diff options
| author | Chris Lattner <sabre@nondot.org> | 2008-11-27 05:07:53 +0000 |
|---|---|---|
| committer | Chris Lattner <sabre@nondot.org> | 2008-11-27 05:07:53 +0000 |
| commit | 69e067fdd86d34cb81ccdffb82415b4f89144218 (patch) | |
| tree | d46bd6e3e971ab351b6c1d2cd5fa268d3da580bd /test/Transforms/JumpThreading | |
| parent | dc52cf48dc8f790de2634dcc5b4f6fe203f4c765 (diff) | |
| download | external_llvm-69e067fdd86d34cb81ccdffb82415b4f89144218.zip external_llvm-69e067fdd86d34cb81ccdffb82415b4f89144218.tar.gz external_llvm-69e067fdd86d34cb81ccdffb82415b4f89144218.tar.bz2 | |
Make jump threading substantially more powerful, in the following ways:
1. Make it fold blocks separated by an unconditional branch. This enables
jump threading to see a broader scope.
2. Make jump threading able to eliminate locally redundant loads when they
feed the branch condition of a block. This frequently occurs due to
reg2mem running.
3. Make jump threading able to eliminate *partially redundant* loads when
they feed the branch condition of a block. This is common in code with
lots of loads and stores like C++ code and 255.vortex.
This implements thread-loads.ll and rdar://6402033.
Per the fixme's, several pieces of this should be moved into Transforms/Utils.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@60148 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/Transforms/JumpThreading')
| -rw-r--r-- | test/Transforms/JumpThreading/thread-loads.ll | 34 |
1 files changed, 34 insertions, 0 deletions
diff --git a/test/Transforms/JumpThreading/thread-loads.ll b/test/Transforms/JumpThreading/thread-loads.ll new file mode 100644 index 0000000..5c0b256 --- /dev/null +++ b/test/Transforms/JumpThreading/thread-loads.ll @@ -0,0 +1,34 @@ +; RUN: llvm-as < %s | opt -jump-threading -mem2reg -simplifycfg | llvm-dis | grep {ret i32 1} +; rdar://6402033 + +; Test that we can thread through the block with the partially redundant load (%2). +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" + +define i32 @foo(i32* %P) nounwind { +entry: + %0 = tail call i32 (...)* @f1() nounwind ; <i32> [#uses=1] + %1 = icmp eq i32 %0, 0 ; <i1> [#uses=1] + br i1 %1, label %bb1, label %bb + +bb: ; preds = %entry + store i32 42, i32* %P, align 4 + br label %bb1 + +bb1: ; preds = %entry, %bb + %res.0 = phi i32 [ 1, %bb ], [ 0, %entry ] ; <i32> [#uses=2] + %2 = load i32* %P, align 4 ; <i32> [#uses=1] + %3 = icmp sgt i32 %2, 36 ; <i1> [#uses=1] + br i1 %3, label %bb3, label %bb2 + +bb2: ; preds = %bb1 + %4 = tail call i32 (...)* @f2() nounwind ; <i32> [#uses=0] + ret i32 %res.0 + +bb3: ; preds = %bb1 + ret i32 %res.0 +} + +declare i32 @f1(...) + +declare i32 @f2(...) |