Skip to content
Merged
Show file tree
Hide file tree
Changes from 2 commits
Commits
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
7 changes: 7 additions & 0 deletions llvm/lib/Transforms/Vectorize/VPlanUtils.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -66,6 +66,13 @@ bool vputils::isHeaderMask(const VPValue *V, const VPlan &Plan) {
m_One(), m_Specific(&Plan.getVF()))) ||
IsWideCanonicalIV(A));

if (match(V,
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
if (match(V,
// For scalar plans, the header mask uses the scalar steps.
if (match(V,

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Done in 23bce03

m_ICmp(m_ScalarIVSteps(
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Looks like this pattern is now used twice in this function, i.e.

m_ScalarIVSteps(m_Specific(Plan.getVectorLoopRegion()->getCanonicalIV()),
                m_One(), m_Specific(&Plan.getVF()))

Is it worth creating a specific pattern match for this? Something like

  m_CanonicalScalarIVSteps(Plan)

?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Good point, I've added a helper in efca5e5

m_Specific(Plan.getVectorLoopRegion()->getCanonicalIV()),
m_One(), m_Specific(&Plan.getVF())),
m_Specific(Plan.getBackedgeTakenCount()))))
return true;

return match(V, m_ICmp(m_VPValue(A), m_VPValue(B))) && IsWideCanonicalIV(A) &&
B == Plan.getBackedgeTakenCount();
}
Expand Down
Original file line number Diff line number Diff line change
@@ -0,0 +1,61 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals none --version 6
; RUN: opt -p loop-vectorize -prefer-predicate-over-epilogue=predicate-else-scalar-epilogue -force-vector-width=1 -force-vector-interleave=2 -S %s | FileCheck %s

define i64 @live_out_scalar_vf(i64 %n) {
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

if possible, might be good to add this to llvm/test/Transforms/LoopVectorize/tail-folding-vectorization-factor-1.ll, which already contains a set of test cases for interleaving only with tail-folding.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Done in c29428f

; CHECK-LABEL: define i64 @live_out_scalar_vf(
; CHECK-SAME: i64 [[N:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*:]]
; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[N]], 1
; CHECK-NEXT: br label %[[VECTOR_PH:.*]]
; CHECK: [[VECTOR_PH]]:
; CHECK-NEXT: [[N_RND_UP:%.*]] = add i64 [[TMP0]], 1
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], 2
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
; CHECK-NEXT: [[TRIP_COUNT_MINUS_1:%.*]] = sub i64 [[TMP0]], 1
; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
; CHECK: [[VECTOR_BODY]]:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: [[VECTOR_RECUR:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[TMP2:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP1:%.*]] = add i64 [[INDEX]], 0
; CHECK-NEXT: [[TMP2]] = add i64 [[INDEX]], 1
; CHECK-NEXT: [[TMP3:%.*]] = icmp ugt i64 [[TMP1]], [[TRIP_COUNT_MINUS_1]]
; CHECK-NEXT: [[TMP4:%.*]] = icmp ugt i64 [[TMP2]], [[TRIP_COUNT_MINUS_1]]
; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 2
; CHECK-NEXT: [[TMP5:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP5]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: [[TMP6:%.*]] = icmp eq i1 [[TMP4]], false
; CHECK-NEXT: [[TMP7:%.*]] = zext i1 [[TMP6]] to i64
; CHECK-NEXT: [[TMP8:%.*]] = add i64 1, [[TMP7]]
; CHECK-NEXT: [[TMP9:%.*]] = icmp eq i1 [[TMP3]], false
; CHECK-NEXT: [[TMP10:%.*]] = zext i1 [[TMP9]] to i64
; CHECK-NEXT: [[TMP11:%.*]] = add i64 0, [[TMP10]]
; CHECK-NEXT: [[TMP12:%.*]] = icmp ne i64 [[TMP10]], 1
; CHECK-NEXT: [[TMP13:%.*]] = select i1 [[TMP12]], i64 [[TMP11]], i64 [[TMP8]]
; CHECK-NEXT: [[LAST_ACTIVE_LANE:%.*]] = sub i64 [[TMP13]], 1
; CHECK-NEXT: [[TMP14:%.*]] = sub i64 [[LAST_ACTIVE_LANE]], 1
; CHECK-NEXT: [[TMP17:%.*]] = sub i64 [[TMP14]], 1
; CHECK-NEXT: [[TMP15:%.*]] = icmp uge i64 [[TMP14]], 1
; CHECK-NEXT: [[TMP16:%.*]] = select i1 [[TMP15]], i64 [[TMP2]], i64 [[TMP1]]
; CHECK-NEXT: [[TMP18:%.*]] = icmp eq i64 [[LAST_ACTIVE_LANE]], 0
; CHECK-NEXT: [[TMP19:%.*]] = select i1 [[TMP18]], i64 [[VECTOR_RECUR]], i64 [[TMP16]]
; CHECK-NEXT: br label %[[EXIT:.*]]
; CHECK: [[EXIT]]:
; CHECK-NEXT: ret i64 [[TMP19]]
;
entry:
br label %loop

loop:
%iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
; Need to use a phi otherwise the header mask will use a
; VPWidenCanonicalIVRecipe instead of a VPScalarIVStepsRecipe.
%exitval = phi i64 [ 0, %entry ], [ %iv, %loop ]
%iv.next = add i64 %iv, 1
%ec = icmp eq i64 %iv, %n
br i1 %ec, label %exit, label %loop

exit:
ret i64 %exitval
}

Loading