LLM inference in C/C++
C++ ggml
sycl: fix compiler warnings - missing prototypes, dead code, extra semicolons (#30271)
Michael Taylordd002b91f583
diff --git a/cmake/common.cmake b/cmake/common.cmakeindex bcf403e0ee..ee8d5bf7b1 100644--- a/cmake/common.cmake+++ b/cmake/common.cmake@@ -2,7 +2,7 @@ include("ggml/cmake/common.cmake")function(llama_add_compile_flags)if (LLAMA_FATAL_WARNINGS)- if (CMAKE_CXX_COMPILER_ID MATCHES "GNU" OR CMAKE_CXX_COMPILER_ID MATCHES "Clang")+ if (CMAKE_CXX_COMPILER_ID MATCHES "GNU" OR CMAKE_CXX_COMPILER_ID MATCHES "Clang" OR CMAKE_CXX_COMPILER_ID MATCHES "IntelLLVM")list(APPEND C_FLAGS -Werror)list(APPEND CXX_FLAGS -Werror)elseif (CMAKE_CXX_COMPILER_ID STREQUAL "MSVC")diff --git a/ggml/cmake/common.cmake b/ggml/cmake/common.cmakeindex f3610298ff..42b65a5805 100644--- a/ggml/cmake/common.cmake+++ b/ggml/cmake/common.cmake@@ -2,10 +2,16 @@ function(ggml_get_flags CCID CCVER)set(C_FLAGS "")set(CXX_FLAGS "")- if (CCID MATCHES "Clang")+ if (CCID MATCHES "Clang" OR CCID MATCHES "IntelLLVM")set(C_FLAGS -Wunreachable-code-break -Wunreachable-code-return)set(CXX_FLAGS -Wunreachable-code-break -Wunreachable-code-return -Wmissing-prototypes -Wextra-semi)+ if (CCID STREQUAL "IntelLLVM")+ # for Intel DPC++ and LLVM SYCL, using debug does not disable optimization+ list(APPEND C_FLAGS -Rno-debug-disables-optimization)+ list(APPEND CXX_FLAGS -Rno-debug-disables-optimization)+ endif()+if ((CCID STREQUAL "Clang" AND CCVER VERSION_GREATER_EQUAL 3.8.0) OR(CCID STREQUAL "AppleClang" AND CCVER VERSION_GREATER_EQUAL 7.3.0)diff --git a/ggml/src/ggml-sycl/CMakeLists.txt b/ggml/src/ggml-sycl/CMakeLists.txtindex dfdb4746d0..71c76737f4 100644--- a/ggml/src/ggml-sycl/CMakeLists.txt+++ b/ggml/src/ggml-sycl/CMakeLists.txt@@ -44,7 +44,7 @@ if (WIN32)if(DEFINED ENV{LEVEL_ZERO_V1_SDK_PATH})set(LEVEL_ZERO_V1_SDK_PATH $ENV{LEVEL_ZERO_V1_SDK_PATH})if(EXISTS "${LEVEL_ZERO_V1_SDK_PATH}")- target_include_directories(ggml-sycl PRIVATE "${LEVEL_ZERO_V1_SDK_PATH}/include")+ target_include_directories(ggml-sycl SYSTEM PRIVATE "${LEVEL_ZERO_V1_SDK_PATH}/include")set(LEVEL_ZERO_V1_SDK_LIB_PATH "${LEVEL_ZERO_V1_SDK_PATH}/lib")else()message(WARNING "LEVEL_ZERO_V1_SDK_PATH set but folder not found: ${LEVEL_ZERO_V1_SDK_PATH}")diff --git a/ggml/src/ggml-sycl/concat.cpp b/ggml/src/ggml-sycl/concat.cppindex bd5f3b2ceb..d4c257cf78 100644--- a/ggml/src/ggml-sycl/concat.cpp+++ b/ggml/src/ggml-sycl/concat.cpp@@ -504,6 +504,5 @@ void ggml_sycl_op_concat(ggml_backend_sycl_context & ctx, ggml_tensor *dst) {default:fprintf(stderr, "%s: unsupported types: dst: %s\n", __func__, ggml_type_name(dst->type));GGML_ASSERT(false);- break;}}diff --git a/ggml/src/ggml-sycl/convert.cpp b/ggml/src/ggml-sycl/convert.cppindex 45c60e8e5c..092967b6f6 100644--- a/ggml/src/ggml-sycl/convert.cpp+++ b/ggml/src/ggml-sycl/convert.cpp@@ -757,7 +757,6 @@ to_fp16_sycl_t ggml_get_to_fp16_sycl(ggml_type type, ggml_tensor * dst) {#endifdefault:GGML_ABORT("fatal error: unsupport data type=%s\n", ggml_type_name(type));- return nullptr;}}@@ -861,7 +860,6 @@ to_fp32_sycl_t ggml_get_to_fp32_sycl(ggml_type type, ggml_tensor *dst) {#endifdefault:GGML_ABORT("fatal error: unsupport data type=%s\n", ggml_type_name(type));- return nullptr;}}@@ -877,7 +875,6 @@ to_bf16_sycl_t ggml_get_to_bf16_sycl(ggml_type