Skip to content

Commit

Permalink
AMDGPU: Add amdgpu.no.fine.grained.memory when upgrading old atomic i…
Browse files Browse the repository at this point in the history 
…ntrinsics (llvm#89655)

This should replicate the old intrinsic behavior better when codegen of
the raw instruction will require metadata in the future.
  • Loading branch information
@arsenm @lravenclaw
arsenm authored and lravenclaw committed Jul 3, 2024
1 parent 730be96 commit 4dbeb7a
Show file tree
Hide file tree
Showing 2 changed files with 27 additions and 21 deletions.
8 changes: 7 additions & 1 deletion llvm/lib/IR/AutoUpgrade.cpp
View file
Original file line number Diff line number Diff line change
Expand Up @@ -2359,7 +2359,8 @@ static Value *upgradeAMDGCNIntrinsicCall(StringRef Name, CallBase *CI,
return nullptr;

Value *Ptr = CI->getArgOperand(0);
if (!isa<PointerType>(Ptr->getType())) // Malformed.
PointerType *PtrTy = dyn_cast<PointerType>(Ptr->getType());
if (!PtrTy) // Malformed.
return nullptr;

Value *Val = CI->getArgOperand(1);
Expand Down Expand Up @@ -2405,6 +2406,11 @@ static Value *upgradeAMDGCNIntrinsicCall(StringRef Name, CallBase *CI,
AtomicRMWInst *RMW =
Builder.CreateAtomicRMW(RMWOp, Ptr, Val, std::nullopt, Order, SSID);

if (PtrTy->getAddressSpace() != 3) {
RMW->setMetadata("amdgpu.no.fine.grained.memory",
MDNode::get(F->getContext(), {}));
}

if (IsVolatile)
RMW->setVolatile(true);

Expand Down
40 changes: 20 additions & 20 deletions llvm/test/Bitcode/amdgcn-atomic.ll
View file
Original file line number Diff line number Diff line change
Expand Up @@ -2,13 +2,13 @@


define void @atomic_inc(ptr %ptr0, ptr addrspace(1) %ptr1, ptr addrspace(3) %ptr3) {
; CHECK: atomicrmw uinc_wrap ptr %ptr0, i32 42 syncscope("agent") seq_cst, align 4
; CHECK: atomicrmw uinc_wrap ptr %ptr0, i32 42 syncscope("agent") seq_cst, align 4, !amdgpu.no.fine.grained.memory !0
%result0 = call i32 @llvm.amdgcn.atomic.inc.i32.p0(ptr %ptr0, i32 42, i32 0, i32 0, i1 false)

; CHECK: atomicrmw uinc_wrap ptr addrspace(1) %ptr1, i32 43 syncscope("agent") seq_cst, align 4
; CHECK: atomicrmw uinc_wrap ptr addrspace(1) %ptr1, i32 43 syncscope("agent") seq_cst, align 4, !amdgpu.no.fine.grained.memory !0
%result1 = call i32 @llvm.amdgcn.atomic.inc.i32.p1(ptr addrspace(1) %ptr1, i32 43, i32 0, i32 0, i1 false)

; CHECK: atomicrmw uinc_wrap ptr addrspace(3) %ptr3, i32 46 syncscope("agent") seq_cst, align 4
; CHECK: atomicrmw uinc_wrap ptr addrspace(3) %ptr3, i32 46 syncscope("agent") seq_cst, align 4{{$}}
%result2 = call i32 @llvm.amdgcn.atomic.inc.i32.p3(ptr addrspace(3) %ptr3, i32 46, i32 0, i32 0, i1 false)

; CHECK: atomicrmw uinc_wrap ptr %ptr0, i64 48 syncscope("agent") seq_cst, align 8
Expand All @@ -26,13 +26,13 @@ define void @atomic_inc(ptr %ptr0, ptr addrspace(1) %ptr1, ptr addrspace(3) %ptr
}

define void @atomic_dec(ptr %ptr0, ptr addrspace(1) %ptr1, ptr addrspace(3) %ptr3) {
; CHECK: atomicrmw udec_wrap ptr %ptr0, i32 42 syncscope("agent") seq_cst, align 4
; CHECK: atomicrmw udec_wrap ptr %ptr0, i32 42 syncscope("agent") seq_cst, align 4, !amdgpu.no.fine.grained.memory !0
%result0 = call i32 @llvm.amdgcn.atomic.dec.i32.p0(ptr %ptr0, i32 42, i32 0, i32 0, i1 false)

