[IRBuilder] Fold consistently for or/and whether constant is LHS or RHS

Without this, we have the unfortunate property that tests are dependent on the order of operads passed the CreateOr and CreateAnd functions.  In actual usage, we'd promptly optimize them away, but it made tests slightly more verbose than they should have been.

llvm-svn: 365260

2 files changed, 39 insertions, 41 deletions

diff --git a/llvm/test/Transforms/LoopVectorize/X86/illegal-parallel-loop-uniform-write.ll b/llvm/test/Transforms/LoopVectorize/X86/illegal-parallel-loop-uniform-write.ll
index 43c834ed808..da1ce0eef26 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/illegal-parallel-loop-uniform-write.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/illegal-parallel-loop-uniform-write.ll
@@ -71,34 +71,33 @@ define void @foo(i32* nocapture %a, i32* nocapture %b, i32 %k, i32 %m) #0 {
 ; CHECK-NEXT:    [[TMP13:%.*]] = icmp slt i32 [[TMP10]], [[TMP8]]
 ; CHECK-NEXT:    [[TMP14:%.*]] = select i1 false, i1 [[TMP12]], i1 [[TMP13]]
 ; CHECK-NEXT:    [[TMP15:%.*]] = or i1 [[TMP14]], [[MUL_OVERFLOW]]
-; CHECK-NEXT:    [[TMP16:%.*]] = or i1 false, [[TMP15]]
-; CHECK-NEXT:    br i1 [[TMP16]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
+; CHECK-NEXT:    br i1 [[TMP15]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
 ; CHECK:       vector.ph:
 ; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[TMP2]], 4
 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[TMP2]], [[N_MOD_VF]]
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[TMP17:%.*]] = trunc i64 [[INDEX]] to i32
-; CHECK-NEXT:    [[TMP18:%.*]] = add i32 [[TMP17]], 0
-; CHECK-NEXT:    [[TMP19:%.*]] = add i32 [[ADD_US]], [[TMP18]]
-; CHECK-NEXT:    [[TMP20:%.*]] = sext i32 [[TMP19]] to i64
-; CHECK-NEXT:    [[TMP21:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP20]]
-; CHECK-NEXT:    [[TMP22:%.*]] = getelementptr inbounds i32, i32* [[TMP21]], i32 0
-; CHECK-NEXT:    [[TMP23:%.*]] = bitcast i32* [[TMP22]] to <4 x i32>*
-; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP23]], align 4
-; CHECK-NEXT:    [[TMP24:%.*]] = add nsw <4 x i32> [[WIDE_LOAD]], <i32 1, i32 1, i32 1, i32 1>
-; CHECK-NEXT:    [[TMP25:%.*]] = extractelement <4 x i32> [[TMP24]], i32 0
+; CHECK-NEXT:    [[TMP16:%.*]] = trunc i64 [[INDEX]] to i32
+; CHECK-NEXT:    [[TMP17:%.*]] = add i32 [[TMP16]], 0
+; CHECK-NEXT:    [[TMP18:%.*]] = add i32 [[ADD_US]], [[TMP17]]
+; CHECK-NEXT:    [[TMP19:%.*]] = sext i32 [[TMP18]] to i64
+; CHECK-NEXT:    [[TMP20:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP19]]
+; CHECK-NEXT:    [[TMP21:%.*]] = getelementptr inbounds i32, i32* [[TMP20]], i32 0
+; CHECK-NEXT:    [[TMP22:%.*]] = bitcast i32* [[TMP21]] to <4 x i32>*
+; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP22]], align 4
+; CHECK-NEXT:    [[TMP23:%.*]] = add nsw <4 x i32> [[WIDE_LOAD]], <i32 1, i32 1, i32 1, i32 1>
+; CHECK-NEXT:    [[TMP24:%.*]] = extractelement <4 x i32> [[TMP23]], i32 0
