47abbf4fe9
A VPInstruction only has its first lane used if all users use its first lane only. Use vputils::onlyFirstLaneUsed to continue checking the recipe's users to handle more cases. Besides allowing additional introduction of scalar steps when interleaving in some cases, this also enables using an Add VPInstruction to model the increment - as a follow up.
168 lines
8.7 KiB
LLVM
168 lines
8.7 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt < %s -passes=loop-vectorize -force-vector-interleave=4 -pass-remarks='loop-vectorize' -disable-output -S 2>&1 | FileCheck %s --check-prefix=CHECK-REMARKS
|
|
; RUN: opt < %s -passes=loop-vectorize -force-vector-interleave=4 -S | FileCheck %s
|
|
|
|
; These tests are to check that fold-tail procedure produces correct scalar code when
|
|
; loop-vectorization is only unrolling but not vectorizing.
|
|
|
|
; CHECK-REMARKS: remark: {{.*}} interleaved loop (interleaved count: 4)
|
|
; CHECK-REMARKS-NEXT: remark: {{.*}} interleaved loop (interleaved count: 4)
|
|
; CHECK-REMARKS-NOT: remark: {{.*}} vectorized loop
|
|
|
|
define void @VF1-VPlanExe(ptr %dst) {
|
|
; CHECK-LABEL: @VF1-VPlanExe(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
|
|
; CHECK: vector.ph:
|
|
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
|
|
; CHECK: vector.body:
|
|
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_STORE_CONTINUE6:%.*]] ]
|
|
; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0
|
|
; CHECK-NEXT: [[TMP1:%.*]] = add i64 [[INDEX]], 1
|
|
; CHECK-NEXT: [[TMP2:%.*]] = add i64 [[INDEX]], 2
|
|
; CHECK-NEXT: [[TMP3:%.*]] = add i64 [[INDEX]], 3
|
|
; CHECK-NEXT: [[TMP4:%.*]] = icmp ule i64 [[TMP0]], 14
|
|
; CHECK-NEXT: [[TMP5:%.*]] = icmp ule i64 [[TMP1]], 14
|
|
; CHECK-NEXT: [[TMP6:%.*]] = icmp ule i64 [[TMP2]], 14
|
|
; CHECK-NEXT: [[TMP7:%.*]] = icmp ule i64 [[TMP3]], 14
|
|
; CHECK-NEXT: br i1 [[TMP4]], label [[PRED_STORE_IF:%.*]], label [[PRED_STORE_CONTINUE:%.*]]
|
|
; CHECK: pred.store.if:
|
|
; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds i32, ptr [[DST:%.*]], i64 [[TMP0]]
|
|
; CHECK-NEXT: store i32 0, ptr [[TMP8]], align 4
|
|
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE]]
|
|
; CHECK: pred.store.continue:
|
|
; CHECK-NEXT: br i1 [[TMP5]], label [[PRED_STORE_IF1:%.*]], label [[PRED_STORE_CONTINUE2:%.*]]
|
|
; CHECK: pred.store.if1:
|
|
; CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds i32, ptr [[DST]], i64 [[TMP1]]
|
|
; CHECK-NEXT: store i32 0, ptr [[TMP9]], align 4
|
|
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE2]]
|
|
; CHECK: pred.store.continue2:
|
|
; CHECK-NEXT: br i1 [[TMP6]], label [[PRED_STORE_IF3:%.*]], label [[PRED_STORE_CONTINUE4:%.*]]
|
|
; CHECK: pred.store.if3:
|
|
; CHECK-NEXT: [[TMP10:%.*]] = getelementptr inbounds i32, ptr [[DST]], i64 [[TMP2]]
|
|
; CHECK-NEXT: store i32 0, ptr [[TMP10]], align 4
|
|
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE4]]
|
|
; CHECK: pred.store.continue4:
|
|
; CHECK-NEXT: br i1 [[TMP7]], label [[PRED_STORE_IF5:%.*]], label [[PRED_STORE_CONTINUE6]]
|
|
; CHECK: pred.store.if5:
|
|
