diff --git a/clang/include/clang/Driver/Options.td b/clang/include/clang/Driver/Options.td
index 01a3ad0943b4c..e5f2fec88706d 100644
--- a/clang/include/clang/Driver/Options.td
+++ b/clang/include/clang/Driver/Options.td
@@ -5413,6 +5413,10 @@ def mlam_bh : Flag<["-"], "mlam-bh">, Group<m_loongarch_Features_Group>,
   HelpText<"Enable amswap[_db].{b/h} and amadd[_db].{b/h}">;
 def mno_lam_bh : Flag<["-"], "mno-lam-bh">, Group<m_loongarch_Features_Group>,
   HelpText<"Disable amswap[_db].{b/h} and amadd[_db].{b/h}">;
+def mld_seq_sa : Flag<["-"], "mld-seq-sa">, Group<m_loongarch_Features_Group>,
+  HelpText<"Do not generate load-load barrier instructions (dbar 0x700)">;
+def mno_ld_seq_sa : Flag<["-"], "mno-ld-seq-sa">, Group<m_loongarch_Features_Group>,
+  HelpText<"Generate load-load barrier instructions (dbar 0x700)">;
 def mannotate_tablejump : Flag<["-"], "mannotate-tablejump">, Group<m_loongarch_Features_Group>,
   HelpText<"Enable annotate table jump instruction to correlate it with the jump table.">;
 def mno_annotate_tablejump : Flag<["-"], "mno-annotate-tablejump">, Group<m_loongarch_Features_Group>,
diff --git a/clang/lib/Basic/Targets/LoongArch.cpp b/clang/lib/Basic/Targets/LoongArch.cpp
index 07b22b35f603c..3f2d7317532aa 100644
--- a/clang/lib/Basic/Targets/LoongArch.cpp
+++ b/clang/lib/Basic/Targets/LoongArch.cpp
@@ -205,7 +205,7 @@ void LoongArchTargetInfo::getTargetDefines(const LangOptions &Opts,
       // TODO: As more features of the V1.1 ISA are supported, a unified "v1.1"
       // arch feature set will be used to include all sub-features belonging to
       // the V1.1 ISA version.
-      if (HasFeatureFrecipe && HasFeatureLAM_BH)
+      if (HasFeatureFrecipe && HasFeatureLAM_BH && HasFeatureLD_SEQ_SA)
         Builder.defineMacro("__loongarch_arch",
                             Twine('"') + "la64v1.1" + Twine('"'));
       else
@@ -239,6 +239,9 @@ void LoongArchTargetInfo::getTargetDefines(const LangOptions &Opts,
   if (HasFeatureLAM_BH)
     Builder.defineMacro("__loongarch_lam_bh", Twine(1));
 
+  if (HasFeatureLD_SEQ_SA)
+    Builder.defineMacro("__loongarch_ld_seq_sa", Twine(1));
+
   StringRef ABI = getABI();
   if (ABI == "lp64d" || ABI == "lp64f" || ABI == "lp64s")
     Builder.defineMacro("__loongarch_lp64");
@@ -317,6 +320,8 @@ bool LoongArchTargetInfo::handleTargetFeatures(
       HasFeatureFrecipe = true;
     else if (Feature == "+lam-bh")
       HasFeatureLAM_BH = true;
+    else if (Feature == "+ld-seq-sa")
+      HasFeatureLD_SEQ_SA = true;
   }
   return true;
 }
diff --git a/clang/lib/Basic/Targets/LoongArch.h b/clang/lib/Basic/Targets/LoongArch.h
index 3585e9f7968b4..e5eae7a8fcf67 100644
--- a/clang/lib/Basic/Targets/LoongArch.h
+++ b/clang/lib/Basic/Targets/LoongArch.h
@@ -31,6 +31,7 @@ class LLVM_LIBRARY_VISIBILITY LoongArchTargetInfo : public TargetInfo {
   bool HasFeatureLASX;
   bool HasFeatureFrecipe;
   bool HasFeatureLAM_BH;
+  bool HasFeatureLD_SEQ_SA;
 
 public:
   LoongArchTargetInfo(const llvm::Triple &Triple, const TargetOptions &)
@@ -41,6 +42,7 @@ class LLVM_LIBRARY_VISIBILITY LoongArchTargetInfo : public TargetInfo {
     HasFeatureLASX = false;
     HasFeatureFrecipe = false;
     HasFeatureLAM_BH = false;
+    HasFeatureLD_SEQ_SA = false;
     LongDoubleWidth = 128;
     LongDoubleAlign = 128;
     LongDoubleFormat = &llvm::APFloat::IEEEquad();
diff --git a/clang/lib/Driver/ToolChains/Arch/LoongArch.cpp b/clang/lib/Driver/ToolChains/Arch/LoongArch.cpp
index 987db4638fca8..67b71a3ec623e 100644
--- a/clang/lib/Driver/ToolChains/Arch/LoongArch.cpp
+++ b/clang/lib/Driver/ToolChains/Arch/LoongArch.cpp
@@ -274,6 +274,15 @@ void loongarch::getLoongArchTargetFeatures(const Driver &D,
     else
       Features.push_back("-lam-bh");
   }
+
+  // Select ld-seq-sa feature determined by -m[no-]ld-seq-sa.
+  if (const Arg *A = Args.getLastArg(options::OPT_mld_seq_sa,
+                                     options::OPT_mno_ld_seq_sa)) {
+    if (A->getOption().matches(options::OPT_mld_seq_sa))
+      Features.push_back("+ld-seq-sa");
+    else
+      Features.push_back("-ld-seq-sa");
+  }
 }
 
 std::string loongarch::postProcessTargetCPUString(const std::string &CPU,
diff --git a/clang/test/Driver/loongarch-march.c b/clang/test/Driver/loongarch-march.c
index d4cd5b07ae905..c7091336f3bc8 100644
--- a/clang/test/Driver/loongarch-march.c
+++ b/clang/test/Driver/loongarch-march.c
@@ -39,21 +39,21 @@
 
 // CC1-LA64V1P1: "-target-cpu" "loongarch64"
 // CC1-LA64V1P1-NOT: "-target-feature"
-// CC1-LA64V1P1: "-target-feature" "+64bit" "-target-feature" "+d" "-target-feature" "+lsx" "-target-feature" "+ual" "-target-feature" "+frecipe" "-target-feature" "+lam-bh"
+// CC1-LA64V1P1: "-target-feature" "+64bit" "-target-feature" "+d" "-target-feature" "+lsx" "-target-feature" "+ual" "-target-feature" "+frecipe" "-target-feature" "+lam-bh" "-target-feature" "+ld-seq-sa"
 // CC1-LA64V1P1-NOT: "-target-feature"
 // CC1-LA64V1P1: "-target-abi" "lp64d"
 
 // CC1-LA664: "-target-cpu" "la664"
 // CC1-LA664-NOT: "-target-feature"
-// CC1-LA664: "-target-feature" "+64bit" "-target-feature" "+f" "-target-feature" "+d" "-target-feature" "+lsx" "-target-feature" "+lasx" "-target-feature" "+ual" "-target-feature" "+frecipe" "-target-feature" "+lam-bh"
+// CC1-LA664: "-target-feature" "+64bit" "-target-feature" "+f" "-target-feature" "+d" "-target-feature" "+lsx" "-target-feature" "+lasx" "-target-feature" "+ual" "-target-feature" "+frecipe" "-target-feature" "+lam-bh" "-target-feature" "+ld-seq-sa"
 // CC1-LA664-NOT: "-target-feature"
 // CC1-LA664: "-target-abi" "lp64d"
 
 // IR-LOONGARCH64: attributes #[[#]] ={{.*}}"target-cpu"="loongarch64" {{.*}}"target-features"="+64bit,+d,+f,+ual"
 // IR-LA464: attributes #[[#]] ={{.*}}"target-cpu"="la464" {{.*}}"target-features"="+64bit,+d,+f,+lasx,+lsx,+ual"
 // IR-LA64V1P0: attributes #[[#]] ={{.*}}"target-cpu"="loongarch64" {{.*}}"target-features"="+64bit,+d,+lsx,+ual"
-// IR-LA64V1P1: attributes #[[#]] ={{.*}}"target-cpu"="loongarch64" {{.*}}"target-features"="+64bit,+d,+frecipe,+lam-bh,+lsx,+ual"
-// IR-LA664: attributes #[[#]] ={{.*}}"target-cpu"="la664" {{.*}}"target-features"="+64bit,+d,+f,+frecipe,+lam-bh,+lasx,+lsx,+ual"
+// IR-LA64V1P1: attributes #[[#]] ={{.*}}"target-cpu"="loongarch64" {{.*}}"target-features"="+64bit,+d,+frecipe,+lam-bh,+ld-seq-sa,+lsx,+ual"
+// IR-LA664: attributes #[[#]] ={{.*}}"target-cpu"="la664" {{.*}}"target-features"="+64bit,+d,+f,+frecipe,+lam-bh,+lasx,+ld-seq-sa,+lsx,+ual"
 
 int foo(void) {
   return 3;
diff --git a/clang/test/Driver/loongarch-mld-seq-sa.c b/clang/test/Driver/loongarch-mld-seq-sa.c
new file mode 100644
index 0000000000000..3d1d90d3f9cf7
--- /dev/null
+++ b/clang/test/Driver/loongarch-mld-seq-sa.c
@@ -0,0 +1,30 @@
+/// Test -m[no]ld-seq-sa options.
+
+// RUN: %clang --target=loongarch64 -mld-seq-sa -fsyntax-only %s -### 2>&1 | \
+// RUN:     FileCheck %s --check-prefix=CC1-ld-seq-sa
+// RUN: %clang --target=loongarch64 -mno-ld-seq-sa -fsyntax-only %s -### 2>&1 | \
+// RUN:     FileCheck %s --check-prefix=CC1-NO-ld-seq-sa
+// RUN: %clang --target=loongarch64 -mno-ld-seq-sa -mld-seq-sa -fsyntax-only %s -### 2>&1 | \
+// RUN:     FileCheck %s --check-prefix=CC1-ld-seq-sa
+// RUN: %clang --target=loongarch64  -mld-seq-sa -mno-ld-seq-sa -fsyntax-only %s -### 2>&1 | \
+// RUN:     FileCheck %s --check-prefix=CC1-NO-ld-seq-sa
+
+// RUN: %clang --target=loongarch64 -mld-seq-sa -S -emit-llvm %s -o - | \
+// RUN: FileCheck %s --check-prefix=IR-ld-seq-sa
+// RUN: %clang --target=loongarch64 -mno-ld-seq-sa -S -emit-llvm %s -o - | \
+// RUN: FileCheck %s --check-prefix=IR-NO-ld-seq-sa
+// RUN: %clang --target=loongarch64 -mno-ld-seq-sa -mld-seq-sa -S -emit-llvm %s -o - | \
+// RUN: FileCheck %s --check-prefix=IR-ld-seq-sa
+// RUN: %clang --target=loongarch64 -mld-seq-sa -mno-ld-seq-sa -S -emit-llvm %s -o - | \
+// RUN: FileCheck %s --check-prefix=IR-NO-ld-seq-sa
+
+
+// CC1-ld-seq-sa: "-target-feature" "+ld-seq-sa"
+// CC1-NO-ld-seq-sa: "-target-feature" "-ld-seq-sa"
+
+// IR-ld-seq-sa: attributes #[[#]] ={{.*}}"target-features"="{{(.*,)?}}+ld-seq-sa{{(,.*)?}}"
+// IR-NO-ld-seq-sa: attributes #[[#]] ={{.*}}"target-features"="{{(.*,)?}}-ld-seq-sa{{(,.*)?}}"
+
+int foo(void) {
+  return 42;
+}
diff --git a/clang/test/Preprocessor/init-loongarch.c b/clang/test/Preprocessor/init-loongarch.c
index 8019292e0f10e..0eb6977a2553c 100644
--- a/clang/test/Preprocessor/init-loongarch.c
+++ b/clang/test/Preprocessor/init-loongarch.c
@@ -798,7 +798,7 @@
 // LA64-FPU0-LP64S-NOT: #define __loongarch_single_float
 // LA64-FPU0-LP64S: #define __loongarch_soft_float 1
 
-/// Check __loongarch_arch{_tune/_frecipe/_lam_bh}.
+/// Check __loongarch_arch{_tune/_frecipe/_lam_bh/_ld_seq_sa}.
 
