diff options
| author | Chris Lattner <sabre@nondot.org> | 2008-12-17 05:28:49 +0000 |
|---|---|---|
| committer | Chris Lattner <sabre@nondot.org> | 2008-12-17 05:28:49 +0000 |
| commit | bce4afe83968bf6504aaf0791d4c49f971d58c52 (patch) | |
| tree | 3db8976f506224bfe1233cd30606ff176f339e0f /test/Transforms/GlobalOpt | |
| parent | 89b64bd7e5032292adc308da0d867979734da8c1 (diff) | |
| download | llvm-bce4afe83968bf6504aaf0791d4c49f971d58c52.tar.gz llvm-bce4afe83968bf6504aaf0791d4c49f971d58c52.tar.bz2 llvm-bce4afe83968bf6504aaf0791d4c49f971d58c52.tar.xz | |
Enhance heap sra to be substantially more aggressive w.r.t PHI
nodes. This allows it to do fairly general phi insertion if a
load from a pointer global wants to be SRAd but the load is used
by (recursive) phi nodes. This fixes a pessimization on ppc
introduced by Load PRE.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@61123 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/Transforms/GlobalOpt')
| -rw-r--r-- | test/Transforms/GlobalOpt/heap-sra-phi.ll | 41 |
1 files changed, 41 insertions, 0 deletions
diff --git a/test/Transforms/GlobalOpt/heap-sra-phi.ll b/test/Transforms/GlobalOpt/heap-sra-phi.ll new file mode 100644 index 0000000000..5f46a77f6b --- /dev/null +++ b/test/Transforms/GlobalOpt/heap-sra-phi.ll @@ -0,0 +1,41 @@ +; RUN: llvm-as < %s | opt -globalopt | llvm-dis | grep {tmp.f1 = phi i32. } +; RUN: llvm-as < %s | opt -globalopt | llvm-dis | grep {tmp.f0 = phi i32. } + +target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:128:128" +target triple = "i386-apple-darwin7" + %struct.foo = type { i32, i32 } +@X = internal global %struct.foo* null ; <%struct.foo**> [#uses=2] + +define void @bar(i32 %Size) nounwind noinline { +entry: + %tmp = malloc [1000000 x %struct.foo] ; <[1000000 x %struct.foo]*> [#uses=1] + %.sub = getelementptr [1000000 x %struct.foo]* %tmp, i32 0, i32 0 ; <%struct.foo*> [#uses=1] + store %struct.foo* %.sub, %struct.foo** @X, align 4 + ret void +} + +define i32 @baz() nounwind readonly noinline { +bb1.thread: + %tmpLD1 = load %struct.foo** @X, align 4 ; <%struct.foo*> [#uses=1] + br label %bb1 + +bb1: ; preds = %bb1, %bb1.thread + %tmp = phi %struct.foo* [%tmpLD1, %bb1.thread ], [ %tmpLD2, %bb1 ] ; <i32> [#uses=2] + %i.0.reg2mem.0 = phi i32 [ 0, %bb1.thread ], [ %indvar.next, %bb1 ] ; <i32> [#uses=2] + %sum.0.reg2mem.0 = phi i32 [ 0, %bb1.thread ], [ %tmp3, %bb1 ] ; <i32> [#uses=1] + %tmp1 = getelementptr %struct.foo* %tmp, i32 %i.0.reg2mem.0, i32 0 ; <i32*> [#uses=1] + %tmp2 = load i32* %tmp1, align 4 ; <i32> [#uses=1] + %tmp6 = add i32 %tmp2, %sum.0.reg2mem.0 ; <i32> [#uses=2] + %tmp4 = getelementptr %struct.foo* %tmp, i32 %i.0.reg2mem.0, i32 1 ; <i32*> [#uses=1] + %tmp5 = load i32 * %tmp4 + %tmp3 = add i32 %tmp5, %tmp6 + %indvar.next = add i32 %i.0.reg2mem.0, 1 ; <i32> [#uses=2] + + %tmpLD2 = load %struct.foo** @X, align 4 ; <%struct.foo*> [#uses=1] + + %exitcond = icmp eq i32 %indvar.next, 1200 ; <i1> [#uses=1] + br i1 %exitcond, label %bb2, label %bb1 + +bb2: ; preds = %bb1 + ret i32 %tmp3 +} |