[llvm-branch-commits] [openmp] e007b32 - [OpenMP] Add time profiling for libomptarget
Giorgis Georgakoudis via llvm-branch-commits
llvm-branch-commits at lists.llvm.org
Fri Dec 11 18:58:20 PST 2020
Author: Giorgis Georgakoudis
Date: 2020-12-11T18:53:37-08:00
New Revision: e007b328642946afc9e06bed9a098c7e23989900
URL: https://github.com/llvm/llvm-project/commit/e007b328642946afc9e06bed9a098c7e23989900
DIFF: https://github.com/llvm/llvm-project/commit/e007b328642946afc9e06bed9a098c7e23989900.diff
LOG: [OpenMP] Add time profiling for libomptarget
Reviewed By: jdoerfert
Differential Revision: https://reviews.llvm.org/D93055
Added:
Modified:
openmp/CMakeLists.txt
openmp/libomptarget/src/CMakeLists.txt
openmp/libomptarget/src/api.cpp
openmp/libomptarget/src/interface.cpp
openmp/libomptarget/src/private.h
openmp/libomptarget/src/rtl.cpp
Removed:
################################################################################
diff --git a/openmp/CMakeLists.txt b/openmp/CMakeLists.txt
index 6cc36d9b7577..dc0d3a6e718a 100644
--- a/openmp/CMakeLists.txt
+++ b/openmp/CMakeLists.txt
@@ -82,6 +82,8 @@ endif()
option(OPENMP_ENABLE_LIBOMPTARGET "Enable building libomptarget for offloading."
${ENABLE_LIBOMPTARGET})
+option(OPENMP_ENABLE_LIBOMPTARGET_PROFILING "Enable time profiling for libomptarget."
+ ${ENABLE_LIBOMPTARGET})
if (OPENMP_ENABLE_LIBOMPTARGET)
# Check that the library can actually be built.
if (APPLE OR WIN32)
diff --git a/openmp/libomptarget/src/CMakeLists.txt b/openmp/libomptarget/src/CMakeLists.txt
index 46f1969d14e7..586589da401d 100644
--- a/openmp/libomptarget/src/CMakeLists.txt
+++ b/openmp/libomptarget/src/CMakeLists.txt
@@ -21,11 +21,23 @@ set(src_files
omptarget.cpp
)
-# Build libomptarget library with libdl dependency.
-add_library(omptarget SHARED ${src_files})
-target_link_libraries(omptarget
- ${CMAKE_DL_LIBS}
- "-Wl,--version-script=${CMAKE_CURRENT_SOURCE_DIR}/exports")
+# Build libomptarget library with libdl dependency. Add LLVMSupport
+# dependency if building in-tree with profiling enabled.
+if(OPENMP_STANDALONE_BUILD OR (NOT OPENMP_ENABLE_LIBOMPTARGET_PROFILING))
+ add_library(omptarget SHARED ${src_files})
+ target_link_libraries(omptarget
+ ${CMAKE_DL_LIBS}
+ "-Wl,--version-script=${CMAKE_CURRENT_SOURCE_DIR}/exports")
+else()
+ set(LLVM_LINK_COMPONENTS
+ Support
+ )
+ add_llvm_library(omptarget SHARED ${src_files}
+ LINK_LIBS ${CMAKE_DL_LIBS}
+ "-Wl,--version-script=${CMAKE_CURRENT_SOURCE_DIR}/exports"
+ )
+ target_compile_definitions(omptarget PUBLIC OMPTARGET_PROFILE_ENABLED)
+endif()