 // RUN: %clang --target=loongarch64 -x c -E -dM %s -o - | \
 // RUN:   FileCheck --match-full-lines --check-prefix=ARCH-TUNE -DARCH=la64v1.0 -DTUNE=loongarch64 %s
@@ -823,11 +823,11 @@
 // RUN: %clang --target=loongarch64 -x c -E -dM %s -o - -march=loongarch64 -Xclang -target-feature -Xclang +lsx | \
 // RUN:   FileCheck --match-full-lines --check-prefix=ARCH-TUNE -DARCH=la64v1.0 -DTUNE=loongarch64 %s
 // RUN: %clang --target=loongarch64 -x c -E -dM %s -o - -march=la64v1.1 | \
-// RUN:   FileCheck --match-full-lines  --check-prefixes=ARCH-TUNE,FRECIPE,LAM-BH -DARCH=la64v1.1 -DTUNE=loongarch64 %s
+// RUN:   FileCheck --match-full-lines  --check-prefixes=ARCH-TUNE,FRECIPE,LAM-BH,LD-SEQ-SA -DARCH=la64v1.1 -DTUNE=loongarch64 %s
 // RUN: %clang --target=loongarch64 -x c -E -dM %s -o - -march=la64v1.1 -Xclang -target-feature -Xclang -frecipe | \
-// RUN:   FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,LAM-BH -DARCH=la64v1.0 -DTUNE=loongarch64 %s
+// RUN:   FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,LAM-BH,LD-SEQ-SA -DARCH=la64v1.0 -DTUNE=loongarch64 %s
 // RUN: %clang --target=loongarch64 -x c -E -dM %s -o - -march=la64v1.1 -Xclang -target-feature -Xclang -lsx | \
-// RUN:   FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,FRECIPE,LAM-BH -DARCH=loongarch64 -DTUNE=loongarch64 %s
+// RUN:   FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,FRECIPE,LAM-BH,LD-SEQ-SA -DARCH=loongarch64 -DTUNE=loongarch64 %s
 // RUN: %clang --target=loongarch64 -x c -E -dM %s -o - -march=loongarch64 -Xclang -target-feature -Xclang +frecipe | \
 // RUN:   FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,FRECIPE -DARCH=loongarch64 -DTUNE=loongarch64 %s
 // RUN: %clang --target=loongarch64 -x c -E -dM %s -o - -march=loongarch64 -Xclang -target-feature -Xclang +lsx -Xclang -target-feature -Xclang +frecipe | \
@@ -835,25 +835,34 @@
 // RUN: %clang --target=loongarch64 -x c -E -dM %s -o - -march=la64v1.0 -Xclang -target-feature -Xclang +lam-bh | \
 // RUN:   FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,LAM-BH -DARCH=la64v1.0 -DTUNE=loongarch64 %s
 // RUN: %clang --target=loongarch64 -x c -E -dM %s -o - -march=la64v1.1 -Xclang -target-feature -Xclang -lam-bh | \
-// RUN:   FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,FRECIPE -DARCH=la64v1.0 -DTUNE=loongarch64 %s
+// RUN:   FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,FRECIPE,LD-SEQ-SA -DARCH=la64v1.0 -DTUNE=loongarch64 %s
 // RUN: %clang --target=loongarch64 -x c -E -dM %s -o - -march=loongarch64 -Xclang -target-feature -Xclang +lam-bh | \
 // RUN:   FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,LAM-BH -DARCH=loongarch64 -DTUNE=loongarch64 %s
 // RUN: %clang --target=loongarch64 -x c -E -dM %s -o - -march=loongarch64 -Xclang -target-feature -Xclang +lsx -Xclang -target-feature -Xclang +lam-bh | \
 // RUN:   FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,LAM-BH -DARCH=la64v1.0 -DTUNE=loongarch64 %s
-// RUN: %clang --target=loongarch64 -x c -E -dM %s -o - -march=la64v1.0 -Xclang -target-feature -Xclang +frecipe -Xclang -target-feature -Xclang +lam-bh | \
+// RUN: %clang --target=loongarch64 -x c -E -dM %s -o - -march=la64v1.0 -Xclang -target-feature -Xclang +ld-seq-sa | \
+// RUN:   FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,LD-SEQ-SA -DARCH=la64v1.0 -DTUNE=loongarch64 %s
+// RUN: %clang --target=loongarch64 -x c -E -dM %s -o - -march=la64v1.1 -Xclang -target-feature -Xclang -ld-seq-sa | \
+// RUN:   FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,FRECIPE,LAM-BH -DARCH=la64v1.0 -DTUNE=loongarch64 %s
+// RUN: %clang --target=loongarch64 -x c -E -dM %s -o - -march=loongarch64 -Xclang -target-feature -Xclang +ld-seq-sa | \
+// RUN:   FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,LD-SEQ-SA -DARCH=loongarch64 -DTUNE=loongarch64 %s
+// RUN: %clang --target=loongarch64 -x c -E -dM %s -o - -march=loongarch64 -Xclang -target-feature -Xclang +lsx -Xclang -target-feature -Xclang +ld-seq-sa | \
+// RUN:   FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,LD-SEQ-SA -DARCH=la64v1.0 -DTUNE=loongarch64 %s
+// RUN: %clang --target=loongarch64 -x c -E -dM %s -o - -march=la64v1.0 -Xclang -target-feature -Xclang +frecipe -Xclang -target-feature -Xclang +lam-bh  -Xclang -target-feature -Xclang +ld-seq-sa | \
 // RUN:   FileCheck --match-full-lines --check-prefixes=ARCH-TUNE -DARCH=la64v1.1 -DTUNE=loongarch64 %s
 // RUN: %clang --target=loongarch64 -x c -E -dM %s -o - -march=la664 | \
-// RUN:   FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,FRECIPE,LAM-BH -DARCH=la664 -DTUNE=la664 %s
+// RUN:   FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,FRECIPE,LAM-BH,LD-SEQ-SA -DARCH=la664 -DTUNE=la664 %s
 // RUN: %clang --target=loongarch64 -x c -E -dM %s -o - -mtune=la664 | \
 // RUN:   FileCheck --match-full-lines --check-prefix=ARCH-TUNE -DARCH=la64v1.0 -DTUNE=la664 %s
 // RUN: %clang --target=loongarch64 -x c -E -dM %s -o - -march=loongarch64 -mtune=la664 | \
 // RUN:   FileCheck --match-full-lines --check-prefix=ARCH-TUNE -DARCH=loongarch64 -DTUNE=la664 %s
 // RUN: %clang --target=loongarch64 -x c -E -dM %s -o - -march=la664 -mtune=loongarch64 | \
-// RUN:   FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,FRECIPE,LAM-BH -DARCH=la664 -DTUNE=loongarch64 %s
+// RUN:   FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,FRECIPE,LAM-BH,LD-SEQ-SA -DARCH=la664 -DTUNE=loongarch64 %s
 
 // ARCH-TUNE: #define __loongarch_arch "[[ARCH]]"
 // FRECIPE: #define __loongarch_frecipe 1
 // LAM-BH: #define __loongarch_lam_bh 1
+// LD-SEQ-SA: #define __loongarch_ld_seq_sa 1
 // ARCH-TUNE: #define __loongarch_tune "[[TUNE]]"
 
 // RUN: %clang --target=loongarch64 -mlsx -x c -E -dM %s -o - \
diff --git a/llvm/include/llvm/TargetParser/LoongArchTargetParser.def b/llvm/include/llvm/TargetParser/LoongArchTargetParser.def
index 6cd2018b7b59c..324d5c18e6dea 100644
--- a/llvm/include/llvm/TargetParser/LoongArchTargetParser.def
+++ b/llvm/include/llvm/TargetParser/LoongArchTargetParser.def
@@ -12,6 +12,7 @@ LOONGARCH_FEATURE("+lvz", FK_LVZ)
 LOONGARCH_FEATURE("+ual", FK_UAL)
 LOONGARCH_FEATURE("+frecipe", FK_FRECIPE)
 LOONGARCH_FEATURE("+lam-bh", FK_LAM_BH)
+LOONGARCH_FEATURE("+ld-seq-sa", FK_LD_SEQ_SA)
 
 #undef LOONGARCH_FEATURE
 
@@ -21,6 +22,6 @@ LOONGARCH_FEATURE("+lam-bh", FK_LAM_BH)
 
 LOONGARCH_ARCH("loongarch64", AK_LOONGARCH64, FK_64BIT | FK_FP32 | FK_FP64 | FK_UAL)
 LOONGARCH_ARCH("la464", AK_LA464, FK_64BIT | FK_FP32 | FK_FP64 | FK_LSX | FK_LASX | FK_UAL)
-LOONGARCH_ARCH("la664", AK_LA664, FK_64BIT | FK_FP32 | FK_FP64 | FK_LSX | FK_LASX | FK_UAL | FK_FRECIPE | FK_LAM_BH)
+LOONGARCH_ARCH("la664", AK_LA664, FK_64BIT | FK_FP32 | FK_FP64 | FK_LSX | FK_LASX | FK_UAL | FK_FRECIPE | FK_LAM_BH | FK_LD_SEQ_SA)
 
 #undef LOONGARCH_ARCH
diff --git a/llvm/include/llvm/TargetParser/LoongArchTargetParser.h b/llvm/include/llvm/TargetParser/LoongArchTargetParser.h
index b5be03b1b67fb..00957b84ab576 100644
--- a/llvm/include/llvm/TargetParser/LoongArchTargetParser.h
+++ b/llvm/include/llvm/TargetParser/LoongArchTargetParser.h
@@ -53,6 +53,10 @@ enum FeatureKind : uint32_t {
   // Atomic memory swap and add instructions for byte and half word are
   // available.
   FK_LAM_BH = 1 << 10,
+
+  // Do not generate load-load barrier instructions (dbar 0x700).
+  FK_LD_SEQ_SA = 1 << 12,
+
 };
 
 struct FeatureInfo {
diff --git a/llvm/lib/Target/LoongArch/LoongArch.td b/llvm/lib/Target/LoongArch/LoongArch.td
index ecd00cd6d5d61..100bdba36c440 100644
--- a/llvm/lib/Target/LoongArch/LoongArch.td
+++ b/llvm/lib/Target/LoongArch/LoongArch.td
@@ -118,6 +118,11 @@ def FeatureLAM_BH
                         "Support amswap[_db].{b/h} and amadd[_db].{b/h} instructions.">;
 def HasLAM_BH : Predicate<"Subtarget->hasLAM_BH()">;
 
+def FeatureLD_SEQ_SA
+    : SubtargetFeature<"ld-seq-sa", "HasLD_SEQ_SA", "true",
+                        "Don't use load-load barrier (dbar 0x700).">;
+def HasLD_SEQ_SA : Predicate<"Subtarget->hasLD_SEQ_SA()">;
+
 def TunePreferWInst
     : SubtargetFeature<"prefer-w-inst", "PreferWInst", "true",
                        "Prefer instructions with W suffix">;
diff --git a/llvm/lib/Target/LoongArch/LoongArchExpandAtomicPseudoInsts.cpp b/llvm/lib/Target/LoongArch/LoongArchExpandAtomicPseudoInsts.cpp
index 18a532b55ee5a..35f84425cb0eb 100644
--- a/llvm/lib/Target/LoongArch/LoongArchExpandAtomicPseudoInsts.cpp
+++ b/llvm/lib/Target/LoongArch/LoongArchExpandAtomicPseudoInsts.cpp
@@ -588,7 +588,9 @@ bool LoongArchExpandAtomicPseudo::expandAtomicCmpXchg(
 
   // .tail:
   //   dbar 0x700 | acquire
-  BuildMI(TailMBB, DL, TII->get(LoongArch::DBAR)).addImm(hint);
+
+  if (!(hint == 0x700 && MF->getSubtarget<LoongArchSubtarget>().hasLD_SEQ_SA()))
+    BuildMI(TailMBB, DL, TII->get(LoongArch::DBAR)).addImm(hint);
 
   NextMBBI = MBB.end();
   MI.eraseFromParent();
diff --git a/llvm/lib/TargetParser/Host.cpp b/llvm/lib/TargetParser/Host.cpp
index b295db5a29c36..e0c857b60c409 100644
--- a/llvm/lib/TargetParser/Host.cpp
+++ b/llvm/lib/TargetParser/Host.cpp
@@ -2011,8 +2011,9 @@ const StringMap<bool> sys::getHostCPUFeatures() {
 const StringMap<bool> sys::getHostCPUFeatures() {
   unsigned long hwcap = getauxval(AT_HWCAP);
   bool HasFPU = hwcap & (1UL << 3); // HWCAP_LOONGARCH_FPU
-  uint32_t cpucfg2 = 0x2;
+  const uint32_t cpucfg2 = 0x2, cpucfg3 = 0x3;
   __asm__("cpucfg %[cpucfg2], %[cpucfg2]\n\t" : [cpucfg2] "+r"(cpucfg2));
+  __asm__("cpucfg %[cpucfg3], %[cpucfg3]\n\t" : [cpucfg3] "+r"(cpucfg3));
 
   StringMap<bool> Features;
 
@@ -2026,12 +2027,13 @@ const StringMap<bool> sys::getHostCPUFeatures() {
   Features["frecipe"] = cpucfg2 & (1U << 25); // CPUCFG.2.FRECIPE
   Features["lam-bh"] = cpucfg2 & (1U << 27);  // CPUCFG.2.LAM_BH
 