; CHECK: atomicrmw udec_wrap ptr addrspace(1) %ptr1, i32 43 syncscope("agent") seq_cst, align 4
; CHECK: atomicrmw udec_wrap ptr addrspace(1) %ptr1, i32 43 syncscope("agent") seq_cst, align 4, !amdgpu.no.fine.grained.memory !0
%result1 = call i32 @llvm.amdgcn.atomic.dec.i32.p1(ptr addrspace(1) %ptr1, i32 43, i32 0, i32 0, i1 false)

; CHECK: atomicrmw udec_wrap ptr addrspace(3) %ptr3, i32 46 syncscope("agent") seq_cst, align 4
; CHECK: atomicrmw udec_wrap ptr addrspace(3) %ptr3, i32 46 syncscope("agent") seq_cst, align 4{{$}}
%result2 = call i32 @llvm.amdgcn.atomic.dec.i32.p3(ptr addrspace(3) %ptr3, i32 46, i32 0, i32 0, i1 false)

; CHECK: atomicrmw udec_wrap ptr %ptr0, i64 48 syncscope("agent") seq_cst, align 8
Expand All @@ -51,49 +51,49 @@ define void @atomic_dec(ptr %ptr0, ptr addrspace(1) %ptr1, ptr addrspace(3) %ptr

; Test some invalid ordering handling
define void @ordering(ptr %ptr0, ptr addrspace(1) %ptr1, ptr addrspace(3) %ptr3) {
; CHECK: atomicrmw volatile uinc_wrap ptr %ptr0, i32 42 syncscope("agent") seq_cst, align 4
; CHECK: atomicrmw volatile uinc_wrap ptr %ptr0, i32 42 syncscope("agent") seq_cst, align 4, !amdgpu.no.fine.grained.memory !0
%result0 = call i32 @llvm.amdgcn.atomic.inc.i32.p0(ptr %ptr0, i32 42, i32 -1, i32 0, i1 true)

; CHECK: atomicrmw volatile uinc_wrap ptr addrspace(1) %ptr1, i32 43 syncscope("agent") seq_cst, align 4
; CHECK: atomicrmw volatile uinc_wrap ptr addrspace(1) %ptr1, i32 43 syncscope("agent") seq_cst, align 4, !amdgpu.no.fine.grained.memory !0
%result1 = call i32 @llvm.amdgcn.atomic.inc.i32.p1(ptr addrspace(1) %ptr1, i32 43, i32 0, i32 0, i1 true)

; CHECK: atomicrmw uinc_wrap ptr addrspace(1) %ptr1, i32 43 syncscope("agent") seq_cst, align 4
; CHECK: atomicrmw uinc_wrap ptr addrspace(1) %ptr1, i32 43 syncscope("agent") seq_cst, align 4, !amdgpu.no.fine.grained.memory !0
%result2 = call i32 @llvm.amdgcn.atomic.inc.i32.p1(ptr addrspace(1) %ptr1, i32 43, i32 1, i32 0, i1 false)

; CHECK: atomicrmw volatile uinc_wrap ptr addrspace(1) %ptr1, i32 43 syncscope("agent") monotonic, align 4
; CHECK: atomicrmw volatile uinc_wrap ptr addrspace(1) %ptr1, i32 43 syncscope("agent") monotonic, align 4, !amdgpu.no.fine.grained.memory !0
%result3 = call i32 @llvm.amdgcn.atomic.inc.i32.p1(ptr addrspace(1) %ptr1, i32 43, i32 2, i32 0, i1 true)

; CHECK: atomicrmw uinc_wrap ptr addrspace(1) %ptr1, i32 43 syncscope("agent") seq_cst, align 4
; CHECK: atomicrmw uinc_wrap ptr addrspace(1) %ptr1, i32 43 syncscope("agent") seq_cst, align 4, !amdgpu.no.fine.grained.memory !0
%result4 = call i32 @llvm.amdgcn.atomic.inc.i32.p1(ptr addrspace(1) %ptr1, i32 43, i32 3, i32 0, i1 false)

