Skip to content
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

GH-38090: [C++][Emscripten] acero/hash_join: Suppress shorten-64-to-32 warnings #38093

Closed
wants to merge 1 commit into from
Closed

GH-38090: [C++][Emscripten] acero/hash_join: Suppress shorten-64-to-32 warnings #38093

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
19 changes: 11 additions & 8 deletions cpp/src/arrow/acero/hash_join.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -462,11 +462,11 @@ class HashJoinBasicImpl : public HashJoinImpl {
std::vector<const uint8_t*>* nn_bit_vectors,
std::vector<int64_t>* nn_offsets,
std::vector<uint8_t>* nn_bit_vector_all_nulls) {
int num_cols = static_cast<int>(batch.values.size());
auto num_cols = batch.values.size();
nn_bit_vectors->resize(num_cols);
nn_offsets->resize(num_cols);
nn_bit_vector_all_nulls->clear();
for (int64_t i = 0; i < num_cols; ++i) {
for (size_t i = 0; i < num_cols; ++i) {
const uint8_t* nn = nullptr;
int64_t offset = 0;
if (batch[i].is_array()) {
Expand All @@ -478,9 +478,10 @@ class HashJoinBasicImpl : public HashJoinImpl {
ARROW_DCHECK(batch[i].is_scalar());
if (!batch[i].scalar_as<arrow::internal::PrimitiveScalarBase>().is_valid) {
if (nn_bit_vector_all_nulls->empty()) {
nn_bit_vector_all_nulls->resize(bit_util::BytesForBits(batch.length));
nn_bit_vector_all_nulls->resize(
static_cast<size_t>(bit_util::BytesForBits(batch.length)));
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We should consider making BytesForBits return size_t.

memset(nn_bit_vector_all_nulls->data(), 0,
bit_util::BytesForBits(batch.length));
static_cast<size_t>(bit_util::BytesForBits(batch.length)));
}
nn = nn_bit_vector_all_nulls->data();
}
Expand Down Expand Up @@ -704,8 +705,10 @@ class HashJoinBasicImpl : public HashJoinImpl {
}
if (!hash_table_empty_) {
int32_t num_rows = hash_table_keys_.num_rows();
local_state->has_match.resize(bit_util::BytesForBits(num_rows));
memset(local_state->has_match.data(), 0, bit_util::BytesForBits(num_rows));
local_state->has_match.resize(
static_cast<size_t>(bit_util::BytesForBits(num_rows)));
memset(local_state->has_match.data(), 0,
static_cast<size_t>(bit_util::BytesForBits(num_rows)));
}
local_state->is_has_match_initialized = true;
}
Expand All @@ -716,8 +719,8 @@ class HashJoinBasicImpl : public HashJoinImpl {
}

int32_t num_rows = hash_table_keys_.num_rows();
has_match_.resize(bit_util::BytesForBits(num_rows));
memset(has_match_.data(), 0, bit_util::BytesForBits(num_rows));
has_match_.resize(static_cast<size_t>(bit_util::BytesForBits(num_rows)));
memset(has_match_.data(), 0, static_cast<size_t>(bit_util::BytesForBits(num_rows)));

for (size_t tid = 0; tid < local_states_.size(); ++tid) {
if (!local_states_[tid].is_initialized) {
Expand Down
12 changes: 6 additions & 6 deletions cpp/src/arrow/acero/hash_join_dict.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -107,7 +107,7 @@ static Result<std::shared_ptr<ArrayData>> ConvertImp(
ARROW_ASSIGN_OR_RAISE(std::shared_ptr<Buffer> to_nn_buf,
AllocateBitmap(batch_length, ctx->memory_pool()));
uint8_t* to_nn = to_nn_buf->mutable_data();
memset(to_nn, 0xff, bit_util::BytesForBits(batch_length));
memset(to_nn, 0xff, static_cast<size_t>(bit_util::BytesForBits(batch_length)));

if (!is_scalar) {
const ArrayData& arr = *input.array();
Expand Down Expand Up @@ -143,11 +143,11 @@ static Result<std::shared_ptr<ArrayData>> ConvertImp(
to[i] = to_value;
}

