[NVPTX] Support for memory orderings for cmpxchg

llvm/include/llvm/CodeGen/TargetLowering.h

@@ -2173,6 +2173,14 @@ class TargetLoweringBase {
     return false;
   }
 
+  // The memory ordering that AtomicExpandPass should assign to a atomic
+  // instruction that it has lowered by adding fences. This can be used
+  // to "fold" one of the fences into the atomic instruction.
+  virtual AtomicOrdering
+  atomicOperationOrderAfterFenceSplit(const Instruction *I) const {
+    return AtomicOrdering::Monotonic;
+  }
+
   /// Whether AtomicExpandPass should automatically insert a trailing fence
   /// without reducing the ordering for this atomic. Defaults to false.
   virtual bool

llvm/lib/CodeGen/AtomicExpandPass.cpp

@@ -324,8 +324,10 @@ bool AtomicExpandImpl::processAtomicInstr(Instruction *I) {
       // failure path. As a result, fence insertion is directly done by
       // expandAtomicCmpXchg in that case.
       FenceOrdering = CASI->getMergedOrdering();
-      CASI->setSuccessOrdering(AtomicOrdering::Monotonic);
-      CASI->setFailureOrdering(AtomicOrdering::Monotonic);
+      auto CASOrdering = TLI->atomicOperationOrderAfterFenceSplit(CASI);
+
+      CASI->setSuccessOrdering(CASOrdering);
+      CASI->setFailureOrdering(CASOrdering);
     }
 
     if (FenceOrdering != AtomicOrdering::Monotonic) {

llvm/lib/Target/NVPTX/NVPTXISelLowering.cpp

@@ -42,13 +42,15 @@
 #include "llvm/IR/FPEnv.h"
 #include "llvm/IR/Function.h"
 #include "llvm/IR/GlobalValue.h"
+#include "llvm/IR/IRBuilder.h"
 #include "llvm/IR/Instruction.h"
 #include "llvm/IR/Instructions.h"
 #include "llvm/IR/IntrinsicsNVPTX.h"
 #include "llvm/IR/Module.h"
 #include "llvm/IR/Type.h"
 #include "llvm/IR/Value.h"
 #include "llvm/Support/Alignment.h"
+#include "llvm/Support/AtomicOrdering.h"
 #include "llvm/Support/Casting.h"
 #include "llvm/Support/CodeGen.h"
 #include "llvm/Support/CommandLine.h"
@@ -995,6 +997,7 @@ NVPTXTargetLowering::NVPTXTargetLowering(const NVPTXTargetMachine &TM,
   // actions
   computeRegisterProperties(STI.getRegisterInfo());
 
+  // PTX support for 16-bit CAS is emulated. Only use 32+
   setMinCmpXchgSizeInBits(STI.getMinCmpXchgSizeInBits());
   setMaxAtomicSizeInBitsSupported(64);
   setMaxDivRemBitWidthSupported(64);
@@ -5565,6 +5568,70 @@ NVPTXTargetLowering::shouldExpandAtomicRMWInIR(AtomicRMWInst *AI) const {
   return AtomicExpansionKind::CmpXChg;
 }
 