; CHECK: atomicrmw volatile udec_wrap ptr %ptr0, i32 42 syncscope("agent") seq_cst, align 4
; CHECK: atomicrmw volatile udec_wrap ptr %ptr0, i32 42 syncscope("agent") seq_cst, align 4, !amdgpu.no.fine.grained.memory !0
%result5 = call i32 @llvm.amdgcn.atomic.dec.i32.p0(ptr %ptr0, i32 42, i32 0, i32 4, i1 true)

; CHECK: atomicrmw udec_wrap ptr %ptr0, i32 42 syncscope("agent") seq_cst, align 4
; CHECK: atomicrmw udec_wrap ptr %ptr0, i32 42 syncscope("agent") seq_cst, align 4, !amdgpu.no.fine.grained.memory !0
%result6 = call i32 @llvm.amdgcn.atomic.dec.i32.p0(ptr %ptr0, i32 42, i32 0, i32 5, i1 false)

; CHECK: atomicrmw volatile udec_wrap ptr %ptr0, i32 42 syncscope("agent") seq_cst, align 4
; CHECK: atomicrmw volatile udec_wrap ptr %ptr0, i32 42 syncscope("agent") seq_cst, align 4, !amdgpu.no.fine.grained.memory !0
%result7 = call i32 @llvm.amdgcn.atomic.dec.i32.p0(ptr %ptr0, i32 42, i32 0, i32 6, i1 true)

; CHECK: atomicrmw udec_wrap ptr %ptr0, i32 42 syncscope("agent") seq_cst, align 4
; CHECK: atomicrmw udec_wrap ptr %ptr0, i32 42 syncscope("agent") seq_cst, align 4, !amdgpu.no.fine.grained.memory !0
%result8 = call i32 @llvm.amdgcn.atomic.dec.i32.p0(ptr %ptr0, i32 42, i32 0, i32 7, i1 false)

; CHECK:= atomicrmw volatile udec_wrap ptr %ptr0, i32 42 syncscope("agent") seq_cst, align 4
; CHECK:= atomicrmw volatile udec_wrap ptr %ptr0, i32 42 syncscope("agent") seq_cst, align 4, !amdgpu.no.fine.grained.memory !0
%result9 = call i32 @llvm.amdgcn.atomic.dec.i32.p0(ptr %ptr0, i32 42, i32 0, i32 8, i1 true)

; CHECK:= atomicrmw volatile udec_wrap ptr addrspace(1) %ptr1, i32 43 syncscope("agent") seq_cst, align 4
; CHECK:= atomicrmw volatile udec_wrap ptr addrspace(1) %ptr1, i32 43 syncscope("agent") seq_cst, align 4, !amdgpu.no.fine.grained.memory !0
%result10 = call i32 @llvm.amdgcn.atomic.dec.i32.p1(ptr addrspace(1) %ptr1, i32 43, i32 3, i32 0, i1 true)
ret void
}

define void @immarg_violations(ptr %ptr0, i32 %val32, i1 %val1) {
; CHECK: atomicrmw udec_wrap ptr %ptr0, i32 42 syncscope("agent") seq_cst, align 4
; CHECK: atomicrmw udec_wrap ptr %ptr0, i32 42 syncscope("agent") seq_cst, align 4, !amdgpu.no.fine.grained.memory !0
%result0 = call i32 @llvm.amdgcn.atomic.dec.i32.p0(ptr %ptr0, i32 42, i32 %val32, i32 0, i1 false)

; CHECK: atomicrmw udec_wrap ptr %ptr0, i32 42 syncscope("agent") monotonic, align 4
; CHECK: atomicrmw udec_wrap ptr %ptr0, i32 42 syncscope("agent") monotonic, align 4, !amdgpu.no.fine.grained.memory !0
%result1 = call i32 @llvm.amdgcn.atomic.dec.i32.p0(ptr %ptr0, i32 42, i32 2, i32 %val32, i1 false)

; CHECK: atomicrmw volatile udec_wrap ptr %ptr0, i32 42 syncscope("agent") monotonic, align 4
; CHECK: atomicrmw volatile udec_wrap ptr %ptr0, i32 42 syncscope("agent") monotonic, align 4, !amdgpu.no.fine.grained.memory !0
%result2 = call i32 @llvm.amdgcn.atomic.dec.i32.p0(ptr %ptr0, i32 42, i32 2, i32 0, i1 %val1)
ret void
}
Expand Down

0 comments on commit 4dbeb7a

Please sign in to comment.