diff --git a/0001-Support-LoongArch.patch b/0001-Support-LoongArch.patch
new file mode 100644
index 0000000000000000000000000000000000000000..e36cfc20b7d19c7e78cb100bad598993a3126b04
--- /dev/null
+++ b/0001-Support-LoongArch.patch
@@ -0,0 +1,773 @@
+diff --git a/openmp/README.rst b/openmp/README.rst
+index 0e4916f44..0daeb3389 100644
+--- a/openmp/README.rst
++++ b/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|s390x``
++**LIBOMP_ARCH** = ``aarch64|arm|i386|mic|mips|mips64|ppc64|ppc64le|x86_64|riscv64|s390x|loongarch64``
+   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, LoongArch64, and s390x 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``
+diff --git a/openmp/runtime/CMakeLists.txt b/openmp/runtime/CMakeLists.txt
+index 041b60efa..0c3d642b8 100644
+--- a/openmp/runtime/CMakeLists.txt
++++ b/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 ${LIBOMP_DETECTED_ARCH} CACHE STRING
+-    "The architecture to build for (x86_64/i386/arm/ppc/ppc64/ppc64le/aarch64/mic/mips/mips64/riscv64/loongarch64/ve/s390x/wasm32).")
++    "The architecture to build for (x86_64/i386/arm/ppc/ppc64/ppc64le/aarch64/mic/mips/mips64/riscv64/ve/s390x/wasm32/loongarch64).")
+   # Should assertions be enabled?  They are on by default.
+   set(LIBOMP_ENABLE_ASSERTIONS TRUE CACHE BOOL
+     "enable assertions?")
+@@ -63,14 +63,14 @@ else() # Part of LLVM build
+     set(LIBOMP_ARCH arm)
+   elseif(LIBOMP_NATIVE_ARCH MATCHES "riscv64")
+     set(LIBOMP_ARCH riscv64)
+-  elseif(LIBOMP_NATIVE_ARCH MATCHES "loongarch64")
+-    set(LIBOMP_ARCH loongarch64)
+   elseif(LIBOMP_NATIVE_ARCH MATCHES "ve")
+     set(LIBOMP_ARCH ve)
+   elseif(LIBOMP_NATIVE_ARCH MATCHES "s390x")
+     set(LIBOMP_ARCH s390x)
+   elseif(LIBOMP_NATIVE_ARCH MATCHES "wasm")
+     set(LIBOMP_ARCH wasm32)
++  elseif(LIBOMP_NATIVE_ARCH MATCHES "loongarch64")
++    set(LIBOMP_ARCH loongarch64)
+   else()
+     # last ditch effort
+     libomp_get_architecture(LIBOMP_ARCH)
+@@ -91,7 +91,7 @@ if(LIBOMP_ARCH STREQUAL "aarch64")
+   endif()
+ endif()
+ 
+-libomp_check_variable(LIBOMP_ARCH 32e x86_64 32 i386 arm ppc ppc64 ppc64le aarch64 aarch64_a64fx mic mips mips64 riscv64 loongarch64 ve s390x wasm32)
++libomp_check_variable(LIBOMP_ARCH 32e x86_64 32 i386 arm ppc ppc64 ppc64le aarch64 aarch64_a64fx mic mips mips64 riscv64 ve s390x wasm32 loongarch64)
+ 
+ set(LIBOMP_LIB_TYPE normal CACHE STRING
+   "Performance,Profiling,Stubs library (normal/profile/stubs)")
+@@ -175,11 +175,11 @@ set(MIC FALSE)
+ set(MIPS64 FALSE)
+ set(MIPS FALSE)
+ set(RISCV64 FALSE)
+-set(LOONGARCH64 FALSE)
+ set(VE FALSE)
+ set(S390X FALSE)
+ set(WASM FALSE)
+ set(PPC FALSE)
++set(LoongArch64 FALSE)
+ if("${LIBOMP_ARCH}" STREQUAL "i386" OR "${LIBOMP_ARCH}" STREQUAL "32")    # IA-32 architecture
+   set(IA32 TRUE)
+ elseif("${LIBOMP_ARCH}" STREQUAL "x86_64" OR "${LIBOMP_ARCH}" STREQUAL "32e") # Intel(R) 64 architecture
+@@ -206,14 +206,14 @@ elseif("${LIBOMP_ARCH}" STREQUAL "mips64") # MIPS64 architecture
+     set(MIPS64 TRUE)
