Add openmp support to System z (#66081)

* openmp/README.rst
  - Add s390x to those platforms supported

* openmp/libomptarget/plugins-nextgen/CMakeLists.txt
  - Add s390x subdirectory

* openmp/libomptarget/plugins-nextgen/s390x/CMakeLists.txt
  - Add s390x definitions

* openmp/runtime/CMakeLists.txt
  - Add s390x to those platforms supported

* openmp/runtime/cmake/LibompGetArchitecture.cmake
  - Define s390x ARCHITECTURE

* openmp/runtime/cmake/LibompMicroTests.cmake
  - Add dependencies for System z (aka s390x)

* openmp/runtime/cmake/LibompUtils.cmake
  - Add S390X to the mix

* openmp/runtime/cmake/config-ix.cmake
  - Add s390x as a supported LIPOMP_ARCH

* openmp/runtime/src/kmp_affinity.h
  - Define __NR_sched_[get|set]addinity for s390x

* openmp/runtime/src/kmp_config.h.cmake
  - Define CACHE_LINE for s390x

* openmp/runtime/src/kmp_os.h
  - Add KMP_ARCH_S390X to support checks

* openmp/runtime/src/kmp_platform.h
  - Define KMP_ARCH_S390X

* openmp/runtime/src/kmp_runtime.cpp
  - Generate code when KMP_ARCH_S390X is defined

* openmp/runtime/src/kmp_tasking.cpp
  - Generate code when KMP_ARCH_S390X is defined

* openmp/runtime/src/thirdparty/ittnotify/ittnotify_config.h
  - Define ITT_ARCH_S390X

* openmp/runtime/src/z_Linux_asm.S
  - Instantiate __kmp_invoke_microtask for s390x

* openmp/runtime/src/z_Linux_util.cpp
  - Generate code when KMP_ARCH_S390X is defined

* openmp/runtime/test/ompt/callback.h
  - Define print_possible_return_addresses for s390x

* openmp/runtime/tools/lib/Platform.pm
  - Return s390x as platform and host architecture

* openmp/runtime/tools/lib/Uname.pm
  - Set hardware platform value for s390x

openmp/README.rst

@@ -141,7 +141,7 @@ Options for all Libraries
 Options for ``libomp``
 ----------------------
 
-**LIBOMP_ARCH** = ``aarch64|arm|i386|loongarch64|mic|mips|mips64|ppc64|ppc64le|x86_64|riscv64``
+**LIBOMP_ARCH** = ``aarch64|arm|i386|loongarch64|mic|mips|mips64|ppc64|ppc64le|x86_64|riscv64|s390x``
   The default value for this option is chosen based on probing the compiler for
   architecture macros (e.g., is ``__x86_64__`` predefined by compiler?).
 
@@ -198,7 +198,7 @@ Optional Features
 **LIBOMP_OMPT_SUPPORT** = ``ON|OFF``
   Include support for the OpenMP Tools Interface (OMPT).
   This option is supported and ``ON`` by default for x86, x86_64, AArch64,
-  PPC64, RISCV64 and LoongArch64 on Linux* and macOS*.
+  PPC64, RISCV64, LoongArch64, and s390x on Linux* and macOS*.
   This option is ``OFF`` if this feature is not supported for the platform.
 
 **LIBOMP_OMPT_OPTIONAL** = ``ON|OFF``

openmp/libomptarget/plugins-nextgen/CMakeLists.txt

@@ -96,6 +96,7 @@ add_subdirectory(cuda)
 add_subdirectory(ppc64)
 add_subdirectory(ppc64le)
 add_subdirectory(x86_64)
+add_subdirectory(s390x)
 
