[LV] Enable vectorization of loops with conditional stores by default

[mssimpso]

Summary

This patch sets the default value of the "-enable-cond-stores-vec" command line option to "true".

[mkuper]

LGTM

llvm/trunk/lib/Transforms/Vectorize/LoopVectorize.cpp

static cl::opt<unsigned> NumberOfStoresToPredicate(
     "vectorize-num-stores-pred", cl::init(1), cl::Hidden,
     cl::desc("Max number of stores to be predicated behind an if."));
 
 static cl::opt<bool> EnableIndVarRegisterHeur(
     "enable-ind-var-reg-heur", cl::init(true), cl::Hidden,
     cl::desc("Count the induction variable only once when interleaving"));
 
 static cl::opt<bool> EnableCondStoresVectorization(
-    "enable-cond-stores-vec", cl::init(false), cl::Hidden,
+    "enable-cond-stores-vec", cl::init(true), cl::Hidden,
     cl::desc("Enable if predication of stores during vectorization."));
 
 static cl::opt<unsigned> MaxNestedScalarReductionIC(
     "max-nested-scalar-reduction-interleave", cl::init(2), cl::Hidden,
     cl::desc("The maximum interleave count to use when interleaving a scalar "
              "reduction in a nested loop."));
 
 static cl::opt<unsigned> PragmaVectorizeMemoryCheckThreshold(

llvm/trunk/test/Transforms/LoopVectorize/AArch64/predication_costs.ll

 ; REQUIRES: asserts
-; RUN: opt < %s -force-vector-width=2 -enable-cond-stores-vec -loop-vectorize -debug-only=loop-vectorize -disable-output 2>&1 | FileCheck %s
+; RUN: opt < %s -force-vector-width=2 -loop-vectorize -debug-only=loop-vectorize -disable-output 2>&1 | FileCheck %s
 
 target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
 target triple = "aarch64--linux-gnu"
 
 ; Check predication-related cost calculations, including scalarization overhead
 ; and block probability scaling. Note that the functionality being tested is
 ; not specific to AArch64. We specify a target to get actual values for the
 ; instruction costs.

llvm/trunk/test/Transforms/LoopVectorize/conditional-assignment.ll

-; RUN: opt < %s -loop-vectorize -S -pass-remarks-missed='loop-vectorize' -pass-remarks-analysis='loop-vectorize' 2>&1 | FileCheck %s
-; RUN: opt < %s -passes=loop-vectorize -S -pass-remarks-missed='loop-vectorize' -pass-remarks-analysis='loop-vectorize' 2>&1 | FileCheck %s
+; RUN: opt < %s -enable-cond-stores-vec=false -loop-vectorize -S -pass-remarks-missed='loop-vectorize' -pass-remarks-analysis='loop-vectorize' 2>&1 | FileCheck %s
+; RUN: opt < %s -enable-cond-stores-vec=false -passes=loop-vectorize -S -pass-remarks-missed='loop-vectorize' -pass-remarks-analysis='loop-vectorize' 2>&1 | FileCheck %s
 
 ; CHECK: remark: source.c:2:8: loop not vectorized: store that is conditionally executed prevents vectorization
 
 target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
 
 ; Function Attrs: nounwind ssp uwtable
 define void @conditional_store(i32* noalias nocapture %indices) #0 !dbg !4 {
 entry:

llvm/trunk/test/Transforms/LoopVectorize/consecutive-ptr-uniforms.ll

 ; REQUIRES: asserts
 ; RUN: opt < %s -loop-vectorize -force-vector-width=4 -force-vector-interleave=1 -instcombine -debug-only=loop-vectorize -disable-output -print-after=instcombine 2>&1 | FileCheck %s
-; RUN: opt < %s -loop-vectorize -force-vector-width=4 -force-vector-interleave=1 -enable-interleaved-mem-accesses -enable-cond-stores-vec -instcombine -debug-only=loop-vectorize -disable-output -print-after=instcombine 2>&1 | FileCheck %s --check-prefix=INTER
+; RUN: opt < %s -loop-vectorize -force-vector-width=4 -force-vector-interleave=1 -enable-interleaved-mem-accesses -instcombine -debug-only=loop-vectorize -disable-output -print-after=instcombine 2>&1 | FileCheck %s --check-prefix=INTER
 
 target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
 
 %pair = type { i32, i32 }
 
 ; CHECK-LABEL: consecutive_ptr_forward
 ;
 ; Check that a forward consecutive pointer is recognized as uniform and remains

llvm/trunk/test/Transforms/LoopVectorize/if-pred-stores.ll

 ; RUN: opt -S -vectorize-num-stores-pred=1 -force-vector-width=1 -force-vector-interleave=2 -loop-vectorize -verify-loop-info -simplifycfg < %s | FileCheck %s --check-prefix=UNROLL
 ; RUN: opt -S -vectorize-num-stores-pred=1 -force-vector-width=1 -force-vector-interleave=2 -loop-vectorize -verify-loop-info < %s | FileCheck %s --check-prefix=UNROLL-NOSIMPLIFY
-; RUN: opt -S -vectorize-num-stores-pred=1 -force-vector-width=2 -force-vector-interleave=1 -loop-vectorize -enable-cond-stores-vec -verify-loop-info -simplifycfg < %s | FileCheck %s --check-prefix=VEC
+; RUN: opt -S -vectorize-num-stores-pred=1 -force-vector-width=2 -force-vector-interleave=1 -loop-vectorize -verify-loop-info -simplifycfg < %s | FileCheck %s --check-prefix=VEC
 
 target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
 
 ; Test predication of stores.
 define i32 @test(i32* nocapture %f) #0 {
 entry:
   br label %for.body
 

llvm/trunk/test/Transforms/LoopVectorize/interleaved-accesses-pred-stores.ll

-; RUN: opt -S -loop-vectorize -instcombine -force-vector-width=2 -force-vector-interleave=1 -enable-interleaved-mem-accesses -vectorize-num-stores-pred=1 -enable-cond-stores-vec < %s | FileCheck %s
+; RUN: opt -S -loop-vectorize -instcombine -force-vector-width=2 -force-vector-interleave=1 -enable-interleaved-mem-accesses < %s | FileCheck %s
 
 target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
 %pair = type { i64, i64 }
 
 ; Ensure that we vectorize the interleaved load group even though the loop
 ; contains a conditional store. The store group contains gaps and is not
 ; vectorized.
 ;