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
|
//===-- SISchedule.td - SI Scheduling definitons -------------------------===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// MachineModel definitions for Southern Islands (SI)
//
//===----------------------------------------------------------------------===//
def SI_Itin : ProcessorItineraries <[], [], []>;
def WriteBranch : SchedWrite;
def WriteExport : SchedWrite;
def WriteLDS : SchedWrite;
def WriteSALU : SchedWrite;
def WriteSMEM : SchedWrite;
def WriteVMEM : SchedWrite;
// Vector ALU instructions
def WriteDouble : SchedWrite;
def WriteDoubleAdd : SchedWrite;
def WriteFloat : SchedWrite;
def WriteFloatFMA : SchedWrite;
def WriteFloatTrans : SchedWrite;
def WriteInt : SchedWrite;
def WriteIntMUL : SchedWrite;
def WriteConversion : SchedWrite;
def WriteI24 : SchedWrite;
def SIModel : SchedMachineModel;
// BufferSize = 0 means the processors are in-order.
let BufferSize = 0 in {
// XXX: Are the resource counts correct?
def HWBranch : ProcResource<1>;
def HWExport : ProcResource<7>; // Taken from S_WAITCNT
def HWLGKM : ProcResource<31>; // Taken from S_WAITCNT
def HWSALU : ProcResource<1>;
def HWVMEM : ProcResource<15>; // Taken from S_WAITCNT
def HWVALU : ProcResource<1>;
}
let SchedModel = SIModel in {
class HWWriteRes<SchedWrite write, list<ProcResourceKind> resources,
int latency> : WriteRes<write, resources> {
let Latency = latency;
}
class HWVALUWriteRes<SchedWrite write, int latency> :
HWWriteRes<write, [HWVALU], latency>;
// The latency numbers are taken from AMD Accelerated Parallel Processing
// guide. They may not be acurate.
def : HWWriteRes<WriteBranch, [HWBranch], 100>; // XXX: Guessed ???
def : HWWriteRes<WriteExport, [HWExport], 100>; // XXX: Guessed ???
def : HWWriteRes<WriteLDS, [HWLGKM], 32>; // 2 - 64
def : HWWriteRes<WriteSALU, [HWSALU], 1>;
def : HWWriteRes<WriteSMEM, [HWLGKM], 10>; // XXX: Guessed ???
def : HWWriteRes<WriteVMEM, [HWVMEM], 450>; // 300 - 600
// XXX: These definitions assume full double-precision speed, some devices are
// slower. These are also taken from the AMD Accelerated Parallel Processing
// guide and may not be accurate.
def : HWVALUWriteRes<WriteDouble, 4>;
def : HWVALUWriteRes<WriteDoubleAdd, 2>;
def : HWVALUWriteRes<WriteFloat, 1>;
def : HWVALUWriteRes<WriteFloatFMA, 1>;
def : HWVALUWriteRes<WriteFloatTrans, 4>;
def : HWVALUWriteRes<WriteInt, 1>;
def : HWVALUWriteRes<WriteIntMUL, 4>;
def : HWVALUWriteRes<WriteConversion, 4>;
def : HWVALUWriteRes<WriteI24, 1>;
} // End SchedModel = SIModel
|
