blob: 995d9ae3907fc5c2d1126cf2cb311b9a9b0d812b (
plain)
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
|
//===--- AMDGPUMacroFusion.cpp - AMDGPU Macro Fusion ----------------------===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
/// \file This file contains the AMDGPU implementation of the DAG scheduling
/// mutation to pair instructions back to back.
//
//===----------------------------------------------------------------------===//
#include "AMDGPUMacroFusion.h"
#include "AMDGPUSubtarget.h"
#include "SIInstrInfo.h"
#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
#include "llvm/CodeGen/MacroFusion.h"
using namespace llvm;
namespace {
/// Check if the instr pair, FirstMI and SecondMI, should be fused
/// together. Given SecondMI, when FirstMI is unspecified, then check if
/// SecondMI may be part of a fused pair at all.
static bool shouldScheduleAdjacent(const TargetInstrInfo &TII_,
const TargetSubtargetInfo &TSI,
const MachineInstr *FirstMI,
const MachineInstr &SecondMI) {
const SIInstrInfo &TII = static_cast<const SIInstrInfo&>(TII_);
switch (SecondMI.getOpcode()) {
case AMDGPU::V_ADDC_U32_e64:
case AMDGPU::V_SUBB_U32_e64:
case AMDGPU::V_CNDMASK_B32_e64: {
// Try to cluster defs of condition registers to their uses. This improves
// the chance VCC will be available which will allow shrinking to VOP2
// encodings.
if (!FirstMI)
return true;
const MachineOperand *Src2 = TII.getNamedOperand(SecondMI,
AMDGPU::OpName::src2);
return FirstMI->definesRegister(Src2->getReg());
}
default:
return false;
}
return false;
}
} // end namespace
namespace llvm {
std::unique_ptr<ScheduleDAGMutation> createAMDGPUMacroFusionDAGMutation () {
return createMacroFusionDAGMutation(shouldScheduleAdjacent);
}
} // end namespace llvm
|
