From 3e608b5495b7b7746bc4f31e5092bdb71e1c5ec9 Mon Sep 17 00:00:00 2001
From: Mergen Nachin <mnachin@meta.com>
Date: Mon, 8 Sep 2025 11:29:07 -0400
Subject: [PATCH] Fix aarch64/arm64 Linux wheel build failure due to missing
 libatomic linking

Problem

The tokenizers library fails to build on aarch64 Linux systems during CI with:
/opt/rh/gcc-toolset-13/root/usr/libexec/gcc/aarch64-redhat-linux/13/ld: cannot find -latomic: No such file or directory

Root Cause

- On aarch64, certain atomic operations require explicit linking with libatomic
- The sentencepiece dependency detects libatomic (Found atomic: /usr/lib64/libatomic.so.1) but incorrectly adds just the string "atomic" to link flags instead of the actual library path
- This causes the linker to fail when building the Python extension

Solution

Added proper libatomic detection and linking for aarch64/arm64 systems in two places:
1. For the tokenizers static library
2. For the pytorch_tokenizers_cpp Python extension module

The fix uses CMake's find_library to locate libatomic and explicitly links it when building on aarch64/arm64 architectures.
---
 CMakeLists.txt | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/CMakeLists.txt b/CMakeLists.txt
index 5fec1ea..acae029 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -94,6 +94,15 @@ target_include_directories(
 )
 target_link_libraries(tokenizers PUBLIC sentencepiece-static re2::re2)
 
+# Link with atomic library on aarch64/arm64 systems
+# Some aarch64 systems require explicit linking with libatomic for certain atomic operations
+if(CMAKE_SYSTEM_PROCESSOR MATCHES "aarch64|arm64")
+  find_library(ATOMIC_LIB NAMES atomic libatomic.so libatomic.so.1)
+  if(ATOMIC_LIB)
+    target_link_libraries(tokenizers PUBLIC ${ATOMIC_LIB})
+  endif()
+endif()
+
 if(SUPPORT_REGEX_LOOKAHEAD)
   set(PCRE2_STATIC_PIC ON)
   set(PCRE2_BUILD_PCRE2_8 ON)
@@ -160,6 +169,18 @@ if(TOKENIZERS_BUILD_PYTHON)
   # Link with the tokenizers library
   target_link_libraries(pytorch_tokenizers_cpp PRIVATE tokenizers)
 
+  # Link with atomic library on aarch64/arm64 systems
+  # Some aarch64 systems require explicit linking with libatomic for certain atomic operations
+  if(CMAKE_SYSTEM_PROCESSOR MATCHES "aarch64|arm64")
+    find_library(ATOMIC_LIB NAMES atomic libatomic.so libatomic.so.1)
+    if(ATOMIC_LIB)
+      target_link_libraries(pytorch_tokenizers_cpp PRIVATE ${ATOMIC_LIB})
+      message(STATUS "Found libatomic: ${ATOMIC_LIB}")
+    else()
+      message(WARNING "libatomic not found on aarch64 - build may fail")
+    endif()
+  endif()
+
   # Set properties for the Python extension
   target_compile_definitions(pytorch_tokenizers_cpp PRIVATE VERSION_INFO=${PROJECT_VERSION})