+  Features["ld-seq-sa"] = cpucfg3 & (1U << 23); // CPUCFG.3.LD_SEQ_SA
+
   // TODO: Need to complete.
   // Features["div32"] = cpucfg2 & (1U << 26);       // CPUCFG.2.DIV32
   // Features["lamcas"] = cpucfg2 & (1U << 28);      // CPUCFG.2.LAMCAS
   // Features["llacq-screl"] = cpucfg2 & (1U << 29); // CPUCFG.2.LLACQ_SCREL
   // Features["scq"] = cpucfg2 & (1U << 30);         // CPUCFG.2.SCQ
-  // Features["ld-seq-sa"] = cpucfg3 & (1U << 23); // CPUCFG.3.LD_SEQ_SA
   return Features;
 }
 #elif defined(__linux__) && defined(__riscv)
diff --git a/llvm/lib/TargetParser/LoongArchTargetParser.cpp b/llvm/lib/TargetParser/LoongArchTargetParser.cpp
index 27e3b5683c5a6..9b8407a73bea3 100644
--- a/llvm/lib/TargetParser/LoongArchTargetParser.cpp
+++ b/llvm/lib/TargetParser/LoongArchTargetParser.cpp
@@ -53,6 +53,7 @@ bool LoongArch::getArchFeatures(StringRef Arch,
     if (Arch == "la64v1.1") {
       Features.push_back("+frecipe");
       Features.push_back("+lam-bh");
+      Features.push_back("+ld-seq-sa");
     }
     return true;
   }
diff --git a/llvm/test/CodeGen/LoongArch/ir-instruction/atomic-cmpxchg.ll b/llvm/test/CodeGen/LoongArch/ir-instruction/atomic-cmpxchg.ll
index ad98397dfe8f0..4ff15f2b7e448 100644
--- a/llvm/test/CodeGen/LoongArch/ir-instruction/atomic-cmpxchg.ll
+++ b/llvm/test/CodeGen/LoongArch/ir-instruction/atomic-cmpxchg.ll
@@ -1,5 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc --mtriple=loongarch64 -mattr=+d < %s | FileCheck %s --check-prefix=LA64
+; RUN: llc --mtriple=loongarch64 -mattr=+d,-ld-seq-sa < %s | FileCheck %s --check-prefixes=LA64,NO-LD-SEQ-SA
+; RUN: llc --mtriple=loongarch64 -mattr=+d,+ld-seq-sa < %s | FileCheck %s --check-prefixes=LA64,LD-SEQ-SA
 
 define void @cmpxchg_i8_acquire_acquire(ptr %ptr, i8 %cmp, i8 %val) nounwind {
 ; LA64-LABEL: cmpxchg_i8_acquire_acquire:
@@ -100,99 +101,177 @@ define void @cmpxchg_i64_acquire_acquire(ptr %ptr, i64 %cmp, i64 %val) nounwind
 }
 
 define void @cmpxchg_i8_acquire_monotonic(ptr %ptr, i8 %cmp, i8 %val) nounwind {
-; LA64-LABEL: cmpxchg_i8_acquire_monotonic:
-; LA64:       # %bb.0:
-; LA64-NEXT:    slli.d $a3, $a0, 3
-; LA64-NEXT:    bstrins.d $a0, $zero, 1, 0
-; LA64-NEXT:    ori $a4, $zero, 255
-; LA64-NEXT:    sll.w $a4, $a4, $a3
-; LA64-NEXT:    andi $a1, $a1, 255
-; LA64-NEXT:    sll.w $a1, $a1, $a3
-; LA64-NEXT:    andi $a2, $a2, 255
-; LA64-NEXT:    sll.w $a2, $a2, $a3
-; LA64-NEXT:  .LBB4_1: # =>This Inner Loop Header: Depth=1
-; LA64-NEXT:    ll.w $a3, $a0, 0
-; LA64-NEXT:    and $a5, $a3, $a4
-; LA64-NEXT:    bne $a5, $a1, .LBB4_3
-; LA64-NEXT:  # %bb.2: # in Loop: Header=BB4_1 Depth=1
-; LA64-NEXT:    andn $a5, $a3, $a4
-; LA64-NEXT:    or $a5, $a5, $a2
-; LA64-NEXT:    sc.w $a5, $a0, 0
-; LA64-NEXT:    beqz $a5, .LBB4_1
-; LA64-NEXT:    b .LBB4_4
-; LA64-NEXT:  .LBB4_3:
-; LA64-NEXT:    dbar 1792
-; LA64-NEXT:  .LBB4_4:
-; LA64-NEXT:    ret
+; NO-LD-SEQ-SA-LABEL: cmpxchg_i8_acquire_monotonic:
+; NO-LD-SEQ-SA:       # %bb.0:
+; NO-LD-SEQ-SA-NEXT:    slli.d $a3, $a0, 3
+; NO-LD-SEQ-SA-NEXT:    bstrins.d $a0, $zero, 1, 0
+; NO-LD-SEQ-SA-NEXT:    ori $a4, $zero, 255
+; NO-LD-SEQ-SA-NEXT:    sll.w $a4, $a4, $a3
+; NO-LD-SEQ-SA-NEXT:    andi $a1, $a1, 255
+; NO-LD-SEQ-SA-NEXT:    sll.w $a1, $a1, $a3
+; NO-LD-SEQ-SA-NEXT:    andi $a2, $a2, 255
+; NO-LD-SEQ-SA-NEXT:    sll.w $a2, $a2, $a3
+; NO-LD-SEQ-SA-NEXT:  .LBB4_1: # =>This Inner Loop Header: Depth=1
+; NO-LD-SEQ-SA-NEXT:    ll.w $a3, $a0, 0
+; NO-LD-SEQ-SA-NEXT:    and $a5, $a3, $a4
+; NO-LD-SEQ-SA-NEXT:    bne $a5, $a1, .LBB4_3
+; NO-LD-SEQ-SA-NEXT:  # %bb.2: # in Loop: Header=BB4_1 Depth=1
+; NO-LD-SEQ-SA-NEXT:    andn $a5, $a3, $a4
+; NO-LD-SEQ-SA-NEXT:    or $a5, $a5, $a2
+; NO-LD-SEQ-SA-NEXT:    sc.w $a5, $a0, 0
+; NO-LD-SEQ-SA-NEXT:    beqz $a5, .LBB4_1
+; NO-LD-SEQ-SA-NEXT:    b .LBB4_4
+; NO-LD-SEQ-SA-NEXT:  .LBB4_3:
+; NO-LD-SEQ-SA-NEXT:    dbar 1792
+; NO-LD-SEQ-SA-NEXT:  .LBB4_4:
+; NO-LD-SEQ-SA-NEXT:    ret
+;
+; LD-SEQ-SA-LABEL: cmpxchg_i8_acquire_monotonic:
+; LD-SEQ-SA:       # %bb.0:
+; LD-SEQ-SA-NEXT:    slli.d $a3, $a0, 3
+; LD-SEQ-SA-NEXT:    bstrins.d $a0, $zero, 1, 0
+; LD-SEQ-SA-NEXT:    ori $a4, $zero, 255
+; LD-SEQ-SA-NEXT:    sll.w $a4, $a4, $a3
+; LD-SEQ-SA-NEXT:    andi $a1, $a1, 255
+; LD-SEQ-SA-NEXT:    sll.w $a1, $a1, $a3
+; LD-SEQ-SA-NEXT:    andi $a2, $a2, 255
+; LD-SEQ-SA-NEXT:    sll.w $a2, $a2, $a3
+; LD-SEQ-SA-NEXT:  .LBB4_1: # =>This Inner Loop Header: Depth=1
+; LD-SEQ-SA-NEXT:    ll.w $a3, $a0, 0
+; LD-SEQ-SA-NEXT:    and $a5, $a3, $a4
+; LD-SEQ-SA-NEXT:    bne $a5, $a1, .LBB4_3
+; LD-SEQ-SA-NEXT:  # %bb.2: # in Loop: Header=BB4_1 Depth=1
+; LD-SEQ-SA-NEXT:    andn $a5, $a3, $a4
+; LD-SEQ-SA-NEXT:    or $a5, $a5, $a2
+; LD-SEQ-SA-NEXT:    sc.w $a5, $a0, 0
+; LD-SEQ-SA-NEXT:    beqz $a5, .LBB4_1
+; LD-SEQ-SA-NEXT:    b .LBB4_4
+; LD-SEQ-SA-NEXT:  .LBB4_3:
+; LD-SEQ-SA-NEXT:  .LBB4_4:
+; LD-SEQ-SA-NEXT:    ret
   %res = cmpxchg ptr %ptr, i8 %cmp, i8 %val acquire monotonic
   ret void
 }
 
 define void @cmpxchg_i16_acquire_monotonic(ptr %ptr, i16 %cmp, i16 %val) nounwind {
-; LA64-LABEL: cmpxchg_i16_acquire_monotonic:
-; LA64:       # %bb.0:
-; LA64-NEXT:    slli.d $a3, $a0, 3
-; LA64-NEXT:    bstrins.d $a0, $zero, 1, 0
-; LA64-NEXT:    lu12i.w $a4, 15
-; LA64-NEXT:    ori $a4, $a4, 4095
-; LA64-NEXT:    sll.w $a4, $a4, $a3
-; LA64-NEXT:    bstrpick.d $a1, $a1, 15, 0
-; LA64-NEXT:    sll.w $a1, $a1, $a3
-; LA64-NEXT:    bstrpick.d $a2, $a2, 15, 0
-; LA64-NEXT:    sll.w $a2, $a2, $a3
-; LA64-NEXT:  .LBB5_1: # =>This Inner Loop Header: Depth=1
-; LA64-NEXT:    ll.w $a3, $a0, 0
-; LA64-NEXT:    and $a5, $a3, $a4
-; LA64-NEXT:    bne $a5, $a1, .LBB5_3
-; LA64-NEXT:  # %bb.2: # in Loop: Header=BB5_1 Depth=1
-; LA64-NEXT:    andn $a5, $a3, $a4
-; LA64-NEXT:    or $a5, $a5, $a2
-; LA64-NEXT:    sc.w $a5, $a0, 0
-; LA64-NEXT:    beqz $a5, .LBB5_1
-; LA64-NEXT:    b .LBB5_4
-; LA64-NEXT:  .LBB5_3:
-; LA64-NEXT:    dbar 1792
-; LA64-NEXT:  .LBB5_4:
-; LA64-NEXT:    ret
+; NO-LD-SEQ-SA-LABEL: cmpxchg_i16_acquire_monotonic:
+; NO-LD-SEQ-SA:       # %bb.0:
+; NO-LD-SEQ-SA-NEXT:    slli.d $a3, $a0, 3
+; NO-LD-SEQ-SA-NEXT:    bstrins.d $a0, $zero, 1, 0
+; NO-LD-SEQ-SA-NEXT:    lu12i.w $a4, 15
+; NO-LD-SEQ-SA-NEXT:    ori $a4, $a4, 4095
+; NO-LD-SEQ-SA-NEXT:    sll.w $a4, $a4, $a3
+; NO-LD-SEQ-SA-NEXT:    bstrpick.d $a1, $a1, 15, 0
+; NO-LD-SEQ-SA-NEXT:    sll.w $a1, $a1, $a3
+; NO-LD-SEQ-SA-NEXT:    bstrpick.d $a2, $a2, 15, 0
+; NO-LD-SEQ-SA-NEXT:    sll.w $a2, $a2, $a3
+; NO-LD-SEQ-SA-NEXT:  .LBB5_1: # =>This Inner Loop Header: Depth=1
+; NO-LD-SEQ-SA-NEXT:    ll.w $a3, $a0, 0
+; NO-LD-SEQ-SA-NEXT:    and $a5, $a3, $a4
+; NO-LD-SEQ-SA-NEXT:    bne $a5, $a1, .LBB5_3
+; NO-LD-SEQ-SA-NEXT:  # %bb.2: # in Loop: Header=BB5_1 Depth=1
+; NO-LD-SEQ-SA-NEXT:    andn $a5, $a3, $a4
+; NO-LD-SEQ-SA-NEXT:    or $a5, $a5, $a2
+; NO-LD-SEQ-SA-NEXT:    sc.w $a5, $a0, 0
+; NO-LD-SEQ-SA-NEXT:    beqz $a5, .LBB5_1
+; NO-LD-SEQ-SA-NEXT:    b .LBB5_4
+; NO-LD-SEQ-SA-NEXT:  .LBB5_3:
+; NO-LD-SEQ-SA-NEXT:    dbar 1792
+; NO-LD-SEQ-SA-NEXT:  .LBB5_4:
+; NO-LD-SEQ-SA-NEXT:    ret
+;
+; LD-SEQ-SA-LABEL: cmpxchg_i16_acquire_monotonic:
+; LD-SEQ-SA:       # %bb.0:
+; LD-SEQ-SA-NEXT:    slli.d $a3, $a0, 3
+; LD-SEQ-SA-NEXT:    bstrins.d $a0, $zero, 1, 0
+; LD-SEQ-SA-NEXT:    lu12i.w $a4, 15
+; LD-SEQ-SA-NEXT:    ori $a4, $a4, 4095
+; LD-SEQ-SA-NEXT:    sll.w $a4, $a4, $a3
+; LD-SEQ-SA-NEXT:    bstrpick.d $a1, $a1, 15, 0
+; LD-SEQ-SA-NEXT:    sll.w $a1, $a1, $a3
+; LD-SEQ-SA-NEXT:    bstrpick.d $a2, $a2, 15, 0
+; LD-SEQ-SA-NEXT:    sll.w $a2, $a2, $a3
+; LD-SEQ-SA-NEXT:  .LBB5_1: # =>This Inner Loop Header: Depth=1
+; LD-SEQ-SA-NEXT:    ll.w $a3, $a0, 0
+; LD-SEQ-SA-NEXT:    and $a5, $a3, $a4
+; LD-SEQ-SA-NEXT:    bne $a5, $a1, .LBB5_3
+; LD-SEQ-SA-NEXT:  # %bb.2: # in Loop: Header=BB5_1 Depth=1
+; LD-SEQ-SA-NEXT:    andn $a5, $a3, $a4
+; LD-SEQ-SA-NEXT:    or $a5, $a5, $a2
+; LD-SEQ-SA-NEXT:    sc.w $a5, $a0, 0
+; LD-SEQ-SA-NEXT:    beqz $a5, .LBB5_1
+; LD-SEQ-SA-NEXT:    b .LBB5_4
+; LD-SEQ-SA-NEXT:  .LBB5_3:
+; LD-SEQ-SA-NEXT:  .LBB5_4:
+; LD-SEQ-SA-NEXT:    ret
   %res = cmpxchg ptr %ptr, i16 %cmp, i16 %val acquire monotonic
   ret void
 }
 
