Skip to content

[LV] add test for low TC under ARM MVE #93181

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

Closed
wants to merge 1 commit into from
Closed

[LV] add test for low TC under ARM MVE #93181

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
272 changes: 272 additions & 0 deletions llvm/test/Transforms/LoopVectorize/ARM/low-trip-count.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,272 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -passes=loop-vectorize,simplifycfg -mtriple=thumbv8.1m -mattr=+mve -S < %s | FileCheck %s

define void @trip1_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture noundef readonly %src) #0 {
; CHECK-LABEL: @trip1_i8(
; CHECK-NEXT: entry:
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[I_08:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i8, ptr [[SRC:%.*]], i64 [[I_08]]
; CHECK-NEXT: [[TMP0:%.*]] = load i8, ptr [[ARRAYIDX]], align 1
; CHECK-NEXT: [[MUL:%.*]] = shl i8 [[TMP0]], 1
; CHECK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i8, ptr [[DST:%.*]], i64 [[I_08]]
; CHECK-NEXT: [[TMP1:%.*]] = load i8, ptr [[ARRAYIDX1]], align 1
; CHECK-NEXT: [[ADD:%.*]] = add i8 [[MUL]], [[TMP1]]
; CHECK-NEXT: store i8 [[ADD]], ptr [[ARRAYIDX1]], align 1
; CHECK-NEXT: [[INC]] = add nuw nsw i64 [[I_08]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INC]], 1
; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_END:%.*]], label [[FOR_BODY]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
entry:
br label %for.body

for.body: ; preds = %entry, %for.body
%i.08 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
%arrayidx = getelementptr inbounds i8, ptr %src, i64 %i.08
%0 = load i8, ptr %arrayidx, align 1
%mul = shl i8 %0, 1
%arrayidx1 = getelementptr inbounds i8, ptr %dst, i64 %i.08
%1 = load i8, ptr %arrayidx1, align 1
%add = add i8 %mul, %1
store i8 %add, ptr %arrayidx1, align 1
%inc = add nuw nsw i64 %i.08, 1
%exitcond.not = icmp eq i64 %inc, 1
br i1 %exitcond.not, label %for.end, label %for.body

for.end: ; preds = %for.body
ret void
}

define void @trip3_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture noundef readonly %src) #0 {
; CHECK-LABEL: @trip3_i8(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = add i64 0, 0
; CHECK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 [[TMP0]], i64 3)
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds i8, ptr [[SRC:%.*]], i64 [[TMP0]]
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i8, ptr [[TMP1]], i32 0
; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <4 x i8> @llvm.masked.load.v4i8.p0(ptr [[TMP2]], i32 1, <4 x i1> [[ACTIVE_LANE_MASK]], <4 x i8> poison)
; CHECK-NEXT: [[TMP3:%.*]] = shl <4 x i8> [[WIDE_MASKED_LOAD]], <i8 1, i8 1, i8 1, i8 1>
; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds i8, ptr [[DST:%.*]], i64 [[TMP0]]
; CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds i8, ptr [[TMP4]], i32 0
; CHECK-NEXT: [[WIDE_MASKED_LOAD1:%.*]] = call <4 x i8> @llvm.masked.load.v4i8.p0(ptr [[TMP5]], i32 1, <4 x i1> [[ACTIVE_LANE_MASK]], <4 x i8> poison)
; CHECK-NEXT: [[TMP6:%.*]] = add <4 x i8> [[TMP3]], [[WIDE_MASKED_LOAD1]]
; CHECK-NEXT: call void @llvm.masked.store.v4i8.p0(<4 x i8> [[TMP6]], ptr [[TMP5]], i32 1, <4 x i1> [[ACTIVE_LANE_MASK]])
; CHECK-NEXT: [[INDEX_NEXT:%.*]] = add i64 0, 4
; CHECK-NEXT: ret void
;
entry:
br label %for.body

for.body: ; preds = %entry, %for.body
%i.08 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
%arrayidx = getelementptr inbounds i8, ptr %src, i64 %i.08
%0 = load i8, ptr %arrayidx, align 1
%mul = shl i8 %0, 1
%arrayidx1 = getelementptr inbounds i8, ptr %dst, i64 %i.08
%1 = load i8, ptr %arrayidx1, align 1
%add = add i8 %mul, %1
store i8 %add, ptr %arrayidx1, align 1
%inc = add nuw nsw i64 %i.08, 1
%exitcond.not = icmp eq i64 %inc, 3
br i1 %exitcond.not, label %for.end, label %for.body