# Install libomptarget under the lib destination folder.
install(TARGETS omptarget LIBRARY COMPONENT omptarget
diff --git a/openmp/libomptarget/src/api.cpp b/openmp/libomptarget/src/api.cpp
index cd5cb0c98c63..58f7cec2fdd6 100644
--- a/openmp/libomptarget/src/api.cpp
+++ b/openmp/libomptarget/src/api.cpp
@@ -19,6 +19,7 @@
#include <cstdlib>
EXTERN int omp_get_num_devices(void) {
+ TIMESCOPE();
PM->RTLsMtx.lock();
size_t DevicesSize = PM->Devices.size();
PM->RTLsMtx.unlock();
@@ -29,12 +30,14 @@ EXTERN int omp_get_num_devices(void) {
}
EXTERN int omp_get_initial_device(void) {
+ TIMESCOPE();
int hostDevice = omp_get_num_devices();
DP("Call to omp_get_initial_device returning %d\n", hostDevice);
return hostDevice;
}
EXTERN void *omp_target_alloc(size_t size, int device_num) {
+ TIMESCOPE();
DP("Call to omp_target_alloc for device %d requesting %zu bytes\n",
device_num, size);
@@ -62,6 +65,7 @@ EXTERN void *omp_target_alloc(size_t size, int device_num) {
}
EXTERN void omp_target_free(void *device_ptr, int device_num) {
+ TIMESCOPE();
DP("Call to omp_target_free for device %d and address " DPxMOD "\n",
device_num, DPxPTR(device_ptr));
@@ -86,6 +90,7 @@ EXTERN void omp_target_free(void *device_ptr, int device_num) {
}
EXTERN int omp_target_is_present(void *ptr, int device_num) {
+ TIMESCOPE();
DP("Call to omp_target_is_present for device %d and address " DPxMOD "\n",
device_num, DPxPTR(ptr));
@@ -125,6 +130,7 @@ EXTERN int omp_target_is_present(void *ptr, int device_num) {
EXTERN int omp_target_memcpy(void *dst, void *src, size_t length,
size_t dst_offset, size_t src_offset, int dst_device, int src_device) {
+ TIMESCOPE();
DP("Call to omp_target_memcpy, dst device %d, src device %d, "
"dst addr " DPxMOD ", src addr " DPxMOD ", dst offset %zu, "
"src offset %zu, length %zu\n", dst_device, src_device, DPxPTR(dst),
@@ -190,6 +196,7 @@ EXTERN int omp_target_memcpy_rect(void *dst, void *src, size_t element_size,
int num_dims, const size_t *volume, const size_t *dst_offsets,
const size_t *src_offsets, const size_t *dst_dimensions,
const size_t *src_dimensions, int dst_device, int src_device) {
+ TIMESCOPE();
DP("Call to omp_target_memcpy_rect, dst device %d, src device %d, "
"dst addr " DPxMOD ", src addr " DPxMOD ", dst offsets " DPxMOD ", "
"src offsets " DPxMOD ", dst dims " DPxMOD ", src dims " DPxMOD ", "
@@ -244,6 +251,7 @@ EXTERN int omp_target_memcpy_rect(void *dst, void *src, size_t element_size,
EXTERN int omp_target_associate_ptr(void *host_ptr, void *device_ptr,
size_t size, size_t device_offset, int device_num) {
+ TIMESCOPE();
DP("Call to omp_target_associate_ptr with host_ptr " DPxMOD ", "
"device_ptr " DPxMOD ", size %zu, device_offset %zu, device_num %d\n",
DPxPTR(host_ptr), DPxPTR(device_ptr), size, device_offset, device_num);
@@ -271,6 +279,7 @@ EXTERN int omp_target_associate_ptr(void *host_ptr, void *device_ptr,
}
EXTERN int omp_target_disassociate_ptr(void *host_ptr, int device_num) {
+ TIMESCOPE();
DP("Call to omp_target_disassociate_ptr with host_ptr " DPxMOD ", "
"device_num %d\n", DPxPTR(host_ptr), device_num);
diff --git a/openmp/libomptarget/src/interface.cpp b/openmp/libomptarget/src/interface.cpp
index a1ff650c193c..b17be27275e7 100644
--- a/openmp/libomptarget/src/interface.cpp
+++ b/openmp/libomptarget/src/interface.cpp
@@ -81,18 +81,21 @@ static void HandleTargetOutcome(bool success, ident_t *loc = nullptr) {
////////////////////////////////////////////////////////////////////////////////
/// adds requires flags
EXTERN void __tgt_register_requires(int64_t flags) {
+ TIMESCOPE();
PM->RTLs.RegisterRequires(flags);
}
////////////////////////////////////////////////////////////////////////////////
/// adds a target shared library to the target execution image
EXTERN void __tgt_register_lib(__tgt_bin_desc *desc) {
+ TIMESCOPE();
PM->RTLs.RegisterLib(desc);
}
////////////////////////////////////////////////////////////////////////////////
/// unloads a target shared library
EXTERN void __tgt_unregister_lib(__tgt_bin_desc *desc) {
+ TIMESCOPE();
PM->RTLs.UnregisterLib(desc);
}
@@ -101,6 +104,7 @@ EXTERN void __tgt_unregister_lib(__tgt_bin_desc *desc) {
/// and passes the data to the device.