 # Make sure the parent scope can see the plugins that will be created.
 set(LIBOMPTARGET_SYSTEM_TARGETS "${LIBOMPTARGET_SYSTEM_TARGETS}" PARENT_SCOPE)

openmp/libomptarget/plugins-nextgen/s390x/CMakeLists.txt

@@ -0,0 +1,17 @@
+##===----------------------------------------------------------------------===##
+#
+# Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+# See https://llvm.org/LICENSE.txt for license information.
+# SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+#
+##===----------------------------------------------------------------------===##
+#
+# Build a plugin for a s390x machine if available.
+#
+##===----------------------------------------------------------------------===##
+
+if(CMAKE_SYSTEM_NAME MATCHES "Linux")
+ build_generic_elf64("SystemZ" "S390X" "s390x" "s390x-ibm-linux-gnu" "22")
+else()
+ libomptarget_say("Not building s390x NextGen offloading plugin: machine not found in the system.")
+endif()

openmp/runtime/CMakeLists.txt

@@ -30,7 +30,7 @@ if(${OPENMP_STANDALONE_BUILD})
   # If adding a new architecture, take a look at cmake/LibompGetArchitecture.cmake
   libomp_get_architecture(LIBOMP_DETECTED_ARCH)
   set(LIBOMP_ARCH ${LIBOMP_DETECTED_ARCH} CACHE STRING
-    "The architecture to build for (x86_64/i386/arm/ppc64/ppc64le/aarch64/mic/mips/mips64/riscv64/loongarch64/ve).")
+    "The architecture to build for (x86_64/i386/arm/ppc64/ppc64le/aarch64/mic/mips/mips64/riscv64/loongarch64/ve/s390x).")
   # Should assertions be enabled?  They are on by default.
   set(LIBOMP_ENABLE_ASSERTIONS TRUE CACHE BOOL
     "enable assertions?")
@@ -65,6 +65,8 @@ else() # Part of LLVM build
     set(LIBOMP_ARCH loongarch64)
   elseif(LIBOMP_NATIVE_ARCH MATCHES "ve")
     set(LIBOMP_ARCH ve)
+  elseif(LIBOMP_NATIVE_ARCH MATCHES "s390x")
+    set(LIBOMP_ARCH s390x)
   else()
     # last ditch effort
     libomp_get_architecture(LIBOMP_ARCH)
@@ -85,7 +87,7 @@ if(LIBOMP_ARCH STREQUAL "aarch64")
   endif()
 endif()
 
-libomp_check_variable(LIBOMP_ARCH 32e x86_64 32 i386 arm ppc64 ppc64le aarch64 aarch64_a64fx mic mips mips64 riscv64 loongarch64 ve)
+libomp_check_variable(LIBOMP_ARCH 32e x86_64 32 i386 arm ppc64 ppc64le aarch64 aarch64_a64fx mic mips mips64 riscv64 loongarch64 ve s390x)
 
 set(LIBOMP_LIB_TYPE normal CACHE STRING
   "Performance,Profiling,Stubs library (normal/profile/stubs)")
@@ -165,6 +167,7 @@ set(MIPS FALSE)
 set(RISCV64 FALSE)
 set(LOONGARCH64 FALSE)
 set(VE FALSE)
+set(S390X FALSE)
 if("${LIBOMP_ARCH}" STREQUAL "i386" OR "${LIBOMP_ARCH}" STREQUAL "32")    # IA-32 architecture
   set(IA32 TRUE)
 elseif("${LIBOMP_ARCH}" STREQUAL "x86_64" OR "${LIBOMP_ARCH}" STREQUAL "32e") # Intel(R) 64 architecture
@@ -193,6 +196,8 @@ elseif("${LIBOMP_ARCH}" STREQUAL "loongarch64") # LoongArch64 architecture
     set(LOONGARCH64 TRUE)
 elseif("${LIBOMP_ARCH}" STREQUAL "ve") # VE architecture
     set(VE TRUE)
+elseif("${LIBOMP_ARCH}" STREQUAL "s390x") # S390x (Z) architecture
+    set(S390X TRUE)
 endif()
 
 # Set some flags based on build_type

openmp/runtime/cmake/LibompGetArchitecture.cmake

@@ -51,6 +51,8 @@ function(libomp_get_architecture return_arch)
       #error ARCHITECTURE=loongarch64
     #elif defined(__ve__)
       #error ARCHITECTURE=ve
+    #elif defined(__s390x__)
+      #error ARCHITECTURE=s390x
     #else
       #error ARCHITECTURE=UnknownArchitecture
     #endif

