[openmp] Support building for armv7 Windows with mingw tools

This does things in the same way as
D137168 / a356782 and
D101173 / 4fb0aaf did for aarch64.

This adds a C implementation of __kmp_invoke_microtask in the same
way as the fallback C implementation in z_Linux_util.cpp.

Both the existing C fallback used on arm linux, and this one added here,
fail test/misc_bugs/many-microtask-args.c similarly (which could be
considered as an XFAIL).

Differential Revision: https://reviews.llvm.org/D138689

openmp/runtime/src/kmp.h

@@ -3616,7 +3616,7 @@ extern void __kmp_check_stack_overlap(kmp_info_t *thr);
 extern void __kmp_expand_host_name(char *buffer, size_t size);
 extern void __kmp_expand_file_name(char *result, size_t rlen, char *pattern);
 
-#if KMP_ARCH_X86 || KMP_ARCH_X86_64 || (KMP_OS_WINDOWS && KMP_ARCH_AARCH64)
+#if KMP_ARCH_X86 || KMP_ARCH_X86_64 || (KMP_OS_WINDOWS && (KMP_ARCH_AARCH64 || KMP_ARCH_ARM))
 extern void
 __kmp_initialize_system_tick(void); /* Initialize timer tick value */
 #endif

openmp/runtime/src/kmp_atomic.cpp

@@ -832,7 +832,7 @@ static inline kmp_cmplx128_a16_t operator/(kmp_cmplx128_a16_t &lhs,
 // end of the first part of the workaround for C78287
 #endif // USE_CMPXCHG_FIX
 
-#if KMP_OS_WINDOWS && KMP_ARCH_AARCH64
+#if KMP_OS_WINDOWS && (KMP_ARCH_AARCH64 || KMP_ARCH_ARM)
 // Undo explicit type casts to get MSVC ARM64 to build. Uses
 // OP_CMPXCHG_WORKAROUND definition for OP_CMPXCHG
 #undef OP_CMPXCHG
@@ -863,7 +863,7 @@ static inline kmp_cmplx128_a16_t operator/(kmp_cmplx128_a16_t &lhs,
   (*lhs) = (*lhs)OP rhs;                                                       \
   __kmp_release_atomic_lock(&ATOMIC_LOCK##LCK_ID, gtid);
 
-#endif // KMP_OS_WINDOWS && KMP_ARCH_AARCH64
+#endif // KMP_OS_WINDOWS && (KMP_ARCH_AARCH64 || KMP_ARCH_ARM)
 
 #if KMP_ARCH_X86 || KMP_ARCH_X86_64
 

openmp/runtime/src/kmp_os.h

@@ -184,7 +184,7 @@ typedef unsigned long long kmp_uint64;
 #error "Can't determine size_t printf format specifier."
 #endif
 
-#if KMP_ARCH_X86
+#if KMP_ARCH_X86 || KMP_ARCH_ARM
 #define KMP_SIZE_T_MAX (0xFFFFFFFF)
 #else
 #define KMP_SIZE_T_MAX (0xFFFFFFFFFFFFFFFF)
@@ -456,7 +456,7 @@ enum kmp_mem_fence_type {
 
 // Synchronization primitives
 
-#if KMP_ASM_INTRINS && KMP_OS_WINDOWS && !(KMP_ARCH_AARCH64 && defined(__GNUC__))
+#if KMP_ASM_INTRINS && KMP_OS_WINDOWS && !((KMP_ARCH_AARCH64 || KMP_ARCH_ARM) && defined(__GNUC__))
 
 #if KMP_MSVC_COMPAT && !KMP_COMPILER_CLANG
 #pragma intrinsic(InterlockedExchangeAdd)

openmp/runtime/src/kmp_platform.h

@@ -101,6 +101,9 @@
 #elif defined(__aarch64__) || defined(_M_ARM64)
 #undef KMP_ARCH_AARCH64
 #define KMP_ARCH_AARCH64 1
+#elif defined(__arm__) || defined(_M_ARM)
+#undef KMP_ARCH_ARMV7
+#define KMP_ARCH_ARMV7 1
 #else
 #undef KMP_ARCH_X86
 #define KMP_ARCH_X86 1

openmp/runtime/src/z_Windows_NT-586_util.cpp

@@ -12,7 +12,7 @@
 
 #include "kmp.h"
 
-#if (KMP_ARCH_X86 || KMP_ARCH_X86_64 || KMP_ARCH_AARCH64)
+#if (KMP_ARCH_X86 || KMP_ARCH_X86_64 || KMP_ARCH_AARCH64 || KMP_ARCH_ARM)
 /* Only 32-bit "add-exchange" instruction on IA-32 architecture causes us to
    use compare_and_store for these routines */
 
@@ -189,4 +189,95 @@ int __kmp_invoke_microtask(microtask_t pkfn, int gtid, int tid, int argc,
 }
 #endif
 