for.end: ; preds = %for.body
ret void
}

define void @trip5_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture noundef readonly %src) #0 {
; CHECK-LABEL: @trip5_i8(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = add i64 0, 0
; CHECK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i64(i64 [[TMP0]], i64 5)
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds i8, ptr [[SRC:%.*]], i64 [[TMP0]]
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i8, ptr [[TMP1]], i32 0
; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <8 x i8> @llvm.masked.load.v8i8.p0(ptr [[TMP2]], i32 1, <8 x i1> [[ACTIVE_LANE_MASK]], <8 x i8> poison)
; CHECK-NEXT: [[TMP3:%.*]] = shl <8 x i8> [[WIDE_MASKED_LOAD]], <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds i8, ptr [[DST:%.*]], i64 [[TMP0]]
; CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds i8, ptr [[TMP4]], i32 0
; CHECK-NEXT: [[WIDE_MASKED_LOAD1:%.*]] = call <8 x i8> @llvm.masked.load.v8i8.p0(ptr [[TMP5]], i32 1, <8 x i1> [[ACTIVE_LANE_MASK]], <8 x i8> poison)
; CHECK-NEXT: [[TMP6:%.*]] = add <8 x i8> [[TMP3]], [[WIDE_MASKED_LOAD1]]
; CHECK-NEXT: call void @llvm.masked.store.v8i8.p0(<8 x i8> [[TMP6]], ptr [[TMP5]], i32 1, <8 x i1> [[ACTIVE_LANE_MASK]])
; CHECK-NEXT: [[INDEX_NEXT:%.*]] = add i64 0, 8
; CHECK-NEXT: ret void
;
entry:
br label %for.body

for.body: ; preds = %entry, %for.body
%i.08 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
%arrayidx = getelementptr inbounds i8, ptr %src, i64 %i.08
%0 = load i8, ptr %arrayidx, align 1
%mul = shl i8 %0, 1
%arrayidx1 = getelementptr inbounds i8, ptr %dst, i64 %i.08
%1 = load i8, ptr %arrayidx1, align 1
%add = add i8 %mul, %1
store i8 %add, ptr %arrayidx1, align 1
%inc = add nuw nsw i64 %i.08, 1
%exitcond.not = icmp eq i64 %inc, 5
br i1 %exitcond.not, label %for.end, label %for.body

for.end: ; preds = %for.body
ret void
}

define void @trip8_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture noundef readonly %src) #0 {
; CHECK-LABEL: @trip8_i8(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = add i64 0, 0
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds i8, ptr [[SRC:%.*]], i64 [[TMP0]]
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i8, ptr [[TMP1]], i32 0
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <8 x i8>, ptr [[TMP2]], align 1
; CHECK-NEXT: [[TMP3:%.*]] = shl <8 x i8> [[WIDE_LOAD]], <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds i8, ptr [[DST:%.*]], i64 [[TMP0]]
; CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds i8, ptr [[TMP4]], i32 0
; CHECK-NEXT: [[WIDE_LOAD1:%.*]] = load <8 x i8>, ptr [[TMP5]], align 1
; CHECK-NEXT: [[TMP6:%.*]] = add <8 x i8> [[TMP3]], [[WIDE_LOAD1]]
; CHECK-NEXT: store <8 x i8> [[TMP6]], ptr [[TMP5]], align 1
; CHECK-NEXT: [[INDEX_NEXT:%.*]] = add nuw i64 0, 8
; CHECK-NEXT: ret void
;
entry:
br label %for.body

for.body: ; preds = %entry, %for.body
%i.08 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
%arrayidx = getelementptr inbounds i8, ptr %src, i64 %i.08
%0 = load i8, ptr %arrayidx, align 1
%mul = shl i8 %0, 1
%arrayidx1 = getelementptr inbounds i8, ptr %dst, i64 %i.08
%1 = load i8, ptr %arrayidx1, align 1
%add = add i8 %mul, %1
store i8 %add, ptr %arrayidx1, align 1
%inc = add nuw nsw i64 %i.08, 1
%exitcond.not = icmp eq i64 %inc, 8
br i1 %exitcond.not, label %for.end, label %for.body

for.end: ; preds = %for.body
ret void
}

define void @trip16_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture noundef readonly %src) #0 {
; CHECK-LABEL: @trip16_i8(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = add i64 0, 0
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds i8, ptr [[SRC:%.*]], i64 [[TMP0]]
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i8, ptr [[TMP1]], i32 0
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <16 x i8>, ptr [[TMP2]], align 1
; CHECK-NEXT: [[TMP3:%.*]] = shl <16 x i8> [[WIDE_LOAD]], <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds i8, ptr [[DST:%.*]], i64 [[TMP0]]
; CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds i8, ptr [[TMP4]], i32 0
; CHECK-NEXT: [[WIDE_LOAD1:%.*]] = load <16 x i8>, ptr [[TMP5]], align 1
; CHECK-NEXT: [[TMP6:%.*]] = add <16 x i8> [[TMP3]], [[WIDE_LOAD1]]
; CHECK-NEXT: store <16 x i8> [[TMP6]], ptr [[TMP5]], align 1
; CHECK-NEXT: [[INDEX_NEXT:%.*]] = add nuw i64 0, 16
; CHECK-NEXT: ret void
;
entry:
br label %for.body

