Skip to content

Alternative approach to handling memory offset shift #9406

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
JakeStevens merged 1 commit into from
Mar 26, 2025
Merged

Alternative approach to handling memory offset shift #9406

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
5 changes: 2 additions & 3 deletions runtime/executor/tensor_parser_exec_aten.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,16 +56,15 @@ ET_NODISCARD Result<void*> getMemPlannedPtr(
const uint32_t memory_offset_high = allocation_info->memory_offset_high();

size_t memory_offset = memory_offset_low;
if (memory_offset_high > 0) {
if ((sizeof(size_t) > sizeof(uint32_t)) && (memory_offset_high > 0)) {
// The compiler should remove this always-true check on 64-bit systems.
ET_CHECK_OR_RETURN_ERROR(
sizeof(size_t) >= sizeof(uint64_t),
NotSupported,
"size_t cannot hold memory offset 0x%08" PRIx32 ".%08" PRIx32,
memory_offset_high,
memory_offset_low);
memory_offset |= static_cast<size_t>(memory_offset_high)
<< (sizeof(size_t) - sizeof(uint32_t));
memory_offset |= static_cast<size_t>(memory_offset_high) << 32;
}
return allocator->get_offset_address(memory_id, memory_offset, nbytes);
}
Expand Down
Loading