 define void @cmpxchg_i32_acquire_monotonic(ptr %ptr, i32 %cmp, i32 %val) nounwind {
-; LA64-LABEL: cmpxchg_i32_acquire_monotonic:
-; LA64:       # %bb.0:
-; LA64-NEXT:    addi.w $a1, $a1, 0
-; LA64-NEXT:  .LBB6_1: # =>This Inner Loop Header: Depth=1
-; LA64-NEXT:    ll.w $a3, $a0, 0
-; LA64-NEXT:    bne $a3, $a1, .LBB6_3
-; LA64-NEXT:  # %bb.2: # in Loop: Header=BB6_1 Depth=1
-; LA64-NEXT:    move $a4, $a2
-; LA64-NEXT:    sc.w $a4, $a0, 0
-; LA64-NEXT:    beqz $a4, .LBB6_1
-; LA64-NEXT:    b .LBB6_4
-; LA64-NEXT:  .LBB6_3:
-; LA64-NEXT:    dbar 1792
-; LA64-NEXT:  .LBB6_4:
-; LA64-NEXT:    ret
+; NO-LD-SEQ-SA-LABEL: cmpxchg_i32_acquire_monotonic:
+; NO-LD-SEQ-SA:       # %bb.0:
+; NO-LD-SEQ-SA-NEXT:    addi.w $a1, $a1, 0
+; NO-LD-SEQ-SA-NEXT:  .LBB6_1: # =>This Inner Loop Header: Depth=1
+; NO-LD-SEQ-SA-NEXT:    ll.w $a3, $a0, 0
+; NO-LD-SEQ-SA-NEXT:    bne $a3, $a1, .LBB6_3
+; NO-LD-SEQ-SA-NEXT:  # %bb.2: # in Loop: Header=BB6_1 Depth=1
+; NO-LD-SEQ-SA-NEXT:    move $a4, $a2
+; NO-LD-SEQ-SA-NEXT:    sc.w $a4, $a0, 0
+; NO-LD-SEQ-SA-NEXT:    beqz $a4, .LBB6_1
+; NO-LD-SEQ-SA-NEXT:    b .LBB6_4
+; NO-LD-SEQ-SA-NEXT:  .LBB6_3:
+; NO-LD-SEQ-SA-NEXT:    dbar 1792
+; NO-LD-SEQ-SA-NEXT:  .LBB6_4:
+; NO-LD-SEQ-SA-NEXT:    ret
+;
+; LD-SEQ-SA-LABEL: cmpxchg_i32_acquire_monotonic:
+; LD-SEQ-SA:       # %bb.0:
+; LD-SEQ-SA-NEXT:    addi.w $a1, $a1, 0
+; LD-SEQ-SA-NEXT:  .LBB6_1: # =>This Inner Loop Header: Depth=1
+; LD-SEQ-SA-NEXT:    ll.w $a3, $a0, 0
+; LD-SEQ-SA-NEXT:    bne $a3, $a1, .LBB6_3
+; LD-SEQ-SA-NEXT:  # %bb.2: # in Loop: Header=BB6_1 Depth=1
+; LD-SEQ-SA-NEXT:    move $a4, $a2
+; LD-SEQ-SA-NEXT:    sc.w $a4, $a0, 0
+; LD-SEQ-SA-NEXT:    beqz $a4, .LBB6_1
+; LD-SEQ-SA-NEXT:    b .LBB6_4
+; LD-SEQ-SA-NEXT:  .LBB6_3:
+; LD-SEQ-SA-NEXT:  .LBB6_4:
+; LD-SEQ-SA-NEXT:    ret
   %res = cmpxchg ptr %ptr, i32 %cmp, i32 %val acquire monotonic
   ret void
 }
 
 define void @cmpxchg_i64_acquire_monotonic(ptr %ptr, i64 %cmp, i64 %val) nounwind {
-; LA64-LABEL: cmpxchg_i64_acquire_monotonic:
-; LA64:       # %bb.0:
-; LA64-NEXT:  .LBB7_1: # =>This Inner Loop Header: Depth=1
-; LA64-NEXT:    ll.d $a3, $a0, 0
-; LA64-NEXT:    bne $a3, $a1, .LBB7_3
-; LA64-NEXT:  # %bb.2: # in Loop: Header=BB7_1 Depth=1
-; LA64-NEXT:    move $a4, $a2
-; LA64-NEXT:    sc.d $a4, $a0, 0
-; LA64-NEXT:    beqz $a4, .LBB7_1
-; LA64-NEXT:    b .LBB7_4
-; LA64-NEXT:  .LBB7_3:
-; LA64-NEXT:    dbar 1792
-; LA64-NEXT:  .LBB7_4:
-; LA64-NEXT:    ret
+; NO-LD-SEQ-SA-LABEL: cmpxchg_i64_acquire_monotonic:
+; NO-LD-SEQ-SA:       # %bb.0:
+; NO-LD-SEQ-SA-NEXT:  .LBB7_1: # =>This Inner Loop Header: Depth=1
+; NO-LD-SEQ-SA-NEXT:    ll.d $a3, $a0, 0
+; NO-LD-SEQ-SA-NEXT:    bne $a3, $a1, .LBB7_3
+; NO-LD-SEQ-SA-NEXT:  # %bb.2: # in Loop: Header=BB7_1 Depth=1
+; NO-LD-SEQ-SA-NEXT:    move $a4, $a2
+; NO-LD-SEQ-SA-NEXT:    sc.d $a4, $a0, 0
+; NO-LD-SEQ-SA-NEXT:    beqz $a4, .LBB7_1
+; NO-LD-SEQ-SA-NEXT:    b .LBB7_4
+; NO-LD-SEQ-SA-NEXT:  .LBB7_3:
+; NO-LD-SEQ-SA-NEXT:    dbar 1792
+; NO-LD-SEQ-SA-NEXT:  .LBB7_4:
+; NO-LD-SEQ-SA-NEXT:    ret
+;
+; LD-SEQ-SA-LABEL: cmpxchg_i64_acquire_monotonic:
+; LD-SEQ-SA:       # %bb.0:
+; LD-SEQ-SA-NEXT:  .LBB7_1: # =>This Inner Loop Header: Depth=1
+; LD-SEQ-SA-NEXT:    ll.d $a3, $a0, 0
+; LD-SEQ-SA-NEXT:    bne $a3, $a1, .LBB7_3
+; LD-SEQ-SA-NEXT:  # %bb.2: # in Loop: Header=BB7_1 Depth=1
+; LD-SEQ-SA-NEXT:    move $a4, $a2
+; LD-SEQ-SA-NEXT:    sc.d $a4, $a0, 0
+; LD-SEQ-SA-NEXT:    beqz $a4, .LBB7_1
+; LD-SEQ-SA-NEXT:    b .LBB7_4
+; LD-SEQ-SA-NEXT:  .LBB7_3:
+; LD-SEQ-SA-NEXT:  .LBB7_4:
+; LD-SEQ-SA-NEXT:    ret
   %res = cmpxchg ptr %ptr, i64 %cmp, i64 %val acquire monotonic
   ret void
 }
@@ -416,316 +495,564 @@ define i1 @cmpxchg_i64_acquire_acquire_reti1(ptr %ptr, i64 %cmp, i64 %val) nounw
 }
 
 define void @cmpxchg_i8_monotonic_monotonic(ptr %ptr, i8 %cmp, i8 %val) nounwind {
-; LA64-LABEL: cmpxchg_i8_monotonic_monotonic:
-; LA64:       # %bb.0:
-; LA64-NEXT:    slli.d $a3, $a0, 3
-; LA64-NEXT:    bstrins.d $a0, $zero, 1, 0
-; LA64-NEXT:    ori $a4, $zero, 255
-; LA64-NEXT:    sll.w $a4, $a4, $a3
-; LA64-NEXT:    andi $a1, $a1, 255
-; LA64-NEXT:    sll.w $a1, $a1, $a3
-; LA64-NEXT:    andi $a2, $a2, 255
-; LA64-NEXT:    sll.w $a2, $a2, $a3
-; LA64-NEXT:  .LBB16_1: # =>This Inner Loop Header: Depth=1
-; LA64-NEXT:    ll.w $a3, $a0, 0
-; LA64-NEXT:    and $a5, $a3, $a4
-; LA64-NEXT:    bne $a5, $a1, .LBB16_3
-; LA64-NEXT:  # %bb.2: # in Loop: Header=BB16_1 Depth=1
-; LA64-NEXT:    andn $a5, $a3, $a4
-; LA64-NEXT:    or $a5, $a5, $a2
-; LA64-NEXT:    sc.w $a5, $a0, 0
-; LA64-NEXT:    beqz $a5, .LBB16_1
-; LA64-NEXT:    b .LBB16_4
-; LA64-NEXT:  .LBB16_3:
-; LA64-NEXT:    dbar 1792
-; LA64-NEXT:  .LBB16_4:
-; LA64-NEXT:    ret
+; NO-LD-SEQ-SA-LABEL: cmpxchg_i8_monotonic_monotonic:
+; NO-LD-SEQ-SA:       # %bb.0:
+; NO-LD-SEQ-SA-NEXT:    slli.d $a3, $a0, 3
+; NO-LD-SEQ-SA-NEXT:    bstrins.d $a0, $zero, 1, 0
+; NO-LD-SEQ-SA-NEXT:    ori $a4, $zero, 255
+; NO-LD-SEQ-SA-NEXT:    sll.w $a4, $a4, $a3
+; NO-LD-SEQ-SA-NEXT:    andi $a1, $a1, 255
+; NO-LD-SEQ-SA-NEXT:    sll.w $a1, $a1, $a3
+; NO-LD-SEQ-SA-NEXT:    andi $a2, $a2, 255
+; NO-LD-SEQ-SA-NEXT:    sll.w $a2, $a2, $a3
+; NO-LD-SEQ-SA-NEXT:  .LBB16_1: # =>This Inner Loop Header: Depth=1
+; NO-LD-SEQ-SA-NEXT:    ll.w $a3, $a0, 0
+; NO-LD-SEQ-SA-NEXT:    and $a5, $a3, $a4
+; NO-LD-SEQ-SA-NEXT:    bne $a5, $a1, .LBB16_3
+; NO-LD-SEQ-SA-NEXT:  # %bb.2: # in Loop: Header=BB16_1 Depth=1
+; NO-LD-SEQ-SA-NEXT:    andn $a5, $a3, $a4
+; NO-LD-SEQ-SA-NEXT:    or $a5, $a5, $a2
+; NO-LD-SEQ-SA-NEXT:    sc.w $a5, $a0, 0
+; NO-LD-SEQ-SA-NEXT:    beqz $a5, .LBB16_1
+; NO-LD-SEQ-SA-NEXT:    b .LBB16_4
+; NO-LD-SEQ-SA-NEXT:  .LBB16_3:
+; NO-LD-SEQ-SA-NEXT:    dbar 1792
+; NO-LD-SEQ-SA-NEXT:  .LBB16_4:
+; NO-LD-SEQ-SA-NEXT:    ret
+;
+; LD-SEQ-SA-LABEL: cmpxchg_i8_monotonic_monotonic:
+; LD-SEQ-SA:       # %bb.0:
+; LD-SEQ-SA-NEXT:    slli.d $a3, $a0, 3
+; LD-SEQ-SA-NEXT:    bstrins.d $a0, $zero, 1, 0
+; LD-SEQ-SA-NEXT:    ori $a4, $zero, 255
+; LD-SEQ-SA-NEXT:    sll.w $a4, $a4, $a3
+; LD-SEQ-SA-NEXT:    andi $a1, $a1, 255
+; LD-SEQ-SA-NEXT:    sll.w $a1, $a1, $a3
+; LD-SEQ-SA-NEXT:    andi $a2, $a2, 255
+; LD-SEQ-SA-NEXT:    sll.w $a2, $a2, $a3
+; LD-SEQ-SA-NEXT:  .LBB16_1: # =>This Inner Loop Header: Depth=1
+; LD-SEQ-SA-NEXT:    ll.w $a3, $a0, 0
+; LD-SEQ-SA-NEXT:    and $a5, $a3, $a4
+; LD-SEQ-SA-NEXT:    bne $a5, $a1, .LBB16_3
+; LD-SEQ-SA-NEXT:  # %bb.2: # in Loop: Header=BB16_1 Depth=1
+; LD-SEQ-SA-NEXT:    andn $a5, $a3, $a4
+; LD-SEQ-SA-NEXT:    or $a5, $a5, $a2
+; LD-SEQ-SA-NEXT:    sc.w $a5, $a0, 0
+; LD-SEQ-SA-NEXT:    beqz $a5, .LBB16_1
+; LD-SEQ-SA-NEXT:    b .LBB16_4
+; LD-SEQ-SA-NEXT:  .LBB16_3:
+; LD-SEQ-SA-NEXT:  .LBB16_4:
+; LD-SEQ-SA-NEXT:    ret
   %res = cmpxchg ptr %ptr, i8 %cmp, i8 %val monotonic monotonic
   ret void
 }
 
