LLM inference in C/C++
C++ ggml
ggml-cpu : disable PCH and fix CACHE_LINE_SIZE ambiguity to fix heap corruption (#28882)
Georgi Gerganov2f539596c6e9
diff --git a/ggml/src/ggml-cpu/CMakeLists.txt b/ggml/src/ggml-cpu/CMakeLists.txtindex 83088e1471..1c7338eea4 100644--- a/ggml/src/ggml-cpu/CMakeLists.txt+++ b/ggml/src/ggml-cpu/CMakeLists.txt@@ -675,12 +675,6 @@ function(ggml_add_cpu_backend_variant_impl tag_name)target_compile_options(${GGML_CPU_NAME} PRIVATE ${ARCH_FLAGS})target_compile_definitions(${GGML_CPU_NAME} PRIVATE ${ARCH_DEFINITIONS})- if (CMAKE_C_COMPILER_ID STREQUAL "GNU" AND NOT GGML_SYSTEM_ARCH STREQUAL "x86")- message(STATUS "Skipping PCH for ${GGML_CPU_NAME}: GCC PCH is only enabled for x86 (arch: ${GGML_SYSTEM_ARCH})")- else()- target_precompile_headers(${GGML_CPU_NAME} PRIVATE ggml-impl.h)- endif()-if (EMSCRIPTEN)set_target_properties(${GGML_CPU_NAME} PROPERTIES COMPILE_FLAGS "-msimd128")endif()diff --git a/ggml/src/ggml-cpu/ops.h b/ggml/src/ggml-cpu/ops.hindex ce2b3e870b..2728b08b6c 100644--- a/ggml/src/ggml-cpu/ops.h+++ b/ggml/src/ggml-cpu/ops.h@@ -5,10 +5,10 @@//// cache line//--#if defined(__cpp_lib_hardware_interference_size)-#define CACHE_LINE_SIZE std::hardware_destructive_interference_size-#else+// TODO: rework CACHE_LINE_SIZE so std::hardware_destructive_interference_size+// can be used consistently between C and C++ TUs; the previous macro form+// diverged based on include order and undersized the work buffer.+// ref: https://github.com/ggml-org/llama.cpp/pull/28882#if defined(__POWER9_VECTOR__)#define CACHE_LINE_SIZE 128#elif defined(__VXE__) || defined(__VXE2__)@@ -16,17 +16,8 @@#else#define CACHE_LINE_SIZE 64#endif-#endif-// -Winterference-size was introduced in GCC 12-#if defined(__cplusplus) && defined(__GNUC__) && !defined(__clang__) && __GNUC__ >= 12-#pragma GCC diagnostic push-#pragma GCC diagnostic ignored "-Winterference-size"-#endifstatic const size_t CACHE_LINE_SIZE_F32 = CACHE_LINE_SIZE/sizeof(float);-#if defined(__cplusplus) && defined(__GNUC__) && !defined(__clang__) && __GNUC__ >= 12-#pragma GCC diagnostic pop-#endif// Work buffer size for im2col operations in CONV2D#define GGML_IM2COL_WORK_SIZE (16 * 1024 * 1024)