diff options
author | Chris Lattner <sabre@nondot.org> | 2010-09-06 01:10:22 +0000 |
---|---|---|
committer | Chris Lattner <sabre@nondot.org> | 2010-09-06 01:10:22 +0000 |
commit | 50fb46983ccae116bdbda64471f4861108766135 (patch) | |
tree | 37d2530f9bdaa937d848861d34ebd2bd584ece6a /test | |
parent | adc799112dc180b3cd099038c05101b85d217716 (diff) | |
download | llvm-50fb46983ccae116bdbda64471f4861108766135.tar.gz llvm-50fb46983ccae116bdbda64471f4861108766135.tar.bz2 llvm-50fb46983ccae116bdbda64471f4861108766135.tar.xz |
Teach loop rotate to hoist trivially invariant instructions
in the duplicated block instead of duplicating them.
Duplicating them into the end of the loop and the preheader
means that we got a phi node in the header of the loop,
which prevented LICM from hoisting them. GVN would
usually come around later and merge the duplicated
instructions so we'd get reasonable output... except that
anything dependent on the shoulda-been-hoisted value can't
be hoisted. In PR5319 (which this fixes), a memory value
didn't get promoted.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@113134 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test')
-rw-r--r-- | test/Transforms/LoopRotate/basic.ll | 35 |
1 files changed, 35 insertions, 0 deletions
diff --git a/test/Transforms/LoopRotate/basic.ll b/test/Transforms/LoopRotate/basic.ll new file mode 100644 index 0000000000..b7bcb21d56 --- /dev/null +++ b/test/Transforms/LoopRotate/basic.ll @@ -0,0 +1,35 @@ +; RUN: opt -S -loop-rotate %s | FileCheck %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" +target triple = "x86_64-apple-darwin10.0.0" + +; PR5319 - The "arrayidx" gep should be hoisted, not duplicated. We should +; end up with one phi node. +define void @test1() nounwind ssp { +; CHECK: @test1 +entry: + %array = alloca [20 x i32], align 16 + br label %for.cond + +for.cond: ; preds = %for.body, %entry + %i.0 = phi i32 [ 0, %entry ], [ %inc, %for.body ] + %cmp = icmp slt i32 %i.0, 100 + %arrayidx = getelementptr inbounds [20 x i32]* %array, i64 0, i64 0 + br i1 %cmp, label %for.body, label %for.end + +; CHECK: for.body: +; CHECK-NEXT: phi i32 [ 0 +; CHECK-NEXT: store i32 0 + +for.body: ; preds = %for.cond + store i32 0, i32* %arrayidx, align 16 + %inc = add nsw i32 %i.0, 1 + br label %for.cond + +for.end: ; preds = %for.cond + %arrayidx.lcssa = phi i32* [ %arrayidx, %for.cond ] + call void @g(i32* %arrayidx.lcssa) nounwind + ret void +} + +declare void @g(i32*) + |