endif()
add_library(ggml
+ ggml-backend-dl.cpp
ggml-backend-reg.cpp)
add_library(ggml::ggml ALIAS ggml)
--- /dev/null
+#include "ggml-backend-dl.h"
+
+#ifdef _WIN32
+
+dl_handle * dl_load_library(const fs::path & path) {
+ // suppress error dialogs for missing DLLs
+ DWORD old_mode = SetErrorMode(SEM_FAILCRITICALERRORS);
+ SetErrorMode(old_mode | SEM_FAILCRITICALERRORS);
+
+ HMODULE handle = LoadLibraryW(path.wstring().c_str());
+
+ SetErrorMode(old_mode);
+
+ return handle;
+}
+
+void * dl_get_sym(dl_handle * handle, const char * name) {
+ DWORD old_mode = SetErrorMode(SEM_FAILCRITICALERRORS);
+ SetErrorMode(old_mode | SEM_FAILCRITICALERRORS);
+
+ void * p = (void *) GetProcAddress(handle, name);
+
+ SetErrorMode(old_mode);
+
+ return p;
+}
+
+const char * dl_error() {
+ return "";
+}
+
+#else
+
+dl_handle * dl_load_library(const fs::path & path) {
+ dl_handle * handle = dlopen(path.string().c_str(), RTLD_NOW | RTLD_LOCAL);
+ return handle;
+}
+
+void * dl_get_sym(dl_handle * handle, const char * name) {
+ return dlsym(handle, name);
+}
+
+const char * dl_error() {
+ const char *rslt = dlerror();
+ return rslt != nullptr ? rslt : "";
+}
+
+#endif
--- /dev/null
+#pragma once
+
+#ifdef _WIN32
+# define WIN32_LEAN_AND_MEAN
+# ifndef NOMINMAX
+# define NOMINMAX
+# endif
+# include <windows.h>
+# include <winevt.h>
+#else
+# include <dlfcn.h>
+# include <unistd.h>
+#endif
+#include <filesystem>
+
+namespace fs = std::filesystem;
+
+#ifdef _WIN32
+
+using dl_handle = std::remove_pointer_t<HMODULE>;
+
+struct dl_handle_deleter {
+ void operator()(HMODULE handle) {
+ FreeLibrary(handle);
+ }
+};
+
+#else
+
+using dl_handle = void;
+
+struct dl_handle_deleter {
+ void operator()(void * handle) {
+ dlclose(handle);
+ }
+};
+
+#endif
+
+using dl_handle_ptr = std::unique_ptr<dl_handle, dl_handle_deleter>;
+
+dl_handle * dl_load_library(const fs::path & path);
+void * dl_get_sym(dl_handle * handle, const char * name);
+const char * dl_error();
+
#include "ggml-backend-impl.h"
#include "ggml-backend.h"
+#include "ggml-backend-dl.h"
#include "ggml-impl.h"
#include <algorithm>
#include <cstring>
}
}
-#ifdef _WIN32
-
-using dl_handle = std::remove_pointer_t<HMODULE>;
-
-struct dl_handle_deleter {
- void operator()(HMODULE handle) {
- FreeLibrary(handle);
- }
-};
-
-static dl_handle * dl_load_library(const fs::path & path) {
- // suppress error dialogs for missing DLLs
- DWORD old_mode = SetErrorMode(SEM_FAILCRITICALERRORS);
- SetErrorMode(old_mode | SEM_FAILCRITICALERRORS);
-
- HMODULE handle = LoadLibraryW(path.wstring().c_str());
-
- SetErrorMode(old_mode);
-
- return handle;
-}
-
-static void * dl_get_sym(dl_handle * handle, const char * name) {
- DWORD old_mode = SetErrorMode(SEM_FAILCRITICALERRORS);
- SetErrorMode(old_mode | SEM_FAILCRITICALERRORS);
-
- void * p = (void *) GetProcAddress(handle, name);
-
- SetErrorMode(old_mode);
-
- return p;
-}
-
-static const char * dl_error() {
- return "";
-}
-
-#else
-
-using dl_handle = void;
-
-struct dl_handle_deleter {
- void operator()(void * handle) {
- dlclose(handle);
- }
-};
-
-static void * dl_load_library(const fs::path & path) {
- dl_handle * handle = dlopen(path.string().c_str(), RTLD_NOW | RTLD_LOCAL);
-
- return handle;
-}
-
-static void * dl_get_sym(dl_handle * handle, const char * name) {
- return dlsym(handle, name);
-}
-
-static const char * dl_error() {
- const char *rslt = dlerror();
- return rslt != nullptr ? rslt : "";
-}
-
-#endif
-
-using dl_handle_ptr = std::unique_ptr<dl_handle, dl_handle_deleter>;
-
struct ggml_backend_reg_entry {
ggml_backend_reg_t reg;
dl_handle_ptr handle;
+file(TO_CMAKE_PATH "${HEXAGON_SDK_ROOT}" HEXAGON_SDK_ROOT)
+file(TO_CMAKE_PATH "${HEXAGON_TOOLS_ROOT}" HEXAGON_TOOLS_ROOT)
+
+if (NOT IS_DIRECTORY "${HEXAGON_SDK_ROOT}" OR NOT IS_DIRECTORY "${HEXAGON_TOOLS_ROOT}")
+ message(FATAL_ERROR "Make sure HEXAGON_SDK_ROOT and HEXAGON_TOOLS_ROOT point to the correct Hexagon SDK installation.")
+endif()
+
+message(STATUS "hexagon: using ${HEXAGON_SDK_ROOT} and ${HEXAGON_TOOLS_ROOT} for building libggml-htp skels")
+
include(${HEXAGON_SDK_ROOT}/build/cmake/hexagon_fun.cmake)
include(ExternalProject)
option(GGML_HEXAGON_HTP_DEBUG "ggml-hexagon: enable HTP debug output" OFF)
+set(GGML_HEXAGON_HTP_CERT "$ENV{HEXAGON_HTP_CERT}" CACHE PATH "ggml-hexagon: enable HTP library signing using certificate")
set(GGML_HEXAGON_FP32_QUANTIZE_GROUP_SIZE 128 CACHE STRING "ggml-hexagon: quantize group size (32, 64, or 128)")
add_library(htp_iface OBJECT
target_link_options(htp_iface PUBLIC -ldl)
endif()
-link_custom_library(htp_iface cdsprpc)
-link_custom_library(htp_iface rpcmem)
-
set(TARGET_NAME ggml-hexagon)
ggml_add_backend_library(${TARGET_NAME}
- ggml-hexagon.cpp htp-utils.c htp-utils.h ../../include/ggml-hexagon.h)
+ ggml-hexagon.cpp
+ htp-drv.cpp
+ htp-drv.h
+ libdl.h
+ ../../include/ggml-hexagon.h)
target_link_libraries(${TARGET_NAME} PRIVATE htp_iface)
target_include_directories(${TARGET_NAME} PRIVATE ${CMAKE_CURRENT_SOURCE_DIR}/htp ${CMAKE_CURRENT_BINARY_DIR})
-# Build HTP bits
-set(HTP_CMAKE_ARGS
- -DCMAKE_TOOLCHAIN_FILE=${CMAKE_CURRENT_SOURCE_DIR}/htp/cmake-toolchain.cmake
- -DCMAKE_BUILD_TYPE=Release
- -DCMAKE_INSTALL_LIBDIR=${CMAKE_CURRENT_BINARY_DIR}
- -DHEXAGON_SDK_ROOT=$ENV{HEXAGON_SDK_ROOT}
- -DHEXAGON_TOOLS_ROOT=$ENV{HEXAGON_TOOLS_ROOT}
- -DHEXAGON_HTP_DEBUG=${GGML_HEXAGON_HTP_DEBUG}
- -DGGML_HEXAGON_FP32_QUANTIZE_GROUP_SIZE=${GGML_HEXAGON_FP32_QUANTIZE_GROUP_SIZE})
-
-ExternalProject_Add(htp-v68
- SOURCE_DIR ${CMAKE_CURRENT_SOURCE_DIR}/htp BUILD_ALWAYS ON
- CMAKE_ARGS ${HTP_CMAKE_ARGS} -DDSP_VERSION=v68 -DPREBUILT_LIB_DIR="toolv19_v68")
-
-ExternalProject_Add(htp-v69
- SOURCE_DIR ${CMAKE_CURRENT_SOURCE_DIR}/htp BUILD_ALWAYS ON
- CMAKE_ARGS ${HTP_CMAKE_ARGS} -DDSP_VERSION=v69 -DPREBUILT_LIB_DIR="toolv19_v69")
-
-ExternalProject_Add(htp-v73
- SOURCE_DIR ${CMAKE_CURRENT_SOURCE_DIR}/htp BUILD_ALWAYS ON
- CMAKE_ARGS ${HTP_CMAKE_ARGS} -DDSP_VERSION=v73 -DPREBUILT_LIB_DIR="toolv19_v73")
-
-ExternalProject_Add(htp-v75
- SOURCE_DIR ${CMAKE_CURRENT_SOURCE_DIR}/htp BUILD_ALWAYS ON
- CMAKE_ARGS ${HTP_CMAKE_ARGS} -DDSP_VERSION=v75 -DPREBUILT_LIB_DIR="toolv19_v75")
-
-ExternalProject_Add(htp-v79
- SOURCE_DIR ${CMAKE_CURRENT_SOURCE_DIR}/htp BUILD_ALWAYS ON
