32(vreinterpretq_s32_u32(vsubq_u32(w4[i], rvVec)), z));
}
auto combined =
vcombine_u8(vmovn_u16(vcombine_u16(conflicting[0], conflicting[1])),
vmovn_u16(vcombine_u16(conflicting[2], conflicting[3])));
uint64_t compared = vget_lane_u64(
vreinterpret_u64_u8(vshrn_n_u16(vreinterpretq_u16_u8(combined), 4)), 0);
vreinterpret_u64_u8(vshrn_n_u16(
vreinterpretq_u16_u8(conflictMask16(vs, readVersion)), 4)),
0);
return !(compared & mask);
@@ -2142,26 +2172,10 @@ bool scan16(const InternalVersionT *vs, int begin, int end,
assert(begin <= end);
#if defined(HAS_ARM_NEON)
uint32x4_t w4[4];
memcpy(w4, vs, sizeof(w4));
uint32_t rv;
memcpy(&rv, &readVersion, sizeof(rv));
const auto rvVec = vdupq_n_u32(rv);
int32x4_t z;
memset(&z, 0, sizeof(z));
uint16x4_t conflicting[4];
for (int i = 0; i < 4; ++i) {
conflicting[i] =
vmovn_u32(vcgtq_s32(vreinterpretq_s32_u32(vsubq_u32(w4[i], rvVec)), z));
}
auto combined =
vcombine_u8(vmovn_u16(vcombine_u16(conflicting[0], conflicting[1])),
vmovn_u16(vcombine_u16(conflicting[2], conflicting[3])));
uint64_t conflict = vget_lane_u64(
vreinterpret_u64_u8(vshrn_n_u16(vreinterpretq_u16_u8(combined), 4)), 0);
vreinterpret_u64_u8(vshrn_n_u16(
vreinterpretq_u16_u8(conflictMask16(vs, readVersion)), 4)),
0);
conflict &= end == 16 ? -1 : (uint64_t(1) << (end << 2)) - 1;
conflict >>= begin << 2;
@@ -2275,26 +2289,11 @@ bool checkMaxBetweenExclusiveImpl(Node16 *n, int begin, int end,
const bool firstRangeOk =
!child->entryPresent || child->entry.rangeVersion <= readVersion;
uint32x4_t w4[4];
memcpy(w4, self->childMaxVersion, sizeof(w4));
uint32_t rv;
memcpy(&rv, &readVersion, sizeof(rv));
const auto rvVec = vdupq_n_u32(rv);
int32x4_t z;
memset(&z, 0, sizeof(z));
uint16x4_t conflicting[4];
for (int i = 0; i < 4; ++i) {
conflicting[i] =
vmovn_u32(vcgtq_s32(vreinterpretq_s32_u32(vsubq_u32(w4[i], rvVec)), z));
}
auto combined =
vcombine_u8(vmovn_u16(vcombine_u16(conflicting[0], conflicting[1])),
vmovn_u16(vcombine_u16(conflicting[2], conflicting[3])));
uint64_t compared = vget_lane_u64(
vreinterpret_u64_u8(vshrn_n_u16(vreinterpretq_u16_u8(combined), 4)), 0);
vreinterpret_u64_u8(vshrn_n_u16(vreinterpretq_u16_u8(conflictMask16(
self->childMaxVersion, readVersion)),
4)),
0);
return !(compared & mask) && firstRangeOk;