diff options
| author | Hal Finkel <hfinkel@anl.gov> | 2013-08-28 18:33:10 +0000 |
|---|---|---|
| committer | Hal Finkel <hfinkel@anl.gov> | 2013-08-28 18:33:10 +0000 |
| commit | 435798e96a64738b55a01055dde1bc9a88a15191 (patch) | |
| tree | 085525155e3ac51b8f7b9ed02f0f4326c5a0c0cd /test/Transforms/LoopVectorize | |
| parent | 4f066b6db8a7a95b206725aecf99a64fd6e9415c (diff) | |
| download | llvm-435798e96a64738b55a01055dde1bc9a88a15191.tar.gz llvm-435798e96a64738b55a01055dde1bc9a88a15191.tar.bz2 llvm-435798e96a64738b55a01055dde1bc9a88a15191.tar.xz | |
Disable unrolling in the loop vectorizer when disabled in the pass manager
When unrolling is disabled in the pass manager, the loop vectorizer should also
not unroll loops. This will allow the -fno-unroll-loops option in Clang to
behave as expected (even for vectorizable loops). The loop vectorizer's
-force-vector-unroll option will (continue to) override the pass-manager
setting (including -force-vector-unroll=0 to force use of the internal
auto-selection logic).
In order to test this, I added a flag to opt (-disable-loop-unrolling) to force
disable unrolling through opt (the analog of -fno-unroll-loops in Clang). Also,
this fixes a small bug in opt where the loop vectorizer was enabled only after
the pass manager populated the queue of passes (the global_alias.ll test needed
a slight update to the RUN line as a result of this fix).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@189499 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/Transforms/LoopVectorize')
| -rw-r--r-- | test/Transforms/LoopVectorize/X86/unroll-pm.ll | 31 | ||||
| -rw-r--r-- | test/Transforms/LoopVectorize/global_alias.ll | 2 |
2 files changed, 32 insertions, 1 deletions
diff --git a/test/Transforms/LoopVectorize/X86/unroll-pm.ll b/test/Transforms/LoopVectorize/X86/unroll-pm.ll new file mode 100644 index 0000000000..5064fec286 --- /dev/null +++ b/test/Transforms/LoopVectorize/X86/unroll-pm.ll @@ -0,0 +1,31 @@ +; RUN: opt < %s -O2 -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx -force-vector-width=4 -S | FileCheck %s +; RUN: opt < %s -O2 -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx -force-vector-width=4 -disable-loop-unrolling -S | FileCheck %s -check-prefix=CHECK-NOUNRL + +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" +;CHECK-LABEL: @bar( +;CHECK: store <4 x i32> +;CHECK: store <4 x i32> +;CHECK: ret +;CHECK-NOUNRL-LABEL: @bar( +;CHECK-NOUNRL: store <4 x i32> +;CHECK-NOUNRL-NOT: store <4 x i32> +;CHECK-NOUNRL: ret +define i32 @bar(i32* nocapture %A, i32 %n) nounwind uwtable ssp { + %1 = icmp sgt i32 %n, 0 + br i1 %1, label %.lr.ph, label %._crit_edge + +.lr.ph: ; preds = %0, %.lr.ph + %indvars.iv = phi i64 [ %indvars.iv.next, %.lr.ph ], [ 0, %0 ] + %2 = getelementptr inbounds i32* %A, i64 %indvars.iv + %3 = load i32* %2, align 4 + %4 = add nsw i32 %3, 6 + store i32 %4, i32* %2, align 4 + %indvars.iv.next = add i64 %indvars.iv, 1 + %lftr.wideiv = trunc i64 %indvars.iv.next to i32 + %exitcond = icmp eq i32 %lftr.wideiv, %n + br i1 %exitcond, label %._crit_edge, label %.lr.ph + +._crit_edge: ; preds = %.lr.ph, %0 + ret i32 undef +} diff --git a/test/Transforms/LoopVectorize/global_alias.ll b/test/Transforms/LoopVectorize/global_alias.ll index ae72d3c608..4fd4c989de 100644 --- a/test/Transforms/LoopVectorize/global_alias.ll +++ b/test/Transforms/LoopVectorize/global_alias.ll @@ -1,4 +1,4 @@ -; RUN: opt < %s -O3 -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s +; RUN: opt < %s -O1 -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:64:128-a0:0:64-n32-S64" |