1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
|
; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -mtriple=powerpc64-unknown-linux-gnu -mcpu=g5 -disable-ppc-unaligned | 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-f128:128:128-v128:128:128-n32:64"
target triple = "powerpc64-unknown-linux-gnu"
define i32 @stores(i32 %arg) {
; CHECK: cost of 1 {{.*}} store
store i8 undef, ptr undef, align 4
; CHECK: cost of 1 {{.*}} store
store i16 undef, ptr undef, align 4
; CHECK: cost of 1 {{.*}} store
store i32 undef, ptr undef, align 4
; CHECK: cost of 2 {{.*}} store
store i64 undef, ptr undef, align 4
; CHECK: cost of 4 {{.*}} store
store i128 undef, ptr undef, align 4
ret i32 undef
}
define i32 @loads(i32 %arg) {
; CHECK: cost of 1 {{.*}} load
load i8, ptr undef, align 4
; CHECK: cost of 1 {{.*}} load
load i16, ptr undef, align 4
; CHECK: cost of 1 {{.*}} load
load i32, ptr undef, align 4
; CHECK: cost of 2 {{.*}} load
load i64, ptr undef, align 4
; CHECK: cost of 4 {{.*}} load
load i128, ptr undef, align 4
; FIXME: There actually are sub-vector Altivec loads, and so we could handle
; this with a small expense, but we don't currently.
; CHECK: cost of 42 {{.*}} load
load <4 x i16>, ptr undef, align 2
; CHECK: cost of 2 {{.*}} load
load <4 x i32>, ptr undef, align 4
; CHECK: cost of 46 {{.*}} load
load <3 x float>, ptr undef, align 1
ret i32 undef
}
|
