[OpenMP] Add LoongArch64 support

GCC, glibc, binutils, and LLVM have added support for LoongArch64.
This patch adds support for LLVM OpenMP following D59880 for RISCV64.

Reviewed By: MaskRay, SixWeining

Differential Revision: https://reviews.llvm.org/D132925

openmp/README.rst

@@ -137,7 +137,7 @@ Options for all Libraries
 Options for ``libomp``
 ----------------------
 
-**LIBOMP_ARCH** = ``aarch64|arm|i386|mic|mips|mips64|ppc64|ppc64le|x86_64|riscv64``
+**LIBOMP_ARCH** = ``aarch64|arm|i386|loongarch64|mic|mips|mips64|ppc64|ppc64le|x86_64|riscv64``
   The default value for this option is chosen based on probing the compiler for
   architecture macros (e.g., is ``__x86_64__`` predefined by compiler?).
 
@@ -194,7 +194,7 @@ 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 and RISCV64 on Linux* and macOS*.
+  PPC64, RISCV64 and LoongArch64 on Linux* and macOS*.
   This option is ``OFF`` if this feature is not supported for the platform.
 
 **LIBOMP_OMPT_OPTIONAL** = ``ON|OFF``

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).")
+    "The architecture to build for (x86_64/i386/arm/ppc64/ppc64le/aarch64/mic/mips/mips64/riscv64/loongarch64).")
   # Should assertions be enabled?  They are on by default.
   set(LIBOMP_ENABLE_ASSERTIONS TRUE CACHE BOOL
     "enable assertions?")
@@ -61,6 +61,8 @@ else() # Part of LLVM build
     set(LIBOMP_ARCH arm)
   elseif(LIBOMP_NATIVE_ARCH MATCHES "riscv64")
     set(LIBOMP_ARCH riscv64)
+  elseif(LIBOMP_NATIVE_ARCH MATCHES "loongarch64")
+    set(LIBOMP_ARCH loongarch64)
   else()
     # last ditch effort
     libomp_get_architecture(LIBOMP_ARCH)
@@ -81,7 +83,7 @@ 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)
+libomp_check_variable(LIBOMP_ARCH 32e x86_64 32 i386 arm ppc64 ppc64le aarch64 aarch64_a64fx mic mips mips64 riscv64 loongarch64)
 
 set(LIBOMP_LIB_TYPE normal CACHE STRING
   "Performance,Profiling,Stubs library (normal/profile/stubs)")
@@ -159,6 +161,7 @@ set(MIC FALSE)
 set(MIPS64 FALSE)
 set(MIPS FALSE)
 set(RISCV64 FALSE)
+set(LOONGARCH64 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
@@ -181,8 +184,10 @@ elseif("${LIBOMP_ARCH}" STREQUAL "mips") # MIPS architecture
     set(MIPS TRUE)
 elseif("${LIBOMP_ARCH}" STREQUAL "mips64") # MIPS64 architecture
     set(MIPS64 TRUE)
-  elseif("${LIBOMP_ARCH}" STREQUAL "riscv64") # RISCV64 architecture
+elseif("${LIBOMP_ARCH}" STREQUAL "riscv64") # RISCV64 architecture
     set(RISCV64 TRUE)
+elseif("${LIBOMP_ARCH}" STREQUAL "loongarch64") # LoongArch64 architecture
+    set(LOONGARCH64 TRUE)
 endif()
 
 # Set some flags based on build_type

openmp/runtime/README.txt

@@ -54,6 +54,7 @@ Architectures Supported
 * IBM(R) Power architecture (little endian)
 * MIPS and MIPS64 architecture
 * RISCV64 architecture
+* LoongArch64 architecture
 
 Supported RTL Build Configurations
 ==================================

openmp/runtime/cmake/LibompGetArchitecture.cmake

@@ -47,6 +47,8 @@ function(libomp_get_architecture return_arch)
       #error ARCHITECTURE=mips
     #elif defined(__riscv) && __riscv_xlen == 64
       #error ARCHITECTURE=riscv64
+    #elif defined(__loongarch__) && __loongarch_grlen == 64
+      #error ARCHITECTURE=loongarch64
     #else
       #error ARCHITECTURE=UnknownArchitecture
     #endif

openmp/runtime/cmake/LibompMicroTests.cmake

@@ -214,6 +214,9 @@ else()
     elseif(${RISCV64})
       libomp_append(libomp_expected_library_deps libc.so.6)
       libomp_append(libomp_expected_library_deps ld.so.1)
+    elseif(${LOONGARCH64})
+      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