; CHECK-NEXT: [[TMP11:%.*]] = getelementptr inbounds i32, ptr [[DST]], i64 [[TMP3]]
|
|
; CHECK-NEXT: store i32 0, ptr [[TMP11]], align 4
|
|
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE6]]
|
|
; CHECK: pred.store.continue6:
|
|
; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 4
|
|
; CHECK-NEXT: [[TMP12:%.*]] = icmp eq i64 [[INDEX_NEXT]], 16
|
|
; CHECK-NEXT: br i1 [[TMP12]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
|
|
; CHECK: middle.block:
|
|
; CHECK-NEXT: br i1 true, label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
|
|
; CHECK: scalar.ph:
|
|
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ 16, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
|
|
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
|
|
; CHECK: for.cond.cleanup:
|
|
; CHECK-NEXT: ret void
|
|
; CHECK: for.body:
|
|
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
|
|
; CHECK-NEXT: [[DST_PTR:%.*]] = getelementptr inbounds i32, ptr [[DST]], i64 [[INDVARS_IV]]
|
|
; CHECK-NEXT: store i32 0, ptr [[DST_PTR]], align 4
|
|
; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
|
|
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 15
|
|
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
|
|
;
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.cond.cleanup:
|
|
ret void
|
|
|
|
for.body:
|
|
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
|
|
%dst.ptr = getelementptr inbounds i32, ptr %dst, i64 %indvars.iv
|
|
store i32 0, ptr %dst.ptr
|
|
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
|
|
%exitcond = icmp eq i64 %indvars.iv.next, 15
|
|
br i1 %exitcond, label %for.cond.cleanup, label %for.body
|
|
}
|
|
|
|
define void @VF1-VPWidenCanonicalIVRecipeExe(ptr %ptr1) {
|
|
; CHECK-LABEL: @VF1-VPWidenCanonicalIVRecipeExe(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: [[PTR2:%.*]] = getelementptr inbounds double, ptr [[PTR1:%.*]], i64 15
|
|
; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
|
|
; CHECK: vector.ph:
|
|
; CHECK-NEXT: [[IND_END:%.*]] = getelementptr i8, ptr [[PTR1]], i64 128
|
|
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
|
|
; CHECK: vector.body:
|
|
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_STORE_CONTINUE12:%.*]] ]
|
|
; CHECK-NEXT: [[VEC_IV:%.*]] = add i64 [[INDEX]], 0
|
|
; CHECK-NEXT: [[VEC_IV4:%.*]] = add i64 [[INDEX]], 1
|
|
; CHECK-NEXT: [[VEC_IV5:%.*]] = add i64 [[INDEX]], 2
|
|
; CHECK-NEXT: [[VEC_IV6:%.*]] = add i64 [[INDEX]], 3
|
|
; CHECK-NEXT: [[TMP0:%.*]] = icmp ule i64 [[VEC_IV]], 14
|
|
; CHECK-NEXT: [[TMP1:%.*]] = icmp ule i64 [[VEC_IV4]], 14
|
|
; CHECK-NEXT: [[TMP2:%.*]] = icmp ule i64 [[VEC_IV5]], 14
|
|
; CHECK-NEXT: [[TMP3:%.*]] = icmp ule i64 [[VEC_IV6]], 14
|
|
; CHECK-NEXT: br i1 [[TMP0]], label [[PRED_STORE_IF:%.*]], label [[PRED_STORE_CONTINUE:%.*]]
|
|
; CHECK: pred.store.if:
|
|
; CHECK-NEXT: [[TMP4:%.*]] = add i64 [[INDEX]], 0
|
|
; CHECK-NEXT: [[TMP5:%.*]] = mul i64 [[TMP4]], 8
|
|
; CHECK-NEXT: [[NEXT_GEP:%.*]] = getelementptr i8, ptr [[PTR1]], i64 [[TMP5]]
|
|
; CHECK-NEXT: store double 0.000000e+00, ptr [[NEXT_GEP]], align 8