+bool NVPTXTargetLowering::shouldInsertFencesForAtomic(
+    const Instruction *I) const {
+  auto *CI = dyn_cast<AtomicCmpXchgInst>(I);
+  // When CAS bitwidth is not supported on the hardware, the CAS is emulated
+  // using a retry loop that uses a higher-bitwidth monotonic CAS. We enforce
+  // the memory order using explicit fences around the retry loop.
+  // The memory order of natively supported CAS operations can be enforced
+  // by lowering to an atom.cas with the right memory synchronizing effect.
+  // However, atom.cas only supports relaxed, acquire, release and acq_rel.
+  // So we also use explicit fences for enforcing memory order for
+  // seq_cast CAS with natively-supported bitwidths.
+  return CI &&
+         (cast<IntegerType>(CI->getCompareOperand()->getType())->getBitWidth() <
+              STI.getMinCmpXchgSizeInBits() ||
+          CI->getMergedOrdering() == AtomicOrdering::SequentiallyConsistent);
+}
+
+AtomicOrdering NVPTXTargetLowering::atomicOperationOrderAfterFenceSplit(
+    const Instruction *I) const {
+  auto *CI = dyn_cast<AtomicCmpXchgInst>(I);
+  bool BitwidthSupportedAndIsSeqCst =
+      CI && CI->getMergedOrdering() == AtomicOrdering::SequentiallyConsistent &&
+      cast<IntegerType>(CI->getCompareOperand()->getType())->getBitWidth() >=
+          STI.getMinCmpXchgSizeInBits();
+  return BitwidthSupportedAndIsSeqCst ? AtomicOrdering::Acquire
+                                      : AtomicOrdering::Monotonic;
+}
+
+Instruction *NVPTXTargetLowering::emitLeadingFence(IRBuilderBase &Builder,
+                                                   Instruction *Inst,
+                                                   AtomicOrdering Ord) const {
+  if (!isa<AtomicCmpXchgInst>(Inst))
+    return TargetLoweringBase::emitLeadingFence(Builder, Inst, Ord);
+
+  // Specialize for cmpxchg
+  // Emit a fence.sc leading fence for cmpxchg seq_cst which are not emulated
+  if (isReleaseOrStronger(Ord))
+    return Ord == AtomicOrdering::SequentiallyConsistent
+               ? Builder.CreateFence(AtomicOrdering::SequentiallyConsistent)
+               : Builder.CreateFence(AtomicOrdering::Release);
+
+  return nullptr;
+}
+
+Instruction *NVPTXTargetLowering::emitTrailingFence(IRBuilderBase &Builder,
+                                                    Instruction *Inst,
+                                                    AtomicOrdering Ord) const {
+  // Specialize for cmpxchg
+  if (!isa<AtomicCmpXchgInst>(Inst))
+    return TargetLoweringBase::emitTrailingFence(Builder, Inst, Ord);
+
+  auto CASWidth =
+      cast<IntegerType>(
+          dyn_cast<AtomicCmpXchgInst>(Inst)->getCompareOperand()->getType())
+          ->getBitWidth();
+  // Do not emit a trailing fence for cmpxchg seq_cst which are not emulated
+  if (isAcquireOrStronger(Ord) &&
+      (Ord != AtomicOrdering::SequentiallyConsistent ||
+       CASWidth < STI.getMinCmpXchgSizeInBits()))
+    return Builder.CreateFence(AtomicOrdering::Acquire);
+
+  return nullptr;
+}
+
 // Pin NVPTXTargetObjectFile's vtables to this file.
 NVPTXTargetObjectFile::~NVPTXTargetObjectFile() = default;
 

llvm/lib/Target/NVPTX/NVPTXISelLowering.h

@@ -17,6 +17,7 @@
 #include "NVPTX.h"
 #include "llvm/CodeGen/SelectionDAG.h"
 #include "llvm/CodeGen/TargetLowering.h"
+#include "llvm/Support/AtomicOrdering.h"
 
 namespace llvm {
 namespace NVPTXISD {
@@ -260,6 +261,16 @@ class NVPTXTargetLowering : public TargetLowering {
     return true;
   }
 
+  bool shouldInsertFencesForAtomic(const Instruction *) const override;
+
+  AtomicOrdering
+  atomicOperationOrderAfterFenceSplit(const Instruction *I) const override;
+
+  Instruction *emitLeadingFence(IRBuilderBase &Builder, Instruction *Inst,
+                                AtomicOrdering Ord) const override;
+  Instruction *emitTrailingFence(IRBuilderBase &Builder, Instruction *Inst,
+                                 AtomicOrdering Ord) const override;
+
 private:
   const NVPTXSubtarget &STI; // cache the subtarget here
   SDValue getParamSymbol(SelectionDAG &DAG, int idx, EVT) const;

llvm/lib/Target/NVPTX/NVPTXIntrinsics.td

@@ -1962,41 +1962,41 @@ multiclass F_ATOMIC_2_NEG<ValueType regT, NVPTXRegClass regclass, string SpaceSt
 
 // has 3 operands
 multiclass F_ATOMIC_3_imp<ValueType ptrT, NVPTXRegClass ptrclass,
-  ValueType regT, NVPTXRegClass regclass,
+  ValueType regT, NVPTXRegClass regclass, string SemStr,
   string SpaceStr, string TypeStr, string OpcStr, PatFrag IntOp,
   Operand IMMType, list<Predicate> Pred> {
   let mayLoad = 1, mayStore = 1, hasSideEffects = 1 in {
     def reg : NVPTXInst<(outs regclass:$dst),
       (ins ptrclass:$addr, regclass:$b, regclass:$c),
-      !strconcat("atom", SpaceStr, OpcStr, TypeStr, " \t$dst, [$addr], $b, $c;"),
+      !strconcat("atom", SemStr, SpaceStr, OpcStr, TypeStr, " \t$dst, [$addr], $b, $c;"),
       [(set (regT regclass:$dst), (IntOp (ptrT ptrclass:$addr), (regT regclass:$b), (regT regclass:$c)))]>,
     Requires<Pred>;
 