+ elseif("${LIBOMP_ARCH}" STREQUAL "riscv64") # RISCV64 architecture
+     set(RISCV64 TRUE)
+-elseif("${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)
+ elseif("${LIBOMP_ARCH}" STREQUAL "wasm32") # WebAssembly architecture
+     set(WASM TRUE)
++elseif("${LIBOMP_ARCH}" STREQUAL "loongarch64") # LoongArch64 architecture
++    set(LoongArch64 TRUE)
+ endif()
+ 
+ # Set some flags based on build_type
+diff --git a/openmp/runtime/cmake/LibompGetArchitecture.cmake b/openmp/runtime/cmake/LibompGetArchitecture.cmake
+index d7f81870f..8667b1154 100644
+--- a/openmp/runtime/cmake/LibompGetArchitecture.cmake
++++ b/openmp/runtime/cmake/LibompGetArchitecture.cmake
+@@ -49,14 +49,14 @@ 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
+     #elif defined(__ve__)
+       #error ARCHITECTURE=ve
+     #elif defined(__s390x__)
+       #error ARCHITECTURE=s390x
+     #elif defined(__wasm32__)
+       #error ARCHITECTURE=wasm32
++    #elif defined(__loongarch__) && defined(__loongarch64)
++      #error ARCHITECTURE=loongarch64
+     #else
+       #error ARCHITECTURE=UnknownArchitecture
+     #endif
+diff --git a/openmp/runtime/cmake/LibompMicroTests.cmake b/openmp/runtime/cmake/LibompMicroTests.cmake
+index e8cc218af..a15b330b5 100644
+--- a/openmp/runtime/cmake/LibompMicroTests.cmake
++++ b/openmp/runtime/cmake/LibompMicroTests.cmake
+@@ -214,10 +214,10 @@ else()
+     elseif(${RISCV64})
+       libomp_append(libomp_expected_library_deps libc.so.6)
+       libomp_append(libomp_expected_library_deps ld.so.1)
+-    elseif(${LOONGARCH64})
++    elseif(${S390X})
+       libomp_append(libomp_expected_library_deps libc.so.6)
+       libomp_append(libomp_expected_library_deps ld.so.1)
+-    elseif(${S390X})
++    elseif(${LoongArch64})
+       libomp_append(libomp_expected_library_deps libc.so.6)
+       libomp_append(libomp_expected_library_deps ld.so.1)
+     endif()
+diff --git a/openmp/runtime/cmake/LibompUtils.cmake b/openmp/runtime/cmake/LibompUtils.cmake
+index 139eabb45..4f20fe6da 100644
+--- a/openmp/runtime/cmake/LibompUtils.cmake
++++ b/openmp/runtime/cmake/LibompUtils.cmake
+@@ -109,12 +109,12 @@ function(libomp_get_legal_arch return_arch_string)
+     set(${return_arch_string} "MIPS64" PARENT_SCOPE)
+   elseif(${RISCV64})
+     set(${return_arch_string} "RISCV64" PARENT_SCOPE)
+-  elseif(${LOONGARCH64})
+-    set(${return_arch_string} "LOONGARCH64" PARENT_SCOPE)
+   elseif(${VE})
+     set(${return_arch_string} "VE" PARENT_SCOPE)
+   elseif(${S390X})
+     set(${return_arch_string} "S390X" 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}")
+diff --git a/openmp/runtime/cmake/config-ix.cmake b/openmp/runtime/cmake/config-ix.cmake
+index 76f471a44..2372f9ce5 100644
+--- a/openmp/runtime/cmake/config-ix.cmake
++++ b/openmp/runtime/cmake/config-ix.cmake
+@@ -330,7 +330,6 @@ else()
+       (LIBOMP_ARCH STREQUAL ppc64le) OR
+       (LIBOMP_ARCH STREQUAL ppc64) OR
+       (LIBOMP_ARCH STREQUAL riscv64) OR
+-      (LIBOMP_ARCH STREQUAL loongarch64) OR
+       (LIBOMP_ARCH STREQUAL s390x))
+      AND # OS supported?