- CMAKE_ARGS ${HTP_CMAKE_ARGS} -DDSP_VERSION=v79 -DPREBUILT_LIB_DIR="toolv19_v79")
-
-ExternalProject_Add(htp-v81
- SOURCE_DIR ${CMAKE_CURRENT_SOURCE_DIR}/htp BUILD_ALWAYS ON
- CMAKE_ARGS ${HTP_CMAKE_ARGS} -DDSP_VERSION=v81 -DPREBUILT_LIB_DIR="toolv19_v81")
+# Build HTP skels
+set(HTP_SKELS)
+function(build_htp_skel V)
+ ExternalProject_Add(htp-${V}
+ SOURCE_DIR ${CMAKE_CURRENT_SOURCE_DIR}/htp BUILD_ALWAYS ON
+ BUILD_BYPRODUCTS ${CMAKE_CURRENT_BINARY_DIR}/libggml-htp-${V}.so
+ CMAKE_ARGS
+ -DCMAKE_BUILD_TYPE=Release
+ -DCMAKE_TOOLCHAIN_FILE=${CMAKE_CURRENT_SOURCE_DIR}/htp/cmake-toolchain.cmake
+ -DCMAKE_INSTALL_LIBDIR=${CMAKE_CURRENT_BINARY_DIR}
+ -DHEXAGON_SDK_ROOT=${HEXAGON_SDK_ROOT}
+ -DHEXAGON_TOOLS_ROOT=${HEXAGON_TOOLS_ROOT}
+ -DHEXAGON_HTP_DEBUG=${GGML_HEXAGON_HTP_DEBUG}
+ -DGGML_HEXAGON_FP32_QUANTIZE_GROUP_SIZE=${GGML_HEXAGON_FP32_QUANTIZE_GROUP_SIZE}
+ -DDSP_VERSION=${V}
+ -DPREBUILT_LIB_DIR="toolv19_${V}")
+ list(APPEND HTP_SKELS ${CMAKE_CURRENT_BINARY_DIR}/libggml-htp-${V}.so)
+ set(HTP_SKELS ${HTP_SKELS} PARENT_SCOPE)
+endfunction()
+
+build_htp_skel(v68)
+build_htp_skel(v69)
+build_htp_skel(v73)
+build_htp_skel(v75)
+build_htp_skel(v79)
+build_htp_skel(v81)
# Install Hexagon skels required at runtime
-install(FILES
- ${CMAKE_CURRENT_BINARY_DIR}/libggml-htp-v68.so
- ${CMAKE_CURRENT_BINARY_DIR}/libggml-htp-v69.so
- ${CMAKE_CURRENT_BINARY_DIR}/libggml-htp-v73.so
- ${CMAKE_CURRENT_BINARY_DIR}/libggml-htp-v75.so
- ${CMAKE_CURRENT_BINARY_DIR}/libggml-htp-v79.so
- ${CMAKE_CURRENT_BINARY_DIR}/libggml-htp-v81.so
- TYPE LIB)
+install(FILES ${HTP_SKELS} TYPE LIB)
+
+if (CMAKE_SYSTEM_NAME MATCHES Windows AND GGML_HEXAGON_HTP_CERT)
+ file(TO_CMAKE_PATH "$ENV{WINDOWS_SDK_BIN}/arm64" WINSDK_BIN0_ARM64)
+ file(TO_CMAKE_PATH "$ENV{WINDOWS_SDK_BIN}/x86" WINSDK_BIN0_X86)
+ file(TO_CMAKE_PATH "$ENV{WindowsSdkVerBinPath}/arm64" WINSDK_BIN1_ARM64)
+ file(TO_CMAKE_PATH "$ENV{WindowsSdkVerBinPath}/x86" WINSDK_BIN1_X86)
+
+ set(WINSDK_PATHS ${WINSDK_BIN0_ARM64} ${WINSDK_BIN0_X86} ${WINSDK_BIN1_ARM64} ${WINSDK_BIN1_X86})
+
+ find_program(INF2CAT NAMES inf2cat.exe PATHS ${WINSDK_PATHS} REQUIRED)
+ find_program(SIGNTOOL NAMES signtool.exe PATHS ${WINSDK_PATHS} REQUIRED)
+
+ message(STATUS "hexagon: using ${GGML_HEXAGON_HTP_CERT} to sign libggml-htp skels")
+
+ set(LIBGGML_HTP_CAT ${CMAKE_CURRENT_BINARY_DIR}/libggml-htp.cat)
+ add_custom_target(libggml-htp-cat
+ BYPRODUCTS ${LIBGGML_HTP_CAT}
+ DEPENDS libggml-htp.inf ${HTP_SKELS}
+ COMMAND ${CMAKE_COMMAND} -E copy ${CMAKE_CURRENT_SOURCE_DIR}/libggml-htp.inf ${CMAKE_CURRENT_BINARY_DIR}
+ COMMAND ${INF2CAT} /driver:${CMAKE_CURRENT_BINARY_DIR} /os:10_25H2_ARM64
+ COMMAND ${SIGNTOOL} sign /fd sha256 /f ${GGML_HEXAGON_HTP_CERT} ${LIBGGML_HTP_CAT}
+ COMMENT "generating and signing libggml-htp.cat file"
+ VERBATIM
+ )
+
+ add_dependencies(${TARGET_NAME} libggml-htp-cat)
+ install(FILES ${LIBGGML_HTP_CAT} TYPE LIB)
+endif()
#ifdef _WIN32
# include <sal.h>
-# ifndef _WINDOWS
-# define _WINDOWS
-# endif
#else
# include <semaphore.h>
# include <unistd.h>
#pragma clang diagnostic ignored "-Wnested-anon-types"
#pragma clang diagnostic ignored "-Wgnu-anonymous-struct"
-#include "htp-utils.h"
-
#include <AEEStdErr.h>
#include <dspqueue.h>
#include <rpcmem.h>
#include "op-desc.h"
#include "htp-msg.h"
#include "htp_iface.h"
+#include "htp-drv.h"
static size_t opt_ndev = 1;
static size_t opt_nhvx = 0; // use all
0, // flags - the framework will autoset this
n_bufs, // number of buffers
bufs, // buffer references
- sizeof(req),
+ sizeof(req), // Message length
(const uint8_t *) &req, // Message
- 1000000 // Timeout
+ DSPQUEUE_TIMEOUT // Timeout
);
if (err != 0) {
// Read response packet from queue
int err = dspqueue_read(q, &flags,
- HTP_MAX_PACKET_BUFFERS, // Maximum number of buffer references
- &n_bufs, // Number of buffer references
- bufs, // Buffer references
- sizeof(rsp), // Max message length
- &rsp_size, // Message length
- (uint8_t *) &rsp,
- 1000000); // Timeout
+ HTP_MAX_PACKET_BUFFERS, // Maximum number of buffer references
+ &n_bufs, // Number of buffer references
+ bufs, // Buffer references
+ sizeof(rsp), // Max message length
+ &rsp_size, // Message length
+ (uint8_t *) &rsp, // Message
+ DSPQUEUE_TIMEOUT); // Timeout
if (err == AEE_EEXPIRED) {
// TODO: might need to bail out if the HTP is stuck on something
ggml_backend_hexagon_buffer_context(ggml_hexagon_session * sess, size_t size, bool repack) {
size += 4 * 1024; // extra page for padding
- if (rpcmem_alloc2) {
- this->base = (uint8_t *) rpcmem_alloc2(RPCMEM_HEAP_ID_SYSTEM, RPCMEM_DEFAULT_FLAGS | RPCMEM_HEAP_NOREG, size);
- } else {
- GGML_LOG_INFO("ggml-hex: %s rpcmem_alloc2 not found, falling back to rpcmem_alloc\n", sess->name.c_str());
- this->base = (uint8_t *) rpcmem_alloc(RPCMEM_HEAP_ID_SYSTEM, RPCMEM_DEFAULT_FLAGS | RPCMEM_HEAP_NOREG, size);
- }
-
+ this->base = (uint8_t *) rpcmem_alloc2(RPCMEM_HEAP_ID_SYSTEM, RPCMEM_DEFAULT_FLAGS | RPCMEM_HEAP_NOREG, size);
if (!this->base) {
GGML_LOG_ERROR("ggml-hex: %s failed to allocate buffer : size %zu\n", sess->name.c_str(), size);
throw std::runtime_error("ggml-hex: rpcmem_alloc failed (see log for details)");
}
static inline bool op_reuse_src1(const ggml_tensor * op1, const ggml_tensor * op0) {
- return (op0 && op0->src[1] == op1->src[1] && ggml_is_quantized(op0->src[0]->type) && ggml_is_quantized(op1->src[1]->type));
+ return (op0 && op0->src[1] == op1->src[1] && ggml_is_quantized(op0->src[0]->type));
}
static inline bool is_compute_op(ggml_tensor *node)
{
- return !(ggml_op_is_empty(node->op) || ggml_is_empty(node));
+ return !ggml_op_is_empty(node->op) && !ggml_is_empty(node) && (node->flags & GGML_TENSOR_FLAG_COMPUTE);
}
// scan the graph and figure out last compute op index
const int last = last_compute_op(graph);
- const struct ggml_tensor * prev_quant_op = nullptr; // prev executed op with quantizer
+ const struct ggml_tensor * prev_op = nullptr; // prev executed op
for (int i = 0; i < graph->n_nodes; ++i) {
ggml_tensor * node = graph->nodes[i];
continue;
}
- if ((node->flags & GGML_TENSOR_FLAG_COMPUTE) == 0) {
- continue;
- }
-
uint32_t flags = 0;
// skip quantizer if src1 is reused
- if (op_reuse_src1(node, prev_quant_op)) {
+ if (op_reuse_src1(node, prev_op)) {
flags |= HTP_OPFLAGS_SKIP_QUANTIZE;