     def imm1 : NVPTXInst<(outs regclass:$dst),
       (ins ptrclass:$addr, IMMType:$b, regclass:$c),
-      !strconcat("atom", SpaceStr, OpcStr, TypeStr, " \t$dst, [$addr], $b, $c;"),
+      !strconcat("atom", SemStr, SpaceStr, OpcStr, TypeStr, " \t$dst, [$addr], $b, $c;"),
       [(set (regT regclass:$dst), (IntOp (ptrT ptrclass:$addr), imm:$b, (regT regclass:$c)))]>,
     Requires<Pred>;
 
     def imm2 : NVPTXInst<(outs regclass:$dst),
       (ins ptrclass:$addr, regclass:$b, IMMType:$c),
-      !strconcat("atom", SpaceStr, OpcStr, TypeStr, " \t$dst, [$addr], $b, $c;", ""),
+      !strconcat("atom", SemStr, SpaceStr, OpcStr, TypeStr, " \t$dst, [$addr], $b, $c;", ""),
       [(set (regT regclass:$dst), (IntOp (ptrT ptrclass:$addr), (regT regclass:$b), imm:$c))]>,
     Requires<Pred>;
 
     def imm3 : NVPTXInst<(outs regclass:$dst),
       (ins ptrclass:$addr, IMMType:$b, IMMType:$c),
-      !strconcat("atom", SpaceStr, OpcStr, TypeStr, " \t$dst, [$addr], $b, $c;"),
+      !strconcat("atom", SemStr, SpaceStr, OpcStr, TypeStr, " \t$dst, [$addr], $b, $c;"),
       [(set (regT regclass:$dst), (IntOp (ptrT ptrclass:$addr), imm:$b, imm:$c))]>,
     Requires<Pred>;
   }
 }
-multiclass F_ATOMIC_3<ValueType regT, NVPTXRegClass regclass, string SpaceStr, string TypeStr,
-  string OpcStr, PatFrag IntOp, Operand IMMType, list<Predicate> Pred = []> {
-  defm p32 : F_ATOMIC_3_imp<i32, Int32Regs, regT, regclass, SpaceStr, TypeStr, OpcStr,
-    IntOp, IMMType, Pred>;
-  defm p64 : F_ATOMIC_3_imp<i64, Int64Regs, regT, regclass, SpaceStr, TypeStr, OpcStr,
-    IntOp, IMMType, Pred>;
+multiclass F_ATOMIC_3<ValueType regT, NVPTXRegClass regclass, string SemStr, string SpaceStr,
+  string TypeStr, string OpcStr, PatFrag IntOp, Operand IMMType, list<Predicate> Pred = []> {
+  defm p32 : F_ATOMIC_3_imp<i32, Int32Regs, regT, regclass, SemStr, SpaceStr, TypeStr,
+    OpcStr, IntOp, IMMType, Pred>;
+  defm p64 : F_ATOMIC_3_imp<i64, Int64Regs, regT, regclass, SemStr, SpaceStr, TypeStr,
+    OpcStr, IntOp, IMMType, Pred>;
 }
 
 // atom_add
@@ -2378,51 +2378,76 @@ defm INT_PTX_ATOM_XOR_GEN_64 : F_ATOMIC_2<i64, Int64Regs, "", ".b64", ".xor",
 defm INT_PTX_ATOM_XOR_GEN_64_USE_G : F_ATOMIC_2<i64, Int64Regs, ".global", ".b64",
   ".xor", atomic_load_xor_i64_gen, i64imm, imm, [hasSM<32>]>;
 