+      ((WIN32 AND LIBOMP_HAVE_PSAPI) OR APPLE OR
+diff --git a/openmp/runtime/src/kmp_affinity.cpp b/openmp/runtime/src/kmp_affinity.cpp
+index 1ac541fbc..c7236ee73 100644
+--- a/openmp/runtime/src/kmp_affinity.cpp
++++ b/openmp/runtime/src/kmp_affinity.cpp
+@@ -3138,16 +3138,6 @@ static bool __kmp_affinity_create_cpuinfo_map(int *line,
+       }
+       (*line)++;
+ 
+-#if KMP_ARCH_LOONGARCH64
+-      // The parsing logic of /proc/cpuinfo in this function highly depends on
+-      // the blank lines between each processor info block. But on LoongArch a
+-      // blank line exists before the first processor info block (i.e. after the
+-      // "system type" line). This blank line was added because the "system
+-      // type" line is unrelated to any of the CPUs. We must skip this line so
+-      // that the original logic works on LoongArch.
+-      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.
+diff --git a/openmp/runtime/src/kmp_affinity.h b/openmp/runtime/src/kmp_affinity.h
+index 1fb70491a..b0ee0a742 100644
+--- a/openmp/runtime/src/kmp_affinity.h
++++ b/openmp/runtime/src/kmp_affinity.h
+@@ -264,7 +264,7 @@ public:
+ #elif __NR_sched_getaffinity != 5196
+ #error Wrong code for getaffinity system call.
+ #endif /* __NR_sched_getaffinity */
+-#elif KMP_ARCH_LOONGARCH64
++#elif KMP_ARCH_RISCV64
+ #ifndef __NR_sched_setaffinity
+ #define __NR_sched_setaffinity 122
+ #elif __NR_sched_setaffinity != 122
+@@ -275,7 +275,7 @@ public:
+ #elif __NR_sched_getaffinity != 123
+ #error Wrong code for getaffinity system call.
+ #endif /* __NR_sched_getaffinity */
+-#elif KMP_ARCH_RISCV64
++#elif KMP_ARCH_LOONGARCH64
+ #ifndef __NR_sched_setaffinity
+ #define __NR_sched_setaffinity 122
+ #elif __NR_sched_setaffinity != 122
+diff --git a/openmp/runtime/src/kmp_os.h b/openmp/runtime/src/kmp_os.h
+index 9cd0aefae..709eadd36 100644
+--- a/openmp/runtime/src/kmp_os.h
++++ b/openmp/runtime/src/kmp_os.h
+@@ -181,8 +181,8 @@ typedef unsigned long long kmp_uint64;
+     KMP_ARCH_PPC
+ #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_S390X
++    KMP_ARCH_MIPS64 || KMP_ARCH_RISCV64 || KMP_ARCH_VE ||                      \
++    KMP_ARCH_S390X || KMP_ARCH_LOONGARCH64
+ #define KMP_SIZE_T_SPEC KMP_UINT64_SPEC
+ #else
+ #error "Can't determine size_t printf format specifier."