for.body: ; preds = %entry, %for.body
%i.08 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
%arrayidx = getelementptr inbounds i8, ptr %src, i64 %i.08
%0 = load i8, ptr %arrayidx, align 1
%mul = shl i8 %0, 1
%arrayidx1 = getelementptr inbounds i8, ptr %dst, i64 %i.08
%1 = load i8, ptr %arrayidx1, align 1
%add = add i8 %mul, %1
store i8 %add, ptr %arrayidx1, align 1
%inc = add nuw nsw i64 %i.08, 1
%exitcond.not = icmp eq i64 %inc, 16
br i1 %exitcond.not, label %for.end, label %for.body

for.end: ; preds = %for.body
ret void
}


define void @trip32_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture noundef readonly %src) #0 {
; CHECK-LABEL: @trip32_i8(
; CHECK-NEXT: entry:
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds i8, ptr [[SRC:%.*]], i64 [[TMP0]]
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i8, ptr [[TMP1]], i32 0
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <16 x i8>, ptr [[TMP2]], align 1
; CHECK-NEXT: [[TMP3:%.*]] = shl <16 x i8> [[WIDE_LOAD]], <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds i8, ptr [[DST:%.*]], i64 [[TMP0]]
; CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds i8, ptr [[TMP4]], i32 0
; CHECK-NEXT: [[WIDE_LOAD1:%.*]] = load <16 x i8>, ptr [[TMP5]], align 1
; CHECK-NEXT: [[TMP6:%.*]] = add <16 x i8> [[TMP3]], [[WIDE_LOAD1]]
; CHECK-NEXT: store <16 x i8> [[TMP6]], ptr [[TMP5]], align 1
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 16
; CHECK-NEXT: [[TMP7:%.*]] = icmp eq i64 [[INDEX_NEXT]], 32
; CHECK-NEXT: br i1 [[TMP7]], label [[FOR_END:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
entry:
br label %for.body

for.body: ; preds = %entry, %for.body
%i.08 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
%arrayidx = getelementptr inbounds i8, ptr %src, i64 %i.08
%0 = load i8, ptr %arrayidx, align 1
%mul = shl i8 %0, 1
%arrayidx1 = getelementptr inbounds i8, ptr %dst, i64 %i.08
%1 = load i8, ptr %arrayidx1, align 1
%add = add i8 %mul, %1
store i8 %add, ptr %arrayidx1, align 1
%inc = add nuw nsw i64 %i.08, 1
%exitcond.not = icmp eq i64 %inc, 32
br i1 %exitcond.not, label %for.end, label %for.body

for.end: ; preds = %for.body
ret void
}

define void @trip24_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture noundef readonly %src) #0 {
; CHECK-LABEL: @trip24_i8(
; CHECK-NEXT: entry:
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds i8, ptr [[SRC:%.*]], i64 [[TMP0]]
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i8, ptr [[TMP1]], i32 0
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <8 x i8>, ptr [[TMP2]], align 1
; CHECK-NEXT: [[TMP3:%.*]] = shl <8 x i8> [[WIDE_LOAD]], <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds i8, ptr [[DST:%.*]], i64 [[TMP0]]
; CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds i8, ptr [[TMP4]], i32 0
; CHECK-NEXT: [[WIDE_LOAD1:%.*]] = load <8 x i8>, ptr [[TMP5]], align 1
; CHECK-NEXT: [[TMP6:%.*]] = add <8 x i8> [[TMP3]], [[WIDE_LOAD1]]
; CHECK-NEXT: store <8 x i8> [[TMP6]], ptr [[TMP5]], align 1
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 8
; CHECK-NEXT: [[TMP7:%.*]] = icmp eq i64 [[INDEX_NEXT]], 24
; CHECK-NEXT: br i1 [[TMP7]], label [[FOR_END:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
entry:
br label %for.body

for.body: ; preds = %entry, %for.body
%i.08 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
%arrayidx = getelementptr inbounds i8, ptr %src, i64 %i.08
%0 = load i8, ptr %arrayidx, align 1
%mul = shl i8 %0, 1
%arrayidx1 = getelementptr inbounds i8, ptr %dst, i64 %i.08
%1 = load i8, ptr %arrayidx1, align 1
%add = add i8 %mul, %1
store i8 %add, ptr %arrayidx1, align 1
%inc = add nuw nsw i64 %i.08, 1
%exitcond.not = icmp eq i64 %inc, 24
br i1 %exitcond.not, label %for.end, label %for.body

for.end: ; preds = %for.body
ret void
}
Loading
Loading