type, ggml_tensor * /*dst*/) {return convert_unary_sycl<sycl::ext::oneapi::bfloat16>;default:GGML_ABORT("fatal error: unsupport data type=%s\n", ggml_type_name(type));- return nullptr;}}#endifdiff --git a/ggml/src/ggml-sycl/count-equal.cpp b/ggml/src/ggml-sycl/count-equal.cppindex 4580354cd9..20126652ba 100644--- a/ggml/src/ggml-sycl/count-equal.cpp+++ b/ggml/src/ggml-sycl/count-equal.cpp@@ -74,6 +74,5 @@ void ggml_sycl_count_equal(ggml_backend_sycl_context &ctx, ggml_tensor *dst) {} break;default:GGML_ASSERT(false);- break;}}diff --git a/ggml/src/ggml-sycl/dpct/helper.hpp b/ggml/src/ggml-sycl/dpct/helper.hppindex 85af4cab68..fd3b9655ad 100644--- a/ggml/src/ggml-sycl/dpct/helper.hpp+++ b/ggml/src/ggml-sycl/dpct/helper.hpp@@ -3159,7 +3159,7 @@ namespace dpct_local_mem_size = local_mem_size;- };+ }static inline std::mutex kernel_function_ptr_map_mutex;public:diff --git a/ggml/src/ggml-sycl/element_wise.cpp b/ggml/src/ggml-sycl/element_wise.cppindex 0d263aa768..c7fe70ac33 100644--- a/ggml/src/ggml-sycl/element_wise.cpp+++ b/ggml/src/ggml-sycl/element_wise.cpp@@ -1169,7 +1169,7 @@ static void swiglu_oai_sycl(const T * x,});}-void ggml_sycl_op_swiglu_oai(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {+static void ggml_sycl_op_swiglu_oai(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {const ggml_tensor * src0 = dst->src[0];const ggml_tensor * src1 = dst->src[1];void * src0_d = src0->data;diff --git a/ggml/src/ggml-sycl/fattn-common.hpp b/ggml/src/ggml-sycl/fattn-common.hppindex 2e8ac6af3f..c37326336d 100644--- a/ggml/src/ggml-sycl/fattn-common.hpp+++ b/ggml/src/ggml-sycl/fattn-common.hpp@@ -832,6 +832,29 @@ static void flash_attn_combine_results(const float * __restrict__ VKQ_parts,dst[tid] = VKQ_numerator / VKQ_denominator;}+// Carries the sub-group size (and grf_size_automatic when use_large_grf) as+// kernel properties via get(properties_tag), in place of the+// reqd_sub_group_size attribute and the deprecated parallel_for overload.+template <typename KernelFunc, uint32_t Size, bool UseGrf>+struct props_kernel {+ KernelFunc kernel;++ void operator()(sycl::nd_item<3> item) const {+ kernel(item);+ }++ auto get(sycl::ext::oneapi::experimental::properties_tag) const {+ if constexpr (UseGrf) {+ return sycl::ext::oneapi::experimental::properties{+ sycl::ext::intel::experimental::grf_size_automatic,+ sycl::ext::oneapi::experimental::sub_group_size<Size> };+ } else {+ return sycl::ext::oneapi::experimental::properties{+ sycl::ext::oneapi::experimental::sub_group_size<Size> };+ }+ }+};+template <fattn_kernel_t fattn_kernel, int warp_size, bool use_large_grf = false>static void lauch_kernel(dpct::dim3 group_range,@@ -881,7 +904,7 @@ static void lauch_kernel(static_cast<sycl::range<3>>(group_range * local_range),static_cast<sycl::range<3>>(local_range));- const auto kernel = [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(warp_size)]] {+ const auto kernel = [=](sycl::nd_item<3> item_ct1) {GGML_UNUSED(item_ct1);fattn_kernel(Q, K, V, mask, sinks, KV_max, dst, dst_meta, scale,max_bias, m0, m1, n_head_log2, logit_softcap, ne00,@@ -892,14 +915,7 @@ static void lauch_kernel(q->submit([&](sycl::handler &cgh) {// grf_size_automatic lets the compiler use the large register file when the kernel needs it. grf_size<256> would say the same but is undefined on devices that do not have it.