[LICM] Enable control flow hoisting by default

[mkazantsev]

LGTM, but I have a suggestion. How about turning the option on explicitly for these tests? So that the "enable by default" patch contains only 1 line and super-easy to revert.

llvm/trunk/lib/Transforms/Scalar/LICM.cpp

 STATISTIC(NumPromoted, "Number of memory locations promoted to registers");
 
 /// Memory promotion is enabled by default.
 static cl::opt<bool>
     DisablePromotion("disable-licm-promotion", cl::Hidden, cl::init(false),
                      cl::desc("Disable memory promotion in LICM pass"));
 
 static cl::opt<bool> ControlFlowHoisting(
-    "licm-control-flow-hoisting", cl::Hidden, cl::init(false),
+    "licm-control-flow-hoisting", cl::Hidden, cl::init(true),
     cl::desc("Enable control flow (and PHI) hoisting in LICM"));
 
 static cl::opt<uint32_t> MaxNumUsesTraversed(
     "licm-max-num-uses-traversed", cl::Hidden, cl::init(8),
     cl::desc("Max num uses visited for identifying load "
              "invariance in loop using invariant start (default = 8)"));
 
 // Default value of zero implies we use the regular alias set tracker mechanism

llvm/trunk/test/Transforms/LICM/hoist-phi.ll

-; RUN: opt -S -licm < %s | FileCheck %s -check-prefixes=CHECK,CHECK-DISABLED
+; RUN: opt -S -licm < %s | FileCheck %s -check-prefixes=CHECK,CHECK-ENABLED
 ; RUN: opt -S -licm -licm-control-flow-hoisting=1 < %s | FileCheck %s -check-prefixes=CHECK,CHECK-ENABLED
 ; RUN: opt -S -licm -licm-control-flow-hoisting=0 < %s | FileCheck %s -check-prefixes=CHECK,CHECK-DISABLED
-; RUN: opt -passes='require<opt-remark-emit>,loop(licm)' -S < %s | FileCheck %s -check-prefixes=CHECK,CHECK-DISABLED
+; RUN: opt -passes='require<opt-remark-emit>,loop(licm)' -S < %s | FileCheck %s -check-prefixes=CHECK,CHECK-ENABLED
 ; RUN: opt -passes='require<opt-remark-emit>,loop(licm)' -licm-control-flow-hoisting=1 -S < %s | FileCheck %s -check-prefixes=CHECK,CHECK-ENABLED
 ; RUN: opt -passes='require<opt-remark-emit>,loop(licm)' -licm-control-flow-hoisting=0 -S < %s | FileCheck %s -check-prefixes=CHECK,CHECK-DISABLED
 
 ; CHECK-LABEL: @triangle_phi
 define void @triangle_phi(i32 %x, i32* %p) {
 ; CHECK-LABEL: entry:
 ; CHECK: %cmp1 = icmp sgt i32 %x, 0
 ; CHECK-ENABLED: br i1 %cmp1, label %[[IF_LICM:.*]], label %[[THEN_LICM:.*]]

llvm/trunk/test/Transforms/LoopVectorize/invariant-store-vectorization.ll

 }
 
 ; 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
+; Since the condition and the phi is loop invariant, they are LICM'ed before
 ; vectorization.
 ; CHECK-LABEL: inv_val_store_to_inv_address_conditional_inv
 ; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[B1:%.*]] = bitcast i32* [[B:%.*]] to i8*
+; CHECK-NEXT:    [[A4:%.*]] = bitcast i32* [[A:%.*]] to i8*
 ; CHECK-NEXT:    [[NTRUNC:%.*]] = trunc i64 [[N:%.*]] to i32
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i32 [[NTRUNC]], [[K:%.*]]
+; CHECK-NEXT:    br i1 [[CMP]], label %[[COND_STORE_LICM:.*]], label %[[COND_STORE_K_LICM:.*]]
+; CHECK:       [[COND_STORE_LICM]]:
+; CHECK-NEXT:    br label %[[LATCH_LICM:.*]]
+; CHECK:       [[COND_STORE_K_LICM]]:
+; CHECK-NEXT:    br label %[[LATCH_LICM]]
+; CHECK:       [[LATCH_LICM]]:
+; CHECK-NEXT:    [[STOREVAL:%.*]] = phi i32 [ [[NTRUNC]], %[[COND_STORE_LICM]] ], [ [[K]], %[[COND_STORE_K_LICM]] ]
 ; CHECK-NEXT:    [[TMP0:%.*]] = icmp sgt i64 [[N]], 1
 ; CHECK-NEXT:    [[SMAX:%.*]] = select i1 [[TMP0]], i64 [[N]], i64 1
 ; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[SMAX]], 4
 ; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_MEMCHECK:%.*]]
 ; CHECK:       vector.memcheck:
-; CHECK-NEXT:    [[A4:%.*]] = bitcast i32* [[A:%.*]] to i8*
-; CHECK-NEXT:    [[B1:%.*]] = bitcast i32* [[B:%.*]] to i8*
 ; CHECK-NEXT:    [[TMP1:%.*]] = icmp sgt i64 [[N]], 1
 ; CHECK-NEXT:    [[SMAX2:%.*]] = select i1 [[TMP1]], i64 [[N]], i64 1
 ; CHECK-NEXT:    [[SCEVGEP:%.*]] = getelementptr i32, i32* [[B]], i64 [[SMAX2]]
 ; CHECK-NEXT:    [[UGLYGEP:%.*]] = getelementptr i8, i8* [[A4]], i64 1
 ; CHECK-NEXT:    [[BOUND0:%.*]] = icmp ugt i8* [[UGLYGEP]], [[B1]]
 ; 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 [[SMAX]], 9223372036854775804
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT5:%.*]] = insertelement <4 x i32> undef, i32 [[NTRUNC]], i32 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT6:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT5]], <4 x i32> undef, <4 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP2:%.*]] = insertelement <4 x i1> undef, i1 [[CMP]], i32 3
-; CHECK-NEXT:    [[TMP3:%.*]] = insertelement <4 x i32> undef, i32 [[K]], i32 3
-; CHECK-NEXT:    [[PREDPHI:%.*]] = select <4 x i1> [[TMP2]], <4 x i32> [[BROADCAST_SPLAT6]], <4 x i32> [[TMP3]]
-; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <4 x i32> [[PREDPHI]], i32 3
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[INDEX]]
 ; CHECK-NEXT:    [[TMP7:%.*]] = bitcast i32* [[TMP6]] to <4 x i32>*
 ; CHECK-NEXT:    store <4 x i32> [[BROADCAST_SPLAT6]], <4 x i32>* [[TMP7]], align 4
-; CHECK-NEXT:    store i32 [[TMP5]], i32* [[A]], align 4
+; CHECK-NEXT:    store i32 [[STOREVAL]], i32* [[A]], align 4
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 4
 ; CHECK-NEXT:    [[TMP8:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
 ; CHECK-NEXT:    br i1 [[TMP8]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[SMAX]], [[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:    [[TMP1:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[I]]
 ; CHECK-NEXT:    store i32 [[NTRUNC]], i32* [[TMP1]], 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:%.*]]
 ; CHECK:       for.end.loopexit:
 ; CHECK-NEXT:    br label [[FOR_END]]
 ; CHECK:       for.end:
 ; CHECK-NEXT:    ret void