+@@ -1049,8 +1049,8 @@ 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_S390X || KMP_ARCH_PPC
++    KMP_ARCH_MIPS64 || KMP_ARCH_RISCV64 || KMP_ARCH_VE ||                      \
++    KMP_ARCH_S390X || KMP_ARCH_PPC || KMP_ARCH_LOONGARCH64
+ #if KMP_OS_WINDOWS
+ #undef KMP_MB
+ #define KMP_MB() std::atomic_thread_fence(std::memory_order_seq_cst)
+diff --git a/openmp/runtime/src/kmp_platform.h b/openmp/runtime/src/kmp_platform.h
+index c06f46db2..0c8b399d8 100644
+--- a/openmp/runtime/src/kmp_platform.h
++++ b/openmp/runtime/src/kmp_platform.h
+@@ -112,9 +112,9 @@
+ #define KMP_ARCH_MIPS 0
+ #define KMP_ARCH_MIPS64 0
+ #define KMP_ARCH_RISCV64 0
+-#define KMP_ARCH_LOONGARCH64 0
+ #define KMP_ARCH_VE 0
+ #define KMP_ARCH_S390X 0
++#define KMP_ARCH_LOONGARCH64 0
+ 
+ #if KMP_OS_WINDOWS
+ #if defined(_M_AMD64) || defined(__x86_64)
+@@ -171,15 +171,15 @@
+ #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
+ #elif defined __ve__
+ #undef KMP_ARCH_VE
+ #define KMP_ARCH_VE 1
+ #elif defined __s390x__
+ #undef KMP_ARCH_S390X
+ #define KMP_ARCH_S390X 1
++#elif defined __loongarch__ && defined __loongarch64
++#undef KMP_ARCH_LOONGARCH64
++#define KMP_ARCH_LOONGARCH64 1
+ #endif
+ #endif
+ 
+@@ -253,8 +253,8 @@
+ // 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_S390X + KMP_ARCH_WASM + KMP_ARCH_PPC)
++              KMP_ARCH_RISCV64 + KMP_ARCH_VE + KMP_ARCH_S390X +                \
++              KMP_ARCH_WASM + KMP_ARCH_PPC + KMP_ARCH_LOONGARCH64)
+ #error Unknown or unsupported architecture
+ #endif
+ 
+diff --git a/openmp/runtime/src/kmp_runtime.cpp b/openmp/runtime/src/kmp_runtime.cpp
+index fc5e8405a..0d83bf071 100644
+--- a/openmp/runtime/src/kmp_runtime.cpp
++++ b/openmp/runtime/src/kmp_runtime.cpp
+@@ -8896,8 +8896,8 @@ __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_S390X || KMP_ARCH_WASM
++    KMP_ARCH_MIPS64 || KMP_ARCH_RISCV64 || KMP_ARCH_VE ||                      \
++    KMP_ARCH_S390X || KMP_ARCH_WASM || 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 ||        \
+diff --git a/openmp/runtime/src/thirdparty/ittnotify/ittnotify_config.h b/openmp/runtime/src/thirdparty/ittnotify/ittnotify_config.h
+index bd3fd9b43..7d3ab79aa 100644
+--- a/openmp/runtime/src/thirdparty/ittnotify/ittnotify_config.h
++++ b/openmp/runtime/src/thirdparty/ittnotify/ittnotify_config.h
+@@ -170,6 +170,10 @@
+ #define ITT_ARCH_S390X 8
+ #endif /* ITT_ARCH_S390X */
+ 
++#ifndef ITT_ARCH_LOONGARCH64
++#define ITT_ARCH_LOONGARCH64 7
++#endif /* ITT_ARCH_LOONGARCH64 */
++
+ #ifndef ITT_ARCH
+ #if defined _M_IX86 || defined __i386__
+ #define ITT_ARCH ITT_ARCH_IA32
+@@ -187,6 +191,8 @@
+ #define ITT_ARCH ITT_ARCH_VE
+ #elif defined __s390x__
+ #define ITT_ARCH ITT_ARCH_S390X
++#elif defined __loongarch__ && defined __loongarch64
++#define ITT_ARCH ITT_ARCH_LOONGARCH64
+ #endif
+ #endif
+ 
+diff --git a/openmp/runtime/src/z_Linux_asm.S b/openmp/runtime/src/z_Linux_asm.S
+index 14987c298..f264280e3 100644
+--- a/openmp/runtime/src/z_Linux_asm.S
++++ b/openmp/runtime/src/z_Linux_asm.S
+@@ -1902,164 +1902,6 @@ __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_VE
+ 
+ //------------------------------------------------------------------------
+@@ -2405,6 +2247,157 @@ __kmp_invoke_microtask:
+ 
+ #endif /* KMP_ARCH_S390X */
+ 
++#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
++//
++// 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        3
++       .type   __kmp_invoke_microtask,@function
++__kmp_invoke_microtask:
++
++       // First, save ra and fp
++       addi.d  $sp, $sp, -16
++       st.d    $ra, $sp, 8
++       st.d    $fp, $sp, 0
++       addi.d  $fp, $sp, 16
++
++       // Compute the dynamic stack size:
++       //
++       // - We need 8 bytes for storing 'gtid' and 'tid', so we can pass them by
++       //   reference
++       // - We need 8 bytes for each argument that cannot be passed to the 'pkfn'
++       //   function by register. Given that we have 8 of such registers (a[0-7])
++       //   and two + 'argc' arguments (consider &gtid and &tid), we need to
++       //   reserve max(0, argc - 6)*8 ext$ra bytes
++       //
++       // The total number of bytes is then max(0, argc - 6)*8 + 8
++
++       // Compute max(0, argc - 6) using the following bithack:
++       // max(0, x) = x - (x & (x >> 31?63)), where x := argc - 6
++       // Source: http://g$raphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax
++       addi.d  $t0, $a3, -6
++       srai.d  $t1, $t0, 63
++       and             $t1, $t0, $t1
++       sub.d   $t0, $t0, $t1
++
++       addi.d  $t0, $t0, 1
++
++       slli.d  $t0, $t0, 3             // t0: total number of bytes for stack storing arguments.