- if constexpr (use_large_grf) {- cgh.parallel_for(- rng,- sycl::ext::oneapi::experimental::properties{ sycl::ext::intel::experimental::grf_size_automatic },- kernel);- } else {- cgh.parallel_for(rng, kernel);- }+ cgh.parallel_for(rng, props_kernel<decltype(kernel), warp_size, use_large_grf>{kernel});});}diff --git a/ggml/src/ggml-sycl/fattn-tile.cpp b/ggml/src/ggml-sycl/fattn-tile.cppindex 9449d75784..db030268e0 100644--- a/ggml/src/ggml-sycl/fattn-tile.cpp+++ b/ggml/src/ggml-sycl/fattn-tile.cpp@@ -54,6 +54,6 @@ void ggml_sycl_flash_attn_ext_tile(ggml_backend_sycl_context & ctx, ggml_tensor} break;default: {GGML_ABORT("Unsupported head size");- } break;+ }}}diff --git a/ggml/src/ggml-sycl/getrows.cpp b/ggml/src/ggml-sycl/getrows.cppindex 9c17daf86a..a3a3209007 100644--- a/ggml/src/ggml-sycl/getrows.cpp+++ b/ggml/src/ggml-sycl/getrows.cpp@@ -652,6 +652,5 @@ void ggml_sycl_op_get_rows_back(ggml_backend_sycl_context & ctx, ggml_tensor * dbreak;default:GGML_ABORT("%s: unsupported src0 type: %s\n", __func__, ggml_type_name(src0->type));- break;}}diff --git a/ggml/src/ggml-sycl/ggml-sycl.cpp b/ggml/src/ggml-sycl/ggml-sycl.cppindex 3cc565d6ba..cbb2188c5c 100644--- a/ggml/src/ggml-sycl/ggml-sycl.cpp+++ b/ggml/src/ggml-sycl/ggml-sycl.cpp@@ -388,14 +388,14 @@ static ze_result_t init_zes() {return res;}-ze_result_t get_zes_init_res() {+static ze_result_t get_zes_init_res() {static ze_result_t zes_init_res = init_zes();GGML_SYCL_DEBUG("[SYCL] call %s: zesInit result: %d\n", __func__, (int) zes_init_res);return zes_init_res;}#endif-void initialize_sycl_begining() {+static void initialize_sycl_begining() {#ifdef GGML_SYCL_SUPPORT_LEVEL_ZERO_API//must be called in initialization stage, before any other Level Zero API callsGGML_SYCL_DEBUG("[SYCL] call %s\n", __func__);@@ -1173,7 +1173,7 @@ static size_t ggml_backend_sycl_buffer_type_get_alignment(ggml_backend_buffer_tyGGML_UNUSED(buft);}-bool is_bmg_g31_arch(int device) {+static bool is_bmg_g31_arch(int device) {return ggml_sycl_info().devices[device].hw_info.arch == gpu_arch::intel_gpu_bmg_g31;}@@ -6326,7 +6326,7 @@ catch (sycl::exception const &exc) {std::exit(1);}-bool sycl_get_mem_info(int device, size_t * free, size_t * total) {+static bool sycl_get_mem_info(int device, size_t * free, size_t * total) {GGML_SYCL_DEBUG("[SYCL] [%s] g_ggml_sycl_get_mem_api=%d\n",__func__, g_ggml_sycl_get_mem_api);@@ -6952,7 +6952,6 @@ static bool do_ggml_backend_sycl_device_supports_op(ggml_backend_dev_t dev, consdefault:return false;}- break;case GGML_OP_MUL_MAT:case GGML_OP_MUL_MAT_ID:{@@ -7045,7 +7044,6 @@ static bool do_ggml_backend_sycl_device_supports_op(ggml_backend_dev_t dev, cons(op->src[1]->type == GGML_TYPE_I64 || op->src[1]->type == GGML_TYPE_I32);return res;}- break;case GGML_OP_DSV4_HC_PRE:return op->src[0]->type == GGML_TYPE_F32 && op->src[1]->type == GGML_TYPE_F32 &&op->type == GGML_TYPE_F32;diff --git a/ggml/src/ggml-sycl/gla.cpp b/ggml/src/ggml-sycl/gla.cppindex 879184fdd3..3794834270 100644--- a/ggml/src/ggml-sycl/gla.cpp+++ b/ggml/src/ggml-sycl/gla.cpp@@ -1,6 +1,7 @@#include <sycl/sycl.hpp>#include "common.hpp"+#include "gla.hpp"template <u_int HEAD_SIZE>static void gated_linear_attn_f32_kernel(const dpct::queue_ptr stream, u_int B, u_int T, u_int C, u_int H, float scale,diff --git a/ggml/src/ggml-sycl/mem.cpp b/ggml/src/ggml-sycl/mem.cppindex ad5bfe0ff1..8a1c3262cc 100644--- a/ggml/src/ggml-sycl/mem.cpp+++ b/ggml/src/ggml-sycl/mem.cpp@@ -27,7 +27,7 @@ const char * mem_api_int2str(int mem_api) {/** Depend on to call zesInit(0) before any other Level Zero API calls, otherwise the Level Zero API calls may fail.