; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -licm -loop-vectorize -force-vector-width=4 -dce -instcombine -licm -S | FileCheck %s
; First licm pass is to hoist/sink invariant stores if possible. Today LICM does
; not hoist/sink the invariant stores. Even if that changes, we should still
; vectorize this loop in case licm is not run.
; The next licm pass after vectorization is to hoist/sink loop invariant
; instructions.
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
; This file separates tests with auto-generated check lines from
; invariant-store-vectorization.ll for maintenance.
; all tests check that it is legal to vectorize the stores to invariant
; address.
; Instcombine'd version of @inv_val_store_to_inv_address_conditional_diff_values.
; Now the store is no longer of invariant value.
; scalar store the value extracted from the last element of the vector value.
define void @inv_val_store_to_inv_address_conditional_diff_values_ic(i32* %a, i64 %n, i32* %b, i32 %k) {
; CHECK-LABEL: @inv_val_store_to_inv_address_conditional_diff_values_ic(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[NTRUNC:%.*]] = trunc i64 [[N:%.*]] to i32
; CHECK-NEXT: [[SMAX6:%.*]] = call i64 @llvm.smax.i64(i64 [[N]], i64 1)
; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[SMAX6]], 4
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_MEMCHECK:%.*]]
; CHECK: vector.memcheck:
; CHECK-NEXT: [[SMAX:%.*]] = call i64 @llvm.smax.i64(i64 [[N]], i64 1)
; CHECK-NEXT: [[SCEVGEP:%.*]] = getelementptr i32, i32* [[B:%.*]], i64 [[SMAX]]
; CHECK-NEXT: [[SCEVGEP4:%.*]] = getelementptr i32, i32* [[A:%.*]], i64 1
; CHECK-NEXT: [[BOUND0:%.*]] = icmp ugt i32* [[SCEVGEP4]], [[B]]
; CHECK-NEXT: [[BOUND1:%.*]] = icmp ugt i32* [[SCEVGEP]], [[A]]
; CHECK-NEXT: [[FOUND_CONFLICT:%.*]] = and i1 [[BOUND0]], [[BOUND1]]
; CHECK-NEXT: br i1 [[FOUND_CONFLICT]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: [[N_VEC:%.*]] = and i64 [[SMAX6]], 9223372036854775804
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> poison, i32 [[K:%.*]], i64 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> poison, <4 x i32> zeroinitializer
; CHECK-NEXT: [[BROADCAST_SPLATINSERT7:%.*]] = insertelement <4 x i32> poison, i32 [[NTRUNC]], i64 0
; CHECK-NEXT: [[BROADCAST_SPLAT8:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT7]], <4 x i32> poison, <4 x i32> zeroinitializer
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP0:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[INDEX]]
; CHECK-NEXT: [[TMP1:%.*]] = bitcast i32* [[TMP0]] to <4 x i32>*
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP1]], align 8, !alias.scope !0, !noalias !3
; CHECK-NEXT: [[DOTNOT:%.*]] = icmp eq <4 x i32> [[WIDE_LOAD]], [[BROADCAST_SPLAT]]
; CHECK-NEXT: [[TMP2:%.*]] = bitcast i32* [[TMP0]] to <4 x i32>*
; CHECK-NEXT: store <4 x i32> [[BROADCAST_SPLAT8]], <4 x i32>* [[TMP2]], align 4, !alias.scope !0, !noalias !3
; CHECK-NEXT: [[PREDPHI:%.*]] = select <4 x i1> [[DOTNOT]], <4 x i32> [[BROADCAST_SPLAT8]], <4 x i32> [[BROADCAST_SPLAT]]
; CHECK-NEXT: [[TMP3:%.*]] = extractelement <4 x i32> [[PREDPHI]], i64 3
; CHECK-NEXT: store i32 [[TMP3]], i32* [[A]], align 4, !alias.scope !3
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT: [[TMP4:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP4]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[SMAX6]], [[N_VEC]]
