-; RUN: opt < %s -gvn -S | FileCheck %s
+; RUN: opt < %s -basicaa -gvn -S | FileCheck %s
; 32-bit little endian target.
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"
; CHECK: ret i8*
}
+; memset -> i16 forwarding.
+define signext i16 @memset_to_i16_local(i16* %A) nounwind ssp {
+entry:
+ %conv = bitcast i16* %A to i8*
+ tail call void @llvm.memset.i64(i8* %conv, i8 1, i64 200, i32 1)
+ %arrayidx = getelementptr inbounds i16* %A, i64 42
+ %tmp2 = load i16* %arrayidx
+ ret i16 %tmp2
+; CHECK: @memset_to_i16_local
+; CHECK-NOT: load
+; CHECK: ret i16 257
+}
+
+; memset -> float forwarding.
+define float @memset_to_float_local(float* %A, i8 %Val) nounwind ssp {
+entry:
+ %conv = bitcast float* %A to i8* ; <i8*> [#uses=1]
+ tail call void @llvm.memset.i64(i8* %conv, i8 %Val, i64 400, i32 1)
+ %arrayidx = getelementptr inbounds float* %A, i64 42 ; <float*> [#uses=1]
+ %tmp2 = load float* %arrayidx ; <float> [#uses=1]
+ ret float %tmp2
+; CHECK: @memset_to_float_local
+; CHECK-NOT: load
+; CHECK: zext
+; CHECK-NEXT: shl
+; CHECK-NEXT: or
+; CHECK-NEXT: shl
+; CHECK-NEXT: or
+; CHECK-NEXT: bitcast
+; CHECK-NEXT: ret float
+}
+
+;; non-local memset -> i16 load forwarding.
+define i16 @memset_to_i16_nonlocal0(i16* %P, i1 %cond) {
+ %P3 = bitcast i16* %P to i8*
+ br i1 %cond, label %T, label %F
+T:
+ tail call void @llvm.memset.i64(i8* %P3, i8 1, i64 400, i32 1)
+ br label %Cont
+
+F:
+ tail call void @llvm.memset.i64(i8* %P3, i8 2, i64 400, i32 1)
+ br label %Cont
+
+Cont:
+ %P2 = getelementptr i16* %P, i32 4
+ %A = load i16* %P2
+ ret i16 %A
+
+; CHECK: @memset_to_i16_nonlocal0
+; CHECK: Cont:
+; CHECK-NEXT: %A = phi i16 [ 514, %F ], [ 257, %T ]
+; CHECK-NOT: load
+; CHECK: ret i16 %A
+}
+
+@GCst = constant {i32, float, i32 } { i32 42, float 14., i32 97 }
+
+; memset -> float forwarding.
+define float @memcpy_to_float_local(float* %A) nounwind ssp {
+entry:
+ %conv = bitcast float* %A to i8* ; <i8*> [#uses=1]
+ tail call void @llvm.memcpy.i64(i8* %conv, i8* bitcast ({i32, float, i32 }* @GCst to i8*), i64 12, i32 1)
+ %arrayidx = getelementptr inbounds float* %A, i64 1 ; <float*> [#uses=1]
+ %tmp2 = load float* %arrayidx ; <float> [#uses=1]
+ ret float %tmp2
+; CHECK: @memcpy_to_float_local
+; CHECK-NOT: load
+; CHECK: ret float 1.400000e+01
+}
+
+
+declare void @llvm.memset.i64(i8* nocapture, i8, i64, i32) nounwind
+declare void @llvm.memcpy.i64(i8* nocapture, i8* nocapture, i64, i32) nounwind
+
+
+
+
;; non-local i32/float -> i8 load forwarding.
define i8 @coerce_mustalias_nonlocal0(i32* %P, i1 %cond) {
%P2 = bitcast i32* %P to float*
; CHECK: ret i8 %A
}
+
;; non-local i32/float -> i8 load forwarding. This also tests that the "P3"
;; bitcast equivalence can be properly phi translated.
define i8 @coerce_mustalias_nonlocal1(i32* %P, i1 %cond) {
declare i1 @cond2() readonly
define i32 @phi_trans2() {
+; CHECK: @phi_trans2
entry:
%P = alloca i32, i32 400
br label %F1
br label %F1
TX:
- ret i32 %x ;; SHOULD NOT BE COMPILED TO 'ret i32 42'.