}
+ prev_op = node;
+
// ask for early notification for the last Op
if (i == last) {
flags |= HTP_OPFLAGS_EARLY_WAKEUP;
} else {
ggml_hexagon_dispatch_op<init_binary_req<false>>(sess, node, flags);
}
- prev_quant_op = node;
break;
case GGML_OP_MUL_MAT_ID:
if (ggml_is_quantized(node->src[0]->type)) {
} else {
ggml_hexagon_dispatch_op<init_binary_id_req<false>>(sess, node, flags);
}
- prev_quant_op = node;
break;
case GGML_OP_MUL:
case GGML_OP_ADD:
}
// that many nodes forward to search for stackable nodes that can reuse VTCM
- constexpr int N_FORWARD = 8;
+ constexpr int N_FORWARD = 16;
for (int i1 = i0 + 1; i1 < i0 + N_FORWARD && i1 < n; i1++) {
if (used[i1]) {
}
}
+#if defined(__ANDROID__)
if (opt_arch < 75) {
opt_ndev = 1;
GGML_LOG_WARN("ggml-hex: forcing ndev to 1 for SoCs archs lower than v75.\n");
}
+#endif
GGML_LOG_INFO("ggml-hex: Hexagon Arch version v%d\n", opt_arch);
opt_arch = strtoul(str_arch, NULL, 0);
}
+ opt_hostbuf = str_hostbuf ? atoi(str_hostbuf) : 1;
+
reg->context = new ggml_hexagon_registry(reg);
HEX_VERBOSE("ggml-hex: size-of-general-req %zu size-of-general-rsp %zu\n", sizeof(struct htp_general_req),
static std::mutex mutex;
std::lock_guard<std::mutex> lock(mutex);
if (!initialized) {
+ auto nErr = htpdrv_init();
+ if (nErr != AEE_SUCCESS) {
+ return NULL;
+ }
+
ggml_hexagon_init(®);
}
--- /dev/null
+// sample drv interface
+
+#pragma clang diagnostic ignored "-Wgnu-anonymous-struct"
+#pragma clang diagnostic ignored "-Wmissing-prototypes"
+#pragma clang diagnostic ignored "-Wsign-compare"
+
+#include <filesystem>
+#include <set>
+#include <sstream>
+#include <string>
+#ifdef _WIN32
+# define WIN32_LEAN_AND_MEAN
+# ifndef NOMINMAX
+# define NOMINMAX
+# endif
+# include <windows.h>
+# include <winevt.h>
+#else
+# include <dlfcn.h>
+# include <unistd.h>
+#endif
+#include "ggml-impl.h"
+#include "htp-drv.h"
+#include "libdl.h"
+
+#include <domain.h>
+
+//
+// Driver API types
+//
+
+typedef void * (*rpcmem_alloc_pfn_t)(int heapid, uint32_t flags, int size);
+typedef void * (*rpcmem_alloc2_pfn_t)(int heapid, uint32_t flags, size_t size);
+typedef void (*rpcmem_free_pfn_t)(void * po);
+typedef int (*rpcmem_to_fd_pfn_t)(void * po);
+
+typedef AEEResult (*dspqueue_create_pfn_t)(int domain,
+ uint32_t flags,
+ uint32_t req_queue_size,
+ uint32_t resp_queue_size,
+ dspqueue_callback_t packet_callback,
+ dspqueue_callback_t error_callback,
+ void * callback_context,
+ dspqueue_t * queue);
+typedef AEEResult (*dspqueue_close_pfn_t)(dspqueue_t queue);
+typedef AEEResult (*dspqueue_export_pfn_t)(dspqueue_t queue, uint64_t *queue_id);
+typedef AEEResult (*dspqueue_write_pfn_t)(dspqueue_t queue, uint32_t flags,
+ uint32_t num_buffers,
+ struct dspqueue_buffer *buffers,
+ uint32_t message_length,
+ const uint8_t *message,
+ uint32_t timeout_us);
+typedef AEEResult (*dspqueue_read_pfn_t)(dspqueue_t queue, uint32_t *flags,
+ uint32_t max_buffers, uint32_t *num_buffers,
+ struct dspqueue_buffer *buffers,
+ uint32_t max_message_length,
+ uint32_t *message_length, uint8_t *message,
+ uint32_t timeout_us);
+
+typedef int (*fastrpc_mmap_pfn_t)(int domain, int fd, void *addr, int offset, size_t length, enum fastrpc_map_flags flags);
+typedef int (*fastrpc_munmap_pfn_t)(int domain, int fd, void *addr, size_t length);
+
+typedef int (*remote_handle64_open_pfn_t)(const char* name, remote_handle64 *ph);
+typedef int (*remote_handle64_invoke_pfn_t)(remote_handle64 h, uint32_t dwScalars, remote_arg *pra);
+typedef int (*remote_handle64_close_pfn_t)(remote_handle h);
+typedef int (*remote_handle_control_pfn_t)(uint32_t req, void* data, uint32_t datalen);
+typedef int (*remote_handle64_control_pfn_t)(remote_handle64 h, uint32_t req, void* data, uint32_t datalen);
+typedef int (*remote_session_control_pfn_t)(uint32_t req, void *data, uint32_t datalen);
+
+//
+// Driver API pfns
+//
+
+rpcmem_alloc_pfn_t rpcmem_alloc_pfn = nullptr;
+rpcmem_alloc2_pfn_t rpcmem_alloc2_pfn = nullptr;
+rpcmem_free_pfn_t rpcmem_free_pfn = nullptr;
+rpcmem_to_fd_pfn_t rpcmem_to_fd_pfn = nullptr;
+
+fastrpc_mmap_pfn_t fastrpc_mmap_pfn = nullptr;
+fastrpc_munmap_pfn_t fastrpc_munmap_pfn = nullptr;
+
+dspqueue_create_pfn_t dspqueue_create_pfn = nullptr;
+dspqueue_close_pfn_t dspqueue_close_pfn = nullptr;
+dspqueue_export_pfn_t dspqueue_export_pfn = nullptr;
+dspqueue_write_pfn_t dspqueue_write_pfn = nullptr;
+dspqueue_read_pfn_t dspqueue_read_pfn = nullptr;
+
+remote_handle64_open_pfn_t remote_handle64_open_pfn = nullptr;
+remote_handle64_invoke_pfn_t remote_handle64_invoke_pfn = nullptr;
+remote_handle64_close_pfn_t remote_handle64_close_pfn = nullptr;
+remote_handle_control_pfn_t remote_handle_control_pfn = nullptr;
+remote_handle64_control_pfn_t remote_handle64_control_pfn = nullptr;
+remote_session_control_pfn_t remote_session_control_pfn = nullptr;
+
+//
+// Driver API
+//
+
+void * rpcmem_alloc(int heapid, uint32_t flags, int size) {
+ return rpcmem_alloc_pfn(heapid, flags, size);
+}
+
+void * rpcmem_alloc2(int heapid, uint32_t flags, size_t size) {
+ if (rpcmem_alloc2_pfn) {
+ return rpcmem_alloc2_pfn(heapid, flags, size);
+ } else {
+ GGML_LOG_INFO("ggml-hex: rpcmem_alloc2 not found, falling back to rpcmem_alloc\n");
+ return rpcmem_alloc_pfn(heapid, flags, size);
+ }
+}
+
+void rpcmem_free(void * po) {
+ return rpcmem_free_pfn(po);
+}
+
+int rpcmem_to_fd(void * po) {
+ return rpcmem_to_fd_pfn(po);
+}
+
+HTPDRV_API int fastrpc_mmap(int domain, int fd, void * addr, int offset, size_t length, enum fastrpc_map_flags flags) {
+ return fastrpc_mmap_pfn(domain, fd, addr, offset, length, flags);
+}
+
+HTPDRV_API int fastrpc_munmap(int domain, int fd, void * addr, size_t length) {
+ return fastrpc_munmap_pfn(domain, fd, addr, length);
+}
+
+AEEResult dspqueue_create(int domain,
+ uint32_t flags,
+ uint32_t req_queue_size,
+ uint32_t resp_queue_size,
+ dspqueue_callback_t packet_callback,
+ dspqueue_callback_t error_callback,
+ void * callback_context,
+ dspqueue_t * queue) {
+ return dspqueue_create_pfn(domain, flags, req_queue_size, resp_queue_size, packet_callback, error_callback,
+ callback_context, queue);
+}
+
+AEEResult dspqueue_close(dspqueue_t queue) {
+ return dspqueue_close_pfn(queue);
+}
+
+AEEResult dspqueue_export(dspqueue_t queue, uint64_t * queue_id) {
