diff options
| author | Nadav Rotem <nrotem@apple.com> | 2013-01-23 01:35:00 +0000 |
|---|---|---|
| committer | Nadav Rotem <nrotem@apple.com> | 2013-01-23 01:35:00 +0000 |
| commit | f148c66ce4c22130ff1ae242582e024ea18492bb (patch) | |
| tree | eddde9b579b2159314db31c954a8a931ecce84e5 /test/Transforms/LoopVectorize/struct_access.ll | |
| parent | 8246df61f6de716acf1f8c64fac3c19970a2c174 (diff) | |
Add support for reverse pointer induction variables. These are loops that contain pointers that count backwards.
For example, this is the hot loop in BZIP:
do {
m = *--p;
*p = ( ... );
} while (--n);
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@173219 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/Transforms/LoopVectorize/struct_access.ll')
| -rw-r--r-- | test/Transforms/LoopVectorize/struct_access.ll | 50 |
1 files changed, 50 insertions, 0 deletions
diff --git a/test/Transforms/LoopVectorize/struct_access.ll b/test/Transforms/LoopVectorize/struct_access.ll new file mode 100644 index 0000000000..de65d0d148 --- /dev/null +++ b/test/Transforms/LoopVectorize/struct_access.ll @@ -0,0 +1,50 @@ +; RUN: opt < %s -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -instcombine -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-S128" +target triple = "x86_64-apple-macosx10.9.0" + +%struct.coordinate = type { i32, i32 } + +; Make sure that we don't generate a wide load when accessing the struct. +; struct coordinate { +; int x; +; int y; +; }; +; +; +; int foo(struct coordinate *A, int n) { +; +; int sum = 0; +; for (int i = 0; i < n; ++i) +; sum += A[i].x; +; +; return sum; +; } + +;CHECK: @foo +;CHECK-NOT: load <4 x i32> +;CHECK: ret +define i32 @foo(%struct.coordinate* nocapture %A, i32 %n) nounwind uwtable readonly ssp { +entry: + %cmp4 = icmp sgt i32 %n, 0 + br i1 %cmp4, label %for.body, label %for.end + +for.body: ; preds = %entry, %for.body + %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ] + %sum.05 = phi i32 [ %add, %for.body ], [ 0, %entry ] + %x = getelementptr inbounds %struct.coordinate* %A, i64 %indvars.iv, i32 0 + %0 = load i32* %x, align 4, !tbaa !0 + %add = add nsw i32 %0, %sum.05 + %indvars.iv.next = add i64 %indvars.iv, 1 + %lftr.wideiv = trunc i64 %indvars.iv.next to i32 + %exitcond = icmp eq i32 %lftr.wideiv, %n + br i1 %exitcond, label %for.end, label %for.body + +for.end: ; preds = %for.body, %entry + %sum.0.lcssa = phi i32 [ 0, %entry ], [ %add, %for.body ] + ret i32 %sum.0.lcssa +} + +!0 = metadata !{metadata !"int", metadata !1} +!1 = metadata !{metadata !"omnipotent char", metadata !2} +!2 = metadata !{metadata !"Simple C/C++ TBAA"} |