-// atom_cas
-
-def atomic_cmp_swap_i16_g: ATOMIC_GLOBAL_CHK<(ops node:$a, node:$b, node:$c),
-  (atomic_cmp_swap_i16 node:$a, node:$b, node:$c)>;
-def atomic_cmp_swap_i16_s: ATOMIC_SHARED_CHK<(ops node:$a, node:$b, node:$c),
-  (atomic_cmp_swap_i16 node:$a, node:$b, node:$c)>;
-def atomic_cmp_swap_i16_gen: ATOMIC_GENERIC_CHK<(ops node:$a, node:$b, node:$c),
-  (atomic_cmp_swap_i16 node:$a, node:$b, node:$c)>;
-def atomic_cmp_swap_i32_g: ATOMIC_GLOBAL_CHK<(ops node:$a, node:$b, node:$c),
-  (atomic_cmp_swap_i32 node:$a, node:$b, node:$c)>;
-def atomic_cmp_swap_i32_s: ATOMIC_SHARED_CHK<(ops node:$a, node:$b, node:$c),
-  (atomic_cmp_swap_i32 node:$a, node:$b, node:$c)>;
-def atomic_cmp_swap_i32_gen: ATOMIC_GENERIC_CHK<(ops node:$a, node:$b, node:$c),
-  (atomic_cmp_swap_i32 node:$a, node:$b, node:$c)>;
-def atomic_cmp_swap_i64_g: ATOMIC_GLOBAL_CHK<(ops node:$a, node:$b, node:$c),
-  (atomic_cmp_swap_i64 node:$a, node:$b, node:$c)>;
-def atomic_cmp_swap_i64_s: ATOMIC_SHARED_CHK<(ops node:$a, node:$b, node:$c),
-  (atomic_cmp_swap_i64 node:$a, node:$b, node:$c)>;
-def atomic_cmp_swap_i64_gen: ATOMIC_GENERIC_CHK<(ops node:$a, node:$b, node:$c),
-  (atomic_cmp_swap_i64 node:$a, node:$b, node:$c)>;
-
-defm INT_PTX_ATOM_CAS_G_16 : F_ATOMIC_3<i16, Int16Regs, ".global", ".b16", ".cas",
-  atomic_cmp_swap_i16_g, i16imm, [hasSM<70>, hasPTX<63>]>;
-defm INT_PTX_ATOM_CAS_S_16 : F_ATOMIC_3<i16, Int16Regs, ".shared", ".b16", ".cas",
-  atomic_cmp_swap_i16_s, i16imm, [hasSM<70>, hasPTX<63>]>;
-defm INT_PTX_ATOM_CAS_GEN_16 : F_ATOMIC_3<i16, Int16Regs, "", ".b16", ".cas",
-  atomic_cmp_swap_i16_gen, i16imm, [hasSM<70>, hasPTX<63>]>;
-defm INT_PTX_ATOM_CAS_GEN_16_USE_G : F_ATOMIC_3<i16, Int16Regs, ".global", ".b16", ".cas",
-  atomic_cmp_swap_i16_gen, i16imm, [hasSM<70>, hasPTX<63>]>;
-defm INT_PTX_ATOM_CAS_G_32 : F_ATOMIC_3<i32, Int32Regs, ".global", ".b32", ".cas",
-  atomic_cmp_swap_i32_g, i32imm>;
-defm INT_PTX_ATOM_CAS_S_32 : F_ATOMIC_3<i32, Int32Regs, ".shared", ".b32", ".cas",
-  atomic_cmp_swap_i32_s, i32imm>;
-defm INT_PTX_ATOM_CAS_GEN_32 : F_ATOMIC_3<i32, Int32Regs, "", ".b32", ".cas",
-  atomic_cmp_swap_i32_gen, i32imm>;
-defm INT_PTX_ATOM_CAS_GEN_32_USE_G : F_ATOMIC_3<i32, Int32Regs, ".global", ".b32",
-  ".cas", atomic_cmp_swap_i32_gen, i32imm>;
-defm INT_PTX_ATOM_CAS_G_64 : F_ATOMIC_3<i64, Int64Regs, ".global", ".b64", ".cas",
-  atomic_cmp_swap_i64_g, i64imm>;
-defm INT_PTX_ATOM_CAS_S_64 : F_ATOMIC_3<i64, Int64Regs, ".shared", ".b64", ".cas",
-  atomic_cmp_swap_i64_s, i64imm>;
-defm INT_PTX_ATOM_CAS_GEN_64 : F_ATOMIC_3<i64, Int64Regs, "", ".b64", ".cas",
-  atomic_cmp_swap_i64_gen, i64imm>;
-defm INT_PTX_ATOM_CAS_GEN_64_USE_G : F_ATOMIC_3<i64, Int64Regs, ".global", ".b64",
-  ".cas", atomic_cmp_swap_i64_gen, i64imm>;
+multiclass ternary_atomic_op_as {
+  // one record per address space
+  def NAME#_generic: PatFrag<(ops node:$ptr, node:$cmp, node:$val),
+      (!cast<SDPatternOperator>(NAME) node:$ptr, node:$cmp, node:$val),
+      AS_match.generic>;
+
+  def NAME#_global: PatFrag<(ops node:$ptr, node:$cmp, node:$val),
+      (!cast<SDPatternOperator>(NAME) node:$ptr, node:$cmp, node:$val),