+ return dspqueue_export_pfn(queue, queue_id);
+}
+
+AEEResult dspqueue_write(dspqueue_t queue,
+ uint32_t flags,
+ uint32_t num_buffers,
+ struct dspqueue_buffer * buffers,
+ uint32_t message_length,
+ const uint8_t * message,
+ uint32_t timeout_us) {
+ return dspqueue_write_pfn(queue, flags, num_buffers, buffers, message_length, message, timeout_us);
+}
+
+AEEResult dspqueue_read(dspqueue_t queue,
+ uint32_t * flags,
+ uint32_t max_buffers,
+ uint32_t * num_buffers,
+ struct dspqueue_buffer * buffers,
+ uint32_t max_message_length,
+ uint32_t * message_length,
+ uint8_t * message,
+ uint32_t timeout_us) {
+ return dspqueue_read_pfn(queue, flags, max_buffers, num_buffers, buffers, max_message_length, message_length,
+ message, timeout_us);
+}
+
+HTPDRV_API int remote_handle64_open(const char * name, remote_handle64 * ph) {
+ return remote_handle64_open_pfn(name, ph);
+}
+
+HTPDRV_API int remote_handle64_invoke(remote_handle64 h, uint32_t dwScalars, remote_arg * pra) {
+ return remote_handle64_invoke_pfn(h, dwScalars, pra);
+}
+
+HTPDRV_API int remote_handle64_close(remote_handle64 h) {
+ return remote_handle64_close_pfn(h);
+}
+
+HTPDRV_API int remote_handle_control(uint32_t req, void * data, uint32_t datalen) {
+ return remote_handle_control_pfn(req, data, datalen);
+}
+
+HTPDRV_API int remote_handle64_control(remote_handle64 h, uint32_t req, void * data, uint32_t datalen) {
+ return remote_handle64_control_pfn(h, req, data, datalen);
+}
+
+HTPDRV_API int remote_session_control(uint32_t req, void * data, uint32_t datalen) {
+ return remote_session_control_pfn(req, data, datalen);
+}
+
+#ifdef _WIN32
+
+static std::string wstr_to_str(std::wstring_view wstr) {
+ std::string result;
+ if (wstr.empty()) {
+ return result;
+ }
+ auto bytes_needed = WideCharToMultiByte(CP_UTF8, WC_ERR_INVALID_CHARS,
+ wstr.data(), (int) wstr.size(),
+ nullptr, 0, nullptr, nullptr);
+ if (bytes_needed == 0) {
+ GGML_LOG_ERROR("ggml-hex: WideCharToMultiByte failed. Error %lu\n", GetLastError());
+ throw std::runtime_error("Invalid wstring input");
+ }
+
+ result.resize(bytes_needed, '\0');
+ int bytes_written = WideCharToMultiByte(CP_UTF8, WC_ERR_INVALID_CHARS,
+ wstr.data(), (int) wstr.size(),
+ result.data(), bytes_needed,
+ nullptr, nullptr);
+ if (bytes_written == 0) {
+ GGML_LOG_ERROR("ggml-hex: WideCharToMultiByte failed. Error %lu\n", GetLastError());
+ throw std::runtime_error("Wstring conversion failed");
+ }
+ return result;
+}
+
+static std::string get_driver_path() {
+ std::wstring serviceName = L"qcnspmcdm";
+ std::string result;
+
+ // Get a handle to the SCM database.
+ SC_HANDLE schSCManager = OpenSCManagerW(NULL, NULL, STANDARD_RIGHTS_READ);
+ if (nullptr == schSCManager) {
+ GGML_LOG_ERROR("ggml-hex: Failed to open SCManager. Error: %lu\n", GetLastError());
+ return result;
+ }
+
+ // Get a handle to the service.
+ SC_HANDLE schService = OpenServiceW(schSCManager, // SCM database
+ serviceName.c_str(), // name of service
+ SERVICE_QUERY_CONFIG); // need query config access
+
+ if (nullptr == schService) {
+ GGML_LOG_ERROR("ggml-hex: Failed to open qcnspmcdm service. Error: %lu\n", GetLastError());
+ CloseServiceHandle(schSCManager);
+ return result;
+ }
+
+ // Store the size of buffer used as an output.
+ DWORD bufferSize;
+ if (!QueryServiceConfigW(schService, NULL, 0, &bufferSize) &&
+ (GetLastError() != ERROR_INSUFFICIENT_BUFFER)) {
+ GGML_LOG_ERROR("ggml-hex: Failed to query service config. Error: %lu\n", GetLastError());
+ CloseServiceHandle(schService);
+ CloseServiceHandle(schSCManager);
+ return result;
+ }
+ // Get the configuration of the service.
+ LPQUERY_SERVICE_CONFIGW serviceConfig =
+ static_cast<LPQUERY_SERVICE_CONFIGW>(LocalAlloc(LMEM_FIXED, bufferSize));
+ if (!QueryServiceConfigW(schService, serviceConfig, bufferSize, &bufferSize)) {
+ fprintf(stderr, "ggml-hex: Failed to query service config. Error: %lu\n", GetLastError());
+ LocalFree(serviceConfig);
+ CloseServiceHandle(schService);
+ CloseServiceHandle(schSCManager);
+ return result;
+ }
+
+ // Read the driver file path get its parent directory
+ std::wstring driverPath = std::wstring(serviceConfig->lpBinaryPathName);
+ driverPath = driverPath.substr(0, driverPath.find_last_of(L"\\"));
+
+ // Clean up resources
+ LocalFree(serviceConfig);
+ CloseServiceHandle(schService);
+ CloseServiceHandle(schSCManager);
+
+ // Driver path would contain invalid path string, like:
+ // \SystemRoot\System32\DriverStore\FileRepository\qcadsprpc8280.inf_arm64_c2b9460c9a072f37
+ // "\SystemRoot" should be replace with a correct one (e.g. C:\Windows)
+ const std::wstring systemRootPlaceholder = L"\\SystemRoot";
+ if (0 != driverPath.compare(0, systemRootPlaceholder.length(), systemRootPlaceholder)) {
+ GGML_LOG_ERROR("ggml-hex: String pattern not found in driver path.\n");
+ return result;
+ }
+
+ // Replace \SystemRoot with an absolute path from system ENV windir
+ const std::wstring systemRootEnv = L"windir";
+
+ // Query the number of wide charactors this variable requires
+ DWORD numWords = GetEnvironmentVariableW(systemRootEnv.c_str(), NULL, 0);
+ if (numWords == 0) {
+ GGML_LOG_ERROR("ggml-hex: Failed get systemRoot environment variable\n");
+ return result;
+ }
+
+ // Query the actual system root name from environment variable
+ std::vector<wchar_t> systemRoot(numWords + 1);
+ numWords = GetEnvironmentVariableW(systemRootEnv.c_str(), systemRoot.data(), numWords + 1);
+ if (numWords == 0) {
+ GGML_LOG_ERROR("ggml-hex: Failed to read windir environment variable\n");
+ return result;
+ }
+ driverPath.replace(0, systemRootPlaceholder.length(), std::wstring(systemRoot.data()));
+
+ return wstr_to_str(driverPath);
+}
+
+#endif
+
+using dl_handle_ptr = std::unique_ptr<dl_handle, dl_handle_deleter>;
+
+int htpdrv_init() {
+ static dl_handle_ptr lib_cdsp_rpc_handle = nullptr;
+ static bool initialized = false;
+#ifdef _WIN32
+ std::string drv_path = get_driver_path() + "\\" + "libcdsprpc.dll";
+#else
+ std::string drv_path = "libcdsprpc.so";
+#endif
+ if (initialized) {
+ GGML_LOG_INFO("ggml-hex: Driver already loaded\n");
+ return AEE_SUCCESS;
+ }
+ GGML_LOG_INFO("ggml-hex: Loading driver %s\n", drv_path.c_str());
+
+ fs::path path{ drv_path.c_str() };
