[llvm] [AMDGPU] Add NoaliasAddrSpace to AAMDnodes (PR #149247)
via llvm-commits
llvm-commits at lists.llvm.org
Sun Jul 20 17:09:03 PDT 2025
https://github.com/Shoreshen updated https://github.com/llvm/llvm-project/pull/149247
>From 504c9c30d5a0b15628314f9c820dfb29d83398ab Mon Sep 17 00:00:00 2001
From: shore <372660931 at qq.com>
Date: Thu, 17 Jul 2025 12:33:24 +0800
Subject: [PATCH] add noaliasaddrspace to aamdnodes
---
llvm/include/llvm/IR/Metadata.h | 24 ++++++++++++-------
llvm/lib/Analysis/TypeBasedAliasAnalysis.cpp | 4 ++++
llvm/lib/CodeGen/MachineOperand.cpp | 4 ++++
llvm/lib/IR/Metadata.cpp | 2 ++
.../AMDGPU/GlobalISel/flat-atomic-fadd.f32.ll | 8 +++----
.../AMDGPU/GlobalISel/flat-atomic-fadd.f64.ll | 4 ++--
6 files changed, 32 insertions(+), 14 deletions(-)
diff --git a/llvm/include/llvm/IR/Metadata.h b/llvm/include/llvm/IR/Metadata.h
index 2de26c0c1f7c7..959003eff860e 100644
--- a/llvm/include/llvm/IR/Metadata.h
+++ b/llvm/include/llvm/IR/Metadata.h
@@ -759,18 +759,18 @@ class MDString : public Metadata {
/// memory access used by the alias-analysis infrastructure.
struct AAMDNodes {
explicit AAMDNodes() = default;
- explicit AAMDNodes(MDNode *T, MDNode *TS, MDNode *S, MDNode *N)
- : TBAA(T), TBAAStruct(TS), Scope(S), NoAlias(N) {}
+ explicit AAMDNodes(MDNode *T, MDNode *TS, MDNode *S, MDNode *N, MDNode *NAS)
+ : TBAA(T), TBAAStruct(TS), Scope(S), NoAlias(N), NoAliasAddrSpace(NAS) {}
bool operator==(const AAMDNodes &A) const {
return TBAA == A.TBAA && TBAAStruct == A.TBAAStruct && Scope == A.Scope &&
- NoAlias == A.NoAlias;
+ NoAlias == A.NoAlias && NoAliasAddrSpace == A.NoAliasAddrSpace;
}
bool operator!=(const AAMDNodes &A) const { return !(*this == A); }
explicit operator bool() const {
- return TBAA || TBAAStruct || Scope || NoAlias;
+ return TBAA || TBAAStruct || Scope || NoAlias || NoAliasAddrSpace;
}
/// The tag for type-based alias analysis.
@@ -785,6 +785,9 @@ struct AAMDNodes {
/// The tag specifying the noalias scope.
MDNode *NoAlias = nullptr;
+ /// The tag specifying the noalias address space scope.
+ MDNode *NoAliasAddrSpace = nullptr;
+
// Shift tbaa Metadata node to start off bytes later
LLVM_ABI static MDNode *shiftTBAA(MDNode *M, size_t off);
@@ -806,6 +809,8 @@ struct AAMDNodes {
Result.TBAAStruct = Other.TBAAStruct == TBAAStruct ? TBAAStruct : nullptr;
Result.Scope = Other.Scope == Scope ? Scope : nullptr;
Result.NoAlias = Other.NoAlias == NoAlias ? NoAlias : nullptr;
+ Result.NoAliasAddrSpace =
+ Other.NoAliasAddrSpace == NoAliasAddrSpace ? NoAliasAddrSpace : nullptr;
return Result;
}
@@ -818,6 +823,7 @@ struct AAMDNodes {
TBAAStruct ? shiftTBAAStruct(TBAAStruct, Offset) : nullptr;
Result.Scope = Scope;
Result.NoAlias = NoAlias;
+ Result.NoAliasAddrSpace = NoAliasAddrSpace;
return Result;
}
@@ -833,6 +839,7 @@ struct AAMDNodes {
Result.TBAAStruct = TBAAStruct;
Result.Scope = Scope;
Result.NoAlias = NoAlias;
+ Result.NoAliasAddrSpace = NoAliasAddrSpace;
return Result;
}
@@ -860,12 +867,12 @@ struct AAMDNodes {
template<>
struct DenseMapInfo<AAMDNodes> {
static inline AAMDNodes getEmptyKey() {
- return AAMDNodes(DenseMapInfo<MDNode *>::getEmptyKey(),
- nullptr, nullptr, nullptr);