; CHECK-NEXT: br i1 [[CMP_N]], label [[FOR_END:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ], [ 0, [[VECTOR_MEMCHECK]] ]
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[I:%.*]] = phi i64 [ [[I_NEXT:%.*]], [[LATCH:%.*]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; CHECK-NEXT: [[I1:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[I]]
; CHECK-NEXT: [[I2:%.*]] = load i32, i32* [[I1]], align 8
; CHECK-NEXT: [[CMP:%.*]] = icmp eq i32 [[I2]], [[K]]
; CHECK-NEXT: store i32 [[NTRUNC]], i32* [[I1]], align 4
; CHECK-NEXT: br i1 [[CMP]], label [[COND_STORE:%.*]], label [[COND_STORE_K:%.*]]
; CHECK: cond_store:
; CHECK-NEXT: br label [[LATCH]]
; CHECK: cond_store_k:
; CHECK-NEXT: br label [[LATCH]]
; CHECK: latch:
; CHECK-NEXT: [[STOREVAL:%.*]] = phi i32 [ [[NTRUNC]], [[COND_STORE]] ], [ [[K]], [[COND_STORE_K]] ]
; CHECK-NEXT: store i32 [[STOREVAL]], i32* [[A]], align 4
; CHECK-NEXT: [[I_NEXT]] = add nuw nsw i64 [[I]], 1
; CHECK-NEXT: [[COND:%.*]] = icmp slt i64 [[I_NEXT]], [[N]]
; CHECK-NEXT: br i1 [[COND]], label [[FOR_BODY]], label [[FOR_END_LOOPEXIT:%.*]], !llvm.loop [[LOOP7:![0-9]+]]
; CHECK: for.end.loopexit:
; CHECK-NEXT: br label [[FOR_END]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
entry:
%ntrunc = trunc i64 %n to i32
br label %for.body
for.body: ; preds = %for.body, %entry
%i = phi i64 [ %i.next, %latch ], [ 0, %entry ]
%i1 = getelementptr inbounds i32, i32* %b, i64 %i
%i2 = load i32, i32* %i1, align 8
%cmp = icmp eq i32 %i2, %k
store i32 %ntrunc, i32* %i1
br i1 %cmp, label %cond_store, label %cond_store_k
cond_store:
br label %latch
cond_store_k:
br label %latch
latch:
%storeval = phi i32 [ %ntrunc, %cond_store ], [ %k, %cond_store_k ]
store i32 %storeval, i32* %a
%i.next = add nuw nsw i64 %i, 1
%cond = icmp slt i64 %i.next, %n
br i1 %cond, label %for.body, label %for.end
for.end: ; preds = %for.body
ret void
}
; invariant val stored to invariant address predicated on invariant condition
; This is not treated as a predicated store since the block the store belongs to
; is the latch block (which doesn't need to be predicated).
; variant/invariant values being stored to invariant address.
; test checks that the last element of the phi is extracted and scalar stored
; into the uniform address within the loop.
; Since the condition and the phi is loop invariant, they are LICM'ed after
; vectorization.
define void @inv_val_store_to_inv_address_conditional_inv(i32* %a, i64 %n, i32* %b, i32 %k) {
; CHECK-LABEL: @inv_val_store_to_inv_address_conditional_inv(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[NTRUNC:%.*]] = trunc i64 [[N:%.*]] to i32
; CHECK-NEXT: [[CMP:%.*]] = icmp eq i32 [[NTRUNC]], [[K:%.*]]
; CHECK-NEXT: [[SMAX6:%.*]] = call i64 @llvm.smax.i64(i64 [[N]], i64 1)
; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[SMAX6]], 4
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_MEMCHECK:%.*]]
; CHECK: vector.memcheck:
; CHECK-NEXT: [[SMAX:%.*]] = call i64 @llvm.smax.i64(i64 [[N]], i64 1)
; CHECK-NEXT: [[SCEVGEP:%.*]] = getelementptr i32, i32* [[B:%.*]], i64 [[SMAX]]
; CHECK-NEXT: [[SCEVGEP4:%.*]] = getelementptr i32, i32* [[A:%.*]], i64 1
; CHECK-NEXT: [[BOUND0:%.*]] = icmp ugt i32* [[SCEVGEP4]], [[B]]
