Check for extractelement with a variable operand for the element number.

[oota-llvm.git] / test / Transforms / GVN / pre-load.ll

diff --git a/test/Transforms/GVN/pre-load.ll b/test/Transforms/GVN/pre-load.ll
index 19ea8720d317283a9ef6f680a2134c15f0bd7949..bf4add42e80b6c0614f14baa5847791f3399c705 100644 (file)
--- a/test/Transforms/GVN/pre-load.ll
+++ b/test/Transforms/GVN/pre-load.ll
@@ -1,4 +1,4 @@
-; RUN: opt < %s -gvn -enable-load-pre -S | FileCheck %s
+; RUN: opt < %s -basicaa -gvn -enable-load-pre -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"
 
 define i32 @test1(i32* %p, i1 %C) {
@@ -239,20 +239,18 @@ return:
   ret void
 }
 
-
-;;; --- todo
-
-;; Here the loaded address isn't available in 'block2' at all.
-define i32 @testX(i32* %p, i32* %q, i32** %Hack, i1 %C) {
-; CHECK: @testX
+;; Here the loaded address isn't available in 'block2' at all, requiring a new
+;; GEP to be inserted into it.
+define i32 @test8(i32* %p, i32* %q, i32** %Hack, i1 %C) {
+; CHECK: @test8
 block1:
        br i1 %C, label %block2, label %block3
 
 block2:
  br label %block4
-; HECK: block2:
-; HECK:   load i32*
-; HECK:   br label %block4
+; CHECK: block2:
+; CHECK:   load i32*
+; CHECK:   br label %block4
 
 block3:
   %A = getelementptr i32* %p, i32 1
@@ -264,10 +262,130 @@ block4:
   %P3 = getelementptr i32* %P2, i32 1
   %PRE = load i32* %P3
   ret i32 %PRE
-; HECK: block4:
-; HECK-NEXT: phi i32 [
-; HECK-NOT: load
-; HECK: ret i32
+; CHECK: block4:
+; CHECK-NEXT: phi i32 [
+; CHECK-NOT: load
+; CHECK: ret i32
 }
 
+;void test9(int N, double* G) {
+;  long j;
+;  for (j = 1; j < N - 1; j++)
+;      G[j+1] = G[j] + G[j+1];
+;}
+
+; This requires phi translation of the adds.
+define void @test9(i32 %N, double* nocapture %G) nounwind ssp {
+entry:
+  add i32 0, 0
+  %1 = add i32 %N, -1                             
+  %2 = icmp sgt i32 %1, 1                         
+  br i1 %2, label %bb.nph, label %return
+
+bb.nph:                                           
+  %tmp = sext i32 %1 to i64                       
+  %tmp7 = add i64 %tmp, -1                        
+  br label %bb
+
+; CHECK: bb.nph:
+; CHECK:   load double*
+; CHECK:   br label %bb
 
+bb:                                               
+  %indvar = phi i64 [ 0, %bb.nph ], [ %tmp9, %bb ] 
+  %tmp8 = add i64 %indvar, 2                      
+  %scevgep = getelementptr double* %G, i64 %tmp8  
+  %tmp9 = add i64 %indvar, 1                      
+  %scevgep10 = getelementptr double* %G, i64 %tmp9 
+  %3 = load double* %scevgep10, align 8           
+  %4 = load double* %scevgep, align 8             
+  %5 = fadd double %3, %4                         
+  store double %5, double* %scevgep, align 8
+  %exitcond = icmp eq i64 %tmp9, %tmp7            
+  br i1 %exitcond, label %return, label %bb
+
+; Should only be one load in the loop.
+; CHECK: bb:
+; CHECK: load double*
+; CHECK-NOT: load double*
+; CHECK: br i1 %exitcond
+
+return:                                           
+  ret void
+}
+
+;void test10(int N, double* G) {
+;  long j;
+;  for (j = 1; j < N - 1; j++)
+;      G[j] = G[j] + G[j+1] + G[j-1];
+;}
+
+; PR5501
+define void @test10(i32 %N, double* nocapture %G) nounwind ssp {
+entry:
+  %0 = add i32 %N, -1
+  %1 = icmp sgt i32 %0, 1
+  br i1 %1, label %bb.nph, label %return
+
+bb.nph:
+  %tmp = sext i32 %0 to i64
+  %tmp8 = add i64 %tmp, -1
+  br label %bb
+; CHECK: bb.nph:
+; CHECK:   load double*
+; CHECK:   load double*
+; CHECK:   br label %bb
+
+
+bb:
+  %indvar = phi i64 [ 0, %bb.nph ], [ %tmp11, %bb ]
+  %scevgep = getelementptr double* %G, i64 %indvar
+  %tmp9 = add i64 %indvar, 2
+  %scevgep10 = getelementptr double* %G, i64 %tmp9
+  %tmp11 = add i64 %indvar, 1
+  %scevgep12 = getelementptr double* %G, i64 %tmp11
+  %2 = load double* %scevgep12, align 8
+  %3 = load double* %scevgep10, align 8
+  %4 = fadd double %2, %3
+  %5 = load double* %scevgep, align 8
+  %6 = fadd double %4, %5
+  store double %6, double* %scevgep12, align 8
+  %exitcond = icmp eq i64 %tmp11, %tmp8
+  br i1 %exitcond, label %return, label %bb
+
+; Should only be one load in the loop.
+; CHECK: bb:
+; CHECK: load double*
+; CHECK-NOT: load double*
+; CHECK: br i1 %exitcond
+
+return:
+  ret void
+}
+
+; Test critical edge splitting.
+define i32 @test11(i32* %p, i1 %C, i32 %N) {
+; CHECK: @test11
+block1:
+        br i1 %C, label %block2, label %block3
+
+block2:
+ %cond = icmp sgt i32 %N, 1
+ br i1 %cond, label %block4, label %block5
+; CHECK: load i32* %p
+; CHECK-NEXT: br label %block4
+
+block3:
+  store i32 0, i32* %p
+  br label %block4
+
+block4:
+  %PRE = load i32* %p
+  br label %block5
+
+block5:
+  %ret = phi i32 [ 0, %block2 ], [ %PRE, %block4 ]
+  ret i32 %ret
+; CHECK: block4:
+; CHECK-NEXT: phi i32
+}