+ return AAMDNodes(DenseMapInfo<MDNode *>::getEmptyKey(), nullptr, nullptr,
+ nullptr, nullptr);
}
static inline AAMDNodes getTombstoneKey() {
- return AAMDNodes(DenseMapInfo<MDNode *>::getTombstoneKey(),
+ return AAMDNodes(DenseMapInfo<MDNode *>::getTombstoneKey(), nullptr,
nullptr, nullptr, nullptr);
}
@@ -873,7 +880,8 @@ struct DenseMapInfo<AAMDNodes> {
return DenseMapInfo<MDNode *>::getHashValue(Val.TBAA) ^
DenseMapInfo<MDNode *>::getHashValue(Val.TBAAStruct) ^
DenseMapInfo<MDNode *>::getHashValue(Val.Scope) ^
- DenseMapInfo<MDNode *>::getHashValue(Val.NoAlias);
+ DenseMapInfo<MDNode *>::getHashValue(Val.NoAlias) ^
+ DenseMapInfo<MDNode *>::getHashValue(Val.NoAliasAddrSpace);
}
static bool isEqual(const AAMDNodes &LHS, const AAMDNodes &RHS) {
diff --git a/llvm/lib/Analysis/TypeBasedAliasAnalysis.cpp b/llvm/lib/Analysis/TypeBasedAliasAnalysis.cpp
index c871070eb037e..7025b8354564a 100644
--- a/llvm/lib/Analysis/TypeBasedAliasAnalysis.cpp
+++ b/llvm/lib/Analysis/TypeBasedAliasAnalysis.cpp
@@ -525,6 +525,8 @@ AAMDNodes AAMDNodes::merge(const AAMDNodes &Other) const {
Result.TBAAStruct = nullptr;
Result.Scope = MDNode::getMostGenericAliasScope(Scope, Other.Scope);
Result.NoAlias = MDNode::intersect(NoAlias, Other.NoAlias);
+ Result.NoAliasAddrSpace = MDNode::getMostGenericNoaliasAddrspace(
+ NoAliasAddrSpace, Other.NoAliasAddrSpace);
return Result;
}
@@ -533,6 +535,8 @@ AAMDNodes AAMDNodes::concat(const AAMDNodes &Other) const {
Result.TBAA = Result.TBAAStruct = nullptr;
Result.Scope = MDNode::getMostGenericAliasScope(Scope, Other.Scope);
Result.NoAlias = MDNode::intersect(NoAlias, Other.NoAlias);
+ Result.NoAliasAddrSpace = MDNode::getMostGenericNoaliasAddrspace(
+ NoAliasAddrSpace, Other.NoAliasAddrSpace);
return Result;
}
diff --git a/llvm/lib/CodeGen/MachineOperand.cpp b/llvm/lib/CodeGen/MachineOperand.cpp
index 0d251697f2567..c612f8de7b50b 100644
--- a/llvm/lib/CodeGen/MachineOperand.cpp
+++ b/llvm/lib/CodeGen/MachineOperand.cpp
@@ -1273,6 +1273,10 @@ void MachineMemOperand::print(raw_ostream &OS, ModuleSlotTracker &MST,
OS << ", !noalias ";
AAInfo.NoAlias->printAsOperand(OS, MST);
}
+ if (AAInfo.NoAliasAddrSpace) {
+ OS << ", !noalias.addrspace ";
+ AAInfo.NoAliasAddrSpace->printAsOperand(OS, MST);
+ }
if (getRanges()) {
OS << ", !range ";
getRanges()->printAsOperand(OS, MST);
diff --git a/llvm/lib/IR/Metadata.cpp b/llvm/lib/IR/Metadata.cpp
index f0448b06e7e82..0961b3eaf56e3 100644
--- a/llvm/lib/IR/Metadata.cpp
+++ b/llvm/lib/IR/Metadata.cpp
@@ -1778,6 +1778,7 @@ AAMDNodes Instruction::getAAMetadata() const {
Result.TBAAStruct = Info.lookup(LLVMContext::MD_tbaa_struct);
Result.Scope = Info.lookup(LLVMContext::MD_alias_scope);
Result.NoAlias = Info.lookup(LLVMContext::MD_noalias);
+ Result.NoAliasAddrSpace = Info.lookup(LLVMContext::MD_noalias_addrspace);
}
return Result;
}
@@ -1787,6 +1788,7 @@ void Instruction::setAAMetadata(const AAMDNodes &N) {
setMetadata(LLVMContext::MD_tbaa_struct, N.TBAAStruct);
setMetadata(LLVMContext::MD_alias_scope, N.Scope);
setMetadata(LLVMContext::MD_noalias, N.NoAlias);
+ setMetadata(LLVMContext::MD_noalias_addrspace, N.NoAliasAddrSpace);
}
void Instruction::setNoSanitizeMetadata() {