; CHECK-NEXT: [[BOUND1:%.*]] = icmp ugt i32* [[SCEVGEP]], [[A]]
; CHECK-NEXT: [[FOUND_CONFLICT:%.*]] = and i1 [[BOUND0]], [[BOUND1]]
; CHECK-NEXT: br i1 [[FOUND_CONFLICT]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: [[N_VEC:%.*]] = and i64 [[SMAX6]], 9223372036854775804
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> poison, i32 [[NTRUNC]], i64 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> poison, <4 x i32> zeroinitializer
; CHECK-NEXT: [[TMP0:%.*]] = insertelement <4 x i1> undef, i1 [[CMP]], i64 3
; CHECK-NEXT: [[BROADCAST_SPLAT10:%.*]] = insertelement <4 x i32> poison, i32 [[K]], i64 3
; CHECK-NEXT: [[PREDPHI:%.*]] = select <4 x i1> [[TMP0]], <4 x i32> [[BROADCAST_SPLAT]], <4 x i32> [[BROADCAST_SPLAT10]]
; CHECK-NEXT: [[TMP1:%.*]] = extractelement <4 x i32> [[PREDPHI]], i64 3
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[INDEX]]
; CHECK-NEXT: [[TMP3:%.*]] = bitcast i32* [[TMP2]] to <4 x i32>*
; CHECK-NEXT: store <4 x i32> [[BROADCAST_SPLAT]], <4 x i32>* [[TMP3]], align 4, !alias.scope !8, !noalias !11
; CHECK-NEXT: store i32 [[TMP1]], i32* [[A]], align 4, !alias.scope !11
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT: [[TMP4:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP4]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP13:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[SMAX6]], [[N_VEC]]
; CHECK-NEXT: br i1 [[CMP_N]], label [[FOR_END:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ], [ 0, [[VECTOR_MEMCHECK]] ]
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[I:%.*]] = phi i64 [ [[I_NEXT:%.*]], [[LATCH:%.*]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; CHECK-NEXT: [[I1:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[I]]
; CHECK-NEXT: store i32 [[NTRUNC]], i32* [[I1]], align 4
; CHECK-NEXT: br i1 [[CMP]], label [[COND_STORE:%.*]], label [[COND_STORE_K:%.*]]
; CHECK: cond_store:
; CHECK-NEXT: br label [[LATCH]]
; CHECK: cond_store_k:
; CHECK-NEXT: br label [[LATCH]]
; CHECK: latch:
; CHECK-NEXT: [[STOREVAL:%.*]] = phi i32 [ [[NTRUNC]], [[COND_STORE]] ], [ [[K]], [[COND_STORE_K]] ]
; CHECK-NEXT: store i32 [[STOREVAL]], i32* [[A]], align 4
; CHECK-NEXT: [[I_NEXT]] = add nuw nsw i64 [[I]], 1
; CHECK-NEXT: [[COND:%.*]] = icmp slt i64 [[I_NEXT]], [[N]]
; CHECK-NEXT: br i1 [[COND]], label [[FOR_BODY]], label [[FOR_END_LOOPEXIT:%.*]], !llvm.loop [[LOOP14:![0-9]+]]
; CHECK: for.end.loopexit:
; CHECK-NEXT: br label [[FOR_END]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
entry:
%ntrunc = trunc i64 %n to i32
%cmp = icmp eq i32 %ntrunc, %k
br label %for.body
for.body: ; preds = %for.body, %entry
%i = phi i64 [ %i.next, %latch ], [ 0, %entry ]
%i1 = getelementptr inbounds i32, i32* %b, i64 %i
%i2 = load i32, i32* %i1, align 8
store i32 %ntrunc, i32* %i1
br i1 %cmp, label %cond_store, label %cond_store_k
cond_store:
br label %latch
cond_store_k:
br label %latch
latch:
%storeval = phi i32 [ %ntrunc, %cond_store ], [ %k, %cond_store_k ]
store i32 %storeval, i32* %a
%i.next = add nuw nsw i64 %i, 1
%cond = icmp slt i64 %i.next, %n
br i1 %cond, label %for.body, label %for.end
for.end: ; preds = %for.body
ret void
}
; variant value stored to uniform address tests that the code gen extracts the
; last element from the variant vector and scalar stores it into the uniform
; address.
