Skip to content

Fix bit packing #447

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

Merged
AlexanderSaydakov merged 3 commits into from
Jan 9, 2025
Merged

Fix bit packing #447

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
5c19333
fixed bit packing
AlexanderSaydakov Jan 9, 2025
666df8b
unused import
AlexanderSaydakov Jan 9, 2025
6e944cf
fixed name clash
AlexanderSaydakov Jan 9, 2025
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
6 changes: 3 additions & 3 deletions theta/include/bit_packing.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -329,7 +329,7 @@ static inline void pack_bits_13(const uint64_t* values, uint8_t* ptr) {

*ptr++ = static_cast<uint8_t>(values[3] >> 4);

*ptr = static_cast<uint8_t>(values[3] >> 4);
*ptr = static_cast<uint8_t>(values[3] << 4);
*ptr++ |= static_cast<uint8_t>(values[4] >> 9);

*ptr++ = static_cast<uint8_t>(values[4] >> 1);
Expand Down Expand Up @@ -4227,7 +4227,7 @@ static inline void unpack_bits_33(uint64_t* values, const uint8_t* ptr) {
values[6] |= *ptr >> 1;

values[7] = static_cast<uint64_t>(*ptr++ & 1) << 32;
values[7] |= *ptr++ << 24;
values[7] |= static_cast<uint64_t>(*ptr++) << 24;
values[7] |= *ptr++ << 16;
values[7] |= *ptr++ << 8;
values[7] |= *ptr;
Expand Down Expand Up @@ -4296,7 +4296,7 @@ static inline void unpack_bits_35(uint64_t* values, const uint8_t* ptr) {
values[1] |= *ptr++ << 6;
values[1] |= *ptr >> 2;

values[2] = static_cast<uint64_t>(*ptr++ & 2) << 33;
values[2] = static_cast<uint64_t>(*ptr++ & 3) << 33;
values[2] |= static_cast<uint64_t>(*ptr++) << 25;
values[2] |= *ptr++ << 17;
values[2] |= *ptr++ << 9;
Expand Down
80 changes: 41 additions & 39 deletions theta/test/bit_packing_test.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,51 +29,53 @@ namespace datasketches {
static const uint64_t IGOLDEN64 = 0x9e3779b97f4a7c13ULL;

TEST_CASE("pack unpack bits") {
for (uint8_t bits = 1; bits <= 63; ++bits) {
int n = 8;
const uint64_t mask = (1ULL << bits) - 1;
std::vector<uint64_t> input(n, 0);
const uint64_t igolden64 = IGOLDEN64;
uint64_t value = 0xaa55aa55aa55aa55ULL; // arbitrary starting value
for (int i = 0; i < n; ++i) {
input[i] = value & mask;
value += igolden64;
}
std::vector<uint8_t> bytes(n * sizeof(uint64_t), 0);
uint8_t offset = 0;
uint8_t* ptr = bytes.data();
for (int i = 0; i < n; ++i) {
offset = pack_bits(input[i], bits, ptr, offset);
}
uint64_t value = 0xaa55aa55aa55aa55ULL; // arbitrary starting value
for (int n = 0; n < 100; ++n) {
for (uint8_t bits = 1; bits <= 63; ++bits) {
int n = 8;
Comment thread
jmalkin marked this conversation as resolved.
const uint64_t mask = (1ULL << bits) - 1;
std::vector<uint64_t> input(n, 0);
for (int i = 0; i < n; ++i) {
input[i] = value & mask;
value += IGOLDEN64;
}
std::vector<uint8_t> bytes(n * sizeof(uint64_t), 0);
uint8_t offset = 0;
uint8_t* ptr = bytes.data();
for (int i = 0; i < n; ++i) {
offset = pack_bits(input[i], bits, ptr, offset);
}

std::vector<uint64_t> output(n, 0);
offset = 0;
const uint8_t* cptr = bytes.data();
for (int i = 0; i < n; ++i) {
offset = unpack_bits(output[i], bits, cptr, offset);
}
for (int i = 0; i < n; ++i) {
REQUIRE(input[i] == output[i]);
std::vector<uint64_t> output(n, 0);
offset = 0;
const uint8_t* cptr = bytes.data();
for (int i = 0; i < n; ++i) {
offset = unpack_bits(output[i], bits, cptr, offset);
}
for (int i = 0; i < n; ++i) {
REQUIRE(input[i] == output[i]);
}
}
}
}

TEST_CASE("pack unpack blocks") {
for (uint8_t bits = 1; bits <= 63; ++bits) {
const uint64_t mask = (1ULL << bits) - 1;
std::vector<uint64_t> input(8, 0);
const uint64_t igolden64 = IGOLDEN64;
uint64_t value = 0xaa55aa55aa55aa55ULL; // arbitrary starting value
for (int i = 0; i < 8; ++i) {
input[i] = value & mask;
value += igolden64;
}
std::vector<uint8_t> bytes(8 * sizeof(uint64_t), 0);
pack_bits_block8(input.data(), bytes.data(), bits);
std::vector<uint64_t> output(8, 0);
unpack_bits_block8(output.data(), bytes.data(), bits);
for (int i = 0; i < 8; ++i) {
REQUIRE((input[i] & mask) == output[i]);
uint64_t value = 0xaa55aa55aa55aa55ULL; // arbitrary starting value
for (int n = 0; n < 100; ++n) {
for (uint8_t bits = 1; bits <= 63; ++bits) {
const uint64_t mask = (1ULL << bits) - 1;
std::vector<uint64_t> input(8, 0);
for (int i = 0; i < 8; ++i) {
input[i] = value & mask;
value += IGOLDEN64;
}
std::vector<uint8_t> bytes(bits, 0);
pack_bits_block8(input.data(), bytes.data(), bits);
std::vector<uint64_t> output(8, 0);
unpack_bits_block8(output.data(), bytes.data(), bits);
for (int i = 0; i < 8; ++i) {
REQUIRE(input[i] == output[i]);
}
}
}
}
Expand Down