openmp/runtime/cmake/LibompMicroTests.cmake

@@ -217,6 +217,9 @@ else()
     elseif(${LOONGARCH64})
       libomp_append(libomp_expected_library_deps libc.so.6)
       libomp_append(libomp_expected_library_deps ld.so.1)
+    elseif(${S390X})
+      libomp_append(libomp_expected_library_deps libc.so.6)
+      libomp_append(libomp_expected_library_deps ld.so.1)
     endif()
     libomp_append(libomp_expected_library_deps libpthread.so.0 IF_FALSE STUBS_LIBRARY)
     libomp_append(libomp_expected_library_deps libhwloc.so.5 LIBOMP_USE_HWLOC)

openmp/runtime/cmake/LibompUtils.cmake

@@ -113,6 +113,8 @@ function(libomp_get_legal_arch return_arch_string)
     set(${return_arch_string} "LOONGARCH64" PARENT_SCOPE)
   elseif(${VE})
     set(${return_arch_string} "VE" PARENT_SCOPE)
+  elseif(${S390X})
+    set(${return_arch_string} "S390X" PARENT_SCOPE)
   else()
     set(${return_arch_string} "${LIBOMP_ARCH}" PARENT_SCOPE)
     libomp_warning_say("libomp_get_legal_arch(): Warning: Unknown architecture: Using ${LIBOMP_ARCH}")

openmp/runtime/cmake/config-ix.cmake

@@ -325,7 +325,8 @@ else()
       (LIBOMP_ARCH STREQUAL ppc64le) OR
       (LIBOMP_ARCH STREQUAL ppc64) OR
       (LIBOMP_ARCH STREQUAL riscv64) OR
-      (LIBOMP_ARCH STREQUAL loongarch64))
+      (LIBOMP_ARCH STREQUAL loongarch64) OR
+      (LIBOMP_ARCH STREQUAL s390x))
      AND # OS supported?
      ((WIN32 AND LIBOMP_HAVE_PSAPI) OR APPLE OR (NOT WIN32 AND LIBOMP_HAVE_WEAK_ATTRIBUTE)))
     set(LIBOMP_HAVE_OMPT_SUPPORT TRUE)

openmp/runtime/src/kmp_affinity.cpp

@@ -2990,6 +2990,9 @@ static bool __kmp_affinity_create_cpuinfo_map(int *line,
 
   unsigned num_avail = 0;
   *line = 0;
+#if KMP_ARCH_S390X
+  bool reading_s390x_sys_info = true;
+#endif
   while (!feof(f)) {
     // Create an inner scoping level, so that all the goto targets at the end of
     // the loop appear in an outer scoping level. This avoids warnings about
@@ -3035,8 +3038,21 @@ static bool __kmp_affinity_create_cpuinfo_map(int *line,
       if (*buf == '\n' && *line == 2)
         continue;
 #endif
+#if KMP_ARCH_S390X
+      // s390x /proc/cpuinfo starts with a variable number of lines containing
+      // the overall system information. Skip them.
+      if (reading_s390x_sys_info) {
+        if (*buf == '\n')
+          reading_s390x_sys_info = false;
+        continue;
+      }
+#endif
 
+#if KMP_ARCH_S390X
+      char s1[] = "cpu number";
+#else
       char s1[] = "processor";
+#endif
       if (strncmp(buf, s1, sizeof(s1) - 1) == 0) {
         CHECK_LINE;
         char *p = strchr(buf + sizeof(s1) - 1, ':');
@@ -3062,6 +3078,23 @@ static bool __kmp_affinity_create_cpuinfo_map(int *line,
             threadInfo[num_avail][osIdIndex]);
         __kmp_read_from_file(path, "%u", &threadInfo[num_avail][pkgIdIndex]);
 
+#if KMP_ARCH_S390X
+        // Disambiguate physical_package_id.
+        unsigned book_id;
+        KMP_SNPRINTF(path, sizeof(path),
+                     "/sys/devices/system/cpu/cpu%u/topology/book_id",
+                     threadInfo[num_avail][osIdIndex]);
+        __kmp_read_from_file(path, "%u", &book_id);
+        threadInfo[num_avail][pkgIdIndex] |= (book_id << 8);
+
+        unsigned drawer_id;
+        KMP_SNPRINTF(path, sizeof(path),
+                     "/sys/devices/system/cpu/cpu%u/topology/drawer_id",
+                     threadInfo[num_avail][osIdIndex]);
+        __kmp_read_from_file(path, "%u", &drawer_id);
+        threadInfo[num_avail][pkgIdIndex] |= (drawer_id << 16);
+#endif
+
         KMP_SNPRINTF(path, sizeof(path),
                      "/sys/devices/system/cpu/cpu%u/topology/core_id",
                      threadInfo[num_avail][osIdIndex]);

