Skip to content

[RISCV] Allow non-canonicalized splats in isProfitableToSinkOperands #161586

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
Oct 1, 2025
Merged

[RISCV] Allow non-canonicalized splats in isProfitableToSinkOperands #161586

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
4 changes: 2 additions & 2 deletions llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3139,8 +3139,8 @@ bool RISCVTTIImpl::isProfitableToSinkOperands(
bool IsVPSplat = match(Op, m_Intrinsic<Intrinsic::experimental_vp_splat>(
m_Value(), m_Value(), m_Value()));
if (!IsVPSplat &&
!match(Op, m_Shuffle(m_InsertElt(m_Undef(), m_Value(), m_ZeroInt()),
m_Undef(), m_ZeroMask())))
!match(Op, m_Shuffle(m_InsertElt(m_Value(), m_Value(), m_ZeroInt()),
m_Value(), m_ZeroMask())))
continue;

// Don't sink i1 splats.
Expand Down
36 changes: 36 additions & 0 deletions llvm/test/CodeGen/RISCV/rvv/sink-splat-operands.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6018,3 +6018,39 @@ vector.latch: ; preds = %for.body419
for.cond.cleanup: ; preds = %vector.latch
ret void
}

;; This is exactly like sink_add_splat except that the splat has operands
;; which haven't been converted to undef.
define void @sink_non_canonical_splat(ptr nocapture %a, i32 signext %x) {
; CHECK-LABEL: sink_non_canonical_splat:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: lui a2, 1
; CHECK-NEXT: add a2, a0, a2
; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, ma
; CHECK-NEXT: .LBB131_1: # %vector.body
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: vle32.v v8, (a0)
; CHECK-NEXT: vadd.vx v8, v8, a1
; CHECK-NEXT: vse32.v v8, (a0)
; CHECK-NEXT: addi a0, a0, 16
; CHECK-NEXT: bne a0, a2, .LBB131_1
; CHECK-NEXT: # %bb.2: # %for.cond.cleanup
; CHECK-NEXT: ret
entry:
%broadcast.splatinsert = insertelement <4 x i32> zeroinitializer, i32 %x, i32 0
%broadcast.splat = shufflevector <4 x i32> %broadcast.splatinsert, <4 x i32> zeroinitializer, <4 x i32> zeroinitializer
br label %vector.body

vector.body: ; preds = %vector.body, %entry
%index = phi i64 [ 0, %entry ], [ %index.next, %vector.body ]
%0 = getelementptr inbounds i32, ptr %a, i64 %index
%wide.load = load <4 x i32>, ptr %0, align 4
%1 = add <4 x i32> %wide.load, %broadcast.splat
store <4 x i32> %1, ptr %0, align 4
%index.next = add nuw i64 %index, 4
%2 = icmp eq i64 %index.next, 1024
br i1 %2, label %for.cond.cleanup, label %vector.body

for.cond.cleanup: ; preds = %vector.body
ret void
}
Loading