Support amcas[_db].{b/h/w/d} instructions.

tangaac · tangaac · commit 481211fa747b · 2024-11-05T16:05:33.000+08:00
diff --git a/clang/include/clang/Driver/Options.td b/clang/include/clang/Driver/Options.td
@@ -5414,6 +5414,10 @@ 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 mlamcas : Flag<["-"], "mlamcas">, Group<m_loongarch_Features_Group>,
+  HelpText<"Enable amcas[_db].{b/h/w/d}">;
+def mno_lamcas : Flag<["-"], "mno-lamcas">, Group<m_loongarch_Features_Group>,
+  HelpText<"Disable amcas[_db].{b/h/w/d}">;
 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
@@ -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 && HasFeatureLAMCAS)
         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 (HasFeatureLAMCAS)
+    Builder.defineMacro("__loongarch_lamcas", 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 == "+lamcas")
+      HasFeatureLAMCAS = true;
   }
   return true;
 }
diff --git 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 HasFeatureLAMCAS;
 
 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;
+    HasFeatureLAMCAS = 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
@@ -269,6 +269,15 @@ void loongarch::getLoongArchTargetFeatures(const Driver &D,
     else
       Features.push_back("-lam-bh");
   }
+
+  // Select lamcas feature determined by -m[no-]lamcas.
+  if (const Arg *A =
+          Args.getLastArg(options::OPT_mlamcas, options::OPT_mno_lamcas)) {
+    if (A->getOption().matches(options::OPT_mlamcas))
+      Features.push_back("+lamcas");
+    else
+      Features.push_back("-lamcas");
+  }
 }
 
 std::string loongarch::postProcessTargetCPUString(const std::string &CPU,
diff --git 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" "+lamcas"
 // 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" "+lamcas"
 // 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,+lamcas,+lsx,+ual"
+// IR-LA664: attributes #[[#]] ={{.*}}"target-cpu"="la664" {{.*}}"target-features"="+64bit,+d,+f,+frecipe,+lam-bh,+lamcas,+lasx,+lsx,+ual"
 
 int foo(void) {
   return 3;
diff --git a/clang/test/Driver/loongarch-mlamcas.c b/clang/test/Driver/loongarch-mlamcas.c
@@ -0,0 +1,30 @@
+/// Test -m[no]lamcas options.
+
+// RUN: %clang --target=loongarch64 -mlamcas -fsyntax-only %s -### 2>&1 | \
+// RUN:     FileCheck %s --check-prefix=CC1-LAMCAS
+// RUN: %clang --target=loongarch64 -mno-lamcas -fsyntax-only %s -### 2>&1 | \
+// RUN:     FileCheck %s --check-prefix=CC1-NO-LAMCAS
+// RUN: %clang --target=loongarch64 -mno-lamcas -mlamcas -fsyntax-only %s -### 2>&1 | \
+// RUN:     FileCheck %s --check-prefix=CC1-LAMCAS
+// RUN: %clang --target=loongarch64  -mlamcas -mno-lamcas -fsyntax-only %s -### 2>&1 | \
+// RUN:     FileCheck %s --check-prefix=CC1-NO-LAMCAS
+
+// RUN: %clang --target=loongarch64 -mlamcas -S -emit-llvm %s -o - | \
+// RUN: FileCheck %s --check-prefix=IR-LAMCAS
+// RUN: %clang --target=loongarch64 -mno-lamcas -S -emit-llvm %s -o - | \
+// RUN: FileCheck %s --check-prefix=IR-NO-LAMCAS
+// RUN: %clang --target=loongarch64 -mno-lamcas -mlamcas -S -emit-llvm %s -o - | \
+// RUN: FileCheck %s --check-prefix=IR-LAMCAS
+// RUN: %clang --target=loongarch64 -mlamcas -mno-lamcas -S -emit-llvm %s -o - | \
+// RUN: FileCheck %s --check-prefix=IR-NO-LAMCAS
+
+
+// CC1-LAMCAS: "-target-feature" "+lamcas"
+// CC1-NO-LAMCAS: "-target-feature" "-lamcas"
+
+// IR-LAMCAS: attributes #[[#]] ={{.*}}"target-features"="{{(.*,)?}}+lamcas{{(,.*)?}}"
+// IR-NO-LAMCAS: attributes #[[#]] ={{.*}}"target-features"="{{(.*,)?}}-lamcas{{(,.*)?}}"
+
+int foo(void) {
+  return 42;
+}
diff --git 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/_lamcas}.
 