+ dl_handle_ptr handle { dl_load_library(path) };
+ if (!handle) {
+ GGML_LOG_ERROR("ggml-hex: failed to load %s: %s\n", path.u8string().c_str(), dl_error());
+ return AEE_EUNABLETOLOAD;
+ }
+
+#define dlsym(drv, type, pfn, symbol, ignore) \
+ do { \
+ pfn = (type) dl_get_sym(drv, #symbol); \
+ if (!ignore && nullptr == pfn) { \
+ GGML_LOG_ERROR("ggml-hex: failed to dlsym %s\n", #symbol); \
+ return AEE_EUNABLETOLOAD; \
+ } \
+ } while (0)
+
+ dlsym(handle.get(), rpcmem_alloc_pfn_t, rpcmem_alloc_pfn, rpcmem_alloc, false);
+ dlsym(handle.get(), rpcmem_alloc2_pfn_t, rpcmem_alloc2_pfn, rpcmem_alloc2, true);
+ dlsym(handle.get(), rpcmem_free_pfn_t, rpcmem_free_pfn, rpcmem_free, false);
+ dlsym(handle.get(), rpcmem_to_fd_pfn_t, rpcmem_to_fd_pfn, rpcmem_to_fd, false);
+ dlsym(handle.get(), fastrpc_mmap_pfn_t, fastrpc_mmap_pfn, fastrpc_mmap, false);
+ dlsym(handle.get(), fastrpc_munmap_pfn_t, fastrpc_munmap_pfn, fastrpc_munmap, false);
+ dlsym(handle.get(), dspqueue_create_pfn_t, dspqueue_create_pfn, dspqueue_create, false);
+ dlsym(handle.get(), dspqueue_close_pfn_t, dspqueue_close_pfn, dspqueue_close, false);
+ dlsym(handle.get(), dspqueue_export_pfn_t, dspqueue_export_pfn, dspqueue_export, false);
+ dlsym(handle.get(), dspqueue_write_pfn_t, dspqueue_write_pfn, dspqueue_write, false);
+ dlsym(handle.get(), dspqueue_read_pfn_t, dspqueue_read_pfn, dspqueue_read, false);
+ dlsym(handle.get(), remote_handle64_open_pfn_t, remote_handle64_open_pfn, remote_handle64_open, false);
+ dlsym(handle.get(), remote_handle64_invoke_pfn_t, remote_handle64_invoke_pfn, remote_handle64_invoke, false);
+ dlsym(handle.get(), remote_handle_control_pfn_t, remote_handle_control_pfn, remote_handle_control, false);
+ dlsym(handle.get(), remote_handle64_control_pfn_t, remote_handle64_control_pfn, remote_handle64_control, false);
+ dlsym(handle.get(), remote_session_control_pfn_t, remote_session_control_pfn, remote_session_control, false);
+ dlsym(handle.get(), remote_handle64_close_pfn_t, remote_handle64_close_pfn, remote_handle64_close, false);
+
+ lib_cdsp_rpc_handle = std::move(handle);
+ initialized = true;
+
+ return AEE_SUCCESS;
+}
+
+domain * get_domain(int domain_id) {
+ int i = 0;
+ int size = sizeof(supported_domains) / sizeof(domain);
+
+ for (i = 0; i < size; i++) {
+ if (supported_domains[i].id == domain_id) {
+ return &supported_domains[i];
+ }
+ }
+
+ return NULL;
+}
+
+int get_hex_arch_ver(int domain, int * arch) {
+ if (!remote_handle_control_pfn) {
+ GGML_LOG_ERROR("ggml-hex: remote_handle_control is not supported on this device\n");
+ return AEE_EUNSUPPORTEDAPI;
+ }
+
+ struct remote_dsp_capability arch_ver;
+ arch_ver.domain = (uint32_t) domain;
+ arch_ver.attribute_ID = ARCH_VER;
+ arch_ver.capability = (uint32_t) 0;
+
+ int err = remote_handle_control(DSPRPC_GET_DSP_INFO, &arch_ver, sizeof(arch_ver));
+ if ((err & 0xff) == (AEE_EUNSUPPORTEDAPI & 0xff)) {
+ GGML_LOG_ERROR("ggml-hex: FastRPC capability API is not supported on this device\n");
+ return AEE_EUNSUPPORTEDAPI;
+ }
+
+ if (err != AEE_SUCCESS) {
+ GGML_LOG_ERROR("ggml-hex: FastRPC capability query failed (err %d)\n", err);
+ return err;
+ }
+
+ switch (arch_ver.capability & 0xff) {
+ case 0x68:
+ *arch = 68;
+ return 0;
+ case 0x69:
+ *arch = 69;
+ return 0;
+ case 0x73:
+ *arch = 73;
+ return 0;
+ case 0x75:
+ *arch = 75;
+ return 0;
+ case 0x79:
+ *arch = 79;
+ return 0;
+ case 0x81:
+ *arch = 81;
+ return 0;
+ }
+ return -1;
+}
--- /dev/null
+#pragma once
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#ifdef _WIN32
+# pragma clang diagnostic ignored "-Wignored-attributes"
+#endif
+
+#include <AEEStdErr.h>
+#include <rpcmem.h>
+#include <remote.h>
+#include <dspqueue.h>
+
+#if defined(_WIN32) && !defined(__MINGW32__)
+# ifdef GGML_BACKEND_BUILD
+# define HTPDRV_API __declspec(dllexport) extern
+# else
+# define HTPDRV_API __declspec(dllimport) extern
+# endif
+#else
+# define HTPDRV_API __attribute__ ((visibility ("default"))) extern
+#endif
+
+/* Offset to differentiate HLOS and Hexagon error codes.
+ Stores the value of AEE_EOFFSET for Hexagon. */
+#ifndef DSP_OFFSET
+# define DSP_OFFSET 0x80000400
+#endif
+
+/* Errno for connection reset by peer. */
+#ifndef ECONNRESET
+# ifdef __hexagon__
+# define ECONNRESET 104
+# endif
+#endif
+
+/* Abstraction of different OS specific sleep APIs.
+ SLEEP accepts input in seconds. */
+#ifndef SLEEP
+# ifdef __hexagon__
+# define SLEEP(x) \
+ { /* Do nothing for simulator. */ \
+ }
+# else
+# ifdef _WIN32
+# define SLEEP(x) Sleep(1000 * x) /* Sleep accepts input in milliseconds. */
+# else
+# define SLEEP(x) sleep(x) /* sleep accepts input in seconds. */
+# endif
+# endif
+#endif
+
+/* Include windows specific header files. */
+#ifdef _WIN32
+# include <windows.h>
+# include <sysinfoapi.h>
+# define _CRT_SECURE_NO_WARNINGS 1
+# define _WINSOCK_DEPRECATED_NO_WARNINGS 1
+#endif
+
+/* Includes and defines for all HLOS except windows */
+#if !defined(__hexagon__) && !defined(_WIN32)
+# include "unistd.h"
+
+# include <sys/time.h>
+#endif
+
+/* Includes and defines for Hexagon and all HLOS except Windows. */
+#if !defined(_WIN32)
+/* Weak reference to remote symbol for compilation. */
+# pragma weak remote_session_control
+# pragma weak remote_handle_control
+# pragma weak remote_handle64_control
+# pragma weak fastrpc_mmap
+# pragma weak fastrpc_munmap
+# pragma weak rpcmem_alloc2
+#endif
+
+#if !defined(_WIN32)
+# pragma weak remote_system_request
+#endif
+
+#ifdef _WIN32
+# define DSPQUEUE_TIMEOUT DSPQUEUE_TIMEOUT_NONE
+#else
+# define DSPQUEUE_TIMEOUT 1000000
+#endif
+
+/**
+ * htpdrv_init API: driver interface entry point
+ *
+ * @return Return AEE error codes as defined in Hexagon SDK.
+ */
+HTPDRV_API int htpdrv_init(void);
+
+/**
+ * get_domain API: get domain struct from domain value.
+ *
+ * @param[in] domain value of a domain
+ * @return Returns domain struct of the domain if it is supported or else
+ * returns NULL.
+ *
+ */
+HTPDRV_API domain * get_domain(int domain_id);
+
+/**
+ * get_hex_arch_ver API: query the Hexagon processor architecture version information
+ *
+ * @param[in] domain_id value of a domain
+ * @param[out] Arch version (73, 75, ...)
+ * @return 0 if query is successful.
+ * non-zero if error, return value points to the error.