EXTERN void __tgt_target_data_begin(int64_t device_id, int32_t arg_num,
void **args_base, void **args, int64_t *arg_sizes, int64_t *arg_types) {
+ TIMESCOPE();
__tgt_target_data_begin_mapper(nullptr, device_id, arg_num, args_base, args,
arg_sizes, arg_types, nullptr, nullptr);
}
@@ -109,6 +113,7 @@ EXTERN void __tgt_target_data_begin_nowait(int64_t device_id, int32_t arg_num,
void **args_base, void **args, int64_t *arg_sizes, int64_t *arg_types,
int32_t depNum, void *depList, int32_t noAliasDepNum,
void *noAliasDepList) {
+ TIMESCOPE();
if (depNum + noAliasDepNum > 0)
__kmpc_omp_taskwait(NULL, __kmpc_global_thread_num(NULL));
@@ -122,6 +127,7 @@ EXTERN void __tgt_target_data_begin_mapper(ident_t *loc, int64_t device_id,
int64_t *arg_types,
map_var_info_t *arg_names,
void **arg_mappers) {
+ TIMESCOPE();
if (IsOffloadDisabled()) return;
DP("Entering data begin region for device %" PRId64 " with %d mappings\n",
@@ -160,6 +166,7 @@ EXTERN void __tgt_target_data_begin_nowait_mapper(
void **args, int64_t *arg_sizes, int64_t *arg_types,
map_var_info_t *arg_names, void **arg_mappers, int32_t depNum,
void *depList, int32_t noAliasDepNum, void *noAliasDepList) {
+ TIMESCOPE();
if (depNum + noAliasDepNum > 0)
__kmpc_omp_taskwait(loc, __kmpc_global_thread_num(loc));
@@ -172,6 +179,7 @@ EXTERN void __tgt_target_data_begin_nowait_mapper(
/// created by the last __tgt_target_data_begin.
EXTERN void __tgt_target_data_end(int64_t device_id, int32_t arg_num,
void **args_base, void **args, int64_t *arg_sizes, int64_t *arg_types) {
+ TIMESCOPE();
__tgt_target_data_end_mapper(nullptr, device_id, arg_num, args_base, args,
arg_sizes, arg_types, nullptr, nullptr);
}
@@ -180,6 +188,7 @@ EXTERN void __tgt_target_data_end_nowait(int64_t device_id, int32_t arg_num,
void **args_base, void **args, int64_t *arg_sizes, int64_t *arg_types,
int32_t depNum, void *depList, int32_t noAliasDepNum,
void *noAliasDepList) {
+ TIMESCOPE();
if (depNum + noAliasDepNum > 0)
__kmpc_omp_taskwait(NULL, __kmpc_global_thread_num(NULL));
@@ -193,6 +202,7 @@ EXTERN void __tgt_target_data_end_mapper(ident_t *loc, int64_t device_id,
int64_t *arg_types,
map_var_info_t *arg_names,
void **arg_mappers) {
+ TIMESCOPE();
if (IsOffloadDisabled()) return;
DP("Entering data end region with %d mappings\n", arg_num);
@@ -236,6 +246,7 @@ EXTERN void __tgt_target_data_end_nowait_mapper(
void **args, int64_t *arg_sizes, int64_t *arg_types,
map_var_info_t *arg_names, void **arg_mappers, int32_t depNum,
void *depList, int32_t noAliasDepNum, void *noAliasDepList) {
+ TIMESCOPE();
if (depNum + noAliasDepNum > 0)
__kmpc_omp_taskwait(loc, __kmpc_global_thread_num(loc));
@@ -245,6 +256,7 @@ EXTERN void __tgt_target_data_end_nowait_mapper(
EXTERN void __tgt_target_data_update(int64_t device_id, int32_t arg_num,
void **args_base, void **args, int64_t *arg_sizes, int64_t *arg_types) {
+ TIMESCOPE();
__tgt_target_data_update_mapper(nullptr, device_id, arg_num, args_base, args,
arg_sizes, arg_types, nullptr, nullptr);
}
@@ -253,6 +265,7 @@ EXTERN void __tgt_target_data_update_nowait(int64_t device_id, int32_t arg_num,
void **args_base, void **args, int64_t *arg_sizes, int64_t *arg_types,
int32_t depNum, void *depList, int32_t noAliasDepNum,
void *noAliasDepList) {
+ TIMESCOPE();
if (depNum + noAliasDepNum > 0)
__kmpc_omp_taskwait(NULL, __kmpc_global_thread_num(NULL));
@@ -266,6 +279,7 @@ EXTERN void __tgt_target_data_update_mapper(ident_t *loc, int64_t device_id,
int64_t *arg_types,
map_var_info_t *arg_names,
void **arg_mappers) {
+ TIMESCOPE();
if (IsOffloadDisabled()) return;