+ ; This load should not be compiled to 'ret i32 42'. An overly clever
+ ; implementation of GVN would see that we're returning 17 if the loop
+ ; executes once or 42 if it executes more than that, but we'd have to do
+ ; loop restructuring to expose this, and GVN shouldn't do this sort of CFG
+ ; transformation.
+
+; CHECK: TX:
+; CHECK: ret i32 %x
+ ret i32 %x
TY:
ret i32 0
}
+define i32 @phi_trans3(i32* %p) {
+; CHECK: @phi_trans3
+block1:
+ br i1 true, label %block2, label %block3
+
+block2:
+ store i32 87, i32* %p
+ br label %block4
+
+block3:
+ %p2 = getelementptr i32* %p, i32 43
+ store i32 97, i32* %p2
+ br label %block4
+
+block4:
+ %A = phi i32 [-1, %block2], [42, %block3]
+ br i1 true, label %block5, label %exit
+
+; CHECK: block4:
+; CHECK-NEXT: %D = phi i32 [ 87, %block2 ], [ 97, %block3 ]
+; CHECK-NOT: load
+
+block5:
+ %B = add i32 %A, 1
+ br i1 true, label %block6, label %exit
+
+block6:
+ %C = getelementptr i32* %p, i32 %B
+ br i1 true, label %block7, label %exit
+
+block7:
+ %D = load i32* %C
+ ret i32 %D
+
+; CHECK: block7:
+; CHECK-NEXT: ret i32 %D
+
+exit:
+ ret i32 -1
+}
+
+define i8 @phi_trans4(i8* %p) {
+; CHECK: @phi_trans4
+entry:
+ %X3 = getelementptr i8* %p, i32 192
+ store i8 192, i8* %X3
+
+ %X = getelementptr i8* %p, i32 4
+ %Y = load i8* %X
+ br label %loop
+
+loop:
+ %i = phi i32 [4, %entry], [192, %loop]
+ %X2 = getelementptr i8* %p, i32 %i
+ %Y2 = load i8* %X2
+
+; CHECK: loop:
+; CHECK-NEXT: %Y2 = phi i8 [ %Y, %entry ], [ 0, %loop ]
+; CHECK-NOT: load i8
+
+ %cond = call i1 @cond2()
+
+ %Z = bitcast i8 *%X3 to i32*
+ store i32 0, i32* %Z
+ br i1 %cond, label %loop, label %out
+
+out:
+ %R = add i8 %Y, %Y2
+ ret i8 %R
+}
+
+define i8 @phi_trans5(i8* %p) {
+; CHECK: @phi_trans5
+entry:
+
+ %X4 = getelementptr i8* %p, i32 2
+ store i8 19, i8* %X4
+
+ %X = getelementptr i8* %p, i32 4
+ %Y = load i8* %X
+ br label %loop
+
+loop:
+ %i = phi i32 [4, %entry], [3, %cont]
+ %X2 = getelementptr i8* %p, i32 %i
+ %Y2 = load i8* %X2 ; Ensure this load is not being incorrectly replaced.
+ %cond = call i1 @cond2()
+ br i1 %cond, label %cont, label %out
+
+cont:
+ %Z = getelementptr i8* %X2, i32 -1
+ %Z2 = bitcast i8 *%Z to i32*
+ store i32 50462976, i32* %Z2 ;; (1 << 8) | (2 << 16) | (3 << 24)
+
+
+; CHECK: store i32
+; CHECK-NEXT: getelementptr i8* %p, i32 3
+; CHECK-NEXT: load i8*
+ br label %loop
+
+out:
+ %R = add i8 %Y, %Y2
+ ret i8 %R
+}
+
+
+; PR6642
+define i32 @memset_to_load() nounwind readnone {
+entry:
+ %x = alloca [256 x i32], align 4 ; <[256 x i32]*> [#uses=2]
+ %tmp = bitcast [256 x i32]* %x to i8* ; <i8*> [#uses=1]
+ call void @llvm.memset.i64(i8* %tmp, i8 0, i64 1024, i32 4)
+ %arraydecay = getelementptr inbounds [256 x i32]* %x, i32 0, i32 0 ; <i32*>
+ %tmp1 = load i32* %arraydecay ; <i32> [#uses=1]
+ ret i32 %tmp1
+; CHECK: @memset_to_load
+; CHECK: ret i32 0
+}