+ *
+ */
+HTPDRV_API int get_hex_arch_ver(int domain, int * arch);
+
+#ifdef __cplusplus
+}
+#endif
+++ /dev/null
-
-#pragma clang diagnostic ignored "-Wgnu-anonymous-struct"
-#pragma clang diagnostic ignored "-Wmissing-prototypes"
-#pragma clang diagnostic ignored "-Wsign-compare"
-
-#define GGML_COMMON_IMPL_C
-#include "ggml-backend-impl.h"
-#include "ggml-common.h"
-#include "ggml-hexagon.h"
-#include "ggml-impl.h"
-
-#include "htp-utils.h"
-
-#include <domain.h>
-#include <remote.h>
-#include <stdbool.h>
-#include <stdint.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-
-domain * get_domain(int domain_id) {
- int i = 0;
- int size = sizeof(supported_domains) / sizeof(domain);
-
- for (i = 0; i < size; i++) {
- if (supported_domains[i].id == domain_id) {
- return &supported_domains[i];
- }
- }
-
- return NULL;
-}
-
-bool is_valid_domain_id(int domain_id, int compute_only) {
- int i = 0;
- int size = sizeof(supported_domains) / sizeof(domain);
-
- if (compute_only) {
- return is_CDSP(domain_id);
- }
-
- for (i = 0; i < size; i++) {
- if (supported_domains[i].id == domain_id) {
- return true;
- }
- }
-
- return false;
-}
-
-int get_domains_info(char * domain_type, int * num_domains, fastrpc_domain ** domains_info) {
- int nErr = AEE_SUCCESS;
- int ss_info = 0;
- if (domain_type != NULL) {
- if (strcmp(domain_type, "LPASS") == 0) {
- ss_info = FASTRPC_LPASS;
- } else if (strcmp(domain_type, "HPASS") == 0) {
- ss_info = FASTRPC_HPASS;
- } else {
- ss_info = FASTRPC_NSP;
- }
- }
- system_req_payload req = { 0 };
- req.id = FASTRPC_GET_DOMAINS;
- req.sys.domains = NULL;
- fastrpc_domain * domain = NULL;
- if (ss_info != 0) {
- req.sys.flags = DOMAINS_LIST_FLAGS_SET_TYPE(req.sys.flags, ss_info);
- } else {
- req.sys.flags = 0;
- }
-#ifdef _WIN32
- nErr = AEE_EUNSUPPORTED;
- goto bail;
-#endif
- if (remote_system_request) {
- nErr = remote_system_request(&req);
- if (nErr != AEE_SUCCESS) {
- GGML_LOG_ERROR("Failure in remote_system_request call: %d.\n", nErr);
- goto bail;
- }
- // Allocate memory for domain-info array
- req.sys.max_domains = req.sys.num_domains;
- if ((req.sys.domains = calloc(req.sys.num_domains, sizeof(fastrpc_domain))) == NULL) {
- nErr = AEE_ENOMEMORY;
- GGML_LOG_ERROR("Unable to allocate memory for req.sys.domains");
- goto bail;
- }
-
- nErr = remote_system_request(&req);
- if (nErr != AEE_SUCCESS) {
- GGML_LOG_ERROR("Failure in remote_system_request call: %d.\n", nErr);
- goto bail;
- }
-
- for (int i = 0; i < req.sys.num_domains; i++) {
- // Verify that only requested type domains were returned
- domain = &req.sys.domains[i];
- if (domain->type != ss_info && domain_type != NULL) {
- nErr = -1;
- GGML_LOG_ERROR("Incorrect data received from remote_system_request.\n");
- goto bail;
- }
- }
- *domains_info = req.sys.domains;
- *num_domains = req.sys.num_domains;
- } else {
- nErr = AEE_EUNSUPPORTED;
- goto bail;
- }
-bail:
- if (nErr && !req.sys.domains) {
- free(req.sys.domains);
- }
- return nErr;
-}
-
-int get_effective_domain_id(char * domain_name, int session_id, int * effec_domain_id) {
- int err = 0;
- remote_rpc_effective_domain_id_t sess = { 0 };
-
- sess.domain_name = domain_name;
- sess.domain_name_len = strlen(domain_name);
- sess.session_id = session_id;
-
- err = remote_session_control(FASTRPC_GET_EFFECTIVE_DOMAIN_ID, &sess, sizeof(sess));
- if (err) {
- GGML_LOG_ERROR("Error 0x%x: failed to get effective domain id for %s, session id %d\n", err, sess.domain_name,
- session_id);
- return err;
- }
-
- *effec_domain_id = sess.effective_domain_id;
- return err;
-}
-
-int get_dsp_support(int * domain) {
- int nErr = AEE_SUCCESS;
- *domain = CDSP_DOMAIN_ID; // DSP domain default value is CDSP_DOMAIN_ID
-
- if (remote_handle_control) {
- struct remote_dsp_capability dsp_capability_domain = { CDSP_DOMAIN_ID, DOMAIN_SUPPORT, 0 };
- nErr = remote_handle_control(DSPRPC_GET_DSP_INFO, &dsp_capability_domain, sizeof(struct remote_dsp_capability));
- if ((nErr & 0xFF) == (AEE_EUNSUPPORTEDAPI & 0xFF)) {
- GGML_LOG_ERROR("\nFastRPC Capability API is not supported on this device\n");
- goto bail;
- }
-
- if (dsp_capability_domain.capability == 0) {
- dsp_capability_domain.domain = ADSP_DOMAIN_ID; // Check for ADSP support.
- dsp_capability_domain.attribute_ID = DOMAIN_SUPPORT;
- dsp_capability_domain.capability = 0;
- nErr = remote_handle_control(DSPRPC_GET_DSP_INFO, &dsp_capability_domain,
- sizeof(struct remote_dsp_capability));
- if (dsp_capability_domain.capability) {
- *domain = ADSP_DOMAIN_ID; // For targets like Agatti (not having cDSP), domain is ADSP_DOMAIN_ID
- }
- }
-
- if (nErr != AEE_SUCCESS) {
- GGML_LOG_ERROR("\nget_dsp_support failed with Error 0x%x\n", nErr);
- goto bail;
- }
- } else {
- nErr = AEE_EUNSUPPORTEDAPI;
- GGML_LOG_ERROR("remote_dsp_capability interface is not supported on this device\n");
- }
-
-bail:
- return nErr;
-}
-
-int get_vtcm_info(int domain, uint32_t * capability, uint32_t attr) {
- int nErr = AEE_SUCCESS;
- *capability = 0;
-
- if (attr == VTCM_PAGE || attr == VTCM_COUNT) {
- } else {
- nErr = AEE_EBADPARM;
- GGML_LOG_ERROR("Unsupported attr. Only VTCM_PAGE and VTCM_COUNT supported\n");
- goto bail;
- }
- if (remote_handle_control) {
- if (domain == ADSP_DOMAIN_ID || domain == CDSP_DOMAIN_ID) {
- /*
- * Query the DSP for VTCM information
- * Since the ADSP does not have a dedicated VTCM, we expect the output to be 0
- */
- struct remote_dsp_capability dsp_capability_vtcm_dsp;
- dsp_capability_vtcm_dsp.domain = (uint32_t) domain;
- dsp_capability_vtcm_dsp.attribute_ID = attr;
- dsp_capability_vtcm_dsp.capability = (uint32_t) 0;
- nErr = remote_handle_control(DSPRPC_GET_DSP_INFO, &dsp_capability_vtcm_dsp,
- sizeof(struct remote_dsp_capability));
- if ((nErr & 0xFF) == (AEE_EUNSUPPORTEDAPI & 0xFF)) {
- GGML_LOG_ERROR("\nFastRPC Capability API is not supported on this device\n");
- GGML_LOG_ERROR("Running the usecase without checking the capability\n");
- nErr = AEE_SUCCESS;
- goto bail;
- } else if (nErr == AEE_SUCCESS) {
- *capability = dsp_capability_vtcm_dsp.capability;
- } else {
- GGML_LOG_ERROR("\nget_vtcm_info failed with Error 0x%x\n", nErr);
- goto bail;
- }
- } else {
- nErr = AEE_EUNSUPPORTED;
- GGML_LOG_ERROR("Unsupported domain %d\n", domain);
- goto bail;
- }
- } else {
- nErr = AEE_EUNSUPPORTEDAPI;
- GGML_LOG_ERROR("remote_dsp_capability interface is not supported on this device\n");
- }
-
-bail:
- return nErr;
-}
-
-bool is_unsignedpd_supported(int domain_id) {
- int nErr = AEE_SUCCESS;
- if (remote_handle_control) {
- struct remote_dsp_capability dsp_capability_domain = { domain_id, UNSIGNED_PD_SUPPORT, 0 };
- nErr = remote_handle_control(DSPRPC_GET_DSP_INFO, &dsp_capability_domain, sizeof(struct remote_dsp_capability));
- if ((nErr & 0xFF) == (AEE_EUNSUPPORTEDAPI & 0xFF)) {
- GGML_LOG_ERROR("\nFastRPC Capability API is not supported on this device. Falling back to signed pd.\n");
- return false;
- }
- if (nErr) {
- GGML_LOG_ERROR("\nERROR 0x%x: FastRPC Capability API failed. Falling back to signed pd.", nErr);
- return false;
- }
- if (dsp_capability_domain.capability == 1) {
- return true;
- }
- } else {
- nErr = AEE_EUNSUPPORTEDAPI;
- GGML_LOG_ERROR("remote_dsp_capability interface is not supported on this device. Falling back to signed pd.\n");
- return false;
