x86-64-double-shifts-var.ll
1.9 KB
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
; RUN: llc < %s -mtriple=x86_64-- -mcpu=k8 | FileCheck %s
; RUN: llc < %s -mtriple=x86_64-- -mcpu=opteron | FileCheck %s
; RUN: llc < %s -mtriple=x86_64-- -mcpu=athlon64 | FileCheck %s
; RUN: llc < %s -mtriple=x86_64-- -mcpu=athlon-fx | FileCheck %s
; RUN: llc < %s -mtriple=x86_64-- -mcpu=k8-sse3 | FileCheck %s
; RUN: llc < %s -mtriple=x86_64-- -mcpu=opteron-sse3 | FileCheck %s
; RUN: llc < %s -mtriple=x86_64-- -mcpu=athlon64-sse3 | FileCheck %s
; RUN: llc < %s -mtriple=x86_64-- -mcpu=amdfam10 | FileCheck %s
; RUN: llc < %s -mtriple=x86_64-- -mcpu=btver1 | FileCheck %s
; RUN: llc < %s -mtriple=x86_64-- -mcpu=btver2 | FileCheck %s
; RUN: llc < %s -mtriple=x86_64-- -mcpu=bdver1 | FileCheck %s
; RUN: llc < %s -mtriple=x86_64-- -mcpu=bdver2 | FileCheck %s
; RUN: llc < %s -mtriple=x86_64-- -mcpu=bdver3 | FileCheck %s
; RUN: llc < %s -mtriple=x86_64-- -mcpu=bdver4 | FileCheck %s
; RUN: llc < %s -mtriple=x86_64-- -mcpu=znver1 | FileCheck %s
; RUN: llc < %s -mtriple=x86_64-- -mcpu=znver2 | FileCheck %s
; Verify that for the X86_64 processors that are known to have poor latency
; double precision shift instructions we do not generate 'shld' or 'shrd'
; instructions.
;uint64_t lshift(uint64_t a, uint64_t b, int c)
;{
; return (a << c) | (b >> (64-c));
;}
define i64 @lshift(i64 %a, i64 %b, i32 %c) nounwind readnone {
entry:
; CHECK-NOT: shld
%sh_prom = zext i32 %c to i64
%shl = shl i64 %a, %sh_prom
%sub = sub nsw i32 64, %c
%sh_prom1 = zext i32 %sub to i64
%shr = lshr i64 %b, %sh_prom1
%or = or i64 %shr, %shl
ret i64 %or
}
;uint64_t rshift(uint64_t a, uint64_t b, int c)
;{
; return (a >> c) | (b << (64-c));
;}
define i64 @rshift(i64 %a, i64 %b, i32 %c) nounwind readnone {
entry:
; CHECK-NOT: shrd
%sh_prom = zext i32 %c to i64
%shr = lshr i64 %a, %sh_prom
%sub = sub nsw i32 64, %c
%sh_prom1 = zext i32 %sub to i64
%shl = shl i64 %b, %sh_prom1
%or = or i64 %shl, %shr
ret i64 %or
}