*/-bool query_free_memory_by_ze(sycl::device dev, size_t & free_bytes, size_t & total_bytes) {+static bool query_free_memory_by_ze(sycl::device dev, size_t & free_bytes, size_t & total_bytes) {GGML_SYCL_DEBUG("[SYCL] call %s: Querying free memory using Level Zero API.\n", __func__);free_bytes = 0;@@ -94,7 +94,7 @@ bool query_free_memory_by_ze(sycl::device dev, size_t & free_bytes, size_t & tot}#endif-bool get_memory_size_by_sycl_api(sycl::device dev, size_t & free_bytes, size_t & total_bytes) {+static bool get_memory_size_by_sycl_api(sycl::device dev, size_t & free_bytes, size_t & total_bytes) {GGML_SYCL_DEBUG("[SYCL] call %s: Querying free memory using SYCL API.\n", __func__);total_bytes = dev.get_info<sycl::info::device::global_mem_size>();diff --git a/ggml/src/ggml-sycl/topk-moe.cpp b/ggml/src/ggml-sycl/topk-moe.cppindex 78574c4b5d..3dd92d2613 100644--- a/ggml/src/ggml-sycl/topk-moe.cpp+++ b/ggml/src/ggml-sycl/topk-moe.cpp@@ -296,7 +296,6 @@ static void ggml_sycl_op_topk_moe(ggml_backend_sycl_context & ctx,break;default:GGML_ASSERT(false && "fatal error");- break;}}diff --git a/ggml/src/ggml-sycl/upscale.cpp b/ggml/src/ggml-sycl/upscale.cppindex e42cb419d8..5f1c16be2b 100644--- a/ggml/src/ggml-sycl/upscale.cpp+++ b/ggml/src/ggml-sycl/upscale.cpp@@ -183,8 +183,8 @@ static void upscale_f32_bilinear_antialias(const float * src0,}namespace bicubic_interpolation {-static float weight1(float x, const float &a) { return ((a + 2) * x - (a + 3)) * x * x + 1; };-static float weight2(float x, const float &a) { return ((a * x - 5 * a) * x + 8 * a) * x - 4 * a; };+static float weight1(float x, const float &a) { return ((a + 2) * x - (a + 3)) * x * x + 1; }+static float weight2(float x, const float &a) { return ((a * x - 5 * a) * x + 8 * a) * x - 4 * a; }static float bicubic(float p0, float p1, float p2, float p3, float x, float a) {const float w0 = weight2(x + 1, a);@@ -192,7 +192,7 @@ static float bicubic(float p0, float p1, float p2, float p3, float x, float a) {const float w2 = weight1(1 - x, a);const float w3 = weight2(2 - x, a);return p0 * w0 + p1 * w1 + p2 * w2 + p3 * w3;-};+}}@@ -358,7 +358,7 @@ static void upscale_f32_bicubic_sycl(const float * x,}}-void ggml_sycl_op_upscale(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {+static void ggml_sycl_op_upscale(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {const ggml_tensor * src0 = dst->src[0];const float * src0_d = (const float *)src0->data;float * dst_d = (float *)dst->data;diff --git a/ggml/src/ggml-sycl/vecdotq.hpp b/ggml/src/ggml-sycl/vecdotq.hppindex 57360a004b..f547b20e68 100644--- a/ggml/src/ggml-sycl/vecdotq.hpp+++ b/ggml/src/ggml-sycl/vecdotq.hpp@@ -442,7 +442,7 @@ template <> struct reorder_vec_dot_q_sycl<GGML_TYPE_Q4_0> {}return vec_dot_q4_0_q8_1_impl(v, u, d, *q8_1_ds);- };+ }};// Load four contiguous dwords per operand instead of loading each value separately.