@@ -109,6 +109,8 @@ function(libomp_get_legal_arch return_arch_string)
     set(${return_arch_string} "MIPS64" PARENT_SCOPE)
   elseif(${RISCV64})
     set(${return_arch_string} "RISCV64" PARENT_SCOPE)
+  elseif(${LOONGARCH64})
+    set(${return_arch_string} "LOONGARCH64" PARENT_SCOPE)
   else()
     set(${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

@@ -321,7 +321,8 @@ else()
       (LIBOMP_ARCH STREQUAL aarch64_a64fx) OR
       (LIBOMP_ARCH STREQUAL ppc64le) OR
       (LIBOMP_ARCH STREQUAL ppc64) OR
-      (LIBOMP_ARCH STREQUAL riscv64))
+      (LIBOMP_ARCH STREQUAL riscv64) OR
+      (LIBOMP_ARCH STREQUAL loongarch64))
      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_os.h

@@ -178,7 +178,7 @@ 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_MIPS64 || KMP_ARCH_RISCV64 || KMP_ARCH_LOONGARCH64
 #define KMP_SIZE_T_SPEC KMP_UINT64_SPEC
 #else
 #error "Can't determine size_t printf format specifier."
@@ -1044,7 +1044,7 @@ 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_MIPS64 || KMP_ARCH_RISCV64 || KMP_ARCH_LOONGARCH64
 #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

@@ -92,6 +92,7 @@
 #define KMP_ARCH_MIPS 0
 #define KMP_ARCH_MIPS64 0
 #define KMP_ARCH_RISCV64 0
+#define KMP_ARCH_LOONGARCH64 0
 
 #if KMP_OS_WINDOWS
 #if defined(_M_AMD64) || defined(__x86_64)
@@ -135,6 +136,9 @@
 #elif defined __riscv && __riscv_xlen == 64
 #undef KMP_ARCH_RISCV64
 #define KMP_ARCH_RISCV64 1
+#elif defined __loongarch__ && __loongarch_grlen == 64
+#undef KMP_ARCH_LOONGARCH64
+#define KMP_ARCH_LOONGARCH64 1
 #endif
 #endif
 
@@ -199,7 +203,7 @@
 // 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_RISCV64 + KMP_ARCH_LOONGARCH64)
 #error Unknown or unsupported architecture
 #endif
 

openmp/runtime/src/kmp_runtime.cpp

@@ -8756,7 +8756,7 @@ __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_MIPS64 || KMP_ARCH_RISCV64 || KMP_ARCH_LOONGARCH64
 
 #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/z_Linux_asm.S

@@ -1725,6 +1725,164 @@ __kmp_invoke_microtask:
 