 define void @cmpxchg_i16_monotonic_monotonic(ptr %ptr, i16 %cmp, i16 %val) nounwind {
-; LA64-LABEL: cmpxchg_i16_monotonic_monotonic:
-; LA64:       # %bb.0:
-; LA64-NEXT:    slli.d $a3, $a0, 3
-; LA64-NEXT:    bstrins.d $a0, $zero, 1, 0
-; LA64-NEXT:    lu12i.w $a4, 15
-; LA64-NEXT:    ori $a4, $a4, 4095
-; LA64-NEXT:    sll.w $a4, $a4, $a3
-; LA64-NEXT:    bstrpick.d $a1, $a1, 15, 0
-; LA64-NEXT:    sll.w $a1, $a1, $a3
-; LA64-NEXT:    bstrpick.d $a2, $a2, 15, 0
-; LA64-NEXT:    sll.w $a2, $a2, $a3
-; LA64-NEXT:  .LBB17_1: # =>This Inner Loop Header: Depth=1
-; LA64-NEXT:    ll.w $a3, $a0, 0
-; LA64-NEXT:    and $a5, $a3, $a4
-; LA64-NEXT:    bne $a5, $a1, .LBB17_3
-; LA64-NEXT:  # %bb.2: # in Loop: Header=BB17_1 Depth=1
-; LA64-NEXT:    andn $a5, $a3, $a4
-; LA64-NEXT:    or $a5, $a5, $a2
-; LA64-NEXT:    sc.w $a5, $a0, 0
-; LA64-NEXT:    beqz $a5, .LBB17_1
-; LA64-NEXT:    b .LBB17_4
-; LA64-NEXT:  .LBB17_3:
-; LA64-NEXT:    dbar 1792
-; LA64-NEXT:  .LBB17_4:
-; LA64-NEXT:    ret
+; NO-LD-SEQ-SA-LABEL: cmpxchg_i16_monotonic_monotonic:
+; NO-LD-SEQ-SA:       # %bb.0:
+; NO-LD-SEQ-SA-NEXT:    slli.d $a3, $a0, 3
+; NO-LD-SEQ-SA-NEXT:    bstrins.d $a0, $zero, 1, 0
+; NO-LD-SEQ-SA-NEXT:    lu12i.w $a4, 15
+; NO-LD-SEQ-SA-NEXT:    ori $a4, $a4, 4095
+; NO-LD-SEQ-SA-NEXT:    sll.w $a4, $a4, $a3
+; NO-LD-SEQ-SA-NEXT:    bstrpick.d $a1, $a1, 15, 0
+; NO-LD-SEQ-SA-NEXT:    sll.w $a1, $a1, $a3
+; NO-LD-SEQ-SA-NEXT:    bstrpick.d $a2, $a2, 15, 0
+; NO-LD-SEQ-SA-NEXT:    sll.w $a2, $a2, $a3
+; NO-LD-SEQ-SA-NEXT:  .LBB17_1: # =>This Inner Loop Header: Depth=1
+; NO-LD-SEQ-SA-NEXT:    ll.w $a3, $a0, 0
+; NO-LD-SEQ-SA-NEXT:    and $a5, $a3, $a4
+; NO-LD-SEQ-SA-NEXT:    bne $a5, $a1, .LBB17_3
+; NO-LD-SEQ-SA-NEXT:  # %bb.2: # in Loop: Header=BB17_1 Depth=1
+; NO-LD-SEQ-SA-NEXT:    andn $a5, $a3, $a4
+; NO-LD-SEQ-SA-NEXT:    or $a5, $a5, $a2
+; NO-LD-SEQ-SA-NEXT:    sc.w $a5, $a0, 0
+; NO-LD-SEQ-SA-NEXT:    beqz $a5, .LBB17_1
+; NO-LD-SEQ-SA-NEXT:    b .LBB17_4
+; NO-LD-SEQ-SA-NEXT:  .LBB17_3:
+; NO-LD-SEQ-SA-NEXT:    dbar 1792
+; NO-LD-SEQ-SA-NEXT:  .LBB17_4:
+; NO-LD-SEQ-SA-NEXT:    ret
+;
+; LD-SEQ-SA-LABEL: cmpxchg_i16_monotonic_monotonic:
+; LD-SEQ-SA:       # %bb.0:
+; LD-SEQ-SA-NEXT:    slli.d $a3, $a0, 3
+; LD-SEQ-SA-NEXT:    bstrins.d $a0, $zero, 1, 0
+; LD-SEQ-SA-NEXT:    lu12i.w $a4, 15
+; LD-SEQ-SA-NEXT:    ori $a4, $a4, 4095
+; LD-SEQ-SA-NEXT:    sll.w $a4, $a4, $a3
+; LD-SEQ-SA-NEXT:    bstrpick.d $a1, $a1, 15, 0
+; LD-SEQ-SA-NEXT:    sll.w $a1, $a1, $a3
+; LD-SEQ-SA-NEXT:    bstrpick.d $a2, $a2, 15, 0
+; LD-SEQ-SA-NEXT:    sll.w $a2, $a2, $a3
+; LD-SEQ-SA-NEXT:  .LBB17_1: # =>This Inner Loop Header: Depth=1
+; LD-SEQ-SA-NEXT:    ll.w $a3, $a0, 0
+; LD-SEQ-SA-NEXT:    and $a5, $a3, $a4
+; LD-SEQ-SA-NEXT:    bne $a5, $a1, .LBB17_3
+; LD-SEQ-SA-NEXT:  # %bb.2: # in Loop: Header=BB17_1 Depth=1
+; LD-SEQ-SA-NEXT:    andn $a5, $a3, $a4
+; LD-SEQ-SA-NEXT:    or $a5, $a5, $a2
+; LD-SEQ-SA-NEXT:    sc.w $a5, $a0, 0
+; LD-SEQ-SA-NEXT:    beqz $a5, .LBB17_1
+; LD-SEQ-SA-NEXT:    b .LBB17_4
+; LD-SEQ-SA-NEXT:  .LBB17_3:
+; LD-SEQ-SA-NEXT:  .LBB17_4:
+; LD-SEQ-SA-NEXT:    ret
   %res = cmpxchg ptr %ptr, i16 %cmp, i16 %val monotonic monotonic
   ret void
 }
 
 define void @cmpxchg_i32_monotonic_monotonic(ptr %ptr, i32 %cmp, i32 %val) nounwind {
-; LA64-LABEL: cmpxchg_i32_monotonic_monotonic:
-; LA64:       # %bb.0:
-; LA64-NEXT:    addi.w $a1, $a1, 0
-; LA64-NEXT:  .LBB18_1: # =>This Inner Loop Header: Depth=1
-; LA64-NEXT:    ll.w $a3, $a0, 0
-; LA64-NEXT:    bne $a3, $a1, .LBB18_3
-; LA64-NEXT:  # %bb.2: # in Loop: Header=BB18_1 Depth=1
-; LA64-NEXT:    move $a4, $a2
-; LA64-NEXT:    sc.w $a4, $a0, 0
-; LA64-NEXT:    beqz $a4, .LBB18_1
-; LA64-NEXT:    b .LBB18_4
-; LA64-NEXT:  .LBB18_3:
-; LA64-NEXT:    dbar 1792
-; LA64-NEXT:  .LBB18_4:
-; LA64-NEXT:    ret
+; NO-LD-SEQ-SA-LABEL: cmpxchg_i32_monotonic_monotonic:
+; NO-LD-SEQ-SA:       # %bb.0:
+; NO-LD-SEQ-SA-NEXT:    addi.w $a1, $a1, 0
+; NO-LD-SEQ-SA-NEXT:  .LBB18_1: # =>This Inner Loop Header: Depth=1
+; NO-LD-SEQ-SA-NEXT:    ll.w $a3, $a0, 0
+; NO-LD-SEQ-SA-NEXT:    bne $a3, $a1, .LBB18_3
+; NO-LD-SEQ-SA-NEXT:  # %bb.2: # in Loop: Header=BB18_1 Depth=1
+; NO-LD-SEQ-SA-NEXT:    move $a4, $a2
+; NO-LD-SEQ-SA-NEXT:    sc.w $a4, $a0, 0
+; NO-LD-SEQ-SA-NEXT:    beqz $a4, .LBB18_1
+; NO-LD-SEQ-SA-NEXT:    b .LBB18_4
+; NO-LD-SEQ-SA-NEXT:  .LBB18_3:
+; NO-LD-SEQ-SA-NEXT:    dbar 1792
+; NO-LD-SEQ-SA-NEXT:  .LBB18_4:
+; NO-LD-SEQ-SA-NEXT:    ret
+;
+; LD-SEQ-SA-LABEL: cmpxchg_i32_monotonic_monotonic:
+; LD-SEQ-SA:       # %bb.0:
+; LD-SEQ-SA-NEXT:    addi.w $a1, $a1, 0
+; LD-SEQ-SA-NEXT:  .LBB18_1: # =>This Inner Loop Header: Depth=1
+; LD-SEQ-SA-NEXT:    ll.w $a3, $a0, 0
+; LD-SEQ-SA-NEXT:    bne $a3, $a1, .LBB18_3
+; LD-SEQ-SA-NEXT:  # %bb.2: # in Loop: Header=BB18_1 Depth=1
+; LD-SEQ-SA-NEXT:    move $a4, $a2
+; LD-SEQ-SA-NEXT:    sc.w $a4, $a0, 0
+; LD-SEQ-SA-NEXT:    beqz $a4, .LBB18_1
+; LD-SEQ-SA-NEXT:    b .LBB18_4
+; LD-SEQ-SA-NEXT:  .LBB18_3:
+; LD-SEQ-SA-NEXT:  .LBB18_4:
+; LD-SEQ-SA-NEXT:    ret
   %res = cmpxchg ptr %ptr, i32 %cmp, i32 %val monotonic monotonic
   ret void
 }
 
 define void @cmpxchg_i64_monotonic_monotonic(ptr %ptr, i64 %cmp, i64 %val) nounwind {
-; LA64-LABEL: cmpxchg_i64_monotonic_monotonic:
-; LA64:       # %bb.0:
-; LA64-NEXT:  .LBB19_1: # =>This Inner Loop Header: Depth=1
-; LA64-NEXT:    ll.d $a3, $a0, 0
-; LA64-NEXT:    bne $a3, $a1, .LBB19_3
-; LA64-NEXT:  # %bb.2: # in Loop: Header=BB19_1 Depth=1
-; LA64-NEXT:    move $a4, $a2
-; LA64-NEXT:    sc.d $a4, $a0, 0
-; LA64-NEXT:    beqz $a4, .LBB19_1
-; LA64-NEXT:    b .LBB19_4
-; LA64-NEXT:  .LBB19_3:
-; LA64-NEXT:    dbar 1792
-; LA64-NEXT:  .LBB19_4:
-; LA64-NEXT:    ret
+; NO-LD-SEQ-SA-LABEL: cmpxchg_i64_monotonic_monotonic:
+; NO-LD-SEQ-SA:       # %bb.0:
+; NO-LD-SEQ-SA-NEXT:  .LBB19_1: # =>This Inner Loop Header: Depth=1
+; NO-LD-SEQ-SA-NEXT:    ll.d $a3, $a0, 0
+; NO-LD-SEQ-SA-NEXT:    bne $a3, $a1, .LBB19_3
+; NO-LD-SEQ-SA-NEXT:  # %bb.2: # in Loop: Header=BB19_1 Depth=1
+; NO-LD-SEQ-SA-NEXT:    move $a4, $a2
+; NO-LD-SEQ-SA-NEXT:    sc.d $a4, $a0, 0
+; NO-LD-SEQ-SA-NEXT:    beqz $a4, .LBB19_1
+; NO-LD-SEQ-SA-NEXT:    b .LBB19_4
+; NO-LD-SEQ-SA-NEXT:  .LBB19_3:
+; NO-LD-SEQ-SA-NEXT:    dbar 1792
+; NO-LD-SEQ-SA-NEXT:  .LBB19_4:
+; NO-LD-SEQ-SA-NEXT:    ret
+;
+; LD-SEQ-SA-LABEL: cmpxchg_i64_monotonic_monotonic:
+; LD-SEQ-SA:       # %bb.0:
+; LD-SEQ-SA-NEXT:  .LBB19_1: # =>This Inner Loop Header: Depth=1
+; LD-SEQ-SA-NEXT:    ll.d $a3, $a0, 0
+; LD-SEQ-SA-NEXT:    bne $a3, $a1, .LBB19_3
+; LD-SEQ-SA-NEXT:  # %bb.2: # in Loop: Header=BB19_1 Depth=1
+; LD-SEQ-SA-NEXT:    move $a4, $a2
+; LD-SEQ-SA-NEXT:    sc.d $a4, $a0, 0
+; LD-SEQ-SA-NEXT:    beqz $a4, .LBB19_1
+; LD-SEQ-SA-NEXT:    b .LBB19_4
+; LD-SEQ-SA-NEXT:  .LBB19_3:
+; LD-SEQ-SA-NEXT:  .LBB19_4:
+; LD-SEQ-SA-NEXT:    ret
   %res = cmpxchg ptr %ptr, i64 %cmp, i64 %val monotonic monotonic
   ret void
 }
 
