[opaque pointer type] Add textual IR support for explicit type parameter to getelemen...

[oota-llvm.git] / test / Transforms / LoopVectorize / flags.ll

diff --git a/test/Transforms/LoopVectorize/flags.ll b/test/Transforms/LoopVectorize/flags.ll
index a4ebb4284881221560e8458593c5dc73dcb6b4eb..a4e392f01a488ee20ade099c52545f78fa24081d 100644 (file)
--- a/test/Transforms/LoopVectorize/flags.ll
+++ b/test/Transforms/LoopVectorize/flags.ll
@@ -1,4 +1,4 @@
-; RUN: opt < %s  -loop-vectorize -force-vector-unroll=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s
+; RUN: opt < %s  -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -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-macosx10.8.0"
@@ -14,7 +14,7 @@ define i32 @flags1(i32 %n, i32* nocapture %A) nounwind uwtable ssp {
 
 .lr.ph:                                           ; preds = %0, %.lr.ph
   %indvars.iv = phi i64 [ %indvars.iv.next, %.lr.ph ], [ 9, %0 ]
-  %2 = getelementptr inbounds i32* %A, i64 %indvars.iv
+  %2 = getelementptr inbounds i32, i32* %A, i64 %indvars.iv
   %3 = load i32* %2, align 4
   %4 = mul nsw i32 %3, 3
   store i32 %4, i32* %2, align 4
@@ -39,7 +39,7 @@ define i32 @flags2(i32 %n, i32* nocapture %A) nounwind uwtable ssp {
 
 .lr.ph:                                           ; preds = %0, %.lr.ph
   %indvars.iv = phi i64 [ %indvars.iv.next, %.lr.ph ], [ 9, %0 ]
-  %2 = getelementptr inbounds i32* %A, i64 %indvars.iv
+  %2 = getelementptr inbounds i32, i32* %A, i64 %indvars.iv
   %3 = load i32* %2, align 4
   %4 = mul i32 %3, 3
   store i32 %4, i32* %2, align 4
@@ -51,3 +51,29 @@ define i32 @flags2(i32 %n, i32* nocapture %A) nounwind uwtable ssp {
 ._crit_edge:                                      ; preds = %.lr.ph, %0
   ret i32 undef
 }
+
+; Make sure we copy fast math flags and use them for the final reduction.
+; CHECK-LABEL: fast_math
+; CHECK: load <4 x float>
+; CHECK: fadd fast <4 x float>
+; CHECK: br
+; CHECK: fadd fast <4 x float>
+; CHECK: fadd fast <4 x float>
+define float @fast_math(float* noalias %s) {
+entry:
+  br label %for.body
+
+for.body:
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %q.04 = phi float [ 0.000000e+00, %entry ], [ %add, %for.body ]
+  %arrayidx = getelementptr inbounds float, float* %s, i64 %indvars.iv
+  %0 = load float* %arrayidx, align 4
+  %add = fadd fast float %q.04, %0
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 256
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:
+  %add.lcssa = phi float [ %add, %for.body ]
+  ret float %add.lcssa
+}