+; CHECK-NEXT:    store i32 [[TMP24]], i32* [[ARRAYIDX7_US]], align 4, !llvm.mem.parallel_loop_access !0
+; CHECK-NEXT:    [[TMP25:%.*]] = extractelement <4 x i32> [[TMP23]], i32 1
 ; CHECK-NEXT:    store i32 [[TMP25]], i32* [[ARRAYIDX7_US]], align 4, !llvm.mem.parallel_loop_access !0
-; CHECK-NEXT:    [[TMP26:%.*]] = extractelement <4 x i32> [[TMP24]], i32 1
+; CHECK-NEXT:    [[TMP26:%.*]] = extractelement <4 x i32> [[TMP23]], i32 2
 ; CHECK-NEXT:    store i32 [[TMP26]], i32* [[ARRAYIDX7_US]], align 4, !llvm.mem.parallel_loop_access !0
-; CHECK-NEXT:    [[TMP27:%.*]] = extractelement <4 x i32> [[TMP24]], i32 2
+; CHECK-NEXT:    [[TMP27:%.*]] = extractelement <4 x i32> [[TMP23]], i32 3
 ; CHECK-NEXT:    store i32 [[TMP27]], i32* [[ARRAYIDX7_US]], align 4, !llvm.mem.parallel_loop_access !0
-; CHECK-NEXT:    [[TMP28:%.*]] = extractelement <4 x i32> [[TMP24]], i32 3
-; CHECK-NEXT:    store i32 [[TMP28]], i32* [[ARRAYIDX7_US]], align 4, !llvm.mem.parallel_loop_access !0
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 4
-; CHECK-NEXT:    [[TMP29:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT:    br i1 [[TMP29]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !5
+; CHECK-NEXT:    [[TMP28:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[TMP28]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !5
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[TMP2]], [[N_VEC]]
 ; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_END_US]], label [[SCALAR_PH]]
diff --git a/llvm/test/Transforms/LoopVectorize/X86/pr35432.ll b/llvm/test/Transforms/LoopVectorize/X86/pr35432.ll
index 6aaa13c183a..db5e0ed8da3 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/pr35432.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/pr35432.ll
@@ -40,16 +40,16 @@ define i32 @main() local_unnamed_addr #0 {
 ; CHECK-NEXT:    [[TMP4:%.*]] = zext i8 [[TMP3]] to i32
 ; CHECK-NEXT:    [[TMP5:%.*]] = add i32 [[TMP4]], 1
 ; CHECK-NEXT:    [[TMP6:%.*]] = icmp ult i32 [[TMP2]], [[TMP4]]
-; CHECK-NEXT:    [[UMAX:%.*]] = select i1 [[TMP6]], i32 [[TMP2]], i32 [[TMP4]]
-; CHECK-NEXT:    [[TMP7:%.*]] = sub i32 [[TMP5]], [[UMAX]]
+; CHECK-NEXT:    [[UMIN:%.*]] = select i1 [[TMP6]], i32 [[TMP2]], i32 [[TMP4]]
+; CHECK-NEXT:    [[TMP7:%.*]] = sub i32 [[TMP5]], [[UMIN]]
 ; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[TMP7]], 8
 ; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]]
 ; CHECK:       vector.scevcheck:
 ; CHECK-NEXT:    [[TMP8:%.*]] = add i8 [[CONV3]], -1
 ; CHECK-NEXT:    [[TMP9:%.*]] = zext i8 [[TMP8]] to i32
 ; CHECK-NEXT:    [[TMP10:%.*]] = icmp ult i32 [[TMP2]], [[TMP9]]
-; CHECK-NEXT:    [[UMAX1:%.*]] = select i1 [[TMP10]], i32 [[TMP2]], i32 [[TMP9]]
-; CHECK-NEXT:    [[TMP11:%.*]] = sub i32 [[TMP9]], [[UMAX1]]
+; CHECK-NEXT:    [[UMIN1:%.*]] = select i1 [[TMP10]], i32 [[TMP2]], i32 [[TMP9]]
+; CHECK-NEXT:    [[TMP11:%.*]] = sub i32 [[TMP9]], [[UMIN1]]
 ; CHECK-NEXT:    [[TMP12:%.*]] = trunc i32 [[TMP11]] to i8
