summaryrefslogtreecommitdiff
path: root/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp
blob: 497811366e2f49590369e4a76ffda15501c8c4c4 (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
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
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
//===-- AMDGPUAsmPrinter.cpp - AMDGPU Assebly printer  --------------------===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// The AMDGPUAsmPrinter is used to print both assembly string and also binary
// code.  When passed an MCAsmStreamer it prints assembly and when passed
// an MCObjectStreamer it outputs binary code.
//
//===----------------------------------------------------------------------===//
//


#include "AMDGPUAsmPrinter.h"
#include "AMDGPU.h"
#include "SIMachineFunctionInfo.h"
#include "SIRegisterInfo.h"
#include "llvm/MC/MCStreamer.h"
#include "llvm/Target/TargetLoweringObjectFile.h"
#include "llvm/Support/TargetRegistry.h"

using namespace llvm;


static AsmPrinter *createAMDGPUAsmPrinterPass(TargetMachine &tm,
                                              MCStreamer &Streamer) {
  return new AMDGPUAsmPrinter(tm, Streamer);
}

extern "C" void LLVMInitializeAMDGPUAsmPrinter() {
  TargetRegistry::RegisterAsmPrinter(TheAMDGPUTarget, createAMDGPUAsmPrinterPass);
}

/// runOnMachineFunction - We need to override this function so we can avoid
/// the call to EmitFunctionHeader(), which the MCPureStreamer can't handle.
bool AMDGPUAsmPrinter::runOnMachineFunction(MachineFunction &MF) {
  const AMDGPUSubtarget &STM = TM.getSubtarget<AMDGPUSubtarget>();
  if (STM.dumpCode()) {
    MF.dump();
  }
  SetupMachineFunction(MF);
  OutStreamer.SwitchSection(getObjFileLowering().getTextSection());
  if (STM.device()->getGeneration() > AMDGPUDeviceInfo::HD6XXX) {
    EmitProgramInfo(MF);
  }
  EmitFunctionBody();
  return false;
}

void AMDGPUAsmPrinter::EmitProgramInfo(MachineFunction &MF) {
  unsigned MaxSGPR = 0;
  unsigned MaxVGPR = 0;
  bool VCCUsed = false;
  const SIRegisterInfo * RI =
                static_cast<const SIRegisterInfo*>(TM.getRegisterInfo());

  for (MachineFunction::iterator BB = MF.begin(), BB_E = MF.end();
                                                  BB != BB_E; ++BB) {
    MachineBasicBlock &MBB = *BB;
    for (MachineBasicBlock::iterator I = MBB.begin(), E = MBB.end();
                                                    I != E; ++I) {
      MachineInstr &MI = *I;

      unsigned numOperands = MI.getNumOperands();
      for (unsigned op_idx = 0; op_idx < numOperands; op_idx++) {
        MachineOperand & MO = MI.getOperand(op_idx);
        unsigned maxUsed;
        unsigned width = 0;
        bool isSGPR = false;
        unsigned reg;
        unsigned hwReg;
        if (!MO.isReg()) {
          continue;
        }
        reg = MO.getReg();
        if (reg == AMDGPU::VCC) {
          VCCUsed = true;
          continue;
        }
        switch (reg) {
        default: break;
        case AMDGPU::EXEC:
        case AMDGPU::SI_LITERAL_CONSTANT:
        case AMDGPU::SREG_LIT_0:
        case AMDGPU::M0:
          continue;
        }

        if (AMDGPU::SReg_32RegClass.contains(reg)) {
          isSGPR = true;
          width = 1;
        } else if (AMDGPU::VReg_32RegClass.contains(reg)) {
          isSGPR = false;
          width = 1;
        } else if (AMDGPU::SReg_64RegClass.contains(reg)) {
          isSGPR = true;
          width = 2;
        } else if (AMDGPU::VReg_64RegClass.contains(reg)) {
          isSGPR = false;
          width = 2;
        } else if (AMDGPU::SReg_128RegClass.contains(reg)) {
          isSGPR = true;
          width = 4;
        } else if (AMDGPU::VReg_128RegClass.contains(reg)) {
          isSGPR = false;
          width = 4;
        } else if (AMDGPU::SReg_256RegClass.contains(reg)) {
          isSGPR = true;
          width = 8;
        } else {
          assert(!"Unknown register class");
        }
        hwReg = RI->getEncodingValue(reg);
        maxUsed = hwReg + width - 1;
        if (isSGPR) {
          MaxSGPR = maxUsed > MaxSGPR ? maxUsed : MaxSGPR;
        } else {
          MaxVGPR = maxUsed > MaxVGPR ? maxUsed : MaxVGPR;
        }
      }
    }
  }
  if (VCCUsed) {
    MaxSGPR += 2;
  }
  SIMachineFunctionInfo * MFI = MF.getInfo<SIMachineFunctionInfo>();
  OutStreamer.EmitIntValue(MaxSGPR + 1, 4);
  OutStreamer.EmitIntValue(MaxVGPR + 1, 4);
  OutStreamer.EmitIntValue(MFI->SPIPSInputAddr, 4);
}