++       sub.d   $sp, $sp, $t0
++
++       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   // gtid
++       st.w    $a2, $fp, -24   // tid
++
++       addi.d  $a0, $fp, -20   // &gtid
++       addi.d  $a1, $fp, -24   // &tid
++
++       beqz    $t3, .L_kmp_3
++       ld.d    $a2, $t4, 0             // argv[0]
++
++       addi.d  $t3, $t3, -1
++       beqz    $t3, .L_kmp_3
++       ld.d    $a3, $t4, 8             // argv[1]
++
++       addi.d  $t3, $t3, -1
++       beqz    $t3, .L_kmp_3
++       ld.d    $a4, $t4, 16    // argv[2]
++
++       addi.d  $t3, $t3, -1
++       beqz    $t3, .L_kmp_3
++       ld.d    $a5, $t4, 24    // argv[3]
++
++       addi.d  $t3, $t3, -1
++       beqz    $t3, .L_kmp_3
++       ld.d    $a6, $t4, 32    // argv[4]
++
++       addi.d  $t3, $t3, -1
++       beqz    $t3, .L_kmp_3
++       ld.d    $a7, $t4, 40    // argv[5]
++
++       // 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
++
++// -- End  __kmp_invoke_microtask
++
++#endif /* KMP_ARCH_LOONGARCH64 */
++
+ #if KMP_ARCH_ARM || KMP_ARCH_MIPS
+     .data
+     COMMON .gomp_critical_user_, 32, 3
+@@ -2419,8 +2412,7 @@ __kmp_unnamed_critical_addr:
+ #endif /* KMP_ARCH_ARM */
+ 
+ #if KMP_ARCH_PPC64 || KMP_ARCH_AARCH64 || KMP_ARCH_MIPS64 ||                   \
+-    KMP_ARCH_RISCV64 || KMP_ARCH_LOONGARCH64 || KMP_ARCH_VE ||                 \
+-    KMP_ARCH_S390X
++    KMP_ARCH_RISCV64 || KMP_ARCH_VE || KMP_ARCH_S390X || KMP_ARCH_LOONGARCH64
+ #ifndef KMP_PREFIX_UNDERSCORE
+ # define KMP_PREFIX_UNDERSCORE(x) x
+ #endif
+@@ -2435,8 +2427,8 @@ 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_LOONGARCH64 || KMP_ARCH_VE || 
+-          KMP_ARCH_S390X */
++          KMP_ARCH_RISCV64 || KMP_ARCH_VE ||
++          KMP_ARCH_S390X || KMP_ARCH_LOONGARCH64 */
+ 
+ #if KMP_OS_LINUX
+ # if KMP_ARCH_ARM || KMP_ARCH_AARCH64
+diff --git a/openmp/runtime/src/z_Linux_util.cpp b/openmp/runtime/src/z_Linux_util.cpp
+index b9ff96873..96cbe1790 100644
+--- a/openmp/runtime/src/z_Linux_util.cpp
++++ b/openmp/runtime/src/z_Linux_util.cpp
+@@ -2521,8 +2521,8 @@ 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_LOONGARCH64 ||            \
+-      KMP_ARCH_ARM || KMP_ARCH_VE || KMP_ARCH_S390X || KMP_ARCH_PPC_XCOFF)
++      KMP_ARCH_PPC64 || KMP_ARCH_RISCV64 || KMP_ARCH_ARM ||                    \
++      KMP_ARCH_VE || KMP_ARCH_S390X || KMP_ARCH_PPC_XCOFF || 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
+diff --git a/openmp/runtime/test/ompt/callback.h b/openmp/runtime/test/ompt/callback.h
+index 05b2006a2..c888b217e 100644
+--- a/openmp/runtime/test/ompt/callback.h
++++ b/openmp/runtime/test/ompt/callback.h
+@@ -217,15 +217,6 @@ 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). And an additional jump
+-// instruction may appear (adding 4 more bytes) when the NOP is referenced
+-// elsewhere (ie. another branch).