+      AS_match.global>;
+
+  def NAME#_shared: PatFrag<(ops node:$ptr, node:$cmp, node:$val),
+      (!cast<SDPatternOperator>(NAME) node:$ptr, node:$cmp, node:$val),
+      AS_match.shared>;
+}
+
+// generate pattern fragments for size x memory order
+// NOTE: i8 cmpxchg is not supported in ptx, and AtomicExpandPass will emulate all i8 cmpxchgs
+// using larger-bitwidth cas
+foreach size = ["i16", "i32", "i64"] in {
+  foreach order = ["", "_monotonic", "_acquire", "_release", "_acq_rel", "_seq_cst"] in {
+    defm atomic_cmp_swap#_#size#order: ternary_atomic_op_as;
+  }
+}
+
+// eg. with type = 32, order = ".acquire", addrspace = ".global",
+// atomic_cmp_swap_pat = atomic_cmp_swap_i32_acquire_global.
+// preds = [hasSM<70>, hasPTX<63>]
+// F_ATOMIC_3<i32, Int32Regs, ".acquire", ".global", ".b32",
+//            ".cas", atomic_cmp_swap_i32_acquire_global, i32imm,
+//            [hasSM<70>, hasPTX<63>]>
+multiclass INT_PTX_ATOM_CAS<string atomic_cmp_swap_pat, string type,
+                           string order, string addrspace, list<Predicate> preds>
+    : F_ATOMIC_3<!cast<ValueType>("i"#type),
+                 !cast<NVPTXRegClass>("Int"#type#"Regs"),
+                 order,
+                 addrspace,
+                 ".b"#type,
+                 ".cas",
+                 !cast<PatFrag>(atomic_cmp_swap_pat),
+                 !cast<Operand>("i"#type#"imm"),
+                 preds>;
+
+// Define atom.cas for all combinations of size x addrspace x memory order
+// supported in PTX *and* on the hardware.
+foreach size = ["32", "64"] in {
+  foreach addrspace = ["generic", "global", "shared"] in {
+    defvar cas_addrspace_string = !if(!eq(addrspace, "generic"), "", "."#addrspace);
+    foreach order = ["acquire", "release", "acq_rel", "monotonic"] in {
+      defvar cas_order_string = !if(!eq(order, "monotonic"), ".relaxed", "."#order);
+      // Note that AtomicExpand will convert cmpxchg seq_cst to a cmpxchg monotonic with fences around it.
+      // Memory orders are only supported for SM70+, PTX63+- so we have two sets of instruction definitions-
+      // for SM70+, and "old" ones which lower to "atom.cas", for earlier archs.
+      defm INT_PTX_ATOM_CAS_#size#_#order#addrspace
+        : INT_PTX_ATOM_CAS<"atomic_cmp_swap_i"#size#_#order#_#addrspace, size,
+                           cas_order_string, cas_addrspace_string,
+                           [hasSM<70>, hasPTX<63>]>;
+      defm INT_PTX_ATOM_CAS_#size#_#order#_old#addrspace
+        : INT_PTX_ATOM_CAS<"atomic_cmp_swap_i"#size#_#order#_#addrspace, size,
+                           "", cas_addrspace_string, []>;
+    }
+  }
+}
+
+// Note that 16-bit CAS support in PTX is emulated.
+defm INT_PTX_ATOM_CAS_G_16 : F_ATOMIC_3<i16, Int16Regs, "", ".global", ".b16", ".cas",
+  atomic_cmp_swap_i16_global, i16imm, [hasSM<70>, hasPTX<63>]>;
+defm INT_PTX_ATOM_CAS_S_16 : F_ATOMIC_3<i16, Int16Regs, "", ".shared", ".b16", ".cas",
+  atomic_cmp_swap_i16_shared, i16imm, [hasSM<70>, hasPTX<63>]>;
+defm INT_PTX_ATOM_CAS_GEN_16 : F_ATOMIC_3<i16, Int16Regs, "", "", ".b16", ".cas",
+  atomic_cmp_swap_i16_generic, i16imm, [hasSM<70>, hasPTX<63>]>;
 
