[llvm] r196294 - opt: Mirror vectorization presets of clang

[Arnold Schwaighofer]

Author: arnolds
Date: Tue Dec  3 10:33:06 2013
New Revision: 196294

URL: http://llvm.org/viewvc/llvm-project?rev=196294&view=rev
Log:
opt: Mirror vectorization presets of clang

clang enables vectorization at optimization levels > 1 and size level < 2. opt
should behave similarily.

Loop vectorization and SLP vectorization can be disabled with the flags
-disable-(loop/slp)-vectorization.

Added:
    llvm/trunk/test/Transforms/LoopVectorize/opt.ll
    llvm/trunk/test/Transforms/SLPVectorizer/X86/opt.ll
Modified:
    llvm/trunk/tools/opt/opt.cpp

Added: llvm/trunk/test/Transforms/LoopVectorize/opt.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Transforms/LoopVectorize/opt.ll?rev=196294&view=auto
==============================================================================
--- llvm/trunk/test/Transforms/LoopVectorize/opt.ll (added)
+++ llvm/trunk/test/Transforms/LoopVectorize/opt.ll Tue Dec  3 10:33:06 2013
@@ -0,0 +1,28 @@
+; RUN: opt -S -O3 -force-vector-width=2 -force-vector-unroll=1 < %s | FileCheck --check-prefix=LOOPVEC %s
+; RUN: opt -S -O3 -disable-loop-vectorization -force-vector-width=2 -force-vector-unroll=1 < %s | FileCheck --check-prefix=NOLOOPVEC %s
+
+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"
+target triple = "x86_64-apple-macosx10.8.0"
+
+; Make sure we can disable vectorization in opt.
+
+; LOOPVEC:       add <2 x i32>
+; NOLOOPVEC-NOT: add <2 x i32>
+
+define i32 @vect(i32* %a) {
+entry:
+  br label %for.body
+
+for.body:
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %red.05 = phi i32 [ 0, %entry ], [ %add, %for.body ]
+  %arrayidx = getelementptr inbounds i32* %a, i64 %indvars.iv
+  %0 = load i32* %arrayidx, align 4
+  %add = add nsw i32 %0, %red.05
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 255
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:
+  ret i32 %add
+}

Added: llvm/trunk/test/Transforms/SLPVectorizer/X86/opt.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Transforms/SLPVectorizer/X86/opt.ll?rev=196294&view=auto
==============================================================================
--- llvm/trunk/test/Transforms/SLPVectorizer/X86/opt.ll (added)
+++ llvm/trunk/test/Transforms/SLPVectorizer/X86/opt.ll Tue Dec  3 10:33:06 2013
@@ -0,0 +1,30 @@
+; RUN: opt < %s -O3 -S -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx | FileCheck %s --check-prefix=SLP
+; RUN: opt < %s -O3 -disable-slp-vectorization -S -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx | FileCheck %s --check-prefix=NOSLP
+
+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"
+target triple = "x86_64-apple-macosx10.8.0"
+
+; Make sure we can disable slp vectorization in opt.
+
+; SLP-LABEL: test1
+; SLP: store <2 x double>
+
+; NOSLP-LABEL: test1
+; NOSLP-NOT: store <2 x double>
+
+
+define void @test1(double* %a, double* %b, double* %c) {
+entry:
+  %i0 = load double* %a, align 8
+  %i1 = load double* %b, align 8
+  %mul = fmul double %i0, %i1
+  %arrayidx3 = getelementptr inbounds double* %a, i64 1
+  %i3 = load double* %arrayidx3, align 8
+  %arrayidx4 = getelementptr inbounds double* %b, i64 1
+  %i4 = load double* %arrayidx4, align 8
+  %mul5 = fmul double %i3, %i4
+  store double %mul, double* %c, align 8
+  %arrayidx5 = getelementptr inbounds double* %c, i64 1
+  store double %mul5, double* %arrayidx5, align 8
+  ret void
+}

Modified: llvm/trunk/tools/opt/opt.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/tools/opt/opt.cpp?rev=196294&r1=196293&r2=196294&view=diff
==============================================================================
--- llvm/trunk/tools/opt/opt.cpp (original)
+++ llvm/trunk/tools/opt/opt.cpp Tue Dec  3 10:33:06 2013
@@ -139,6 +139,16 @@ static cl::opt<bool>
 DisableLoopUnrolling("disable-loop-unrolling",
                      cl::desc("Disable loop unrolling in all relevant passes"),
                      cl::init(false));
+static cl::opt<bool>
+DisableLoopVectorization("disable-loop-vectorization",
+                     cl::desc("Disable the loop vectorization pass"),
+                     cl::init(false));
+
+static cl::opt<bool>
+DisableSLPVectorization("disable-slp-vectorization",
+                        cl::desc("Disable the slp vectorization pass"),
+                        cl::init(false));
+
 
 static cl::opt<bool>
 DisableSimplifyLibCalls("disable-simplify-libcalls",
@@ -461,8 +471,10 @@ static void AddOptimizationPasses(PassMa
   Builder.DisableUnrollLoops = (DisableLoopUnrolling.getNumOccurrences() > 0) ?
                                DisableLoopUnrolling : OptLevel == 0;
 
-  Builder.LoopVectorize = OptLevel > 1 && SizeLevel < 2;
-  Builder.SLPVectorize = true;
+  Builder.LoopVectorize =
+      DisableLoopVectorization ? false : OptLevel > 1 && SizeLevel < 2;
+  Builder.SLPVectorize =
+      DisableSLPVectorization ? false : OptLevel > 1 && SizeLevel < 2;
 
   Builder.populateFunctionPassManager(FPM);
   Builder.populateModulePassManager(MPM);