 #endif /* KMP_ARCH_RISCV64 */
 
+#if KMP_ARCH_LOONGARCH64
+
+//------------------------------------------------------------------------
+//
+// typedef void (*microtask_t)(int *gtid, int *tid, ...);
+//
+// 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
+//
+//   (*pkfn)(&gtid, &tid, argv[0], ...);
+//
+//   return 1;
+// }
+//
+// Parameters:
+//   a0: pkfn
+//   a1: gtid
+//   a2: tid
+//   a3: argc
+//   a4: p_argv
+//   a5: exit_frame_ptr
+//
+// Locals:
+//   __gtid: gtid param pushed on stack so can pass &gtid to pkfn
+//   __tid: tid param pushed on stack so can pass &tid to pkfn
+//
+// Temp registers:
+//
+//  t0: used to calculate the dynamic stack size / used to hold pkfn address
+//  t1: used as temporary for stack placement calculation
+//  t2: used as temporary for stack arguments
+//  t3: used as temporary for number of remaining pkfn parms
+//  t4: used to traverse p_argv array
+//
+// return: a0 (always 1/TRUE)
+//
+
+// -- Begin __kmp_invoke_microtask
+// mark_begin;
+	.text
+	.globl	__kmp_invoke_microtask
+	.p2align	2
+	.type	__kmp_invoke_microtask,@function
+__kmp_invoke_microtask:
+	.cfi_startproc
+
+	// First, save ra and fp
+	addi.d	$sp, $sp, -16
+	st.d	$ra, $sp, 8
+	st.d	$fp, $sp, 0
+	addi.d	$fp, $sp, 16
+	.cfi_def_cfa	22, 0
+	.cfi_offset	1, -8
+	.cfi_offset	22, -16
+
+	// Compute the dynamic stack size:
+	//
+	// - We need 8 bytes for storing 'gtid' and 'tid', so we can pass them by
+	//   reference
+	// - We need 8 bytes for each argument that cannot be passed to the 'pkfn'
+	//   function by register. Given that we have 8 of such registers (a[0-7])
+	//   and two + 'argc' arguments (consider &gtid and &tid), we need to
+	//   reserve max(0, argc - 6)*8 extra bytes
+	//
+	// The total number of bytes is then max(0, argc - 6)*8 + 8
+
+	addi.d  $t0, $a3, -6
+	slt  $t1, $t0, $zero
+	masknez  $t0, $t0, $t1
+	addi.d  $t0, $t0, 1
+	slli.d	$t0, $t0, 3
+	sub.d	$sp, $sp, $t0
+
+	// Align the stack to 16 bytes
+	bstrins.d $sp, $zero, 3, 0
+
+	move	$t0, $a0
+	move	$t3, $a3
+	move	$t4, $a4
+
+#if OMPT_SUPPORT
+	// Save frame pointer into exit_frame
+	st.d	$fp, $a5, 0
+#endif
+
+	// Prepare arguments for the pkfn function (first 8 using a0-a7 registers)
+
+	st.w	$a1, $fp, -20
+	st.w	$a2, $fp, -24
+
+	addi.d	$a0, $fp, -20
+	addi.d	$a1, $fp, -24
+
+	beqz	$t3, .L_kmp_3
+	ld.d	$a2, $t4, 0
+
+	addi.d	$t3, $t3, -1
+	beqz	$t3, .L_kmp_3
+	ld.d	$a3, $t4, 8
+
+	addi.d	$t3, $t3, -1
+	beqz	$t3, .L_kmp_3
+	ld.d	$a4, $t4, 16
+
+	addi.d	$t3, $t3, -1
+	beqz	$t3, .L_kmp_3
+	ld.d	$a5, $t4, 24
+
+	addi.d	$t3, $t3, -1
+	beqz	$t3, .L_kmp_3
+	ld.d	$a6, $t4, 32
+
+	addi.d	$t3, $t3, -1
+	beqz	$t3, .L_kmp_3
+	ld.d	$a7, $t4, 40
+
+	// Prepare any additional argument passed through the stack
+	addi.d	$t4, $t4, 48
+	move	$t1, $sp
+	b .L_kmp_2
+.L_kmp_1:
+	ld.d	$t2, $t4, 0
+	st.d	$t2, $t1, 0
+	addi.d	$t4, $t4, 8
+	addi.d	$t1, $t1, 8
+.L_kmp_2:
+	addi.d	$t3, $t3, -1
+	bnez	$t3, .L_kmp_1
+
+.L_kmp_3:
+	// Call pkfn function
+	jirl	$ra, $t0, 0
+
+	// Restore stack and return
+
+	addi.d	$a0, $zero, 1
+
+	addi.d	$sp, $fp, -16
+	ld.d	$fp, $sp, 0
+	ld.d	$ra, $sp, 8
+	addi.d	$sp, $sp, 16
+	jr $ra
+.Lfunc_end0:
+	.size	__kmp_invoke_microtask, .Lfunc_end0-__kmp_invoke_microtask
+	.cfi_endproc
+
+// -- End  __kmp_invoke_microtask
+
+#endif /* KMP_ARCH_LOONGARCH64 */
+
 #if KMP_ARCH_ARM || KMP_ARCH_MIPS
     .data
     .comm .gomp_critical_user_,32,8
@@ -1736,7 +1894,7 @@ __kmp_unnamed_critical_addr:
     .size __kmp_unnamed_critical_addr,4
 #endif /* KMP_ARCH_ARM */
 
-#if KMP_ARCH_PPC64 || KMP_ARCH_AARCH64 || KMP_ARCH_MIPS64 || KMP_ARCH_RISCV64
+#if KMP_ARCH_PPC64 || KMP_ARCH_AARCH64 || KMP_ARCH_MIPS64 || KMP_ARCH_RISCV64 || KMP_ARCH_LOONGARCH64
 #ifndef KMP_PREFIX_UNDERSCORE
 # define KMP_PREFIX_UNDERSCORE(x) x
 #endif
@@ -1751,7 +1909,7 @@ KMP_PREFIX_UNDERSCORE(__kmp_unnamed_critical_addr):
     .size KMP_PREFIX_UNDERSCORE(__kmp_unnamed_critical_addr),8
 #endif
 #endif /* KMP_ARCH_PPC64 || KMP_ARCH_AARCH64 || KMP_ARCH_MIPS64 ||
-          KMP_ARCH_RISCV64 */
+          KMP_ARCH_RISCV64 || KMP_ARCH_LOONGARCH64 */
 
 #if KMP_OS_LINUX
 # if KMP_ARCH_ARM

openmp/runtime/src/z_Linux_util.cpp

@@ -2440,7 +2440,7 @@ finish: // Clean up and exit.
 
