Index: llvm/trunk/include/llvm/CodeGen/MachineInstr.h =================================================================== --- llvm/trunk/include/llvm/CodeGen/MachineInstr.h +++ llvm/trunk/include/llvm/CodeGen/MachineInstr.h @@ -526,6 +526,11 @@ /// Convergent instructions can not be made control-dependent on any /// additional values. bool isConvergent(QueryType Type = AnyInBundle) const { + if (isInlineAsm()) { + unsigned ExtraInfo = getOperand(InlineAsm::MIOp_ExtraInfo).getImm(); + if (ExtraInfo & InlineAsm::Extra_IsConvergent) + return true; + } return hasProperty(MCID::Convergent, Type); } Index: llvm/trunk/include/llvm/IR/InlineAsm.h =================================================================== --- llvm/trunk/include/llvm/IR/InlineAsm.h +++ llvm/trunk/include/llvm/IR/InlineAsm.h @@ -223,6 +223,7 @@ Extra_AsmDialect = 4, Extra_MayLoad = 8, Extra_MayStore = 16, + Extra_IsConvergent = 32, // Inline asm operands map to multiple SDNode / MachineInstr operands. // The first operand is an immediate describing the asm operand, the low Index: llvm/trunk/lib/CodeGen/MachineInstr.cpp =================================================================== --- llvm/trunk/lib/CodeGen/MachineInstr.cpp +++ llvm/trunk/lib/CodeGen/MachineInstr.cpp @@ -1754,6 +1754,8 @@ OS << " [mayload]"; if (ExtraInfo & InlineAsm::Extra_MayStore) OS << " [maystore]"; + if (ExtraInfo & InlineAsm::Extra_IsConvergent) + OS << " [isconvergent]"; if (ExtraInfo & InlineAsm::Extra_IsAlignStack) OS << " [alignstack]"; if (getInlineAsmDialect() == InlineAsm::AD_ATT) Index: llvm/trunk/lib/CodeGen/MachineVerifier.cpp =================================================================== --- llvm/trunk/lib/CodeGen/MachineVerifier.cpp +++ llvm/trunk/lib/CodeGen/MachineVerifier.cpp @@ -810,8 +810,9 @@ if (!MI->getOperand(1).isImm()) report("Asm flags must be an immediate", MI); // Allowed flags are Extra_HasSideEffects = 1, Extra_IsAlignStack = 2, - // Extra_AsmDialect = 4, Extra_MayLoad = 8, and Extra_MayStore = 16. - if (!isUInt<5>(MI->getOperand(1).getImm())) + // Extra_AsmDialect = 4, Extra_MayLoad = 8, and Extra_MayStore = 16, + // and Extra_IsConvergent = 32. + if (!isUInt<6>(MI->getOperand(1).getImm())) report("Unknown asm flags", &MI->getOperand(1), 1); static_assert(InlineAsm::MIOp_FirstOperand == 2, "Asm format changed"); Index: llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp =================================================================== --- llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp +++ llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp @@ -6763,6 +6763,8 @@ ExtraInfo |= InlineAsm::Extra_HasSideEffects; if (IA->isAlignStack()) ExtraInfo |= InlineAsm::Extra_IsAlignStack; + if (CS.isConvergent()) + ExtraInfo |= InlineAsm::Extra_IsConvergent; // Set the asm dialect. ExtraInfo |= IA->getDialect() * InlineAsm::Extra_AsmDialect; Index: llvm/trunk/test/CodeGen/AMDGPU/convergent-inlineasm.ll =================================================================== --- llvm/trunk/test/CodeGen/AMDGPU/convergent-inlineasm.ll +++ llvm/trunk/test/CodeGen/AMDGPU/convergent-inlineasm.ll @@ -0,0 +1,45 @@ +; RUN: llc -mtriple=amdgcn--amdhsa -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s + +declare i32 @llvm.amdgcn.workitem.id.x() #0 +; GCN-LABEL: {{^}}convergent_inlineasm: +; GCN: BB#0: +; GCN: v_cmp_ne_i32_e64 +; GCN: BB#1: +define void @convergent_inlineasm(i64 addrspace(1)* nocapture %arg) { +bb: + %tmp = call i32 @llvm.amdgcn.workitem.id.x() + %tmp1 = tail call i64 asm "v_cmp_ne_i32_e64 $0, 0, $1", "=s,v"(i32 1) #1 + %tmp2 = icmp eq i32 %tmp, 8 + br i1 %tmp2, label %bb3, label %bb5 + +bb3: ; preds = %bb + %tmp4 = getelementptr i64, i64 addrspace(1)* %arg, i32 %tmp + store i64 %tmp1, i64 addrspace(1)* %arg, align 8 + br label %bb5 + +bb5: ; preds = %bb3, %bb + ret void +} + +; GCN-LABEL: {{^}}nonconvergent_inlineasm: +; GCN: BB#1: +; GCN: v_cmp_ne_i32_e64 +; GCN: BB1_2: +define void @nonconvergent_inlineasm(i64 addrspace(1)* nocapture %arg) { +bb: + %tmp = call i32 @llvm.amdgcn.workitem.id.x() + %tmp1 = tail call i64 asm "v_cmp_ne_i32_e64 $0, 0, $1", "=s,v"(i32 1) + %tmp2 = icmp eq i32 %tmp, 8 + br i1 %tmp2, label %bb3, label %bb5 + +bb3: ; preds = %bb + %tmp4 = getelementptr i64, i64 addrspace(1)* %arg, i32 %tmp + store i64 %tmp1, i64 addrspace(1)* %arg, align 8 + br label %bb5 + +bb5: ; preds = %bb3, %bb + ret void +} + +attributes #0 = { nounwind readnone } +attributes #1 = { convergent nounwind readnone }