DP("Entering data update with %d mappings\n", arg_num);
@@ -291,6 +305,7 @@ EXTERN void __tgt_target_data_update_nowait_mapper(
void **args, int64_t *arg_sizes, int64_t *arg_types,
map_var_info_t *arg_names, void **arg_mappers, int32_t depNum,
void *depList, int32_t noAliasDepNum, void *noAliasDepList) {
+ TIMESCOPE();
if (depNum + noAliasDepNum > 0)
__kmpc_omp_taskwait(loc, __kmpc_global_thread_num(loc));
@@ -300,6 +315,7 @@ EXTERN void __tgt_target_data_update_nowait_mapper(
EXTERN int __tgt_target(int64_t device_id, void *host_ptr, int32_t arg_num,
void **args_base, void **args, int64_t *arg_sizes, int64_t *arg_types) {
+ TIMESCOPE();
return __tgt_target_mapper(nullptr, device_id, host_ptr, arg_num, args_base,
args, arg_sizes, arg_types, nullptr, nullptr);
}
@@ -308,6 +324,7 @@ EXTERN int __tgt_target_nowait(int64_t device_id, void *host_ptr,
int32_t arg_num, void **args_base, void **args, int64_t *arg_sizes,
int64_t *arg_types, int32_t depNum, void *depList, int32_t noAliasDepNum,
void *noAliasDepList) {
+ TIMESCOPE();
if (depNum + noAliasDepNum > 0)
__kmpc_omp_taskwait(NULL, __kmpc_global_thread_num(NULL));
@@ -319,6 +336,7 @@ EXTERN int __tgt_target_mapper(ident_t *loc, int64_t device_id, void *host_ptr,
int32_t arg_num, void **args_base, void **args,
int64_t *arg_sizes, int64_t *arg_types,
map_var_info_t *arg_names, void **arg_mappers) {
+ TIMESCOPE();
if (IsOffloadDisabled()) return OFFLOAD_FAIL;
DP("Entering target region with entry point " DPxMOD " and device Id %"
PRId64 "\n", DPxPTR(host_ptr), device_id);
@@ -353,6 +371,7 @@ EXTERN int __tgt_target_nowait_mapper(
void **args_base, void **args, int64_t *arg_sizes, int64_t *arg_types,
map_var_info_t *arg_names, void **arg_mappers, int32_t depNum,
void *depList, int32_t noAliasDepNum, void *noAliasDepList) {
+ TIMESCOPE();
if (depNum + noAliasDepNum > 0)
__kmpc_omp_taskwait(loc, __kmpc_global_thread_num(loc));
@@ -363,6 +382,7 @@ EXTERN int __tgt_target_nowait_mapper(
EXTERN int __tgt_target_teams(int64_t device_id, void *host_ptr,
int32_t arg_num, void **args_base, void **args, int64_t *arg_sizes,
int64_t *arg_types, int32_t team_num, int32_t thread_limit) {
+ TIMESCOPE();
return __tgt_target_teams_mapper(nullptr, device_id, host_ptr, arg_num,
args_base, args, arg_sizes, arg_types,
nullptr, nullptr, team_num, thread_limit);
@@ -372,6 +392,7 @@ EXTERN int __tgt_target_teams_nowait(int64_t device_id, void *host_ptr,
int32_t arg_num, void **args_base, void **args, int64_t *arg_sizes,
int64_t *arg_types, int32_t team_num, int32_t thread_limit, int32_t depNum,
void *depList, int32_t noAliasDepNum, void *noAliasDepList) {
+ TIMESCOPE();
if (depNum + noAliasDepNum > 0)
__kmpc_omp_taskwait(NULL, __kmpc_global_thread_num(NULL));
@@ -387,6 +408,7 @@ EXTERN int __tgt_target_teams_mapper(ident_t *loc, int64_t device_id,
map_var_info_t *arg_names,
void **arg_mappers, int32_t team_num,
int32_t thread_limit) {
+ TIMESCOPE();
if (IsOffloadDisabled()) return OFFLOAD_FAIL;
DP("Entering target region with entry point " DPxMOD " and device Id %"
PRId64 "\n", DPxPTR(host_ptr), device_id);
@@ -424,6 +446,7 @@ EXTERN int __tgt_target_teams_nowait_mapper(
map_var_info_t *arg_names, void **arg_mappers, int32_t team_num,
int32_t thread_limit, int32_t depNum, void *depList, int32_t noAliasDepNum,
void *noAliasDepList) {
+ TIMESCOPE();
if (depNum + noAliasDepNum > 0)
__kmpc_omp_taskwait(loc, __kmpc_global_thread_num(loc));
@@ -434,6 +457,7 @@ EXTERN int __tgt_target_teams_nowait_mapper(
// Get the current number of components for a user-defined mapper.
