Skip to content

[AMDGPU] Prevent re-visits in LowerBufferFatPointers #159168

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Sep 17, 2025
+32 −0
Merged

[AMDGPU] Prevent re-visits in LowerBufferFatPointers #159168

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions llvm/lib/Target/AMDGPU/AMDGPULowerBufferFatPointers.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2328,6 +2328,12 @@ void SplitPtrStructs::processFunction(Function &F) {
LLVM_DEBUG(dbgs() << "Splitting pointer structs in function: " << F.getName()
<< "\n");
for (Instruction *I : Originals) {
// In some cases, instruction order doesn't reflect program order,
// so the visit() call will have already visited coertain instructions
// by the time this loop gets to them. Avoid re-visiting these so as to,
// for example, avoid processing the same conditional twice.
if (SplitUsers.contains(I))
continue;
auto [Rsrc, Off] = visit(I);
assert(((Rsrc && Off) || (!Rsrc && !Off)) &&
"Can't have a resource but no offset");
Expand Down
26 changes: 26 additions & 0 deletions llvm/test/CodeGen/AMDGPU/lower-buffer-fat-pointers-control-flow.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -455,3 +455,29 @@ loop:
exit:
ret float %sum
}

define void @dominance_not_in_program_order(ptr addrspace(7) inreg %arg) {
; CHECK-LABEL: define void @dominance_not_in_program_order
; CHECK-SAME: ({ ptr addrspace(8), i32 } inreg [[ARG:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: .preheader15:
; CHECK-NEXT: [[ARG_RSRC:%.*]] = extractvalue { ptr addrspace(8), i32 } [[ARG]], 0
; CHECK-NEXT: [[ARG_OFF:%.*]] = extractvalue { ptr addrspace(8), i32 } [[ARG]], 1
; CHECK-NEXT: br label [[DOTLR_PH18:%.*]]
; CHECK: .loopexit:
; CHECK-NEXT: [[SCEVGEP12:%.*]] = add i32 [[LSR_IV11_OFF:%.*]], 16
; CHECK-NEXT: br label [[DOTLR_PH18]]
; CHECK: .lr.ph18:
; CHECK-NEXT: [[LSR_IV11_OFF]] = phi i32 [ [[ARG_OFF]], [[DOTLOOPEXIT:%.*]] ], [ [[ARG_OFF]], [[DOTPREHEADER15:%.*]] ]
; CHECK-NEXT: br label [[DOTLOOPEXIT]]
;
.preheader15:
br label %.lr.ph18

.loopexit: ; preds = %.lr.ph18
%scevgep12 = getelementptr i8, ptr addrspace(7) %lsr.iv11, i32 16
br label %.lr.ph18

.lr.ph18: ; preds = %.loopexit, %.preheader15
%lsr.iv11 = phi ptr addrspace(7) [ %arg, %.loopexit ], [ %arg, %.preheader15 ]
br label %.loopexit
}