 // Support for scoped atomic operations.  Matches
 // int_nvvm_atomic_{op}_{space}_{type}_{scope}

llvm/lib/Target/NVPTX/NVPTXSubtarget.h

@@ -147,7 +147,7 @@ class NVPTXSubtarget : public NVPTXGenSubtargetInfo {
   //  set of equivalent memory operations with a scalar data-type, executed in
   //  an unspecified order on the elements in the vector.
   unsigned getMaxRequiredAlignment() const { return 8; }
-  // Emulated loops with 32-bit/64-bit CAS generate better SASS than 16-bit CAS
+  // Get the smallest cmpxchg word size that the hardware supports.
   unsigned getMinCmpXchgSizeInBits() const { return 32; }
 
   unsigned getPTXVersion() const { return PTXVersion; }

llvm/test/CodeGen/NVPTX/atomics-sm90.ll

@@ -71,7 +71,7 @@ define void @test(ptr %dp0, ptr addrspace(1) %dp1, ptr addrspace(3) %dp3, bfloat
 ; CHECKPTX71-NEXT:    shl.b32 %r30, %r29, %r2;
 ; CHECKPTX71-NEXT:    and.b32 %r31, %r54, %r3;
 ; CHECKPTX71-NEXT:    or.b32 %r32, %r31, %r30;
-; CHECKPTX71-NEXT:    atom.cas.b32 %r6, [%r1], %r54, %r32;
+; CHECKPTX71-NEXT:    atom.relaxed.cas.b32 %r6, [%r1], %r54, %r32;
 ; CHECKPTX71-NEXT:    setp.ne.s32 %p1, %r6, %r54;
 ; CHECKPTX71-NEXT:    mov.u32 %r54, %r6;
 ; CHECKPTX71-NEXT:    @%p1 bra $L__BB0_1;
@@ -87,7 +87,7 @@ define void @test(ptr %dp0, ptr addrspace(1) %dp1, ptr addrspace(3) %dp3, bfloat
 ; CHECKPTX71-NEXT:    shl.b32 %r35, %r34, %r2;
 ; CHECKPTX71-NEXT:    and.b32 %r36, %r55, %r3;
 ; CHECKPTX71-NEXT:    or.b32 %r37, %r36, %r35;
-; CHECKPTX71-NEXT:    atom.cas.b32 %r9, [%r1], %r55, %r37;
+; CHECKPTX71-NEXT:    atom.relaxed.cas.b32 %r9, [%r1], %r55, %r37;
 ; CHECKPTX71-NEXT:    setp.ne.s32 %p2, %r9, %r55;
 ; CHECKPTX71-NEXT:    mov.u32 %r55, %r9;
 ; CHECKPTX71-NEXT:    @%p2 bra $L__BB0_3;
@@ -109,7 +109,7 @@ define void @test(ptr %dp0, ptr addrspace(1) %dp1, ptr addrspace(3) %dp3, bfloat
 ; CHECKPTX71-NEXT:    shl.b32 %r43, %r42, %r11;
 ; CHECKPTX71-NEXT:    and.b32 %r44, %r56, %r12;
 ; CHECKPTX71-NEXT:    or.b32 %r45, %r44, %r43;
-; CHECKPTX71-NEXT:    atom.global.cas.b32 %r15, [%r10], %r56, %r45;
+; CHECKPTX71-NEXT:    atom.relaxed.global.cas.b32 %r15, [%r10], %r56, %r45;
 ; CHECKPTX71-NEXT:    setp.ne.s32 %p3, %r15, %r56;
 ; CHECKPTX71-NEXT:    mov.u32 %r56, %r15;
 ; CHECKPTX71-NEXT:    @%p3 bra $L__BB0_5;
@@ -131,7 +131,7 @@ define void @test(ptr %dp0, ptr addrspace(1) %dp1, ptr addrspace(3) %dp3, bfloat
 ; CHECKPTX71-NEXT:    shl.b32 %r51, %r50, %r17;
 ; CHECKPTX71-NEXT:    and.b32 %r52, %r57, %r18;
 ; CHECKPTX71-NEXT:    or.b32 %r53, %r52, %r51;
-; CHECKPTX71-NEXT:    atom.shared.cas.b32 %r21, [%r16], %r57, %r53;
+; CHECKPTX71-NEXT:    atom.relaxed.shared.cas.b32 %r21, [%r16], %r57, %r53;
 ; CHECKPTX71-NEXT:    setp.ne.s32 %p4, %r21, %r57;
 ; CHECKPTX71-NEXT:    mov.u32 %r57, %r21;
 ; CHECKPTX71-NEXT:    @%p4 bra $L__BB0_7;