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
|
; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -check-prefix=R600 %s
; RUN: llc -march=amdgcn -mcpu=SI -verify-machineinstrs < %s | FileCheck -check-prefix=SI %s
; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=SI %s
; These tests check that fdiv is expanded correctly and also test that the
; scheduler is scheduling the RECIP_IEEE and MUL_IEEE instructions in separate
; instruction groups.
; FUNC-LABEL: {{^}}fdiv_f32:
; R600-DAG: RECIP_IEEE * T{{[0-9]+\.[XYZW]}}, KC0[3].Z
; R600-DAG: RECIP_IEEE * T{{[0-9]+\.[XYZW]}}, KC0[3].Y
; R600-DAG: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW]}}, KC0[3].X, PS
; R600-DAG: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW]}}, KC0[2].W, PS
; SI-DAG: v_rcp_f32
; SI-DAG: v_mul_f32
define void @fdiv_f32(float addrspace(1)* %out, float %a, float %b) {
entry:
%0 = fdiv float %a, %b
store float %0, float addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}fdiv_v2f32:
; R600-DAG: RECIP_IEEE * T{{[0-9]+\.[XYZW]}}, KC0[3].Z
; R600-DAG: RECIP_IEEE * T{{[0-9]+\.[XYZW]}}, KC0[3].Y
; R600-DAG: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW]}}, KC0[3].X, PS
; R600-DAG: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW]}}, KC0[2].W, PS
; SI-DAG: v_rcp_f32
; SI-DAG: v_mul_f32
; SI-DAG: v_rcp_f32
; SI-DAG: v_mul_f32
define void @fdiv_v2f32(<2 x float> addrspace(1)* %out, <2 x float> %a, <2 x float> %b) {
entry:
%0 = fdiv <2 x float> %a, %b
store <2 x float> %0, <2 x float> addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}fdiv_v4f32:
; R600-DAG: RECIP_IEEE * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
; R600-DAG: RECIP_IEEE * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
; R600-DAG: RECIP_IEEE * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
; R600-DAG: RECIP_IEEE * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
; R600-DAG: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}, PS
; R600-DAG: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}, PS
; R600-DAG: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}, PS
; R600-DAG: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}, PS
; SI-DAG: v_rcp_f32
; SI-DAG: v_mul_f32
; SI-DAG: v_rcp_f32
; SI-DAG: v_mul_f32
; SI-DAG: v_rcp_f32
; SI-DAG: v_mul_f32
; SI-DAG: v_rcp_f32
; SI-DAG: v_mul_f32
define void @fdiv_v4f32(<4 x float> addrspace(1)* %out, <4 x float> addrspace(1)* %in) {
%b_ptr = getelementptr <4 x float>, <4 x float> addrspace(1)* %in, i32 1
%a = load <4 x float>, <4 x float> addrspace(1) * %in
%b = load <4 x float>, <4 x float> addrspace(1) * %b_ptr
%result = fdiv <4 x float> %a, %b
store <4 x float> %result, <4 x float> addrspace(1)* %out
ret void
}
|