 // 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
@@ -823,37 +823,46 @@
 // 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,LAMCAS -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,LAMCAS -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,LAMCAS -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 | \
 // RUN:   FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,FRECIPE -DARCH=la64v1.0 -DTUNE=loongarch64 %s
 // 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,LAMCAS -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 +lamcas | \
+// RUN:   FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,LAMCAS -DARCH=la64v1.0 -DTUNE=loongarch64 %s
+// RUN: %clang --target=loongarch64 -x c -E -dM %s -o - -march=la64v1.1 -Xclang -target-feature -Xclang -lamcas | \
+// 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 +lamcas | \
+// RUN:   FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,LAMCAS -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 +lamcas | \
+// RUN:   FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,LAMCAS -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 +lamcas | \
 // 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,LAMCAS -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,LAMCAS -DARCH=la664 -DTUNE=loongarch64 %s
 
 // ARCH-TUNE: #define __loongarch_arch "[[ARCH]]"
 // FRECIPE: #define __loongarch_frecipe 1
 // LAM-BH: #define __loongarch_lam_bh 1
+// LAMCAS: #define __loongarch_lamcas 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
@@ -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("+lamcas", FK_LAMCAS)
 
 #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_LAMCAS)
 
 #undef LOONGARCH_ARCH
diff --git 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,
+
+  // Atomic memory compare and swap instructions for byte, half word, word and
+  // double word are available.
+  FK_LAMCAS = 1 << 11,
 };
 
 struct FeatureInfo {
diff --git a/llvm/lib/Target/LoongArch/AsmParser/LoongArchAsmParser.cpp b/llvm/lib/Target/LoongArch/AsmParser/LoongArchAsmParser.cpp
@@ -1562,7 +1562,9 @@ unsigned LoongArchAsmParser::checkTargetMatchPredicate(MCInst &Inst) {
   unsigned Opc = Inst.getOpcode();
   switch (Opc) {
   default:
-    if (Opc >= LoongArch::AMADD_D && Opc <= LoongArch::AMXOR_W) {
+    // amcas[_db].{b/h/w/d} didn't need this judgement
+    if ((Opc >= LoongArch::AMADD_B && Opc <= LoongArch::AMAND__DB_W) ||
+        (Opc >= LoongArch::AMMAX_D && Opc <= LoongArch::AMXOR__DB_W)) {
       MCRegister Rd = Inst.getOperand(0).getReg();
       MCRegister Rk = Inst.getOperand(1).getReg();
       MCRegister Rj = Inst.getOperand(2).getReg();
diff --git a/llvm/lib/Target/LoongArch/LoongArch.td b/llvm/lib/Target/LoongArch/LoongArch.td
@@ -118,6 +118,12 @@ def FeatureLAM_BH
                         "Support amswap[_db].{b/h} and amadd[_db].{b/h} instructions.">;
 def HasLAM_BH : Predicate<"Subtarget->hasLAM_BH()">;
 
+// Atomic memory compare and swap instructions for byte, half word, word and double word
+def FeatureLAMCAS
+    : SubtargetFeature<"lamcas", "HasLAMCAS", "true",
+                        "Support amcas[_db].{b/h/w/d}.">;
+def HasLAMCAS : Predicate<"Subtarget->hasLAMCAS()">;
+
 def TunePreferWInst
     : SubtargetFeature<"prefer-w-inst", "PreferWInst", "true",
                        "Prefer instructions with W suffix">;
@@ -158,7 +164,8 @@ def : ProcessorModel<"la664", NoSchedModel, [Feature64Bit,
                                              FeatureExtLVZ,
                                              FeatureExtLBT,
                                              FeatureFrecipe,
-                                             FeatureLAM_BH]>;
+                                             FeatureLAM_BH,
+                                             FeatureLAMCAS]>;
 