- }
- return false;
-}
-
-bool get_unsignedpd_support(void) {
- return is_unsignedpd_supported(CDSP_DOMAIN_ID);
-}
-
-bool is_async_fastrpc_supported(int domain) {
- int nErr = AEE_SUCCESS;
- if (remote_handle_control) {
- if (domain == CDSP_DOMAIN_ID) {
- /*
- * Query the DSP for ASYNC_FASTRPC_SUPPORT information
- * Async fastrpc is supported only on CDSP
- */
- struct remote_dsp_capability dsp_capability_async_support;
- dsp_capability_async_support.domain = (uint32_t) domain;
- dsp_capability_async_support.attribute_ID = ASYNC_FASTRPC_SUPPORT;
- dsp_capability_async_support.capability = (uint32_t) 0;
- nErr = remote_handle_control(DSPRPC_GET_DSP_INFO, &dsp_capability_async_support,
- sizeof(struct remote_dsp_capability));
- if ((nErr & 0xFF) == (AEE_EUNSUPPORTEDAPI & 0xFF)) {
- GGML_LOG_ERROR("\nFastRPC Capability API is not supported on this device\n");
- GGML_LOG_ERROR("Running the usecase without checking the capability\n");
- nErr = AEE_SUCCESS;
- goto bail;
- } else if (dsp_capability_async_support.capability == 1) {
- return true;
- }
- if (nErr != AEE_SUCCESS) {
- GGML_LOG_ERROR("\nis_async_fastrpc_supported failed with Error 0x%x\n", nErr);
- goto bail;
- }
- } else {
- nErr = AEE_EUNSUPPORTED;
- GGML_LOG_ERROR("Async fastrpc is not supported on domain %d\n", domain);
- goto bail;
- }
- } else {
- nErr = AEE_EUNSUPPORTEDAPI;
- GGML_LOG_ERROR("remote_dsp_capability interface is not supported on this device\n");
- }
-
-bail:
- return false;
-}
-
-bool is_status_notification_supported(int domain) {
- int nErr = AEE_SUCCESS;
-
- if (remote_handle_control) {
- /*
- * Query the DSP for STATUS_NOTIFICATION_SUPPORT information
- * DSP User PD status notification Support
- */
- struct remote_dsp_capability dsp_capability_status_notification_support;
- dsp_capability_status_notification_support.domain = (uint32_t) domain;
- dsp_capability_status_notification_support.attribute_ID = STATUS_NOTIFICATION_SUPPORT;
- dsp_capability_status_notification_support.capability = (uint32_t) 0;
- nErr = remote_handle_control(DSPRPC_GET_DSP_INFO, &dsp_capability_status_notification_support,
- sizeof(struct remote_dsp_capability));
- if ((nErr & 0xFF) == (AEE_EUNSUPPORTEDAPI & 0xFF)) {
- GGML_LOG_ERROR("\nFastRPC Capability API is not supported on this device\n");
- GGML_LOG_ERROR("Running the usecase without checking the capability\n");
- nErr = AEE_SUCCESS;
- goto bail;
- } else if (dsp_capability_status_notification_support.capability == 1) {
- return true;
- }
- if (nErr != AEE_SUCCESS) {
- GGML_LOG_ERROR("\nis_status_notification_supported failed with Error 0x%x\n", nErr);
- goto bail;
- }
- } else {
- nErr = AEE_EUNSUPPORTEDAPI;
- GGML_LOG_ERROR("remote_dsp_capability interface is not supported on this device\n");
- }
-
-bail:
- return false;
-}
-
-int get_hmx_support_info(int domain, uint32_t * capability, uint32_t attr) {
- int nErr = AEE_SUCCESS;
- *capability = 0;
-
- if (attr != HMX_SUPPORT_SPATIAL && attr != HMX_SUPPORT_DEPTH) {
- nErr = AEE_EBADPARM;
- GGML_LOG_ERROR("Unsupported attr. Only HMX_SUPPORT_SPATIAL and HMX_SUPPORT_DEPTH supported\n");
- goto bail;
- }
- if (remote_handle_control) {
- if (domain == CDSP_DOMAIN_ID) {
- /*
- * Query the DSP for HMX SUPPORT information
- * HMX is supported on CDSP only
- */
- struct remote_dsp_capability dsp_capability_hmx_dsp;
- dsp_capability_hmx_dsp.domain = (uint32_t) domain;
- dsp_capability_hmx_dsp.attribute_ID = attr;
- dsp_capability_hmx_dsp.capability = (uint32_t) 0;
- nErr = remote_handle_control(DSPRPC_GET_DSP_INFO, &dsp_capability_hmx_dsp,
- sizeof(struct remote_dsp_capability));
- if ((nErr & 0xFF) == (AEE_EUNSUPPORTEDAPI & 0xFF)) {
- GGML_LOG_ERROR("\nFastRPC Capability API is not supported on this device\n");
- GGML_LOG_ERROR("Running the usecase without checking the capability\n");
- nErr = AEE_SUCCESS;
- goto bail;
- } else if (nErr == AEE_SUCCESS) {
- *capability = dsp_capability_hmx_dsp.capability;
- } else {
- GGML_LOG_ERROR("\nget_hmx_support_info failed with Error 0x%x\n", nErr);
- goto bail;
- }
- } else {
- nErr = AEE_EUNSUPPORTED;
- GGML_LOG_ERROR("HMX support is not there for domain %d\n", domain);
- goto bail;
- }
- } else {
- nErr = AEE_EUNSUPPORTEDAPI;
- GGML_LOG_ERROR("remote_dsp_capability interface is not supported on this device\n");
- }
-
-bail:
- return nErr;
-}
-
-int get_hex_arch_ver(int domain, int * arch) {
- if (!remote_handle_control) {
- GGML_LOG_ERROR("ggml-hex: remote_handle_control is not supported on this device\n");
- return AEE_EUNSUPPORTEDAPI;
- }
-
- struct remote_dsp_capability arch_ver;
- arch_ver.domain = (uint32_t) domain;
- arch_ver.attribute_ID = ARCH_VER;
- arch_ver.capability = (uint32_t) 0;
-
- int err = remote_handle_control(DSPRPC_GET_DSP_INFO, &arch_ver, sizeof(arch_ver));
- if ((err & 0xff) == (AEE_EUNSUPPORTEDAPI & 0xff)) {
- GGML_LOG_ERROR("ggml-hex: FastRPC capability API is not supported on this device\n");
- return AEE_EUNSUPPORTEDAPI;
- }
-
- if (err != AEE_SUCCESS) {
- GGML_LOG_ERROR("ggml-hex: FastRPC capability query failed (err %d)\n", err);
- return err;
- }
-
- switch (arch_ver.capability & 0xff) {
- case 0x68:
- *arch = 68;
- return 0;
- case 0x69:
- *arch = 69;
- return 0;
- case 0x73:
- *arch = 73;
- return 0;
- case 0x75:
- *arch = 75;
- return 0;
- case 0x79:
- *arch = 79;
- return 0;
- case 0x81:
- *arch = 81;
- return 0;
- }
- return -1;
-}
-
-int get_hvx_support_info(int domain, uint32_t * capability, uint32_t attr) {
- int nErr = AEE_SUCCESS;
- *capability = 0;
-
- if (remote_handle_control) {
- if (domain == CDSP_DOMAIN_ID) {
- /*
- * Query the DSP for HVX SUPPORT information
- * HVX is supported on CDSP only
- */
- struct remote_dsp_capability dsp_capability_hvx_dsp;
- dsp_capability_hvx_dsp.domain = (uint32_t) domain;
- dsp_capability_hvx_dsp.attribute_ID = attr;
- dsp_capability_hvx_dsp.capability = (uint32_t) 0;
- nErr = remote_handle_control(DSPRPC_GET_DSP_INFO, &dsp_capability_hvx_dsp,
- sizeof(struct remote_dsp_capability));
- if ((nErr & 0xFF) == (AEE_EUNSUPPORTEDAPI & 0xFF)) {
- GGML_LOG_ERROR("\nFastRPC Capability API is not supported on this device\n");
- GGML_LOG_ERROR("Running the usecase without checking the capability\n");
- nErr = AEE_SUCCESS;
- goto bail;
- } else if (nErr == AEE_SUCCESS) {
- *capability = dsp_capability_hvx_dsp.capability;
- } else {
- GGML_LOG_ERROR("\nget_hvx_support_info failed with Error 0x%x\n", nErr);
- goto bail;
- }
- } else {
- nErr = AEE_EUNSUPPORTED;
- GGML_LOG_ERROR("HVX support is not available on domain %d\n", domain);
- goto bail;
- }
- } else {
- nErr = AEE_EUNSUPPORTEDAPI;
- GGML_LOG_ERROR("remote_dsp_capability interface is not supported on this device\n");
- }
-
-bail:
- return nErr;
-}
+++ /dev/null
-#ifndef HTP_UTILS_H
-#define HTP_UTILS_H
-
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-#include <AEEStdErr.h>
-#include <inttypes.h>
-#include <remote.h>
-#include <rpcmem.h>
-#include <stdbool.h>
-
-/* Offset to differentiate HLOS and Hexagon error codes.
- Stores the value of AEE_EOFFSET for Hexagon. */
-#ifndef DSP_OFFSET
-# define DSP_OFFSET 0x80000400
-#endif
-
-/* Errno for connection reset by peer. */
-#ifndef ECONNRESET
-# ifdef __hexagon__
-# define ECONNRESET 104
-# endif
-#endif
-
-/* Abstraction of different OS specific sleep APIs.