-#endif /* KMP_ARCH_X86 || KMP_ARCH_X86_64 || KMP_ARCH_AARCH64 */
+#if KMP_ARCH_ARM
+// This matches the generic fallback implementation of __kmp_invoke_microtask
+// from z_Linux_util.cpp, which is used on Linux on ARM.
+int __kmp_invoke_microtask(microtask_t pkfn, int gtid, int tid, int argc,
+                           void *p_argv[]
+#if OMPT_SUPPORT
+                           ,
+                           void **exit_frame_ptr
+#endif
+) {
+#if OMPT_SUPPORT
+  *exit_frame_ptr = OMPT_GET_FRAME_ADDRESS(0);
+#endif
+
+  switch (argc) {
+  default:
+    fprintf(stderr, "Too many args to microtask: %d!\n", argc);
+    fflush(stderr);
+    exit(-1);
+  case 0:
+    (*pkfn)(&gtid, &tid);
+    break;
+  case 1:
+    (*pkfn)(&gtid, &tid, p_argv[0]);
+    break;
+  case 2:
+    (*pkfn)(&gtid, &tid, p_argv[0], p_argv[1]);
+    break;
+  case 3:
+    (*pkfn)(&gtid, &tid, p_argv[0], p_argv[1], p_argv[2]);
+    break;
+  case 4:
+    (*pkfn)(&gtid, &tid, p_argv[0], p_argv[1], p_argv[2], p_argv[3]);
+    break;
+  case 5:
+    (*pkfn)(&gtid, &tid, p_argv[0], p_argv[1], p_argv[2], p_argv[3], p_argv[4]);
+    break;
+  case 6:
+    (*pkfn)(&gtid, &tid, p_argv[0], p_argv[1], p_argv[2], p_argv[3], p_argv[4],
+            p_argv[5]);
+    break;
+  case 7:
+    (*pkfn)(&gtid, &tid, p_argv[0], p_argv[1], p_argv[2], p_argv[3], p_argv[4],
+            p_argv[5], p_argv[6]);
+    break;
+  case 8:
+    (*pkfn)(&gtid, &tid, p_argv[0], p_argv[1], p_argv[2], p_argv[3], p_argv[4],
+            p_argv[5], p_argv[6], p_argv[7]);
+    break;
+  case 9:
+    (*pkfn)(&gtid, &tid, p_argv[0], p_argv[1], p_argv[2], p_argv[3], p_argv[4],
+            p_argv[5], p_argv[6], p_argv[7], p_argv[8]);
+    break;
+  case 10:
+    (*pkfn)(&gtid, &tid, p_argv[0], p_argv[1], p_argv[2], p_argv[3], p_argv[4],
+            p_argv[5], p_argv[6], p_argv[7], p_argv[8], p_argv[9]);
+    break;
+  case 11:
+    (*pkfn)(&gtid, &tid, p_argv[0], p_argv[1], p_argv[2], p_argv[3], p_argv[4],
+            p_argv[5], p_argv[6], p_argv[7], p_argv[8], p_argv[9], p_argv[10]);
+    break;
+  case 12:
+    (*pkfn)(&gtid, &tid, p_argv[0], p_argv[1], p_argv[2], p_argv[3], p_argv[4],
+            p_argv[5], p_argv[6], p_argv[7], p_argv[8], p_argv[9], p_argv[10],
+            p_argv[11]);
+    break;
+  case 13:
+    (*pkfn)(&gtid, &tid, p_argv[0], p_argv[1], p_argv[2], p_argv[3], p_argv[4],
+            p_argv[5], p_argv[6], p_argv[7], p_argv[8], p_argv[9], p_argv[10],
+            p_argv[11], p_argv[12]);
+    break;
+  case 14:
+    (*pkfn)(&gtid, &tid, p_argv[0], p_argv[1], p_argv[2], p_argv[3], p_argv[4],
+            p_argv[5], p_argv[6], p_argv[7], p_argv[8], p_argv[9], p_argv[10],
+            p_argv[11], p_argv[12], p_argv[13]);
+    break;
+  case 15:
+    (*pkfn)(&gtid, &tid, p_argv[0], p_argv[1], p_argv[2], p_argv[3], p_argv[4],
+            p_argv[5], p_argv[6], p_argv[7], p_argv[8], p_argv[9], p_argv[10],
+            p_argv[11], p_argv[12], p_argv[13], p_argv[14]);
+    break;
+  }
+
+#if OMPT_SUPPORT
+  *exit_frame_ptr = 0;
+#endif
+
+  return 1;
+}
+#endif
+
+#endif /* KMP_ARCH_X86 || KMP_ARCH_X86_64 || KMP_ARCH_AARCH64 || KMP_ARCH_ARM */

openmp/runtime/src/z_Windows_NT_util.cpp

@@ -78,7 +78,7 @@ struct SYSTEM_THREAD {
 }; // SYSTEM_THREAD
 
 KMP_BUILD_ASSERT(offsetof(SYSTEM_THREAD, KernelTime) == 0);
-#if KMP_ARCH_X86
+#if KMP_ARCH_X86 || KMP_ARCH_ARM
 KMP_BUILD_ASSERT(offsetof(SYSTEM_THREAD, StartAddress) == 28);
 KMP_BUILD_ASSERT(offsetof(SYSTEM_THREAD, State) == 52);
 #else
@@ -108,7 +108,7 @@ typedef SYSTEM_PROCESS_INFORMATION *PSYSTEM_PROCESS_INFORMATION;
 KMP_BUILD_ASSERT(offsetof(SYSTEM_PROCESS_INFORMATION, NextEntryOffset) == 0);
 KMP_BUILD_ASSERT(offsetof(SYSTEM_PROCESS_INFORMATION, CreateTime) == 32);
 KMP_BUILD_ASSERT(offsetof(SYSTEM_PROCESS_INFORMATION, ImageName) == 56);
-#if KMP_ARCH_X86
+#if KMP_ARCH_X86 || KMP_ARCH_ARM
 KMP_BUILD_ASSERT(offsetof(SYSTEM_PROCESS_INFORMATION, ProcessId) == 68);
 KMP_BUILD_ASSERT(offsetof(SYSTEM_PROCESS_INFORMATION, HandleCount) == 76);
 KMP_BUILD_ASSERT(offsetof(SYSTEM_PROCESS_INFORMATION, VMCounters) == 88);