openmp/runtime/src/kmp_affinity.h

@@ -297,6 +297,17 @@ class KMPHwlocAffinity : public KMPAffinity {
 #elif __NR_sched_getaffinity != 204
 #error Wrong code for getaffinity system call.
 #endif /* __NR_sched_getaffinity */
+#elif KMP_ARCH_S390X
+#ifndef __NR_sched_setaffinity
+#define __NR_sched_setaffinity 239
+#elif __NR_sched_setaffinity != 239
+#error Wrong code for setaffinity system call.
+#endif /* __NR_sched_setaffinity */
+#ifndef __NR_sched_getaffinity
+#define __NR_sched_getaffinity 240
+#elif __NR_sched_getaffinity != 240
+#error Wrong code for getaffinity system call.
+#endif /* __NR_sched_getaffinity */
 #else
 #error Unknown or unsupported architecture
 #endif /* KMP_ARCH_* */

openmp/runtime/src/kmp_config.h.cmake

@@ -104,6 +104,8 @@
 # define CACHE_LINE 128
 #elif KMP_ARCH_AARCH64_A64FX
 # define CACHE_LINE 256
+#elif KMP_ARCH_S390X
+# define CACHE_LINE 256
 #else
 # define CACHE_LINE 64
 #endif

openmp/runtime/src/kmp_os.h

@@ -178,7 +178,8 @@ typedef unsigned long long kmp_uint64;
 #if KMP_ARCH_X86 || KMP_ARCH_ARM || KMP_ARCH_MIPS
 #define KMP_SIZE_T_SPEC KMP_UINT32_SPEC
 #elif KMP_ARCH_X86_64 || KMP_ARCH_PPC64 || KMP_ARCH_AARCH64 ||                 \
-    KMP_ARCH_MIPS64 || KMP_ARCH_RISCV64 || KMP_ARCH_LOONGARCH64 || KMP_ARCH_VE
+    KMP_ARCH_MIPS64 || KMP_ARCH_RISCV64 || KMP_ARCH_LOONGARCH64 ||             \
+    KMP_ARCH_VE || KMP_ARCH_S390X
 #define KMP_SIZE_T_SPEC KMP_UINT64_SPEC
 #else
 #error "Can't determine size_t printf format specifier."
@@ -1043,7 +1044,8 @@ extern kmp_real64 __kmp_xchg_real64(volatile kmp_real64 *p, kmp_real64 v);
 #endif /* KMP_OS_WINDOWS */
 
 #if KMP_ARCH_PPC64 || KMP_ARCH_ARM || KMP_ARCH_AARCH64 || KMP_ARCH_MIPS ||     \
-    KMP_ARCH_MIPS64 || KMP_ARCH_RISCV64 || KMP_ARCH_LOONGARCH64 || KMP_ARCH_VE
+    KMP_ARCH_MIPS64 || KMP_ARCH_RISCV64 || KMP_ARCH_LOONGARCH64 ||             \
+    KMP_ARCH_VE || KMP_ARCH_S390X
 #if KMP_OS_WINDOWS
 #undef KMP_MB
 #define KMP_MB() std::atomic_thread_fence(std::memory_order_seq_cst)

openmp/runtime/src/kmp_platform.h

@@ -101,6 +101,7 @@
 #define KMP_ARCH_RISCV64 0
 #define KMP_ARCH_LOONGARCH64 0
 #define KMP_ARCH_VE 0
+#define KMP_ARCH_S390X 0
 
 #if KMP_OS_WINDOWS
 #if defined(_M_AMD64) || defined(__x86_64)
@@ -153,6 +154,9 @@
 #elif defined __ve__
 #undef KMP_ARCH_VE
 #define KMP_ARCH_VE 1
+#elif defined __s390x__
+#undef KMP_ARCH_S390X
+#define KMP_ARCH_S390X 1
 #endif
 #endif
 