 ; CHECK-NEXT:    [[MUL:%.*]] = call { i8, i1 } @llvm.umul.with.overflow.i8(i8 1, i8 [[TMP12]])
 ; CHECK-NEXT:    [[MUL_RESULT:%.*]] = extractvalue { i8, i1 } [[MUL]], 0
@@ -62,48 +62,47 @@ define i32 @main() local_unnamed_addr #0 {
 ; CHECK-NEXT:    [[TMP18:%.*]] = icmp ugt i32 [[TMP11]], 255
 ; CHECK-NEXT:    [[TMP19:%.*]] = or i1 [[TMP17]], [[TMP18]]
 ; CHECK-NEXT:    [[TMP20:%.*]] = or i1 [[TMP19]], [[MUL_OVERFLOW]]
-; CHECK-NEXT:    [[TMP21:%.*]] = or i1 false, [[TMP20]]
-; CHECK-NEXT:    br i1 [[TMP21]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
+; CHECK-NEXT:    br i1 [[TMP20]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
 ; CHECK:       vector.ph:
 ; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i32 [[TMP7]], 8
 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i32 [[TMP7]], [[N_MOD_VF]]
 ; CHECK-NEXT:    [[CAST_CRD:%.*]] = trunc i32 [[N_VEC]] to i8
 ; CHECK-NEXT:    [[IND_END:%.*]] = sub i8 [[CONV3]], [[CAST_CRD]]
-; CHECK-NEXT:    [[TMP22:%.*]] = insertelement <4 x i32> zeroinitializer, i32 [[DOTPROMOTED]], i32 0
+; CHECK-NEXT:    [[TMP21:%.*]] = insertelement <4 x i32> zeroinitializer, i32 [[DOTPROMOTED]], i32 0
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <4 x i32> [ [[TMP22]], [[VECTOR_PH]] ], [ [[TMP26:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[VEC_PHI2:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP27:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[TMP23:%.*]] = trunc i32 [[INDEX]] to i8
-; CHECK-NEXT:    [[OFFSET_IDX:%.*]] = sub i8 [[CONV3]], [[TMP23]]
+; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <4 x i32> [ [[TMP21]], [[VECTOR_PH]] ], [ [[TMP25:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[VEC_PHI2:%.*]] = phi <4 x i32> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP26:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[TMP22:%.*]] = trunc i32 [[INDEX]] to i8
+; CHECK-NEXT:    [[OFFSET_IDX:%.*]] = sub i8 [[CONV3]], [[TMP22]]
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i8> undef, i8 [[OFFSET_IDX]], i32 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i8> [[BROADCAST_SPLATINSERT]], <4 x i8> undef, <4 x i32> zeroinitializer
 ; CHECK-NEXT:    [[INDUCTION:%.*]] = add <4 x i8> [[BROADCAST_SPLAT]], <i8 0, i8 -1, i8 -2, i8 -3>
 ; CHECK-NEXT:    [[INDUCTION3:%.*]] = add <4 x i8> [[BROADCAST_SPLAT]], <i8 -4, i8 -5, i8 -6, i8 -7>
-; CHECK-NEXT:    [[TMP24:%.*]] = add i8 [[OFFSET_IDX]], 0
-; CHECK-NEXT:    [[TMP25:%.*]] = add i8 [[OFFSET_IDX]], -4
-; CHECK-NEXT:    [[TMP26]] = add <4 x i32> [[VEC_PHI]], <i32 1, i32 1, i32 1, i32 1>
-; CHECK-NEXT:    [[TMP27]] = add <4 x i32> [[VEC_PHI2]], <i32 1, i32 1, i32 1, i32 1>
+; CHECK-NEXT:    [[TMP23:%.*]] = add i8 [[OFFSET_IDX]], 0
+; CHECK-NEXT:    [[TMP24:%.*]] = add i8 [[OFFSET_IDX]], -4
+; CHECK-NEXT:    [[TMP25]] = add <4 x i32> [[VEC_PHI]], <i32 1, i32 1, i32 1, i32 1>
+; CHECK-NEXT:    [[TMP26]] = add <4 x i32> [[VEC_PHI2]], <i32 1, i32 1, i32 1, i32 1>
+; CHECK-NEXT:    [[TMP27:%.*]] = add i8 [[TMP23]], -1