EXTERN int64_t __tgt_mapper_num_components(void *rt_mapper_handle) {
+ TIMESCOPE();
auto *MapperComponentsPtr = (struct MapperComponentsTy *)rt_mapper_handle;
int64_t size = MapperComponentsPtr->Components.size();
DP("__tgt_mapper_num_components(Handle=" DPxMOD ") returns %" PRId64 "\n",
@@ -445,6 +469,7 @@ EXTERN int64_t __tgt_mapper_num_components(void *rt_mapper_handle) {
EXTERN void __tgt_push_mapper_component(void *rt_mapper_handle, void *base,
void *begin, int64_t size,
int64_t type) {
+ TIMESCOPE();
DP("__tgt_push_mapper_component(Handle=" DPxMOD
") adds an entry (Base=" DPxMOD ", Begin=" DPxMOD ", Size=%" PRId64
", Type=0x%" PRIx64 ").\n",
@@ -456,6 +481,7 @@ EXTERN void __tgt_push_mapper_component(void *rt_mapper_handle, void *base,
EXTERN void __kmpc_push_target_tripcount(ident_t *loc, int64_t device_id,
uint64_t loop_tripcount) {
+ TIMESCOPE();
if (IsOffloadDisabled())
return;
diff --git a/openmp/libomptarget/src/private.h b/openmp/libomptarget/src/private.h
index 640226a57c30..a494e1ddb043 100644
--- a/openmp/libomptarget/src/private.h
+++ b/openmp/libomptarget/src/private.h
@@ -107,4 +107,11 @@ static inline void dumpTargetPointerMappings(const DeviceTy &Device) {
}
}
+#ifdef OMPTARGET_PROFILE_ENABLED
+#include "llvm/Support/TimeProfiler.h"
+#define TIMESCOPE() llvm::TimeTraceScope TimeScope(__FUNCTION__)
+#else
+#define TIMESCOPE()
+#endif
+
#endif
diff --git a/openmp/libomptarget/src/rtl.cpp b/openmp/libomptarget/src/rtl.cpp
index b05e8e916e08..d8ed5d2da1c6 100644
--- a/openmp/libomptarget/src/rtl.cpp
+++ b/openmp/libomptarget/src/rtl.cpp
@@ -33,14 +33,35 @@ static const char *RTLNames[] = {
PluginManager *PM;
+#if OMPTARGET_PROFILE_ENABLED
+static char *ProfileTraceFile = nullptr;
+#endif
+
__attribute__((constructor(101))) void init() {
DP("Init target library!\n");
PM = new PluginManager();
+
+#ifdef OMPTARGET_PROFILE_ENABLED
+ ProfileTraceFile = getenv("LIBOMPTARGET_PROFILE");
+ // TODO: add a configuration option for time granularity
+ if (ProfileTraceFile)
+ llvm::timeTraceProfilerInitialize(500 /* us */, "libomptarget");
+#endif
}
__attribute__((destructor(101))) void deinit() {
DP("Deinit target library!\n");
delete PM;
+
+#ifdef OMPTARGET_PROFILE_ENABLED
+ if (ProfileTraceFile) {
+ // TODO: add env var for file output
+ if (auto E = llvm::timeTraceProfilerWrite(ProfileTraceFile, "-"))
+ fprintf(stderr, "Error writing out the time trace\n");
+
+ llvm::timeTraceProfilerCleanup();
+ }
+#endif
}
void RTLsTy::LoadRTLs() {
More information about the llvm-branch-commits
mailing list