@@ -217,7 +221,8 @@
 // TODO: Fixme - This is clever, but really fugly
 #if (1 != KMP_ARCH_X86 + KMP_ARCH_X86_64 + KMP_ARCH_ARM + KMP_ARCH_PPC64 +     \
               KMP_ARCH_AARCH64 + KMP_ARCH_MIPS + KMP_ARCH_MIPS64 +             \
-              KMP_ARCH_RISCV64 + KMP_ARCH_LOONGARCH64 + KMP_ARCH_VE)
+              KMP_ARCH_RISCV64 + KMP_ARCH_LOONGARCH64 + KMP_ARCH_VE +          \
+              KMP_ARCH_S390X)
 #error Unknown or unsupported architecture
 #endif
 

openmp/runtime/src/kmp_runtime.cpp

@@ -8894,7 +8894,8 @@ __kmp_determine_reduction_method(
     int atomic_available = FAST_REDUCTION_ATOMIC_METHOD_GENERATED;
 
 #if KMP_ARCH_X86_64 || KMP_ARCH_PPC64 || KMP_ARCH_AARCH64 ||                   \
-    KMP_ARCH_MIPS64 || KMP_ARCH_RISCV64 || KMP_ARCH_LOONGARCH64 || KMP_ARCH_VE
+    KMP_ARCH_MIPS64 || KMP_ARCH_RISCV64 || KMP_ARCH_LOONGARCH64 ||             \
+    KMP_ARCH_VE || KMP_ARCH_S390X
 
 #if KMP_OS_LINUX || KMP_OS_DRAGONFLY || KMP_OS_FREEBSD || KMP_OS_NETBSD ||     \
     KMP_OS_OPENBSD || KMP_OS_WINDOWS || KMP_OS_DARWIN || KMP_OS_HURD ||        \

openmp/runtime/src/kmp_tasking.cpp

@@ -1554,7 +1554,7 @@ kmp_task_t *__kmp_task_alloc(ident_t *loc_ref, kmp_int32 gtid,
   task = KMP_TASKDATA_TO_TASK(taskdata);
 
 // Make sure task & taskdata are aligned appropriately
-#if KMP_ARCH_X86 || KMP_ARCH_PPC64 || !KMP_HAVE_QUAD
+#if KMP_ARCH_X86 || KMP_ARCH_PPC64 || KMP_ARCH_S390X || !KMP_HAVE_QUAD
   KMP_DEBUG_ASSERT((((kmp_uintptr_t)taskdata) & (sizeof(double) - 1)) == 0);
   KMP_DEBUG_ASSERT((((kmp_uintptr_t)task) & (sizeof(double) - 1)) == 0);
 #else
@@ -1737,8 +1737,12 @@ __kmpc_omp_reg_task_with_affinity(ident_t *loc_ref, kmp_int32 gtid,
 // gtid: global thread ID of caller
 // task: the task to invoke
 // current_task: the task to resume after task invocation
-static void __kmp_invoke_task(kmp_int32 gtid, kmp_task_t *task,
-                              kmp_taskdata_t *current_task) {
+#ifdef __s390x__
+__attribute__((target("backchain")))
+#endif
+static void
+__kmp_invoke_task(kmp_int32 gtid, kmp_task_t *task,
+                  kmp_taskdata_t *current_task) {
   kmp_taskdata_t *taskdata = KMP_TASK_TO_TASKDATA(task);
   kmp_info_t *thread;
   int discard = 0 /* false */;

openmp/runtime/src/thirdparty/ittnotify/ittnotify_config.h

@@ -166,6 +166,10 @@
 #define ITT_ARCH_VE 8
 #endif /* ITT_ARCH_VE */
 
+#ifndef ITT_ARCH_S390X
+#define ITT_ARCH_S390X 8
+#endif /* ITT_ARCH_S390X */
+
 #ifndef ITT_ARCH
 #if defined _M_IX86 || defined __i386__
 #define ITT_ARCH ITT_ARCH_IA32
@@ -181,6 +185,8 @@
 #define ITT_ARCH ITT_ARCH_PPC64
 #elif defined __ve__
 #define ITT_ARCH ITT_ARCH_VE
+#elif defined __s390x__
+#define ITT_ARCH ITT_ARCH_S390X
 #endif
 #endif