 //===----------------------------------------------------------------------===//
 // Define the LoongArch target.
diff --git a/llvm/lib/Target/LoongArch/LoongArchISelLowering.cpp b/llvm/lib/Target/LoongArch/LoongArchISelLowering.cpp
@@ -363,6 +363,10 @@ LoongArchTargetLowering::LoongArchTargetLowering(const TargetMachine &TM,
   setPrefFunctionAlignment(Subtarget.getPrefFunctionAlignment());
   setPrefLoopAlignment(Subtarget.getPrefLoopAlignment());
   setMaxBytesForAlignment(Subtarget.getMaxBytesForAlignment());
+
+  // cmpxchg sizes down to 8 bits become legal if LAMCAS is available.
+  if (Subtarget.hasLAMCAS())
+    setMinCmpXchgSizeInBits(8);
 }
 
 bool LoongArchTargetLowering::isOffsetFoldingLegal(
@@ -5743,6 +5747,10 @@ LoongArchTargetLowering::shouldExpandAtomicRMWInIR(AtomicRMWInst *AI) const {
   }
 
   unsigned Size = AI->getType()->getPrimitiveSizeInBits();
+  if (Subtarget.hasLAMCAS() &&
+      (AI->getOperation() == AtomicRMWInst::Nand || Size < 32))
+    return AtomicExpansionKind::CmpXChg;
+
   if (Size == 8 || Size == 16)
     return AtomicExpansionKind::MaskedIntrinsic;
   return AtomicExpansionKind::None;
@@ -5797,6 +5805,10 @@ getIntrinsicForMaskedAtomicRMWBinOp(unsigned GRLen,
 TargetLowering::AtomicExpansionKind
 LoongArchTargetLowering::shouldExpandAtomicCmpXchgInIR(
     AtomicCmpXchgInst *CI) const {
+
+  if (Subtarget.hasLAMCAS())
+    return AtomicExpansionKind::None;
+
   unsigned Size = CI->getCompareOperand()->getType()->getPrimitiveSizeInBits();
   if (Size == 8 || Size == 16)
     return AtomicExpansionKind::MaskedIntrinsic;
@@ -6292,8 +6304,8 @@ bool LoongArchTargetLowering::hasAndNotCompare(SDValue Y) const {
 }
 
 ISD::NodeType LoongArchTargetLowering::getExtendForAtomicCmpSwapArg() const {
-  // TODO: LAMCAS will use amcas{_DB,}.[bhwd] which does not require extension.
-  return ISD::SIGN_EXTEND;
+  // LAMCAS will use amcas[_DB].{b/h/w/d} which does not require extension.
+  return Subtarget.hasLAMCAS() ? ISD::ANY_EXTEND : ISD::SIGN_EXTEND;
 }
 
 bool LoongArchTargetLowering::shouldSignExtendTypeInLibCall(
diff --git a/llvm/lib/Target/LoongArch/LoongArchInstrInfo.td b/llvm/lib/Target/LoongArch/LoongArchInstrInfo.td
@@ -710,10 +710,16 @@ class STORE_2RI14<bits<32> op>
                "$rd, $rj, $imm14">;
 } // hasSideEffects = 0, mayLoad = 0, mayStore = 1
 
-let hasSideEffects = 0, mayLoad = 1, mayStore = 1, Constraints = "@earlyclobber $rd" in
+let hasSideEffects = 0, mayLoad = 1, mayStore = 1, Constraints = "@earlyclobber $rd" in {
 class AM_3R<bits<32> op>
     : Fmt3R<op, (outs GPR:$rd), (ins GPR:$rk, GPRMemAtomic:$rj),
             "$rd, $rk, $rj">;
+}
+
+let hasSideEffects = 0, mayLoad = 1, mayStore = 1, Constraints = "$rd = $dst" in
+class AMCAS_3R<bits<32> op>
+    : Fmt3R<op, (outs GPR:$dst), (ins GPR:$rd, GPR:$rk, GPRMemAtomic:$rj),
+            "$rd, $rk, $rj">;
 