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/flat-atomic-fadd.f32.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/flat-atomic-fadd.f32.ll
index 340e293cda7b5..6ee0c74863770 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/flat-atomic-fadd.f32.ll
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/flat-atomic-fadd.f32.ll
@@ -12,7 +12,7 @@ define amdgpu_ps void @flat_atomic_fadd_f32_no_rtn_intrinsic(ptr %ptr, float %da
; GFX942-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; GFX942-NEXT: [[REG_SEQUENCE:%[0-9]+]]:vreg_64_align2 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1
; GFX942-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
- ; GFX942-NEXT: FLAT_ATOMIC_ADD_F32 [[REG_SEQUENCE]], [[COPY2]], 0, 0, implicit $exec, implicit $flat_scr :: (load store syncscope("agent") seq_cst (s32) on %ir.ptr)
+ ; GFX942-NEXT: FLAT_ATOMIC_ADD_F32 [[REG_SEQUENCE]], [[COPY2]], 0, 0, implicit $exec, implicit $flat_scr :: (load store syncscope("agent") seq_cst (s32) on %ir.ptr, !noalias.addrspace !0)
; GFX942-NEXT: S_ENDPGM 0
;
; GFX11-LABEL: name: flat_atomic_fadd_f32_no_rtn_intrinsic
@@ -23,7 +23,7 @@ define amdgpu_ps void @flat_atomic_fadd_f32_no_rtn_intrinsic(ptr %ptr, float %da
; GFX11-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; GFX11-NEXT: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1
; GFX11-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
- ; GFX11-NEXT: FLAT_ATOMIC_ADD_F32 [[REG_SEQUENCE]], [[COPY2]], 0, 0, implicit $exec, implicit $flat_scr :: (load store syncscope("agent") seq_cst (s32) on %ir.ptr)
+ ; GFX11-NEXT: FLAT_ATOMIC_ADD_F32 [[REG_SEQUENCE]], [[COPY2]], 0, 0, implicit $exec, implicit $flat_scr :: (load store syncscope("agent") seq_cst (s32) on %ir.ptr, !noalias.addrspace !0)
; GFX11-NEXT: S_ENDPGM 0
%ret = call float @llvm.amdgcn.flat.atomic.fadd.f32.p1.f32(ptr %ptr, float %data)
ret void
@@ -38,7 +38,7 @@ define amdgpu_ps float @flat_atomic_fadd_f32_rtn_intrinsic(ptr %ptr, float %data
; GFX942-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; GFX942-NEXT: [[REG_SEQUENCE:%[0-9]+]]:vreg_64_align2 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1
; GFX942-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
- ; GFX942-NEXT: [[FLAT_ATOMIC_ADD_F32_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_F32_RTN [[REG_SEQUENCE]], [[COPY2]], 0, 1, implicit $exec, implicit $flat_scr :: (load store syncscope("agent") seq_cst (s32) on %ir.ptr)
+ ; GFX942-NEXT: [[FLAT_ATOMIC_ADD_F32_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_F32_RTN [[REG_SEQUENCE]], [[COPY2]], 0, 1, implicit $exec, implicit $flat_scr :: (load store syncscope("agent") seq_cst (s32) on %ir.ptr, !noalias.addrspace !0)
; GFX942-NEXT: $vgpr0 = COPY [[FLAT_ATOMIC_ADD_F32_RTN]]
; GFX942-NEXT: SI_RETURN_TO_EPILOG implicit $vgpr0
;
@@ -50,7 +50,7 @@ define amdgpu_ps float @flat_atomic_fadd_f32_rtn_intrinsic(ptr %ptr, float %data
; GFX11-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; GFX11-NEXT: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1
; GFX11-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