- SLEEP accepts input in seconds. */
-#ifndef SLEEP
-# ifdef __hexagon__
-# define SLEEP(x) \
- { /* Do nothing for simulator. */ \
- }
-# else
-# ifdef _WINDOWS
-# define SLEEP(x) Sleep(1000 * x) /* Sleep accepts input in milliseconds. */
-# else
-# define SLEEP(x) sleep(x) /* sleep accepts input in seconds. */
-# endif
-# endif
-#endif
-
-/* Include windows specific header files. */
-#ifdef _WINDOWS
-# include <sysinfoapi.h>
-# include <windows.h>
-# define _CRT_SECURE_NO_WARNINGS 1
-# define _WINSOCK_DEPRECATED_NO_WARNINGS 1
-/* Including this file for custom implementation of getopt function. */
-# include "getopt_custom.h"
-#endif
-
-/* Includes and defines for all HLOS except windows */
-#if !defined(__hexagon__) && !defined(_WINDOWS)
-# include "unistd.h"
-
-# include <sys/time.h>
-#endif
-
-/* Includes and defines for Hexagon and all HLOS except Windows. */
-#if !defined(_WINDOWS)
-/* Weak reference to remote symbol for compilation. */
-# pragma weak remote_session_control
-# pragma weak remote_handle_control
-# pragma weak remote_handle64_control
-# pragma weak fastrpc_mmap
-# pragma weak fastrpc_munmap
-# pragma weak rpcmem_alloc2
-#endif
-
-#if !defined(_WINDOWS)
-# pragma weak remote_system_request
-#endif
-/**
- * Wrapper for FastRPC Capability API: query DSP support.
- *
- * @param[out] domain pointer to supported domain.
- * @return 0 if query is successful.
- * non-zero if error, return value points to the error.
- */
-int get_dsp_support(int * domain);
-
-/**
- * Wrapper for FastRPC Capability API: query VTCM information.
- *
- * @param[in] domain value of domain in the queried.
- * @param[out] capability capability value of the attribute queried.
- * @param[in] attr value of the attribute to the queried.
- * @return 0 if query is successful.
- * non-zero if error, return value points to the error.
- */
-int get_vtcm_info(int domain, uint32_t * capability, uint32_t attr);
-
-/**
- * Wrapper for FastRPC Capability API: query unsigned pd support on CDSP domain.
- *
- * @return true if unsigned pd is supported.
- * false if unsigned pd is not supported, capability query failed.
- */
-
-bool get_unsignedpd_support(void);
-
-/**
- * Wrapper for FastRPC Capability API: query unsigned pd support.
- *
- * @param[in] domain value of domain in the queried.
- * @return true if unsigned pd is supported.
- * false if unsigned pd is not supported, capability query failed.
- */
-
-bool is_unsignedpd_supported(int domain_id);
-
-/**
- * is_valid_domain_id API: query a domain id is valid.
- *
- * @param[in] domain value of domain in the queried.
- * @param[in] compute_only value of domain is only compared with CDSP domains supported by the target when enabled.
- * @return true if value of domain is valid.
- * false if value of domain is not valid.
- */
-
-bool is_valid_domain_id(int domain_id, int compute_only);
-
-/**
- * get_domain API: get domain struct from domain value.
- *
- * @param[in] domain value of a domain
- * @return Returns domain struct of the domain if it is supported or else
- * returns NULL.
- *
- */
-
-domain * get_domain(int domain_id);
-
-/**
- * get_domains_info API: get information for all the domains available on the device
- *
- * @param[in] domain_type pointer to domain type
- * @param[in] num_domains pointer to number of domains
- * @param[in] domains_info pointer to save discovered domains information.
- * @return 0 if query is successful.
- * non-zero if error, return value points to the error.
- *
- * It is user's responsibility to free the memory used to store the domains info whose address is present in domains_info before closing the application.
- *
- */
-
-int get_domains_info(char * domain_type, int * num_domains, fastrpc_domain ** domains_info);
-
-/**
- * get_effective_domain_id API: get effective domain id for given session id
- *
- * @param[in] domain_name pointer to domain name
- * @param[in] session_id
- * @param[in] effec_domain_id pointer to save obtained effective domain id.
- * @return 0 if query is successful.
- * non-zero if error, return value points to the error.
- *
- */
-
-int get_effective_domain_id(char * domain_name, int session_id, int * effec_domain_id);
-
-/**
- * is_async_fastrpc_supported API: query a domain id has async fastrpc supported or not
- *
- * @param[in] domain_id value of a domain
- * @return Returns true or false stating support of Async FastRPC
- *
- */
-
-bool is_async_fastrpc_supported(int domain_id);
-
-/**
- * is_status_notification_supported API: query the DSP for STATUS_NOTIFICATION_SUPPORT information
- *
- * @param[in] domain_id value of a domain
- * @return Returns true or false stating status notification support information
- *
- */
-bool is_status_notification_supported(int domain_id);
-
-/**
- * get_hmx_support_info API: query the DSP for HMX SUPPORT information
- *
- * @param[in] domain_id value of a domain
- * @param[out] capability capability value of the attribute queried.
- * @param[in] attr value of the attribute to the queried.
- * @return 0 if query is successful.
- * non-zero if error, return value points to the error.
- *
- */
-int get_hmx_support_info(int domain, uint32_t * capability, uint32_t attr);
-
-/**
- * get_hex_arch_ver API: query the Hexagon processor architecture version information
- *
- * @param[in] domain_id value of a domain
- * @param[out] Arch version (73, 75, ...)
- * @return 0 if query is successful.
- * non-zero if error, return value points to the error.
- *
- */
-int get_hex_arch_ver(int domain, int * arch);
-
-/**
- * get_hvx_support_info API: query the DSP for HVX SUPPORT information
- *
- * @param[in] domain_id value of a domain
- * @param[out] capability capability value of the attribute queried.
- * @param[in] attr value of the attribute to the queried.
- * @return 0 if query is successful.
- * non-zero if error, return value points to the error.
- *
- */
-int get_hvx_support_info(int domain, uint32_t * capability, uint32_t attr);
-
-#ifdef __cplusplus
-}
-#endif
-
-#endif //DSP_CAPABILITIES_UTILS_H
--- /dev/null
+#pragma once
+
+#ifdef _WIN32
+# define WIN32_LEAN_AND_MEAN
+# ifndef NOMINMAX
+# define NOMINMAX
+# endif
+# include <windows.h>
+# include <winevt.h>
+#else
+# include <dlfcn.h>
+# include <unistd.h>
+#endif
+#include <filesystem>
+
+namespace fs = std::filesystem;
+
+#ifdef _WIN32
+
+using dl_handle = std::remove_pointer_t<HMODULE>;
+
+struct dl_handle_deleter {
+ void operator()(HMODULE handle) {
+ FreeLibrary(handle);
+ }
+};
+
+static inline dl_handle * dl_load_library(const fs::path & path) {
+ // suppress error dialogs for missing DLLs
+ DWORD old_mode = SetErrorMode(SEM_FAILCRITICALERRORS);
+ SetErrorMode(old_mode | SEM_FAILCRITICALERRORS);
+
+ HMODULE handle = LoadLibraryW(path.wstring().c_str());
+
+ SetErrorMode(old_mode);
+
+ return handle;
+}
+
+static inline void * dl_get_sym(dl_handle * handle, const char * name) {
+ DWORD old_mode = SetErrorMode(SEM_FAILCRITICALERRORS);
+ SetErrorMode(old_mode | SEM_FAILCRITICALERRORS);
+
+ void * p = (void *) GetProcAddress(handle, name);
+
+ SetErrorMode(old_mode);
+
+ return p;
+}
+
+static inline const char * dl_error() {
+ return "";
+}
+
+#else
+
+using dl_handle = void;
+
+struct dl_handle_deleter {
+ void operator()(void * handle) {
+ dlclose(handle);
+ }
+};
+
+static inline dl_handle * dl_load_library(const fs::path & path) {
+ dl_handle * handle = dlopen(path.string().c_str(), RTLD_NOW | RTLD_LOCAL);
+ return handle;
+}
+
+static inline void * dl_get_sym(dl_handle * handle, const char * name) {
+ return dlsym(handle, name);
+}
+
+static inline const char * dl_error() {
+ const char *rslt = dlerror();
+ return rslt != nullptr ? rslt : "";
+}
+
+#endif
--- /dev/null
+[Version]
+Signature = "$WINDOWS NT$"
+Class = ComputeAccelerator
+ClassGuid = {F01A9D53-3FF6-48D2-9F97-C8A7004BE10C}
+Provider = %GGML%
+DriverVer = 01/01/2026,1.0.0.0
+CatalogFile = libggml-htp.cat
+PnpLockDown = 1
+
+[DestinationDirs]
+Drivers_Dir = 6
+
+[SourceDisksNames]
+1 = %DiskId%
+
+[SourceDisksFiles]
+libggml-htp-v68.so = 1
+libggml-htp-v69.so = 1
+libggml-htp-v73.so = 1
+libggml-htp-v75.so = 1
+libggml-htp-v81.so = 1
+
+[ControlFlags]
+ExcludeFromSelect = *
+
+[DefaultInstall.NTarm64]
+CopyFiles=Drivers_Dir
+
+[Drivers_Dir]
+libggml-htp-v68.so,,,0x10 ;COPYFLG_NO_OVERWRITE
+libggml-htp-v69.so,,,0x10 ;COPYFLG_NO_OVERWRITE
+libggml-htp-v73.so,,,0x10 ;COPYFLG_NO_OVERWRITE
+libggml-htp-v75.so,,,0x10 ;COPYFLG_NO_OVERWRITE
+libggml-htp-v81.so,,,0x10 ;COPYFLG_NO_OVERWRITE
+
+[Strings]
+GGML = 'GGML'
+DiskId = 'GGML HTP library'
overview / pkg / ggml / sources / ggml / commitdiff