memset(to_nn, 0xff, bit_util::BytesForBits(batch_length));
memset(to_nn, 0xff, static_cast<size_t>(bit_util::BytesForBits(batch_length)));
return ArrayData::Make(to_type, batch_length,
{std::move(to_nn_buf), std::move(to_buf)});
} else {
memset(to_nn, 0, bit_util::BytesForBits(batch_length));
memset(to_nn, 0, static_cast<size_t>(bit_util::BytesForBits(batch_length)));
return ArrayData::Make(to_type, batch_length,
{std::move(to_nn_buf), std::move(to_buf)});
}
Expand Down Expand Up @@ -249,7 +249,7 @@ Status HashJoinDictBuild::Init(ExecContext* ctx, std::shared_ptr<Array> dictiona
AllocateBuffer(length * sizeof(int32_t), ctx->memory_pool()));
uint8_t* non_nulls = non_nulls_buf->mutable_data();
int32_t* ids = reinterpret_cast<int32_t*>(ids_buf->mutable_data());
memset(non_nulls, 0xff, bit_util::BytesForBits(length));
memset(non_nulls, 0xff, static_cast<size_t>(bit_util::BytesForBits(length)));

int32_t num_entries = 0;
for (int64_t i = 0; i < length; ++i) {
Expand Down Expand Up @@ -310,7 +310,7 @@ Result<std::shared_ptr<ArrayData>> HashJoinDictBuild::RemapInputValues(
AllocateBuffer(batch_length * sizeof(int32_t), ctx->memory_pool()));
uint8_t* non_nulls = non_nulls_buf->mutable_data();
int32_t* ids = reinterpret_cast<int32_t*>(ids_buf->mutable_data());
memset(non_nulls, 0xff, bit_util::BytesForBits(batch_length));
memset(non_nulls, 0xff, static_cast<size_t>(bit_util::BytesForBits(batch_length)));

// Populate output buffers (for scalar only the first entry is populated)
//
Expand All @@ -334,7 +334,7 @@ Result<std::shared_ptr<ArrayData>> HashJoinDictBuild::RemapInputValues(
//
if (is_scalar) {
if (!bit_util::GetBit(non_nulls, 0)) {
memset(non_nulls, 0, bit_util::BytesForBits(batch_length));
memset(non_nulls, 0, static_cast<size_t>(bit_util::BytesForBits(batch_length)));
}
for (int64_t i = 1; i < batch_length; ++i) {
ids[i] = ids[0];
Expand Down
14 changes: 8 additions & 6 deletions cpp/src/arrow/acero/hash_join_node.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -554,9 +554,9 @@ struct BloomFilterPushdownContext {
ExecBatch& batch = *batch_ptr;
if (eval_.num_expected_bloom_filters_ == 0 || batch.length == 0) return Status::OK();

int64_t bit_vector_bytes = bit_util::BytesForBits(batch.length);
auto bit_vector_bytes = static_cast<size_t>(bit_util::BytesForBits(batch.length));
std::vector<uint8_t> selected(bit_vector_bytes);
std::vector<uint32_t> hashes(batch.length);
std::vector<uint32_t> hashes(static_cast<size_t>(batch.length));
std::vector<uint8_t> bv(bit_vector_bytes);

ARROW_ASSIGN_OR_RAISE(arrow::util::TempVectorStack * stack,
Expand Down Expand Up @@ -961,8 +961,9 @@ class HashJoinNode : public ExecNode, public TracedNode {

task_group_probe_ = ctx->RegisterTaskGroup(
[this](size_t thread_index, int64_t task_id) -> Status {
return impl_->ProbeSingleBatch(thread_index,
std::move(queued_batches_to_probe_[task_id]));
return impl_->ProbeSingleBatch(
thread_index,
std::move(queued_batches_to_probe_[static_cast<size_t>(task_id)]));
},
[this](size_t thread_index) -> Status {
return OnQueuedBatchesProbed(thread_index);
Expand Down Expand Up @@ -1070,7 +1071,8 @@ void BloomFilterPushdownContext::Init(

eval_.task_id_ = register_task_group_callback(
[this](size_t thread_index, int64_t task_id) {
return FilterSingleBatch(thread_index, &eval_.batches_[task_id]);
return FilterSingleBatch(thread_index,
&eval_.batches_[static_cast<size_t>(task_id)]);
},
[this](size_t thread_index) {
return eval_.on_finished_(thread_index, std::move(eval_.batches_));
Expand Down Expand Up @@ -1111,7 +1113,7 @@ Status BloomFilterPushdownContext::PushBloomFilter(size_t thread_index) {

Status BloomFilterPushdownContext::BuildBloomFilter_exec_task(size_t thread_index,
int64_t task_id) {
const ExecBatch& input_batch = build_.batches_[task_id];
const ExecBatch& input_batch = build_.batches_[static_cast<size_t>(task_id)];
SchemaProjectionMap key_to_in =
schema_mgr_->proj_maps[1].map(HashJoinProjection::KEY, HashJoinProjection::INPUT);
std::vector<Datum> key_columns(key_to_in.num_cols);
Expand Down