 ; CHECK-NEXT:    [[TMP28:%.*]] = add i8 [[TMP24]], -1
-; CHECK-NEXT:    [[TMP29:%.*]] = add i8 [[TMP25]], -1
+; CHECK-NEXT:    [[TMP29:%.*]] = zext i8 [[TMP27]] to i32
 ; CHECK-NEXT:    [[TMP30:%.*]] = zext i8 [[TMP28]] to i32
-; CHECK-NEXT:    [[TMP31:%.*]] = zext i8 [[TMP29]] to i32
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 8
-; CHECK-NEXT:    [[TMP32:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT:    br i1 [[TMP32]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !0
+; CHECK-NEXT:    [[TMP31:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[TMP31]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !0
 ; CHECK:       middle.block:
-; CHECK-NEXT:    [[BIN_RDX:%.*]] = add <4 x i32> [[TMP27]], [[TMP26]]
+; CHECK-NEXT:    [[BIN_RDX:%.*]] = add <4 x i32> [[TMP26]], [[TMP25]]
 ; CHECK-NEXT:    [[RDX_SHUF:%.*]] = shufflevector <4 x i32> [[BIN_RDX]], <4 x i32> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
 ; CHECK-NEXT:    [[BIN_RDX4:%.*]] = add <4 x i32> [[BIN_RDX]], [[RDX_SHUF]]
 ; CHECK-NEXT:    [[RDX_SHUF5:%.*]] = shufflevector <4 x i32> [[BIN_RDX4]], <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
 ; CHECK-NEXT:    [[BIN_RDX6:%.*]] = add <4 x i32> [[BIN_RDX4]], [[RDX_SHUF5]]
-; CHECK-NEXT:    [[TMP33:%.*]] = extractelement <4 x i32> [[BIN_RDX6]], i32 0
+; CHECK-NEXT:    [[TMP32:%.*]] = extractelement <4 x i32> [[BIN_RDX6]], i32 0
 ; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 [[TMP7]], [[N_VEC]]
 ; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_COND4_FOR_INC9_CRIT_EDGE:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
 ; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i8 [ [[IND_END]], [[MIDDLE_BLOCK]] ], [ [[CONV3]], [[FOR_BODY8_LR_PH]] ], [ [[CONV3]], [[VECTOR_SCEVCHECK]] ]
-; CHECK-NEXT:    [[BC_MERGE_RDX:%.*]] = phi i32 [ [[DOTPROMOTED]], [[FOR_BODY8_LR_PH]] ], [ [[DOTPROMOTED]], [[VECTOR_SCEVCHECK]] ], [ [[TMP33]], [[MIDDLE_BLOCK]] ]
+; CHECK-NEXT:    [[BC_MERGE_RDX:%.*]] = phi i32 [ [[DOTPROMOTED]], [[FOR_BODY8_LR_PH]] ], [ [[DOTPROMOTED]], [[VECTOR_SCEVCHECK]] ], [ [[TMP32]], [[MIDDLE_BLOCK]] ]
 ; CHECK-NEXT:    br label [[FOR_BODY8:%.*]]
 ; CHECK:       for.body8:
 ; CHECK-NEXT:    [[INC5:%.*]] = phi i32 [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ], [ [[INC:%.*]], [[FOR_BODY8]] ]
@@ -114,7 +113,7 @@ define i32 @main() local_unnamed_addr #0 {
 ; CHECK-NEXT:    [[CMP6:%.*]] = icmp ult i32 [[TMP2]], [[CONV5]]
 ; CHECK-NEXT:    br i1 [[CMP6]], label [[FOR_BODY8]], label [[FOR_COND4_FOR_INC9_CRIT_EDGE]], !llvm.loop !2
 ; CHECK:       for.cond4.for.inc9_crit_edge:
-; CHECK-NEXT:    [[INC_LCSSA:%.*]] = phi i32 [ [[INC]], [[FOR_BODY8]] ], [ [[TMP33]], [[MIDDLE_BLOCK]] ]
+; CHECK-NEXT:    [[INC_LCSSA:%.*]] = phi i32 [ [[INC]], [[FOR_BODY8]] ], [ [[TMP32]], [[MIDDLE_BLOCK]] ]
 ; CHECK-NEXT:    store i32 [[INC_LCSSA]], i32* getelementptr inbounds ([192 x [192 x i32]], [192 x [192 x i32]]* @a, i64 0, i64 0, i64 0), align 16
 ; CHECK-NEXT:    br label [[FOR_INC9]]
 ; CHECK:       for.inc9: