diff options
| author | Chris Lattner <sabre@nondot.org> | 2011-01-04 07:46:33 +0000 |
|---|---|---|
| committer | Chris Lattner <sabre@nondot.org> | 2011-01-04 07:46:33 +0000 |
| commit | e41d3c015ce5cafde305d9a6d9baaae1c41bf46a (patch) | |
| tree | 72c2cb4742fdf2d7ee5d0fb96df8911bcba0e7a0 /test/Transforms | |
| parent | b7e9ef0ed1e246bd64d97a768555c8334c0d86e9 (diff) | |
| download | external_llvm-e41d3c015ce5cafde305d9a6d9baaae1c41bf46a.zip external_llvm-e41d3c015ce5cafde305d9a6d9baaae1c41bf46a.tar.gz external_llvm-e41d3c015ce5cafde305d9a6d9baaae1c41bf46a.tar.bz2 | |
Teach loop-idiom to turn a loop containing a memset into a larger memset
when safe.
The testcase is basically this nested loop:
void foo(char *X) {
for (int i = 0; i != 100; ++i)
for (int j = 0; j != 100; ++j)
X[j+i*100] = 0;
}
which gets turned into a single memset now. clang -O3 doesn't optimize
this yet though due to a phase ordering issue I haven't analyzed yet.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@122806 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/Transforms')
| -rw-r--r-- | test/Transforms/LoopIdiom/basic.ll | 33 |
1 files changed, 33 insertions, 0 deletions
diff --git a/test/Transforms/LoopIdiom/basic.ll b/test/Transforms/LoopIdiom/basic.ll index f3b55d7..a94aaf1 100644 --- a/test/Transforms/LoopIdiom/basic.ll +++ b/test/Transforms/LoopIdiom/basic.ll @@ -240,3 +240,36 @@ for.end: ; preds = %for.body, %entry ; CHECK: ret void } +; Two dimensional nested loop should be promoted to one big memset. +define void @test10(i8* %X) nounwind ssp { +entry: + br label %bb.nph + +bb.nph: ; preds = %entry, %for.inc10 + %i.04 = phi i32 [ 0, %entry ], [ %inc12, %for.inc10 ] + br label %for.body5 + +for.body5: ; preds = %for.body5, %bb.nph + %j.02 = phi i32 [ 0, %bb.nph ], [ %inc, %for.body5 ] + %mul = mul nsw i32 %i.04, 100 + %add = add nsw i32 %j.02, %mul + %idxprom = sext i32 %add to i64 + %arrayidx = getelementptr inbounds i8* %X, i64 %idxprom + store i8 0, i8* %arrayidx, align 1 + %inc = add nsw i32 %j.02, 1 + %cmp4 = icmp eq i32 %inc, 100 + br i1 %cmp4, label %for.inc10, label %for.body5 + +for.inc10: ; preds = %for.body5 + %inc12 = add nsw i32 %i.04, 1 + %cmp = icmp eq i32 %inc12, 100 + br i1 %cmp, label %for.end13, label %bb.nph + +for.end13: ; preds = %for.inc10 + ret void +; CHECK: @test10 +; CHECK: entry: +; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* %X, i8 0, i64 10000, i32 1, i1 false) +; CHECK-NOT: store +; CHECK: ret void +} |