|
|
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE]]
|
|
; CHECK: pred.store.continue:
|
|
; CHECK-NEXT: br i1 [[TMP1]], label [[PRED_STORE_IF7:%.*]], label [[PRED_STORE_CONTINUE8:%.*]]
|
|
; CHECK: pred.store.if7:
|
|
; CHECK-NEXT: [[TMP6:%.*]] = add i64 [[INDEX]], 1
|
|
; CHECK-NEXT: [[TMP7:%.*]] = mul i64 [[TMP6]], 8
|
|
; CHECK-NEXT: [[NEXT_GEP1:%.*]] = getelementptr i8, ptr [[PTR1]], i64 [[TMP7]]
|
|
; CHECK-NEXT: store double 0.000000e+00, ptr [[NEXT_GEP1]], align 8
|
|
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE8]]
|
|
; CHECK: pred.store.continue8:
|
|
; CHECK-NEXT: br i1 [[TMP2]], label [[PRED_STORE_IF9:%.*]], label [[PRED_STORE_CONTINUE10:%.*]]
|
|
; CHECK: pred.store.if9:
|
|
; CHECK-NEXT: [[TMP8:%.*]] = add i64 [[INDEX]], 2
|
|
; CHECK-NEXT: [[TMP9:%.*]] = mul i64 [[TMP8]], 8
|
|
; CHECK-NEXT: [[NEXT_GEP2:%.*]] = getelementptr i8, ptr [[PTR1]], i64 [[TMP9]]
|
|
; CHECK-NEXT: store double 0.000000e+00, ptr [[NEXT_GEP2]], align 8
|
|
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE10]]
|
|
; CHECK: pred.store.continue10:
|
|
; CHECK-NEXT: br i1 [[TMP3]], label [[PRED_STORE_IF11:%.*]], label [[PRED_STORE_CONTINUE12]]
|
|
; CHECK: pred.store.if11:
|
|
; CHECK-NEXT: [[TMP10:%.*]] = add i64 [[INDEX]], 3
|
|
; CHECK-NEXT: [[TMP11:%.*]] = mul i64 [[TMP10]], 8
|
|
; CHECK-NEXT: [[NEXT_GEP3:%.*]] = getelementptr i8, ptr [[PTR1]], i64 [[TMP11]]
|
|
; CHECK-NEXT: store double 0.000000e+00, ptr [[NEXT_GEP3]], align 8
|
|
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE12]]
|
|
; CHECK: pred.store.continue12:
|
|
; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 4
|
|
; CHECK-NEXT: [[TMP12:%.*]] = icmp eq i64 [[INDEX_NEXT]], 16
|
|
; CHECK-NEXT: br i1 [[TMP12]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
|
|
; CHECK: middle.block:
|
|
; CHECK-NEXT: br i1 true, label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
|
|
; CHECK: scalar.ph:
|
|
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi ptr [ [[IND_END]], [[MIDDLE_BLOCK]] ], [ [[PTR1]], [[ENTRY:%.*]] ]
|
|
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
|
|
; CHECK: for.cond.cleanup:
|
|
; CHECK-NEXT: ret void
|
|
; CHECK: for.body:
|
|
; CHECK-NEXT: [[ADDR:%.*]] = phi ptr [ [[PTR:%.*]], [[FOR_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
|
|
; CHECK-NEXT: store double 0.000000e+00, ptr [[ADDR]], align 8
|
|
; CHECK-NEXT: [[PTR]] = getelementptr inbounds double, ptr [[ADDR]], i64 1
|
|
; CHECK-NEXT: [[COND:%.*]] = icmp eq ptr [[PTR]], [[PTR2]]
|
|
; CHECK-NEXT: br i1 [[COND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
|
|
;
|
|
entry:
|
|
%ptr2 = getelementptr inbounds double, ptr %ptr1, i64 15
|
|
br label %for.body
|
|
|
|
for.cond.cleanup:
|
|
ret void
|
|
|
|
for.body:
|
|
%addr = phi ptr [ %ptr, %for.body ], [ %ptr1, %entry ]
|
|
store double 0.0, ptr %addr
|
|
%ptr = getelementptr inbounds double, ptr %addr, i64 1
|
|
%cond = icmp eq ptr %ptr, %ptr2
|
|
br i1 %cond, label %for.cond.cleanup, label %for.body
|
|
}
|
|
;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
|
|
; CHECK-REMARKS: {{.*}}
|