define i32 @variant_val_store_to_inv_address(i32* %a, i64 %n, i32* %b, i32 %k) {
; CHECK-LABEL: @variant_val_store_to_inv_address(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[SMAX6:%.*]] = call i64 @llvm.smax.i64(i64 [[N:%.*]], i64 1)
; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[SMAX6]], 4
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_MEMCHECK:%.*]]
; CHECK: vector.memcheck:
; CHECK-NEXT: [[SCEVGEP:%.*]] = getelementptr i32, i32* [[A:%.*]], i64 1
; CHECK-NEXT: [[SMAX:%.*]] = call i64 @llvm.smax.i64(i64 [[N]], i64 1)
; CHECK-NEXT: [[SCEVGEP4:%.*]] = getelementptr i32, i32* [[B:%.*]], i64 [[SMAX]]
; CHECK-NEXT: [[BOUND0:%.*]] = icmp ugt i32* [[SCEVGEP4]], [[A]]
; CHECK-NEXT: [[BOUND1:%.*]] = icmp ugt i32* [[SCEVGEP]], [[B]]
; CHECK-NEXT: [[FOUND_CONFLICT:%.*]] = and i1 [[BOUND0]], [[BOUND1]]
; CHECK-NEXT: br i1 [[FOUND_CONFLICT]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: [[N_VEC:%.*]] = and i64 [[SMAX6]], 9223372036854775804
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP3:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP0:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[INDEX]]
; CHECK-NEXT: [[TMP1:%.*]] = bitcast i32* [[TMP0]] to <4 x i32>*
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP1]], align 8, !alias.scope !15
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <4 x i32> [[WIDE_LOAD]], i64 3
; CHECK-NEXT: store i32 [[TMP2]], i32* [[A]], align 4, !alias.scope !18, !noalias !15
; CHECK-NEXT: [[TMP3]] = add <4 x i32> [[VEC_PHI]], [[WIDE_LOAD]]
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT: [[TMP4:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP4]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP20:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: [[DOTLCSSA:%.*]] = phi <4 x i32> [ [[TMP3]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP5:%.*]] = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> [[DOTLCSSA]])
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[SMAX6]], [[N_VEC]]
; CHECK-NEXT: br i1 [[CMP_N]], label [[FOR_END:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ], [ 0, [[VECTOR_MEMCHECK]] ]
; CHECK-NEXT: [[BC_MERGE_RDX:%.*]] = phi i32 [ [[TMP5]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY]] ], [ 0, [[VECTOR_MEMCHECK]] ]
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[I:%.*]] = phi i64 [ [[I_NEXT:%.*]], [[FOR_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; CHECK-NEXT: [[I0:%.*]] = phi i32 [ [[I3:%.*]], [[FOR_BODY]] ], [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ]
; CHECK-NEXT: [[I1:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[I]]
; CHECK-NEXT: [[I2:%.*]] = load i32, i32* [[I1]], align 8
; CHECK-NEXT: store i32 [[I2]], i32* [[A]], align 4
; CHECK-NEXT: [[I3]] = add i32 [[I0]], [[I2]]
; CHECK-NEXT: [[I_NEXT]] = add nuw nsw i64 [[I]], 1
; CHECK-NEXT: [[COND:%.*]] = icmp slt i64 [[I_NEXT]], [[N]]
; CHECK-NEXT: br i1 [[COND]], label [[FOR_BODY]], label [[FOR_END_LOOPEXIT:%.*]], !llvm.loop [[LOOP21:![0-9]+]]
; CHECK: for.end.loopexit:
; CHECK-NEXT: [[I3_LCSSA:%.*]] = phi i32 [ [[I3]], [[FOR_BODY]] ]
; CHECK-NEXT: br label [[FOR_END]]
; CHECK: for.end:
; CHECK-NEXT: [[RDX_LCSSA:%.*]] = phi i32 [ [[TMP5]], [[MIDDLE_BLOCK]] ], [ [[I3_LCSSA]], [[FOR_END_LOOPEXIT]] ]
; CHECK-NEXT: ret i32 [[RDX_LCSSA]]
;
entry:
%ntrunc = trunc i64 %n to i32
%cmp = icmp eq i32 %ntrunc, %k
br label %for.body
for.body: ; preds = %for.body, %entry
%i = phi i64 [ %i.next, %for.body ], [ 0, %entry ]
%i0 = phi i32 [ %i3, %for.body ], [ 0, %entry ]
%i1 = getelementptr inbounds i32, i32* %b, i64 %i
%i2 = load i32, i32* %i1, align 8
store i32 %i2, i32* %a
%i3 = add i32 %i0, %i2
%i.next = add nuw nsw i64 %i, 1
%cond = icmp slt i64 %i.next, %n
br i1 %cond, label %for.body, label %for.end
for.end: ; preds = %for.body
%rdx.lcssa = phi i32 [ %i3, %for.body ]
ret i32 %rdx.lcssa
}