efd4938723
This patch tries to use an existing VPWidenCanonicalIVRecipe
instead of creating another step-vector for canonical
induction recipes in widenIntOrFpInduction.
This has the following benefits:
1. First step to avoid setting both vector and scalar values for the
same induction def.
2. Reducing complexity of widenIntOrFpInduction through making things
more explicit in VPlan
3. Only need to splat the vector IV for block in masks.
Reviewed By: Ayal
Differential Revision: https://reviews.llvm.org/D116123
166 lines
8.8 KiB
LLVM
166 lines
8.8 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt < %s -loop-vectorize -force-vector-interleave=4 -pass-remarks='loop-vectorize' -disable-output -S 2>&1 | FileCheck %s --check-prefix=CHECK-REMARKS
|
|
; RUN: opt < %s -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(i32* %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_CONTINUE9:%.*]] ]
|
|
; CHECK-NEXT: [[INDUCTION:%.*]] = add i64 [[INDEX]], 0
|
|
; CHECK-NEXT: [[INDUCTION1:%.*]] = add i64 [[INDEX]], 1
|
|
; CHECK-NEXT: [[INDUCTION2:%.*]] = add i64 [[INDEX]], 2
|
|
; CHECK-NEXT: [[INDUCTION3:%.*]] = add i64 [[INDEX]], 3
|
|
; CHECK-NEXT: [[TMP0:%.*]] = icmp ule i64 [[INDUCTION]], 14
|
|
; CHECK-NEXT: [[TMP1:%.*]] = icmp ule i64 [[INDUCTION1]], 14
|
|
; CHECK-NEXT: [[TMP2:%.*]] = icmp ule i64 [[INDUCTION2]], 14
|
|
; CHECK-NEXT: [[TMP3:%.*]] = icmp ule i64 [[INDUCTION3]], 14
|
|
; CHECK-NEXT: br i1 [[TMP0]], label [[PRED_STORE_IF:%.*]], label [[PRED_STORE_CONTINUE:%.*]]
|
|
; CHECK: pred.store.if:
|
|
; CHECK-NEXT: [[SUNK_IND0:%.*]] = add i64 [[INDEX]], 0
|
|
; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds i32, i32* [[DST:%.*]], i64 [[SUNK_IND0]]
|
|
; CHECK-NEXT: store i32 0, i32* [[TMP4]], align 4
|
|
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE]]
|
|
; CHECK: pred.store.continue:
|
|
; CHECK-NEXT: br i1 [[TMP1]], label [[PRED_STORE_IF4:%.*]], label [[PRED_STORE_CONTINUE5:%.*]]
|
|
; CHECK: pred.store.if7:
|
|
; CHECK-NEXT: [[SUNK_IND1:%.*]] = add i64 [[INDEX]], 1
|
|
; CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds i32, i32* [[DST]], i64 [[SUNK_IND1]]
|
|
; CHECK-NEXT: store i32 0, i32* [[TMP5]], align 4
|
|
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE5]]
|
|
; CHECK: pred.store.continue8:
|
|
; CHECK-NEXT: br i1 [[TMP2]], label [[PRED_STORE_IF6:%.*]], label [[PRED_STORE_CONTINUE7:%.*]]
|
|
; CHECK: pred.store.if9:
|
|
; CHECK-NEXT: [[SUNK_IND2:%.*]] = add i64 [[INDEX]], 2
|
|
; CHECK-NEXT: [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[DST]], i64 [[SUNK_IND2]]
|
|
; CHECK-NEXT: store i32 0, i32* [[TMP6]], align 4
|
|
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE7]]
|
|
; CHECK: pred.store.continue10:
|
|
; CHECK-NEXT: br i1 [[TMP3]], label [[PRED_STORE_IF8:%.*]], label [[PRED_STORE_CONTINUE9]]
|
|
; CHECK: pred.store.if11:
|
|
; CHECK-NEXT: [[SUNK_IND3:%.*]] = add i64 [[INDEX]], 3
|
|
; CHECK-NEXT: [[TMP7:%.*]] = getelementptr inbounds i32, i32* [[DST]], i64 [[SUNK_IND3]]
|
|
; CHECK-NEXT: store i32 0, i32* [[TMP7]], align 4
|
|
; CHECK-NEXT: br label [[PRED_STORE_CONTINUE9]]
|
|
; CHECK: pred.store.continue12:
|
|
; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 4
|
|
; CHECK-NEXT: [[TMP8:%.*]] = icmp eq i64 [[INDEX_NEXT]], 16
|
|
; CHECK-NEXT: br i1 [[TMP8]], 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, i32* [[DST]], i64 [[INDVARS_IV]]
|
|
; CHECK-NEXT: store i32 0, i32* [[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 [[LOOP2:![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, i32* %dst, i64 %indvars.iv
|
|
store i32 0, i32* %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(double* %ptr1) {
|
|
; CHECK-LABEL: @VF1-VPWidenCanonicalIVRecipeExe(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: [[PTR2:%.*]] = getelementptr inbounds double, double* [[PTR1:%.*]], i64 15
|
|
; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
|
|
; CHECK: vector.ph:
|
|
; CHECK-NEXT: [[IND_END:%.*]] = getelementptr double, double* [[PTR1]], i64 16
|
|
; 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: [[NEXT_GEP:%.*]] = getelementptr double, double* [[PTR1]], i64 [[TMP4]]
|
|
; CHECK-NEXT: store double 0.000000e+00, double* [[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: [[TMP5:%.*]] = add i64 [[INDEX]], 1
|
|
; CHECK-NEXT: [[NEXT_GEP1:%.*]] = getelementptr double, double* [[PTR1]], i64 [[TMP5]]
|
|
; CHECK-NEXT: store double 0.000000e+00, double* [[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: [[TMP6:%.*]] = add i64 [[INDEX]], 2
|
|
; CHECK-NEXT: [[NEXT_GEP2:%.*]] = getelementptr double, double* [[PTR1]], i64 [[TMP6]]
|
|
; CHECK-NEXT: store double 0.000000e+00, double* [[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: [[TMP7:%.*]] = add i64 [[INDEX]], 3
|
|
; CHECK-NEXT: [[NEXT_GEP3:%.*]] = getelementptr double, double* [[PTR1]], i64 [[TMP7]]
|
|
; CHECK-NEXT: store double 0.000000e+00, double* [[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: [[TMP8:%.*]] = icmp eq i64 [[INDEX_NEXT]], 16
|
|
; CHECK-NEXT: br i1 [[TMP8]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP3:![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 double* [ [[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 double* [ [[PTR:%.*]], [[FOR_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
|
|
; CHECK-NEXT: store double 0.000000e+00, double* [[ADDR]], align 8
|
|
; CHECK-NEXT: [[PTR]] = getelementptr inbounds double, double* [[ADDR]], i64 1
|
|
; CHECK-NEXT: [[COND:%.*]] = icmp eq double* [[PTR]], [[PTR2]]
|
|
; CHECK-NEXT: br i1 [[COND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
|
|
;
|
|
entry:
|
|
%ptr2 = getelementptr inbounds double, double* %ptr1, i64 15
|
|
br label %for.body
|
|
|
|
for.cond.cleanup:
|
|
ret void
|
|
|
|
for.body:
|
|
%addr = phi double* [ %ptr, %for.body ], [ %ptr1, %entry ]
|
|
store double 0.0, double* %addr
|
|
%ptr = getelementptr inbounds double, double* %addr, i64 1
|
|
%cond = icmp eq double* %ptr, %ptr2
|
|
br i1 %cond, label %for.cond.cleanup, label %for.body
|
|
}
|