+-#define print_possible_return_addresses(addr)                                  \
+-  printf("%" PRIu64 ": current_address=%p or %p or %p\n",                      \
+-         ompt_get_thread_data()->value, ((char *)addr) - 4,                    \
+-         ((char *)addr) - 8, ((char *)addr) - 12)
+ #elif KMP_ARCH_VE
+ // On VE the NOP instruction is 8 byte long. In addition, the compiler inserts
+ // a ??? instruction for non-void runtime functions which is ? bytes long.
+diff --git a/openmp/runtime/tools/lib/Platform.pm b/openmp/runtime/tools/lib/Platform.pm
+index 6efd932da..ca44d52d1 100644
+--- a/openmp/runtime/tools/lib/Platform.pm
++++ b/openmp/runtime/tools/lib/Platform.pm
+@@ -63,10 +63,10 @@ sub canon_arch($) {
+             $arch = "mips";
+         } elsif ( $arch =~ m{\Ariscv64} ) {
+             $arch = "riscv64";
+-        } elsif ( $arch =~ m{\Aloongarch64} ) {
+-            $arch = "loongarch64";
+         } elsif ( $arch =~ m{\As390x} ) {
+             $arch = "s390x";
++        } elsif ( $arch =~ m{\Aloongarch64} ) {
++            $arch = "loongarch64";
+         } else {
+             $arch = undef;
+         }; # if
+@@ -97,11 +97,11 @@ sub canon_mic_arch($) {
+         "32e" => "Intel(R) 64",
+         "arm" => "ARM",
+         "aarch64" => "AArch64",
+-        "loongarch64" => "LoongArch64",
+         "mic" => "Intel(R) Many Integrated Core Architecture",
+         "mips" => "MIPS",
+         "mips64" => "MIPS64",
+         "riscv64" => "RISC-V (64-bit)",
++        "loongarch64" => "LoongArch64",
+     );
+ 
+     sub legal_arch($) {
+@@ -124,6 +124,7 @@ sub canon_mic_arch($) {
+         "mic" => "intel64",
+         "mips" => "mips",
+         "mips64" => "MIPS64",
++        "loongarch64" => "loongarch64",
+     );
+ 
+     sub arch_opt($) {
+@@ -230,10 +231,10 @@ sub target_options() {
+         $_host_arch = "mips";
+     } elsif ( $hardware_platform eq "riscv64" ) {
+         $_host_arch = "riscv64";
+-    } elsif ( $hardware_platform eq "loongarch64" ) {
+-        $_host_arch = "loongarch64";
+     } elsif ( $hardware_platform eq "s390x" ) {
+         $_host_arch = "s390x";
++    } elsif ( $hardware_platform eq "loongarch64" ) {
++        $_host_arch = "loongarch64";
+     } else {
+         die "Unsupported host hardware platform: \"$hardware_platform\"; stopped";
+     }; # if
+@@ -423,7 +424,7 @@ 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>, C<loongarch64>, C<s390x>, 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<s390x>, C<loongarch64> or C<undef> is input string is not recognized.