 define i8 @cmpxchg_i8_monotonic_monotonic_reti8(ptr %ptr, i8 %cmp, i8 %val) nounwind {
-; LA64-LABEL: cmpxchg_i8_monotonic_monotonic_reti8:
-; LA64:       # %bb.0:
-; LA64-NEXT:    slli.d $a3, $a0, 3
-; LA64-NEXT:    bstrins.d $a0, $zero, 1, 0
-; LA64-NEXT:    ori $a4, $zero, 255
-; LA64-NEXT:    sll.w $a4, $a4, $a3
-; LA64-NEXT:    andi $a1, $a1, 255
-; LA64-NEXT:    sll.w $a1, $a1, $a3
-; LA64-NEXT:    andi $a2, $a2, 255
-; LA64-NEXT:    sll.w $a2, $a2, $a3
-; LA64-NEXT:  .LBB20_1: # =>This Inner Loop Header: Depth=1
-; LA64-NEXT:    ll.w $a5, $a0, 0
-; LA64-NEXT:    and $a6, $a5, $a4
-; LA64-NEXT:    bne $a6, $a1, .LBB20_3
-; LA64-NEXT:  # %bb.2: # in Loop: Header=BB20_1 Depth=1
-; LA64-NEXT:    andn $a6, $a5, $a4
-; LA64-NEXT:    or $a6, $a6, $a2
-; LA64-NEXT:    sc.w $a6, $a0, 0
-; LA64-NEXT:    beqz $a6, .LBB20_1
-; LA64-NEXT:    b .LBB20_4
-; LA64-NEXT:  .LBB20_3:
-; LA64-NEXT:    dbar 1792
-; LA64-NEXT:  .LBB20_4:
-; LA64-NEXT:    srl.w $a0, $a5, $a3
-; LA64-NEXT:    ret
+; NO-LD-SEQ-SA-LABEL: cmpxchg_i8_monotonic_monotonic_reti8:
+; NO-LD-SEQ-SA:       # %bb.0:
+; NO-LD-SEQ-SA-NEXT:    slli.d $a3, $a0, 3
+; NO-LD-SEQ-SA-NEXT:    bstrins.d $a0, $zero, 1, 0
+; NO-LD-SEQ-SA-NEXT:    ori $a4, $zero, 255
+; NO-LD-SEQ-SA-NEXT:    sll.w $a4, $a4, $a3
+; NO-LD-SEQ-SA-NEXT:    andi $a1, $a1, 255
+; NO-LD-SEQ-SA-NEXT:    sll.w $a1, $a1, $a3
+; NO-LD-SEQ-SA-NEXT:    andi $a2, $a2, 255
+; NO-LD-SEQ-SA-NEXT:    sll.w $a2, $a2, $a3
+; NO-LD-SEQ-SA-NEXT:  .LBB20_1: # =>This Inner Loop Header: Depth=1
+; NO-LD-SEQ-SA-NEXT:    ll.w $a5, $a0, 0
+; NO-LD-SEQ-SA-NEXT:    and $a6, $a5, $a4
+; NO-LD-SEQ-SA-NEXT:    bne $a6, $a1, .LBB20_3
+; NO-LD-SEQ-SA-NEXT:  # %bb.2: # in Loop: Header=BB20_1 Depth=1
+; NO-LD-SEQ-SA-NEXT:    andn $a6, $a5, $a4
+; NO-LD-SEQ-SA-NEXT:    or $a6, $a6, $a2
+; NO-LD-SEQ-SA-NEXT:    sc.w $a6, $a0, 0
+; NO-LD-SEQ-SA-NEXT:    beqz $a6, .LBB20_1
+; NO-LD-SEQ-SA-NEXT:    b .LBB20_4
+; NO-LD-SEQ-SA-NEXT:  .LBB20_3:
+; NO-LD-SEQ-SA-NEXT:    dbar 1792
+; NO-LD-SEQ-SA-NEXT:  .LBB20_4:
+; NO-LD-SEQ-SA-NEXT:    srl.w $a0, $a5, $a3
+; NO-LD-SEQ-SA-NEXT:    ret
+;
+; LD-SEQ-SA-LABEL: cmpxchg_i8_monotonic_monotonic_reti8:
+; LD-SEQ-SA:       # %bb.0:
+; LD-SEQ-SA-NEXT:    slli.d $a3, $a0, 3
+; LD-SEQ-SA-NEXT:    bstrins.d $a0, $zero, 1, 0
+; LD-SEQ-SA-NEXT:    ori $a4, $zero, 255
+; LD-SEQ-SA-NEXT:    sll.w $a4, $a4, $a3
+; LD-SEQ-SA-NEXT:    andi $a1, $a1, 255
+; LD-SEQ-SA-NEXT:    sll.w $a1, $a1, $a3
+; LD-SEQ-SA-NEXT:    andi $a2, $a2, 255
+; LD-SEQ-SA-NEXT:    sll.w $a2, $a2, $a3
+; LD-SEQ-SA-NEXT:  .LBB20_1: # =>This Inner Loop Header: Depth=1
+; LD-SEQ-SA-NEXT:    ll.w $a5, $a0, 0
+; LD-SEQ-SA-NEXT:    and $a6, $a5, $a4
+; LD-SEQ-SA-NEXT:    bne $a6, $a1, .LBB20_3
+; LD-SEQ-SA-NEXT:  # %bb.2: # in Loop: Header=BB20_1 Depth=1
+; LD-SEQ-SA-NEXT:    andn $a6, $a5, $a4
+; LD-SEQ-SA-NEXT:    or $a6, $a6, $a2
+; LD-SEQ-SA-NEXT:    sc.w $a6, $a0, 0
+; LD-SEQ-SA-NEXT:    beqz $a6, .LBB20_1
+; LD-SEQ-SA-NEXT:    b .LBB20_4
+; LD-SEQ-SA-NEXT:  .LBB20_3:
+; LD-SEQ-SA-NEXT:  .LBB20_4:
+; LD-SEQ-SA-NEXT:    srl.w $a0, $a5, $a3
+; LD-SEQ-SA-NEXT:    ret
   %tmp = cmpxchg ptr %ptr, i8 %cmp, i8 %val monotonic monotonic
   %res = extractvalue { i8, i1 } %tmp, 0
   ret i8 %res
 }
 
 define i16 @cmpxchg_i16_monotonic_monotonic_reti16(ptr %ptr, i16 %cmp, i16 %val) nounwind {
-; LA64-LABEL: cmpxchg_i16_monotonic_monotonic_reti16:
-; LA64:       # %bb.0:
-; LA64-NEXT:    slli.d $a3, $a0, 3
-; LA64-NEXT:    bstrins.d $a0, $zero, 1, 0
-; LA64-NEXT:    lu12i.w $a4, 15
-; LA64-NEXT:    ori $a4, $a4, 4095
-; LA64-NEXT:    sll.w $a4, $a4, $a3
-; LA64-NEXT:    bstrpick.d $a1, $a1, 15, 0
-; LA64-NEXT:    sll.w $a1, $a1, $a3
-; LA64-NEXT:    bstrpick.d $a2, $a2, 15, 0
-; LA64-NEXT:    sll.w $a2, $a2, $a3
-; LA64-NEXT:  .LBB21_1: # =>This Inner Loop Header: Depth=1
-; LA64-NEXT:    ll.w $a5, $a0, 0
-; LA64-NEXT:    and $a6, $a5, $a4
-; LA64-NEXT:    bne $a6, $a1, .LBB21_3
-; LA64-NEXT:  # %bb.2: # in Loop: Header=BB21_1 Depth=1
-; LA64-NEXT:    andn $a6, $a5, $a4
-; LA64-NEXT:    or $a6, $a6, $a2
-; LA64-NEXT:    sc.w $a6, $a0, 0
-; LA64-NEXT:    beqz $a6, .LBB21_1
-; LA64-NEXT:    b .LBB21_4
-; LA64-NEXT:  .LBB21_3:
-; LA64-NEXT:    dbar 1792
-; LA64-NEXT:  .LBB21_4:
-; LA64-NEXT:    srl.w $a0, $a5, $a3
-; LA64-NEXT:    ret
+; NO-LD-SEQ-SA-LABEL: cmpxchg_i16_monotonic_monotonic_reti16:
+; NO-LD-SEQ-SA:       # %bb.0:
+; NO-LD-SEQ-SA-NEXT:    slli.d $a3, $a0, 3
+; NO-LD-SEQ-SA-NEXT:    bstrins.d $a0, $zero, 1, 0
+; NO-LD-SEQ-SA-NEXT:    lu12i.w $a4, 15
+; NO-LD-SEQ-SA-NEXT:    ori $a4, $a4, 4095
+; NO-LD-SEQ-SA-NEXT:    sll.w $a4, $a4, $a3
+; NO-LD-SEQ-SA-NEXT:    bstrpick.d $a1, $a1, 15, 0
+; NO-LD-SEQ-SA-NEXT:    sll.w $a1, $a1, $a3
+; NO-LD-SEQ-SA-NEXT:    bstrpick.d $a2, $a2, 15, 0
+; NO-LD-SEQ-SA-NEXT:    sll.w $a2, $a2, $a3
+; NO-LD-SEQ-SA-NEXT:  .LBB21_1: # =>This Inner Loop Header: Depth=1
+; NO-LD-SEQ-SA-NEXT:    ll.w $a5, $a0, 0
+; NO-LD-SEQ-SA-NEXT:    and $a6, $a5, $a4
+; NO-LD-SEQ-SA-NEXT:    bne $a6, $a1, .LBB21_3
+; NO-LD-SEQ-SA-NEXT:  # %bb.2: # in Loop: Header=BB21_1 Depth=1
+; NO-LD-SEQ-SA-NEXT:    andn $a6, $a5, $a4
+; NO-LD-SEQ-SA-NEXT:    or $a6, $a6, $a2
+; NO-LD-SEQ-SA-NEXT:    sc.w $a6, $a0, 0
+; NO-LD-SEQ-SA-NEXT:    beqz $a6, .LBB21_1
+; NO-LD-SEQ-SA-NEXT:    b .LBB21_4
+; NO-LD-SEQ-SA-NEXT:  .LBB21_3:
+; NO-LD-SEQ-SA-NEXT:    dbar 1792
+; NO-LD-SEQ-SA-NEXT:  .LBB21_4:
+; NO-LD-SEQ-SA-NEXT:    srl.w $a0, $a5, $a3
+; NO-LD-SEQ-SA-NEXT:    ret
+;
+; LD-SEQ-SA-LABEL: cmpxchg_i16_monotonic_monotonic_reti16:
+; LD-SEQ-SA:       # %bb.0:
+; LD-SEQ-SA-NEXT:    slli.d $a3, $a0, 3
+; LD-SEQ-SA-NEXT:    bstrins.d $a0, $zero, 1, 0
+; LD-SEQ-SA-NEXT:    lu12i.w $a4, 15
+; LD-SEQ-SA-NEXT:    ori $a4, $a4, 4095
+; LD-SEQ-SA-NEXT:    sll.w $a4, $a4, $a3
+; LD-SEQ-SA-NEXT:    bstrpick.d $a1, $a1, 15, 0
+; LD-SEQ-SA-NEXT:    sll.w $a1, $a1, $a3
+; LD-SEQ-SA-NEXT:    bstrpick.d $a2, $a2, 15, 0
+; LD-SEQ-SA-NEXT:    sll.w $a2, $a2, $a3
+; LD-SEQ-SA-NEXT:  .LBB21_1: # =>This Inner Loop Header: Depth=1
+; LD-SEQ-SA-NEXT:    ll.w $a5, $a0, 0
+; LD-SEQ-SA-NEXT:    and $a6, $a5, $a4
+; LD-SEQ-SA-NEXT:    bne $a6, $a1, .LBB21_3
+; LD-SEQ-SA-NEXT:  # %bb.2: # in Loop: Header=BB21_1 Depth=1
+; LD-SEQ-SA-NEXT:    andn $a6, $a5, $a4
+; LD-SEQ-SA-NEXT:    or $a6, $a6, $a2
+; LD-SEQ-SA-NEXT:    sc.w $a6, $a0, 0
+; LD-SEQ-SA-NEXT:    beqz $a6, .LBB21_1
+; LD-SEQ-SA-NEXT:    b .LBB21_4
+; LD-SEQ-SA-NEXT:  .LBB21_3:
+; LD-SEQ-SA-NEXT:  .LBB21_4:
+; LD-SEQ-SA-NEXT:    srl.w $a0, $a5, $a3
+; LD-SEQ-SA-NEXT:    ret
   %tmp = cmpxchg ptr %ptr, i16 %cmp, i16 %val monotonic monotonic
   %res = extractvalue { i16, i1 } %tmp, 0
   ret i16 %res
 }
 
 define i32 @cmpxchg_i32_monotonic_monotonic_reti32(ptr %ptr, i32 %cmp, i32 %val) nounwind {
-; LA64-LABEL: cmpxchg_i32_monotonic_monotonic_reti32:
-; LA64:       # %bb.0:
-; LA64-NEXT:    addi.w $a3, $a1, 0
-; LA64-NEXT:  .LBB22_1: # =>This Inner Loop Header: Depth=1
-; LA64-NEXT:    ll.w $a1, $a0, 0
-; LA64-NEXT:    bne $a1, $a3, .LBB22_3
-; LA64-NEXT:  # %bb.2: # in Loop: Header=BB22_1 Depth=1
-; LA64-NEXT:    move $a4, $a2
-; LA64-NEXT:    sc.w $a4, $a0, 0
-; LA64-NEXT:    beqz $a4, .LBB22_1
-; LA64-NEXT:    b .LBB22_4
-; LA64-NEXT:  .LBB22_3:
-; LA64-NEXT:    dbar 1792
-; LA64-NEXT:  .LBB22_4:
-; LA64-NEXT:    move $a0, $a1
-; LA64-NEXT:    ret
+; NO-LD-SEQ-SA-LABEL: cmpxchg_i32_monotonic_monotonic_reti32:
+; NO-LD-SEQ-SA:       # %bb.0:
+; NO-LD-SEQ-SA-NEXT:    addi.w $a3, $a1, 0
+; NO-LD-SEQ-SA-NEXT:  .LBB22_1: # =>This Inner Loop Header: Depth=1
+; NO-LD-SEQ-SA-NEXT:    ll.w $a1, $a0, 0
+; NO-LD-SEQ-SA-NEXT:    bne $a1, $a3, .LBB22_3
+; NO-LD-SEQ-SA-NEXT:  # %bb.2: # in Loop: Header=BB22_1 Depth=1
+; NO-LD-SEQ-SA-NEXT:    move $a4, $a2
+; NO-LD-SEQ-SA-NEXT:    sc.w $a4, $a0, 0
+; NO-LD-SEQ-SA-NEXT:    beqz $a4, .LBB22_1
+; NO-LD-SEQ-SA-NEXT:    b .LBB22_4
+; NO-LD-SEQ-SA-NEXT:  .LBB22_3:
+; NO-LD-SEQ-SA-NEXT:    dbar 1792
+; NO-LD-SEQ-SA-NEXT:  .LBB22_4:
+; NO-LD-SEQ-SA-NEXT:    move $a0, $a1
+; NO-LD-SEQ-SA-NEXT:    ret
+;
+; LD-SEQ-SA-LABEL: cmpxchg_i32_monotonic_monotonic_reti32:
+; LD-SEQ-SA:       # %bb.0:
+; LD-SEQ-SA-NEXT:    addi.w $a3, $a1, 0
+; LD-SEQ-SA-NEXT:  .LBB22_1: # =>This Inner Loop Header: Depth=1
+; LD-SEQ-SA-NEXT:    ll.w $a1, $a0, 0
+; LD-SEQ-SA-NEXT:    bne $a1, $a3, .LBB22_3
+; LD-SEQ-SA-NEXT:  # %bb.2: # in Loop: Header=BB22_1 Depth=1
+; LD-SEQ-SA-NEXT:    move $a4, $a2
+; LD-SEQ-SA-NEXT:    sc.w $a4, $a0, 0
+; LD-SEQ-SA-NEXT:    beqz $a4, .LBB22_1
+; LD-SEQ-SA-NEXT:    b .LBB22_4
+; LD-SEQ-SA-NEXT:  .LBB22_3:
+; LD-SEQ-SA-NEXT:  .LBB22_4:
+; LD-SEQ-SA-NEXT:    move $a0, $a1
+; LD-SEQ-SA-NEXT:    ret
   %tmp = cmpxchg ptr %ptr, i32 %cmp, i32 %val monotonic monotonic
   %res = extractvalue { i32, i1 } %tmp, 0
   ret i32 %res
 }
 
