diff options
| author | Michael Kuperstein <mkuper@google.com> | 2016-06-01 17:16:46 +0000 |
|---|---|---|
| committer | Michael Kuperstein <mkuper@google.com> | 2016-06-01 17:16:46 +0000 |
| commit | 3a3c64d23e3d7be3baa93882cc2a23098a032849 (patch) | |
| tree | 9ab0686375b9e8a35d94ba9910aecbbc9bc2749a /llvm/test/Transforms/LoopVectorize/cast-induction.ll | |
| parent | 2c3933f4029ee94ea9070d047293ac2fa2b1f6f0 (diff) | |
| download | bcm5719-llvm-3a3c64d23e3d7be3baa93882cc2a23098a032849.tar.gz bcm5719-llvm-3a3c64d23e3d7be3baa93882cc2a23098a032849.zip | |
[LV] For some IVs, use vector phis instead of widening in the loop body
Previously, whenever we needed a vector IV, we would create it on the fly,
by splatting the scalar IV and adding a step vector. Instead, we can create a
real vector IV. This tends to save a couple of instructions per iteration.
This only changes the behavior for the most basic case - integer primary
IVs with a constant step.
Differential Revision: http://reviews.llvm.org/D20315
llvm-svn: 271410
Diffstat (limited to 'llvm/test/Transforms/LoopVectorize/cast-induction.ll')
| -rw-r--r-- | llvm/test/Transforms/LoopVectorize/cast-induction.ll | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/llvm/test/Transforms/LoopVectorize/cast-induction.ll b/llvm/test/Transforms/LoopVectorize/cast-induction.ll index fae89976a7b..54f68b7bd07 100644 --- a/llvm/test/Transforms/LoopVectorize/cast-induction.ll +++ b/llvm/test/Transforms/LoopVectorize/cast-induction.ll @@ -8,7 +8,7 @@ target triple = "x86_64-apple-macosx10.8.0" @a = common global [2048 x i32] zeroinitializer, align 16 ;CHECK-LABEL: @example12( -;CHECK: trunc i64 +;CHECK: %vec.ind1 = phi <4 x i32> ;CHECK: store <4 x i32> ;CHECK: ret void define void @example12() nounwind uwtable ssp { |