+ 
+ =item B<legal_arch( $arch )>
+ 
+diff --git a/openmp/runtime/tools/lib/Uname.pm b/openmp/runtime/tools/lib/Uname.pm
+index 9dde444d5..db1d93302 100644
+--- a/openmp/runtime/tools/lib/Uname.pm
++++ b/openmp/runtime/tools/lib/Uname.pm
+@@ -158,10 +158,10 @@ 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";
+     } elsif ( $values{ machine } =~ m{\As390x\z} ) {
+         $values{ hardware_platform } = "s390x";
++    } elsif ( $values{ machine } =~ m{\Aloongarch64\z} ) {
++        $values{ hardware_platform } = "loongarch64";
+     } else {
+         die "Unsupported machine (\"$values{ machine }\") returned by POSIX::uname(); stopped";
+     }; # if
diff --git a/libomp.spec b/libomp.spec
index b812378d88e07f72883323c07cb3d70d2e682f2a..8e0db6f2e3917c6b95e242c0f3a5e1779e6343df 100644
--- a/libomp.spec
+++ b/libomp.spec
@@ -1,3 +1,4 @@
+%define anolis_release .0.1
 %bcond_with snapshot_build
 
 %if %{with snapshot_build}
@@ -35,7 +36,7 @@
 
 Name: libomp
 Version: %{libomp_version}%{?rc_ver:~rc%{rc_ver}}%{?llvm_snapshot_version_suffix:~%{llvm_snapshot_version_suffix}}
-Release: 1%{?dist}
+Release: 1%{anolis_release}%{?dist}
 Summary: OpenMP runtime for clang
 
 License: NCSA
@@ -49,6 +50,8 @@ Source1: https://github.com/llvm/llvm-project/releases/download/llvmorg-%{libomp
 Source2: release-keys.asc
 %endif
 
+Patch1:   0001-Support-LoongArch.patch
+
 BuildRequires: clang >= %{maj_ver}
 # For clang-offload-packager
 BuildRequires: clang-tools-extra
@@ -97,6 +100,10 @@ OpenMP header files.
 
 %cmake -GNinja \
 	-DLIBOMP_INSTALL_ALIASES=OFF \
+%ifarch loongarch64
+       -DCMAKE_C_COMPILER=clang \
+       -DCMAKE_CXX_COMPILER=clang++ \
+%endif
 	-DCMAKE_MODULE_PATH=%{_datadir}/llvm/cmake/Modules \
 	-DLLVM_DIR=%{_libdir}/cmake/llvm \
 	-DCMAKE_INSTALL_INCLUDEDIR=%{_prefix}/lib/clang/%{maj_ver}/include \
@@ -125,14 +132,16 @@ rm -rf %{buildroot}%{_libdir}/libarcher_static.a
 %files
 %license LICENSE.TXT
 %{_libdir}/libomp.so
+%ifnarch loongarch64
 %{_libdir}/libompd.so
 %ifnarch %{arm}
 %{_libdir}/libarcher.so
 %endif
+%endif
 %ifnarch %{ix86} %{arm}
 # libomptarget is not supported on 32-bit systems.
 # s390x does not support the offloading plugins.
-%ifnarch s390x
+%ifnarch s390x loongarch64
 %{_libdir}/libomptarget.rtl.amdgpu.so.%{so_suffix}
 %{_libdir}/libomptarget.rtl.cuda.so.%{so_suffix}
 %{_libdir}/libomptarget.rtl.%{libomp_arch}.so.%{so_suffix}
@@ -143,7 +152,7 @@ rm -rf %{buildroot}%{_libdir}/libarcher_static.a
 %files devel
 %{_prefix}/lib/clang/%{maj_ver}/include/omp.h
 %{_prefix}/lib/clang/%{maj_ver}/include/ompx.h
-%ifnarch %{arm}
+%ifnarch %{arm} loongarch64
 %{_prefix}/lib/clang/%{maj_ver}/include/omp-tools.h
 %{_prefix}/lib/clang/%{maj_ver}/include/ompt.h
 %{_prefix}/lib/clang/%{maj_ver}/include/ompt-multiplex.h
@@ -152,7 +161,7 @@ rm -rf %{buildroot}%{_libdir}/libarcher_static.a
 %ifnarch %{ix86} %{arm}
 # libomptarget is not supported on 32-bit systems.
 # s390x does not support the offloading plugins.
-%ifnarch s390x
+%ifnarch s390x loongarch64
 %{_libdir}/libomptarget.rtl.amdgpu.so
 %{_libdir}/libomptarget.rtl.cuda.so
 %{_libdir}/libomptarget.rtl.%{libomp_arch}.so
@@ -164,6 +173,9 @@ rm -rf %{buildroot}%{_libdir}/libarcher_static.a
 %endif
 
 %changelog
+* Thu Dec 05 2024 Chen Li <chenli@loongson.cn> - 18.1.8-1.0.1
+- Add support for LoongArch
+
 * Tue Jul 09 2024 Tom Stellard <tstellar@redhat.com> - 18.1.8-1
 - 18.1.8 Release