 define i64 @cmpxchg_i64_monotonic_monotonic_reti64(ptr %ptr, i64 %cmp, i64 %val) nounwind {
-; LA64-LABEL: cmpxchg_i64_monotonic_monotonic_reti64:
-; LA64:       # %bb.0:
-; LA64-NEXT:  .LBB23_1: # =>This Inner Loop Header: Depth=1
-; LA64-NEXT:    ll.d $a3, $a0, 0
-; LA64-NEXT:    bne $a3, $a1, .LBB23_3
-; LA64-NEXT:  # %bb.2: # in Loop: Header=BB23_1 Depth=1
-; LA64-NEXT:    move $a4, $a2
-; LA64-NEXT:    sc.d $a4, $a0, 0
-; LA64-NEXT:    beqz $a4, .LBB23_1
-; LA64-NEXT:    b .LBB23_4
-; LA64-NEXT:  .LBB23_3:
-; LA64-NEXT:    dbar 1792
-; LA64-NEXT:  .LBB23_4:
-; LA64-NEXT:    move $a0, $a3
-; LA64-NEXT:    ret
+; NO-LD-SEQ-SA-LABEL: cmpxchg_i64_monotonic_monotonic_reti64:
+; NO-LD-SEQ-SA:       # %bb.0:
+; NO-LD-SEQ-SA-NEXT:  .LBB23_1: # =>This Inner Loop Header: Depth=1
+; NO-LD-SEQ-SA-NEXT:    ll.d $a3, $a0, 0
+; NO-LD-SEQ-SA-NEXT:    bne $a3, $a1, .LBB23_3
+; NO-LD-SEQ-SA-NEXT:  # %bb.2: # in Loop: Header=BB23_1 Depth=1
+; NO-LD-SEQ-SA-NEXT:    move $a4, $a2
+; NO-LD-SEQ-SA-NEXT:    sc.d $a4, $a0, 0
+; NO-LD-SEQ-SA-NEXT:    beqz $a4, .LBB23_1
+; NO-LD-SEQ-SA-NEXT:    b .LBB23_4
+; NO-LD-SEQ-SA-NEXT:  .LBB23_3:
+; NO-LD-SEQ-SA-NEXT:    dbar 1792
+; NO-LD-SEQ-SA-NEXT:  .LBB23_4:
+; NO-LD-SEQ-SA-NEXT:    move $a0, $a3
+; NO-LD-SEQ-SA-NEXT:    ret
+;
+; LD-SEQ-SA-LABEL: cmpxchg_i64_monotonic_monotonic_reti64:
+; LD-SEQ-SA:       # %bb.0:
+; LD-SEQ-SA-NEXT:  .LBB23_1: # =>This Inner Loop Header: Depth=1
+; LD-SEQ-SA-NEXT:    ll.d $a3, $a0, 0
+; LD-SEQ-SA-NEXT:    bne $a3, $a1, .LBB23_3
+; LD-SEQ-SA-NEXT:  # %bb.2: # in Loop: Header=BB23_1 Depth=1
+; LD-SEQ-SA-NEXT:    move $a4, $a2
+; LD-SEQ-SA-NEXT:    sc.d $a4, $a0, 0
+; LD-SEQ-SA-NEXT:    beqz $a4, .LBB23_1
+; LD-SEQ-SA-NEXT:    b .LBB23_4
+; LD-SEQ-SA-NEXT:  .LBB23_3:
+; LD-SEQ-SA-NEXT:  .LBB23_4:
+; LD-SEQ-SA-NEXT:    move $a0, $a3
+; LD-SEQ-SA-NEXT:    ret
   %tmp = cmpxchg ptr %ptr, i64 %cmp, i64 %val monotonic monotonic
   %res = extractvalue { i64, i1 } %tmp, 0
   ret i64 %res
 }
 
 define i1 @cmpxchg_i8_monotonic_monotonic_reti1(ptr %ptr, i8 %cmp, i8 %val) nounwind {
-; LA64-LABEL: cmpxchg_i8_monotonic_monotonic_reti1:
-; LA64:       # %bb.0:
-; LA64-NEXT:    slli.d $a3, $a0, 3
-; LA64-NEXT:    bstrins.d $a0, $zero, 1, 0
-; LA64-NEXT:    ori $a4, $zero, 255
-; LA64-NEXT:    sll.w $a4, $a4, $a3
-; LA64-NEXT:    andi $a1, $a1, 255
-; LA64-NEXT:    sll.w $a1, $a1, $a3
-; LA64-NEXT:    andi $a2, $a2, 255
-; LA64-NEXT:    sll.w $a2, $a2, $a3
-; LA64-NEXT:  .LBB24_1: # =>This Inner Loop Header: Depth=1
-; LA64-NEXT:    ll.w $a3, $a0, 0
-; LA64-NEXT:    and $a5, $a3, $a4
-; LA64-NEXT:    bne $a5, $a1, .LBB24_3
-; LA64-NEXT:  # %bb.2: # in Loop: Header=BB24_1 Depth=1
-; LA64-NEXT:    andn $a5, $a3, $a4
-; LA64-NEXT:    or $a5, $a5, $a2
-; LA64-NEXT:    sc.w $a5, $a0, 0
-; LA64-NEXT:    beqz $a5, .LBB24_1
-; LA64-NEXT:    b .LBB24_4
-; LA64-NEXT:  .LBB24_3:
-; LA64-NEXT:    dbar 1792
-; LA64-NEXT:  .LBB24_4:
-; LA64-NEXT:    and $a0, $a3, $a4
-; LA64-NEXT:    xor $a0, $a1, $a0
-; LA64-NEXT:    sltui $a0, $a0, 1
-; LA64-NEXT:    ret
+; NO-LD-SEQ-SA-LABEL: cmpxchg_i8_monotonic_monotonic_reti1:
+; NO-LD-SEQ-SA:       # %bb.0:
+; NO-LD-SEQ-SA-NEXT:    slli.d $a3, $a0, 3
+; NO-LD-SEQ-SA-NEXT:    bstrins.d $a0, $zero, 1, 0
+; NO-LD-SEQ-SA-NEXT:    ori $a4, $zero, 255
+; NO-LD-SEQ-SA-NEXT:    sll.w $a4, $a4, $a3
+; NO-LD-SEQ-SA-NEXT:    andi $a1, $a1, 255
+; NO-LD-SEQ-SA-NEXT:    sll.w $a1, $a1, $a3
+; NO-LD-SEQ-SA-NEXT:    andi $a2, $a2, 255
+; NO-LD-SEQ-SA-NEXT:    sll.w $a2, $a2, $a3
+; NO-LD-SEQ-SA-NEXT:  .LBB24_1: # =>This Inner Loop Header: Depth=1
+; NO-LD-SEQ-SA-NEXT:    ll.w $a3, $a0, 0
+; NO-LD-SEQ-SA-NEXT:    and $a5, $a3, $a4
+; NO-LD-SEQ-SA-NEXT:    bne $a5, $a1, .LBB24_3
+; NO-LD-SEQ-SA-NEXT:  # %bb.2: # in Loop: Header=BB24_1 Depth=1
+; NO-LD-SEQ-SA-NEXT:    andn $a5, $a3, $a4
+; NO-LD-SEQ-SA-NEXT:    or $a5, $a5, $a2
+; NO-LD-SEQ-SA-NEXT:    sc.w $a5, $a0, 0
+; NO-LD-SEQ-SA-NEXT:    beqz $a5, .LBB24_1
+; NO-LD-SEQ-SA-NEXT:    b .LBB24_4
+; NO-LD-SEQ-SA-NEXT:  .LBB24_3:
+; NO-LD-SEQ-SA-NEXT:    dbar 1792
+; NO-LD-SEQ-SA-NEXT:  .LBB24_4:
+; NO-LD-SEQ-SA-NEXT:    and $a0, $a3, $a4
+; NO-LD-SEQ-SA-NEXT:    xor $a0, $a1, $a0
+; NO-LD-SEQ-SA-NEXT:    sltui $a0, $a0, 1
+; NO-LD-SEQ-SA-NEXT:    ret
+;
+; LD-SEQ-SA-LABEL: cmpxchg_i8_monotonic_monotonic_reti1:
+; LD-SEQ-SA:       # %bb.0:
+; LD-SEQ-SA-NEXT:    slli.d $a3, $a0, 3
+; LD-SEQ-SA-NEXT:    bstrins.d $a0, $zero, 1, 0
+; LD-SEQ-SA-NEXT:    ori $a4, $zero, 255
+; LD-SEQ-SA-NEXT:    sll.w $a4, $a4, $a3
+; LD-SEQ-SA-NEXT:    andi $a1, $a1, 255
+; LD-SEQ-SA-NEXT:    sll.w $a1, $a1, $a3
+; LD-SEQ-SA-NEXT:    andi $a2, $a2, 255
+; LD-SEQ-SA-NEXT:    sll.w $a2, $a2, $a3
+; LD-SEQ-SA-NEXT:  .LBB24_1: # =>This Inner Loop Header: Depth=1
+; LD-SEQ-SA-NEXT:    ll.w $a3, $a0, 0
+; LD-SEQ-SA-NEXT:    and $a5, $a3, $a4
+; LD-SEQ-SA-NEXT:    bne $a5, $a1, .LBB24_3
+; LD-SEQ-SA-NEXT:  # %bb.2: # in Loop: Header=BB24_1 Depth=1
+; LD-SEQ-SA-NEXT:    andn $a5, $a3, $a4
+; LD-SEQ-SA-NEXT:    or $a5, $a5, $a2
+; LD-SEQ-SA-NEXT:    sc.w $a5, $a0, 0
+; LD-SEQ-SA-NEXT:    beqz $a5, .LBB24_1
+; LD-SEQ-SA-NEXT:    b .LBB24_4
+; LD-SEQ-SA-NEXT:  .LBB24_3:
+; LD-SEQ-SA-NEXT:  .LBB24_4:
+; LD-SEQ-SA-NEXT:    and $a0, $a3, $a4
+; LD-SEQ-SA-NEXT:    xor $a0, $a1, $a0
+; LD-SEQ-SA-NEXT:    sltui $a0, $a0, 1
+; LD-SEQ-SA-NEXT:    ret
   %tmp = cmpxchg ptr %ptr, i8 %cmp, i8 %val monotonic monotonic
   %res = extractvalue { i8, i1 } %tmp, 1
   ret i1 %res
 }
 
