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
|
; RUN: llc -march=r600 -mcpu=SI -verify-machineinstrs< %s | FileCheck -check-prefix=SI %s
declare i32 @llvm.r600.read.tidig.x() readnone
; SI-LABEL: @test_i64_vreg:
; SI: V_ADD_I32
; SI: V_ADDC_U32
define void @test_i64_vreg(i64 addrspace(1)* noalias %out, i64 addrspace(1)* noalias %inA, i64 addrspace(1)* noalias %inB) {
%tid = call i32 @llvm.r600.read.tidig.x() readnone
%a_ptr = getelementptr i64 addrspace(1)* %inA, i32 %tid
%b_ptr = getelementptr i64 addrspace(1)* %inB, i32 %tid
%a = load i64 addrspace(1)* %a_ptr
%b = load i64 addrspace(1)* %b_ptr
%result = add i64 %a, %b
store i64 %result, i64 addrspace(1)* %out
ret void
}
; Check that the SGPR add operand is correctly moved to a VGPR.
; SI-LABEL: @sgpr_operand:
; SI: V_ADD_I32
; SI: V_ADDC_U32
define void @sgpr_operand(i64 addrspace(1)* noalias %out, i64 addrspace(1)* noalias %in, i64 addrspace(1)* noalias %in_bar, i64 %a) {
%foo = load i64 addrspace(1)* %in, align 8
%result = add i64 %foo, %a
store i64 %result, i64 addrspace(1)* %out
ret void
}
; Swap the arguments. Check that the SGPR -> VGPR copy works with the
; SGPR as other operand.
;
; SI-LABEL: @sgpr_operand_reversed:
; SI: V_ADD_I32
; SI: V_ADDC_U32
define void @sgpr_operand_reversed(i64 addrspace(1)* noalias %out, i64 addrspace(1)* noalias %in, i64 %a) {
%foo = load i64 addrspace(1)* %in, align 8
%result = add i64 %a, %foo
store i64 %result, i64 addrspace(1)* %out
ret void
}
; SI-LABEL: @test_v2i64_sreg:
; SI: S_ADD_I32
; SI: S_ADDC_U32
; SI: S_ADD_I32
; SI: S_ADDC_U32
define void @test_v2i64_sreg(<2 x i64> addrspace(1)* noalias %out, <2 x i64> %a, <2 x i64> %b) {
%result = add <2 x i64> %a, %b
store <2 x i64> %result, <2 x i64> addrspace(1)* %out
ret void
}
; SI-LABEL: @test_v2i64_vreg:
; SI: V_ADD_I32
; SI: V_ADDC_U32
; SI: V_ADD_I32
; SI: V_ADDC_U32
define void @test_v2i64_vreg(<2 x i64> addrspace(1)* noalias %out, <2 x i64> addrspace(1)* noalias %inA, <2 x i64> addrspace(1)* noalias %inB) {
%tid = call i32 @llvm.r600.read.tidig.x() readnone
%a_ptr = getelementptr <2 x i64> addrspace(1)* %inA, i32 %tid
%b_ptr = getelementptr <2 x i64> addrspace(1)* %inB, i32 %tid
%a = load <2 x i64> addrspace(1)* %a_ptr
%b = load <2 x i64> addrspace(1)* %b_ptr
%result = add <2 x i64> %a, %b
store <2 x i64> %result, <2 x i64> addrspace(1)* %out
ret void
}
; SI-LABEL: @trunc_i64_add_to_i32
; SI: S_LOAD_DWORD [[SREG0:s[0-9]+]],
; SI: S_LOAD_DWORD [[SREG1:s[0-9]+]],
; SI: S_ADD_I32 [[SRESULT:s[0-9]+]], [[SREG1]], [[SREG0]]
; SI-NOT: ADDC
; SI: V_MOV_B32_e32 [[VRESULT:v[0-9]+]], [[SRESULT]]
; SI: BUFFER_STORE_DWORD [[VRESULT]],
define void @trunc_i64_add_to_i32(i32 addrspace(1)* %out, i64 %a, i64 %b) {
%add = add i64 %b, %a
%trunc = trunc i64 %add to i32
store i32 %trunc, i32 addrspace(1)* %out, align 8
ret void
}
|
