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
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
|
; RUN: opt < %s -cost-model -analyze -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx | FileCheck %s
; RUN: opt < %s -cost-model -analyze -mtriple=x86_64-apple-macosx10.8.0 -mcpu=core2 | FileCheck %s --check-prefix=SSE3
; RUN: opt < %s -cost-model -analyze -mtriple=x86_64-apple-macosx10.8.0 -mcpu=core-avx2 | FileCheck %s --check-prefix=AVX2
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"
define i32 @add(i32 %arg) {
;CHECK: cost of 1 {{.*}} add
%A = add <4 x i32> undef, undef
;CHECK: cost of 4 {{.*}} add
%B = add <8 x i32> undef, undef
;CHECK: cost of 1 {{.*}} add
%C = add <2 x i64> undef, undef
;CHECK: cost of 4 {{.*}} add
%D = add <4 x i64> undef, undef
;CHECK: cost of 8 {{.*}} add
%E = add <8 x i64> undef, undef
;CHECK: cost of 0 {{.*}} ret
ret i32 undef
}
define i32 @xor(i32 %arg) {
;CHECK: cost of 1 {{.*}} xor
%A = xor <4 x i32> undef, undef
;CHECK: cost of 1 {{.*}} xor
%B = xor <8 x i32> undef, undef
;CHECK: cost of 1 {{.*}} xor
%C = xor <2 x i64> undef, undef
;CHECK: cost of 1 {{.*}} xor
%D = xor <4 x i64> undef, undef
;CHECK: cost of 0 {{.*}} ret
ret i32 undef
}
; CHECK: mul
define void @mul() {
; A <2 x i32> gets expanded to a <2 x i64> vector.
; A <2 x i64> vector multiply is implemented using
; 3 PMULUDQ and 2 PADDS and 4 shifts.
;CHECK: cost of 9 {{.*}} mul
%A0 = mul <2 x i32> undef, undef
;CHECK: cost of 9 {{.*}} mul
%A1 = mul <2 x i64> undef, undef
;CHECK: cost of 18 {{.*}} mul
%A2 = mul <4 x i64> undef, undef
ret void
}
; SSE3: sse3mull
define void @sse3mull() {
; SSE3: cost of 6 {{.*}} mul
%A0 = mul <4 x i32> undef, undef
ret void
; SSE3: avx2mull
}
; AVX2: avx2mull
define void @avx2mull() {
; AVX2: cost of 9 {{.*}} mul
%A0 = mul <4 x i64> undef, undef
ret void
; AVX2: fmul
}
; CHECK: fmul
define i32 @fmul(i32 %arg) {
;CHECK: cost of 1 {{.*}} fmul
%A = fmul <4 x float> undef, undef
;CHECK: cost of 1 {{.*}} fmul
%B = fmul <8 x float> undef, undef
ret i32 undef
}
|