 define i1 @cmpxchg_i16_monotonic_monotonic_reti1(ptr %ptr, i16 %cmp, i16 %val) nounwind {
-; LA64-LABEL: cmpxchg_i16_monotonic_monotonic_reti1:
-; LA64:       # %bb.0:
-; LA64-NEXT:    slli.d $a3, $a0, 3
-; LA64-NEXT:    bstrins.d $a0, $zero, 1, 0
-; LA64-NEXT:    lu12i.w $a4, 15
-; LA64-NEXT:    ori $a4, $a4, 4095
-; LA64-NEXT:    sll.w $a4, $a4, $a3
-; LA64-NEXT:    bstrpick.d $a1, $a1, 15, 0
-; LA64-NEXT:    sll.w $a1, $a1, $a3
-; LA64-NEXT:    bstrpick.d $a2, $a2, 15, 0
-; LA64-NEXT:    sll.w $a2, $a2, $a3
-; LA64-NEXT:  .LBB25_1: # =>This Inner Loop Header: Depth=1
-; LA64-NEXT:    ll.w $a3, $a0, 0
-; LA64-NEXT:    and $a5, $a3, $a4
-; LA64-NEXT:    bne $a5, $a1, .LBB25_3
-; LA64-NEXT:  # %bb.2: # in Loop: Header=BB25_1 Depth=1
-; LA64-NEXT:    andn $a5, $a3, $a4
-; LA64-NEXT:    or $a5, $a5, $a2
-; LA64-NEXT:    sc.w $a5, $a0, 0
-; LA64-NEXT:    beqz $a5, .LBB25_1
-; LA64-NEXT:    b .LBB25_4
-; LA64-NEXT:  .LBB25_3:
-; LA64-NEXT:    dbar 1792
-; LA64-NEXT:  .LBB25_4:
-; LA64-NEXT:    and $a0, $a3, $a4
-; LA64-NEXT:    xor $a0, $a1, $a0
-; LA64-NEXT:    sltui $a0, $a0, 1
-; LA64-NEXT:    ret
+; NO-LD-SEQ-SA-LABEL: cmpxchg_i16_monotonic_monotonic_reti1:
+; NO-LD-SEQ-SA:       # %bb.0:
+; NO-LD-SEQ-SA-NEXT:    slli.d $a3, $a0, 3
+; NO-LD-SEQ-SA-NEXT:    bstrins.d $a0, $zero, 1, 0
+; NO-LD-SEQ-SA-NEXT:    lu12i.w $a4, 15
+; NO-LD-SEQ-SA-NEXT:    ori $a4, $a4, 4095
+; NO-LD-SEQ-SA-NEXT:    sll.w $a4, $a4, $a3
+; NO-LD-SEQ-SA-NEXT:    bstrpick.d $a1, $a1, 15, 0
+; NO-LD-SEQ-SA-NEXT:    sll.w $a1, $a1, $a3
+; NO-LD-SEQ-SA-NEXT:    bstrpick.d $a2, $a2, 15, 0
+; NO-LD-SEQ-SA-NEXT:    sll.w $a2, $a2, $a3
+; NO-LD-SEQ-SA-NEXT:  .LBB25_1: # =>This Inner Loop Header: Depth=1
+; NO-LD-SEQ-SA-NEXT:    ll.w $a3, $a0, 0
+; NO-LD-SEQ-SA-NEXT:    and $a5, $a3, $a4
+; NO-LD-SEQ-SA-NEXT:    bne $a5, $a1, .LBB25_3
+; NO-LD-SEQ-SA-NEXT:  # %bb.2: # in Loop: Header=BB25_1 Depth=1
+; NO-LD-SEQ-SA-NEXT:    andn $a5, $a3, $a4
+; NO-LD-SEQ-SA-NEXT:    or $a5, $a5, $a2
+; NO-LD-SEQ-SA-NEXT:    sc.w $a5, $a0, 0
+; NO-LD-SEQ-SA-NEXT:    beqz $a5, .LBB25_1
+; NO-LD-SEQ-SA-NEXT:    b .LBB25_4
+; NO-LD-SEQ-SA-NEXT:  .LBB25_3:
+; NO-LD-SEQ-SA-NEXT:    dbar 1792
+; NO-LD-SEQ-SA-NEXT:  .LBB25_4:
+; NO-LD-SEQ-SA-NEXT:    and $a0, $a3, $a4
+; NO-LD-SEQ-SA-NEXT:    xor $a0, $a1, $a0
+; NO-LD-SEQ-SA-NEXT:    sltui $a0, $a0, 1
+; NO-LD-SEQ-SA-NEXT:    ret
+;
+; LD-SEQ-SA-LABEL: cmpxchg_i16_monotonic_monotonic_reti1:
+; LD-SEQ-SA:       # %bb.0:
+; LD-SEQ-SA-NEXT:    slli.d $a3, $a0, 3
+; LD-SEQ-SA-NEXT:    bstrins.d $a0, $zero, 1, 0
+; LD-SEQ-SA-NEXT:    lu12i.w $a4, 15
+; LD-SEQ-SA-NEXT:    ori $a4, $a4, 4095
+; LD-SEQ-SA-NEXT:    sll.w $a4, $a4, $a3
+; LD-SEQ-SA-NEXT:    bstrpick.d $a1, $a1, 15, 0
+; LD-SEQ-SA-NEXT:    sll.w $a1, $a1, $a3
+; LD-SEQ-SA-NEXT:    bstrpick.d $a2, $a2, 15, 0
+; LD-SEQ-SA-NEXT:    sll.w $a2, $a2, $a3
+; LD-SEQ-SA-NEXT:  .LBB25_1: # =>This Inner Loop Header: Depth=1
+; LD-SEQ-SA-NEXT:    ll.w $a3, $a0, 0
+; LD-SEQ-SA-NEXT:    and $a5, $a3, $a4
+; LD-SEQ-SA-NEXT:    bne $a5, $a1, .LBB25_3
+; LD-SEQ-SA-NEXT:  # %bb.2: # in Loop: Header=BB25_1 Depth=1
+; LD-SEQ-SA-NEXT:    andn $a5, $a3, $a4
+; LD-SEQ-SA-NEXT:    or $a5, $a5, $a2
+; LD-SEQ-SA-NEXT:    sc.w $a5, $a0, 0
+; LD-SEQ-SA-NEXT:    beqz $a5, .LBB25_1
+; LD-SEQ-SA-NEXT:    b .LBB25_4
+; LD-SEQ-SA-NEXT:  .LBB25_3:
+; LD-SEQ-SA-NEXT:  .LBB25_4:
+; LD-SEQ-SA-NEXT:    and $a0, $a3, $a4
+; LD-SEQ-SA-NEXT:    xor $a0, $a1, $a0
+; LD-SEQ-SA-NEXT:    sltui $a0, $a0, 1
+; LD-SEQ-SA-NEXT:    ret
   %tmp = cmpxchg ptr %ptr, i16 %cmp, i16 %val monotonic monotonic
   %res = extractvalue { i16, i1 } %tmp, 1
   ret i1 %res
 }
 
 define i1 @cmpxchg_i32_monotonic_monotonic_reti1(ptr %ptr, i32 %cmp, i32 %val) nounwind {
-; LA64-LABEL: cmpxchg_i32_monotonic_monotonic_reti1:
-; LA64:       # %bb.0:
-; LA64-NEXT:    addi.w $a1, $a1, 0
-; LA64-NEXT:  .LBB26_1: # =>This Inner Loop Header: Depth=1
-; LA64-NEXT:    ll.w $a3, $a0, 0
-; LA64-NEXT:    bne $a3, $a1, .LBB26_3
-; LA64-NEXT:  # %bb.2: # in Loop: Header=BB26_1 Depth=1
-; LA64-NEXT:    move $a4, $a2
-; LA64-NEXT:    sc.w $a4, $a0, 0
-; LA64-NEXT:    beqz $a4, .LBB26_1
-; LA64-NEXT:    b .LBB26_4
-; LA64-NEXT:  .LBB26_3:
-; LA64-NEXT:    dbar 1792
-; LA64-NEXT:  .LBB26_4:
-; LA64-NEXT:    xor $a0, $a3, $a1
-; LA64-NEXT:    sltui $a0, $a0, 1
-; LA64-NEXT:    ret
+; NO-LD-SEQ-SA-LABEL: cmpxchg_i32_monotonic_monotonic_reti1:
+; NO-LD-SEQ-SA:       # %bb.0:
+; NO-LD-SEQ-SA-NEXT:    addi.w $a1, $a1, 0
+; NO-LD-SEQ-SA-NEXT:  .LBB26_1: # =>This Inner Loop Header: Depth=1
+; NO-LD-SEQ-SA-NEXT:    ll.w $a3, $a0, 0
+; NO-LD-SEQ-SA-NEXT:    bne $a3, $a1, .LBB26_3
+; NO-LD-SEQ-SA-NEXT:  # %bb.2: # in Loop: Header=BB26_1 Depth=1
+; NO-LD-SEQ-SA-NEXT:    move $a4, $a2
+; NO-LD-SEQ-SA-NEXT:    sc.w $a4, $a0, 0
+; NO-LD-SEQ-SA-NEXT:    beqz $a4, .LBB26_1
+; NO-LD-SEQ-SA-NEXT:    b .LBB26_4
+; NO-LD-SEQ-SA-NEXT:  .LBB26_3:
+; NO-LD-SEQ-SA-NEXT:    dbar 1792
+; NO-LD-SEQ-SA-NEXT:  .LBB26_4:
+; NO-LD-SEQ-SA-NEXT:    xor $a0, $a3, $a1
+; NO-LD-SEQ-SA-NEXT:    sltui $a0, $a0, 1
+; NO-LD-SEQ-SA-NEXT:    ret
+;
+; LD-SEQ-SA-LABEL: cmpxchg_i32_monotonic_monotonic_reti1:
+; LD-SEQ-SA:       # %bb.0:
+; LD-SEQ-SA-NEXT:    addi.w $a1, $a1, 0
+; LD-SEQ-SA-NEXT:  .LBB26_1: # =>This Inner Loop Header: Depth=1
+; LD-SEQ-SA-NEXT:    ll.w $a3, $a0, 0
+; LD-SEQ-SA-NEXT:    bne $a3, $a1, .LBB26_3
+; LD-SEQ-SA-NEXT:  # %bb.2: # in Loop: Header=BB26_1 Depth=1
+; LD-SEQ-SA-NEXT:    move $a4, $a2
+; LD-SEQ-SA-NEXT:    sc.w $a4, $a0, 0
+; LD-SEQ-SA-NEXT:    beqz $a4, .LBB26_1
+; LD-SEQ-SA-NEXT:    b .LBB26_4
+; LD-SEQ-SA-NEXT:  .LBB26_3:
+; LD-SEQ-SA-NEXT:  .LBB26_4:
+; LD-SEQ-SA-NEXT:    xor $a0, $a3, $a1
+; LD-SEQ-SA-NEXT:    sltui $a0, $a0, 1
+; LD-SEQ-SA-NEXT:    ret
   %tmp = cmpxchg ptr %ptr, i32 %cmp, i32 %val monotonic monotonic
   %res = extractvalue { i32, i1 } %tmp, 1
   ret i1 %res
 }
 
 define i1 @cmpxchg_i64_monotonic_monotonic_reti1(ptr %ptr, i64 %cmp, i64 %val) nounwind {
-; LA64-LABEL: cmpxchg_i64_monotonic_monotonic_reti1:
-; LA64:       # %bb.0:
-; LA64-NEXT:  .LBB27_1: # =>This Inner Loop Header: Depth=1
-; LA64-NEXT:    ll.d $a3, $a0, 0
-; LA64-NEXT:    bne $a3, $a1, .LBB27_3
-; LA64-NEXT:  # %bb.2: # in Loop: Header=BB27_1 Depth=1
-; LA64-NEXT:    move $a4, $a2
-; LA64-NEXT:    sc.d $a4, $a0, 0
-; LA64-NEXT:    beqz $a4, .LBB27_1
-; LA64-NEXT:    b .LBB27_4
-; LA64-NEXT:  .LBB27_3:
-; LA64-NEXT:    dbar 1792
-; LA64-NEXT:  .LBB27_4:
-; LA64-NEXT:    xor $a0, $a3, $a1
-; LA64-NEXT:    sltui $a0, $a0, 1
-; LA64-NEXT:    ret
+; NO-LD-SEQ-SA-LABEL: cmpxchg_i64_monotonic_monotonic_reti1:
+; NO-LD-SEQ-SA:       # %bb.0:
+; NO-LD-SEQ-SA-NEXT:  .LBB27_1: # =>This Inner Loop Header: Depth=1
+; NO-LD-SEQ-SA-NEXT:    ll.d $a3, $a0, 0
+; NO-LD-SEQ-SA-NEXT:    bne $a3, $a1, .LBB27_3
+; NO-LD-SEQ-SA-NEXT:  # %bb.2: # in Loop: Header=BB27_1 Depth=1
+; NO-LD-SEQ-SA-NEXT:    move $a4, $a2
+; NO-LD-SEQ-SA-NEXT:    sc.d $a4, $a0, 0
+; NO-LD-SEQ-SA-NEXT:    beqz $a4, .LBB27_1
+; NO-LD-SEQ-SA-NEXT:    b .LBB27_4
+; NO-LD-SEQ-SA-NEXT:  .LBB27_3:
+; NO-LD-SEQ-SA-NEXT:    dbar 1792
+; NO-LD-SEQ-SA-NEXT:  .LBB27_4:
+; NO-LD-SEQ-SA-NEXT:    xor $a0, $a3, $a1
+; NO-LD-SEQ-SA-NEXT:    sltui $a0, $a0, 1
+; NO-LD-SEQ-SA-NEXT:    ret
+;
+; LD-SEQ-SA-LABEL: cmpxchg_i64_monotonic_monotonic_reti1:
+; LD-SEQ-SA:       # %bb.0:
+; LD-SEQ-SA-NEXT:  .LBB27_1: # =>This Inner Loop Header: Depth=1
+; LD-SEQ-SA-NEXT:    ll.d $a3, $a0, 0
+; LD-SEQ-SA-NEXT:    bne $a3, $a1, .LBB27_3
+; LD-SEQ-SA-NEXT:  # %bb.2: # in Loop: Header=BB27_1 Depth=1
+; LD-SEQ-SA-NEXT:    move $a4, $a2
+; LD-SEQ-SA-NEXT:    sc.d $a4, $a0, 0
+; LD-SEQ-SA-NEXT:    beqz $a4, .LBB27_1
+; LD-SEQ-SA-NEXT:    b .LBB27_4
+; LD-SEQ-SA-NEXT:  .LBB27_3:
+; LD-SEQ-SA-NEXT:  .LBB27_4:
+; LD-SEQ-SA-NEXT:    xor $a0, $a3, $a1
+; LD-SEQ-SA-NEXT:    sltui $a0, $a0, 1
+; LD-SEQ-SA-NEXT:    ret
   %tmp = cmpxchg ptr %ptr, i64 %cmp, i64 %val monotonic monotonic
   %res = extractvalue { i64, i1 } %tmp, 1
   ret i1 %res