- ; GFX11-NEXT: [[FLAT_ATOMIC_ADD_F32_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_F32_RTN [[REG_SEQUENCE]], [[COPY2]], 0, 1, implicit $exec, implicit $flat_scr :: (load store syncscope("agent") seq_cst (s32) on %ir.ptr)
+ ; GFX11-NEXT: [[FLAT_ATOMIC_ADD_F32_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_ADD_F32_RTN [[REG_SEQUENCE]], [[COPY2]], 0, 1, implicit $exec, implicit $flat_scr :: (load store syncscope("agent") seq_cst (s32) on %ir.ptr, !noalias.addrspace !0)
; GFX11-NEXT: $vgpr0 = COPY [[FLAT_ATOMIC_ADD_F32_RTN]]
; GFX11-NEXT: SI_RETURN_TO_EPILOG implicit $vgpr0
%ret = call float @llvm.amdgcn.flat.atomic.fadd.f32.p1.f32(ptr %ptr, float %data)
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/flat-atomic-fadd.f64.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/flat-atomic-fadd.f64.ll
index c82ae2fbcbbdc..bf3697924c22c 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/flat-atomic-fadd.f64.ll
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/flat-atomic-fadd.f64.ll
@@ -13,7 +13,7 @@ define amdgpu_ps void @flat_atomic_fadd_f64_no_rtn_atomicrmw(ptr %ptr, double %d
; GFX90A_GFX942-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; GFX90A_GFX942-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr3
; GFX90A_GFX942-NEXT: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64_align2 = REG_SEQUENCE [[COPY2]], %subreg.sub0, [[COPY3]], %subreg.sub1
- ; GFX90A_GFX942-NEXT: FLAT_ATOMIC_ADD_F64 [[REG_SEQUENCE]], [[REG_SEQUENCE1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store syncscope("wavefront") monotonic (s64) on %ir.ptr)
+ ; GFX90A_GFX942-NEXT: FLAT_ATOMIC_ADD_F64 [[REG_SEQUENCE]], [[REG_SEQUENCE1]], 0, 0, implicit $exec, implicit $flat_scr :: (load store syncscope("wavefront") monotonic (s64) on %ir.ptr, !noalias.addrspace !0)
; GFX90A_GFX942-NEXT: S_ENDPGM 0
%ret = atomicrmw fadd ptr %ptr, double %data syncscope("wavefront") monotonic, !noalias.addrspace !1, !amdgpu.no.fine.grained.memory !0
ret void
@@ -30,7 +30,7 @@ define amdgpu_ps double @flat_atomic_fadd_f64_rtn_atomicrmw(ptr %ptr, double %da
; GFX90A_GFX942-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
; GFX90A_GFX942-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr3
; GFX90A_GFX942-NEXT: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64_align2 = REG_SEQUENCE [[COPY2]], %subreg.sub0, [[COPY3]], %subreg.sub1
- ; GFX90A_GFX942-NEXT: [[FLAT_ATOMIC_ADD_F64_RTN:%[0-9]+]]:vreg_64_align2 = FLAT_ATOMIC_ADD_F64_RTN [[REG_SEQUENCE]], [[REG_SEQUENCE1]], 0, 1, implicit $exec, implicit $flat_scr :: (load store syncscope("wavefront") monotonic (s64) on %ir.ptr)
+ ; GFX90A_GFX942-NEXT: [[FLAT_ATOMIC_ADD_F64_RTN:%[0-9]+]]:vreg_64_align2 = FLAT_ATOMIC_ADD_F64_RTN [[REG_SEQUENCE]], [[REG_SEQUENCE1]], 0, 1, implicit $exec, implicit $flat_scr :: (load store syncscope("wavefront") monotonic (s64) on %ir.ptr, !noalias.addrspace !0)
; GFX90A_GFX942-NEXT: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[FLAT_ATOMIC_ADD_F64_RTN]].sub0
; GFX90A_GFX942-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[FLAT_ATOMIC_ADD_F64_RTN]].sub1
; GFX90A_GFX942-NEXT: [[V_READFIRSTLANE_B32_:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY4]], implicit $exec
More information about the llvm-commits
mailing list