 #if !(KMP_ARCH_X86 || KMP_ARCH_X86_64 || KMP_MIC ||                            \
       ((KMP_OS_LINUX || KMP_OS_DARWIN) && KMP_ARCH_AARCH64) ||                 \
-      KMP_ARCH_PPC64 || KMP_ARCH_RISCV64)
+      KMP_ARCH_PPC64 || KMP_ARCH_RISCV64 || KMP_ARCH_LOONGARCH64)
 
 // we really only need the case with 1 argument, because CLANG always build
 // a struct of pointers to shared variables referenced in the outlined function

openmp/runtime/test/ompt/callback.h

@@ -207,6 +207,13 @@ ompt_label_##id:
   printf("%" PRIu64 ": current_address=%p or %p\n", \
          ompt_get_thread_data()->value, ((char *)addr) - 8, ((char *)addr) - 12)
 #endif
+#elif KMP_ARCH_LOONGARCH64
+// On LoongArch64 the NOP instruction is 4 bytes long, can be followed by
+// inserted jump instruction (another 4 bytes long).
+#define print_possible_return_addresses(addr)                                  \
+  printf("%" PRIu64 ": current_address=%p or %p\n",                            \
+         ompt_get_thread_data()->value, ((char *)addr) - 4,                    \
+         ((char *)addr) - 8)
 #else
 #error Unsupported target architecture, cannot determine address offset!
 #endif

openmp/runtime/tools/lib/Platform.pm

@@ -63,6 +63,8 @@ sub canon_arch($) {
             $arch = "mips";
         } elsif ( $arch =~ m{\Ariscv64} ) {
             $arch = "riscv64";
+        } elsif ( $arch =~ m{\Aloongarch64} ) {
+            $arch = "loongarch64";
         } else {
             $arch = undef;
         }; # if
@@ -93,6 +95,7 @@ sub canon_mic_arch($) {
         "32e" => "Intel(R) 64",
         "arm" => "ARM",
         "aarch64" => "AArch64",
+        "loongarch64" => "LoongArch64",
         "mic" => "Intel(R) Many Integrated Core Architecture",
         "mips" => "MIPS",
         "mips64" => "MIPS64",
@@ -225,6 +228,8 @@ sub target_options() {
         $_host_arch = "mips";
     } elsif ( $hardware_platform eq "riscv64" ) {
         $_host_arch = "riscv64";
+    } elsif ( $hardware_platform eq "loongarch64" ) {
+        $_host_arch = "loongarch64";
     } else {
         die "Unsupported host hardware platform: \"$hardware_platform\"; stopped";
     }; # if
@@ -414,7 +419,7 @@ the script assumes host architecture is target one.
 
 Input string is an architecture name to canonize. The function recognizes many variants, for example:
 C<32e>, C<Intel64>, C<Intel(R) 64>, etc. Returned string is a canonized architecture name,
-one of: C<32>, C<32e>, C<64>, C<arm>, C<ppc64le>, C<ppc64>, C<mic>, C<mips>, C<mips64>, C<riscv64> or C<undef> is input string is not recognized.
+one of: C<32>, C<32e>, C<64>, C<arm>, C<ppc64le>, C<ppc64>, C<mic>, C<mips>, C<mips64>, C<riscv64>, C<loongarch64> or C<undef> is input string is not recognized.
 
 =item B<legal_arch( $arch )>
 

openmp/runtime/tools/lib/Uname.pm

@@ -158,6 +158,8 @@ if ( 0 ) {
         $values{ hardware_platform } = "mips";
     } elsif ( $values{ machine } =~ m{\Ariscv64\z} ) {
         $values{ hardware_platform } = "riscv64";
+    } elsif ( $values{ machine } =~ m{\Aloongarch64\z} ) {
+        $values{ hardware_platform } = "loongarch64";
     } else {
         die "Unsupported machine (\"$values{ machine }\") returned by POSIX::uname(); stopped";
     }; # if