weaselab/conflict-set
2
0
Fork 0
Code Issues 4 Packages Releases 13 Activity

Write vectorized 32-bit compare by hand for arm in scan16
Some checks failed
Tests / Clang total: 1039, passed: 1039
Details
Clang |Total|New|Outstanding|Fixed|Trend |:-:|:-:|:-:|:-:|:-: |0|0|0|0|:clap:
Details
Tests / SIMD fallback total: 1039, passed: 1039
Details
Tests / Release [gcc] total: 1039, passed: 1039
Details
GNU C Compiler (gcc) |Total|New|Outstanding|Fixed|Trend |:-:|:-:|:-:|:-:|:-: |0|0|0|0|:clap:
Details
Tests / Release [gcc,aarch64] total: 775, passed: 775
Details
Tests / Coverage total: 780, failed: 1, passed: 779
Details
weaselab/conflict-set/pipeline/head There was a failure building this commit
Details

Browse Source
This commit is contained in:
Andrew Noyes
2024-06-28 17:28:59 -07:00
parent b311e5f1f0
commit f762add4d6
1 changed files with 22 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
ConflictSet.cpp
View File

@@ -1776,10 +1776,32 @@ 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);
#if INTERNAL_VERSION_32_BIT
uint32x4_t w4[4];
memcpy(w4, vs, sizeof(w4));
uint32_t rv;
memcpy(&rv, &readVersion, sizeof(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(vsubq_u32(w4[i], vdupq_n_u32(rv)), 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);
#else
uint64_t compared = 0;
for (int i = 0; i < 16; ++i) {
compared |= uint64_t(vs[i] > readVersion) << (i << 2);
}
#endif
return !(compared & mask);
#elif defined(HAS_AVX)