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
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefixes=CHECK,SSE,SSE2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.1 | FileCheck %s --check-prefixes=CHECK,SSE,SSE41
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.2 | FileCheck %s --check-prefixes=CHECK,SSE,SSE42
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefixes=CHECK,AVX,AVX1
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefixes=CHECK,AVX,AVX2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f | FileCheck %s --check-prefixes=CHECK,AVX,AVX512,AVX512F
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw | FileCheck %s --check-prefixes=CHECK,AVX,AVX512,AVX512BW
declare i32 @llvm.uadd.sat.i32 (i32, i32)
declare i64 @llvm.uadd.sat.i64 (i64, i64)
declare <8 x i16> @llvm.uadd.sat.v8i16(<8 x i16>, <8 x i16>)
; fold (uadd_sat c, x) -> (add_ssat x, c)
define i32 @combine_constant_i32(i32 %a0) {
; CHECK-LABEL: combine_constant_i32:
; CHECK: # %bb.0:
; CHECK-NEXT: addl $1, %edi
; CHECK-NEXT: movl $-1, %eax
; CHECK-NEXT: cmovael %edi, %eax
; CHECK-NEXT: retq
%1 = call i32 @llvm.uadd.sat.i32(i32 1, i32 %a0);
ret i32 %1
}
define <8 x i16> @combine_constant_v8i16(<8 x i16> %a0) {
; SSE-LABEL: combine_constant_v8i16:
; SSE: # %bb.0:
; SSE-NEXT: paddusw {{.*}}(%rip), %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: combine_constant_v8i16:
; AVX: # %bb.0:
; AVX-NEXT: vpaddusw {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT: retq
%1 = call <8 x i16> @llvm.uadd.sat.v8i16(<8 x i16> <i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1>, <8 x i16> %a0);
ret <8 x i16> %1
}
; fold (uadd_sat c, 0) -> x
define i32 @combine_zero_i32(i32 %a0) {
; CHECK-LABEL: combine_zero_i32:
; CHECK: # %bb.0:
; CHECK-NEXT: movl %edi, %eax
; CHECK-NEXT: retq
%1 = call i32 @llvm.uadd.sat.i32(i32 %a0, i32 0);
ret i32 %1
}
define <8 x i16> @combine_zero_v8i16(<8 x i16> %a0) {
; CHECK-LABEL: combine_zero_v8i16:
; CHECK: # %bb.0:
; CHECK-NEXT: retq
%1 = call <8 x i16> @llvm.uadd.sat.v8i16(<8 x i16> %a0, <8 x i16> zeroinitializer);
ret <8 x i16> %1
}
; fold (uadd_sat x, y) -> (add x, y) iff no overflow
define i32 @combine_no_overflow_i32(i32 %a0, i32 %a1) {
; CHECK-LABEL: combine_no_overflow_i32:
; CHECK: # %bb.0:
; CHECK-NEXT: shrl $16, %edi
; CHECK-NEXT: shrl $16, %esi
; CHECK-NEXT: addl %edi, %esi
; CHECK-NEXT: movl $-1, %eax
; CHECK-NEXT: cmovael %esi, %eax
; CHECK-NEXT: retq
%1 = lshr i32 %a0, 16
%2 = lshr i32 %a1, 16
%3 = call i32 @llvm.uadd.sat.i32(i32 %1, i32 %2);
ret i32 %3
}
define <8 x i16> @combine_no_overflow_v8i16(<8 x i16> %a0, <8 x i16> %a1) {
; SSE-LABEL: combine_no_overflow_v8i16:
; SSE: # %bb.0:
; SSE-NEXT: psrlw $10, %xmm0
; SSE-NEXT: psrlw $10, %xmm1
; SSE-NEXT: paddusw %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: combine_no_overflow_v8i16:
; AVX: # %bb.0:
; AVX-NEXT: vpsrlw $10, %xmm0, %xmm0
; AVX-NEXT: vpsrlw $10, %xmm1, %xmm1
; AVX-NEXT: vpaddusw %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
%1 = lshr <8 x i16> %a0, <i16 10, i16 10, i16 10, i16 10, i16 10, i16 10, i16 10, i16 10>
%2 = lshr <8 x i16> %a1, <i16 10, i16 10, i16 10, i16 10, i16 10, i16 10, i16 10, i16 10>
%3 = call <8 x i16> @llvm.uadd.sat.v8i16(<8 x i16> %1, <8 x i16> %2);
ret <8 x i16> %3
}
|