 let hasSideEffects = 0, mayLoad = 1, mayStore = 0 in {
 class LLBase<bits<32> op>
@@ -1024,14 +1030,14 @@ def AMMAX__DB_WU : AM_3R<0x38700000>;
 def AMMAX__DB_DU : AM_3R<0x38708000>;
 def AMMIN__DB_WU : AM_3R<0x38710000>;
 def AMMIN__DB_DU : AM_3R<0x38718000>;
-def AMCAS_B     : AM_3R<0x38580000>;
-def AMCAS_H     : AM_3R<0x38588000>;
-def AMCAS_W     : AM_3R<0x38590000>;
-def AMCAS_D     : AM_3R<0x38598000>;
-def AMCAS__DB_B     : AM_3R<0x385a0000>;
-def AMCAS__DB_H     : AM_3R<0x385a8000>;
-def AMCAS__DB_W     : AM_3R<0x385b0000>;
-def AMCAS__DB_D     : AM_3R<0x385b8000>;
+def AMCAS_B     : AMCAS_3R<0x38580000>;
+def AMCAS_H     : AMCAS_3R<0x38588000>;
+def AMCAS_W     : AMCAS_3R<0x38590000>;
+def AMCAS_D     : AMCAS_3R<0x38598000>;
+def AMCAS__DB_B     : AMCAS_3R<0x385a0000>;
+def AMCAS__DB_H     : AMCAS_3R<0x385a8000>;
+def AMCAS__DB_W     : AMCAS_3R<0x385b0000>;
+def AMCAS__DB_D     : AMCAS_3R<0x385b8000>;
 def LL_D : LLBase<0x22000000>;
 def SC_D : SCBase<0x23000000>;
 def SC_Q : SCBase_128<0x38570000>;
@@ -2106,6 +2112,26 @@ def : Pat<(atomic_load_sub_i16 GPR:$rj, GPR:$rk),
           (AMADD__DB_H (SUB_W R0, GPR:$rk), GPR:$rj)>;
 } // Predicates = [ IsLA64, HasLAM_BH ]
 
+let Predicates = [ HasLAMCAS, IsLA64 ] in {
+
+def : Pat<(atomic_cmp_swap_i8_monotonic GPR:$addr, GPR:$cmp, GPR:$new),
+          (AMCAS_B GPR:$cmp, GPR:$new, GPR:$addr)>;
+def : Pat<(atomic_cmp_swap_i16_monotonic GPR:$addr, GPR:$cmp, GPR:$new),
+          (AMCAS_H GPR:$cmp, GPR:$new, GPR:$addr)>;
+def : Pat<(atomic_cmp_swap_i32_monotonic GPR:$addr, GPR:$cmp, GPR:$new),
+          (AMCAS_W GPR:$cmp, GPR:$new, GPR:$addr)>;
+def : Pat<(atomic_cmp_swap_i64_monotonic GPR:$addr, GPR:$cmp, GPR:$new),
+          (AMCAS_D GPR:$cmp, GPR:$new, GPR:$addr)>;
+
+def : Pat<(atomic_cmp_swap_i8 GPR:$addr, GPR:$cmp, GPR:$new),
+          (AMCAS__DB_B GPR:$cmp, GPR:$new, GPR:$addr)>;
+def : Pat<(atomic_cmp_swap_i16 GPR:$addr, GPR:$cmp, GPR:$new),
+          (AMCAS__DB_H GPR:$cmp, GPR:$new, GPR:$addr)>;
+def : Pat<(atomic_cmp_swap_i32 GPR:$addr, GPR:$cmp, GPR:$new),
+          (AMCAS__DB_W GPR:$cmp, GPR:$new, GPR:$addr)>;
+def : Pat<(atomic_cmp_swap_i64 GPR:$addr, GPR:$cmp, GPR:$new),
+          (AMCAS__DB_D GPR:$cmp, GPR:$new, GPR:$addr)>;
+}
 
 let Predicates = [IsLA64] in {
 
diff --git a/llvm/lib/TargetParser/LoongArchTargetParser.cpp b/llvm/lib/TargetParser/LoongArchTargetParser.cpp
diff --git a/llvm/test/CodeGen/LoongArch/ir-instruction/atomic-cmpxchg.ll b/llvm/test/CodeGen/LoongArch/ir-instruction/atomic-cmpxchg.ll
diff --git a/llvm/test/CodeGen/LoongArch/ir-instruction/atomicrmw-lamcas.ll b/llvm/test/CodeGen/LoongArch/ir-instruction/atomicrmw-lamcas.ll
