ggml: allow -march=native on generic ARM platforms

Signed-off-by: Adrien Gallouët <[email protected]>

Author: angt

ggml/src/ggml-cpu/CMakeLists.txt

@@ -151,30 +151,44 @@ function(ggml_add_cpu_backend_variant_impl tag_name)
                 endif ()
             endif ()
         else()
-            check_cxx_compiler_flag(-mfp16-format=ieee COMPILER_SUPPORTS_FP16_FORMAT_I3E)
-            if (NOT "${COMPILER_SUPPORTS_FP16_FORMAT_I3E}" STREQUAL "")
-                list(APPEND ARCH_FLAGS -mfp16-format=ieee)
-            endif()
-            if (${CMAKE_SYSTEM_PROCESSOR} MATCHES "armv6")
-                # Raspberry Pi 1, Zero
-                list(APPEND ARCH_FLAGS -mfpu=neon-fp-armv8 -mno-unaligned-access)
-            endif()
-            if (${CMAKE_SYSTEM_PROCESSOR} MATCHES "armv7")
-                if ("${CMAKE_SYSTEM_NAME}" STREQUAL "Android")
-                    # Android armeabi-v7a
-                    list(APPEND ARCH_FLAGS -mfpu=neon-vfpv4 -mno-unaligned-access -funsafe-math-optimizations)
-                else()
-                    # Raspberry Pi 2
-                    list(APPEND ARCH_FLAGS -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations)
+            if (GGML_NATIVE)
+                set(USER_PROVIDED_MARCH FALSE)
+                foreach(flag_var IN ITEMS CMAKE_C_FLAGS CMAKE_CXX_FLAGS CMAKE_REQUIRED_FLAGS)
+                    if ("${${flag_var}}" MATCHES "-march=[a-zA-Z0-9+._-]+")
+                        set(USER_PROVIDED_MARCH TRUE)
+                        break()
+                    endif()
+                endforeach()
+
+                if (NOT USER_PROVIDED_MARCH)
+                    list(APPEND ARCH_FLAGS "-march=native")
+                endif()
+            else()
+                check_cxx_compiler_flag(-mfp16-format=ieee COMPILER_SUPPORTS_FP16_FORMAT_I3E)
+                if (NOT "${COMPILER_SUPPORTS_FP16_FORMAT_I3E}" STREQUAL "")
+                    list(APPEND ARCH_FLAGS -mfp16-format=ieee)
+                endif()
+                if (${CMAKE_SYSTEM_PROCESSOR} MATCHES "armv6")
+                    # Raspberry Pi 1, Zero
+                    list(APPEND ARCH_FLAGS -mfpu=neon-fp-armv8 -mno-unaligned-access)
+                endif()
+                if (${CMAKE_SYSTEM_PROCESSOR} MATCHES "armv7")
+                    if ("${CMAKE_SYSTEM_NAME}" STREQUAL "Android")
+                        # Android armeabi-v7a
+                        list(APPEND ARCH_FLAGS -mfpu=neon-vfpv4 -mno-unaligned-access -funsafe-math-optimizations)
+                    else()
+                        # Raspberry Pi 2
+                        list(APPEND ARCH_FLAGS -mfpu=neon-fp-armv8 -mno-unaligned-access -funsafe-math-optimizations)
+                    endif()
+                endif()
+                if (${CMAKE_SYSTEM_PROCESSOR} MATCHES "armv8")
+                    # Android arm64-v8a
+                    # Raspberry Pi 3, 4, Zero 2 (32-bit)
+                    list(APPEND ARCH_FLAGS -mno-unaligned-access)
+                endif()
+                if (GGML_SVE)
+                    list(APPEND ARCH_FLAGS -march=armv8.6-a+sve)
                 endif()
-            endif()
-            if (${CMAKE_SYSTEM_PROCESSOR} MATCHES "armv8")
-                # Android arm64-v8a
-                # Raspberry Pi 3, 4, Zero 2 (32-bit)
-                list(APPEND ARCH_FLAGS -mno-unaligned-access)
-            endif()
-            if (GGML_SVE)
-                list(APPEND ARCH_FLAGS -march=armv8.6-a+sve)
             endif()
         endif()
     elseif (CMAKE_OSX_ARCHITECTURES STREQUAL "x86_64" OR CMAKE_GENERATOR_PLATFORM_LWR MATCHES "^(x86_64|i686|amd64|x64|win32)$" OR