File: NVPTXSubtarget.cpp

package info (click to toggle)
llvm-toolchain-11 1%3A11.0.1-2
  • links: PTS, VCS
  • area: main
  • in suites: bullseye
  • size: 995,808 kB
  • sloc: cpp: 4,767,656; ansic: 760,916; asm: 477,436; python: 170,940; objc: 69,804; lisp: 29,914; sh: 23,855; f90: 18,173; pascal: 7,551; perl: 7,471; ml: 5,603; awk: 3,489; makefile: 2,573; xml: 915; cs: 573; fortran: 503; javascript: 452
file content (67 lines) | stat: -rw-r--r-- 2,197 bytes parent folder | download | duplicates (2)
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
//===- NVPTXSubtarget.cpp - NVPTX Subtarget Information -------------------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// This file implements the NVPTX specific subclass of TargetSubtarget.
//
//===----------------------------------------------------------------------===//

#include "NVPTXSubtarget.h"
#include "NVPTXTargetMachine.h"

using namespace llvm;

#define DEBUG_TYPE "nvptx-subtarget"

#define GET_SUBTARGETINFO_ENUM
#define GET_SUBTARGETINFO_TARGET_DESC
#define GET_SUBTARGETINFO_CTOR
#include "NVPTXGenSubtargetInfo.inc"

static cl::opt<bool>
    NoF16Math("nvptx-no-f16-math", cl::ZeroOrMore, cl::Hidden,
              cl::desc("NVPTX Specific: Disable generation of f16 math ops."),
              cl::init(false));

// Pin the vtable to this file.
void NVPTXSubtarget::anchor() {}

NVPTXSubtarget &NVPTXSubtarget::initializeSubtargetDependencies(StringRef CPU,
                                                                StringRef FS) {
    // Provide the default CPU if we don't have one.
    TargetName = std::string(CPU.empty() ? "sm_20" : CPU);

    ParseSubtargetFeatures(TargetName, FS);

    // Set default to PTX 3.2 (CUDA 5.5)
    if (PTXVersion == 0) {
      PTXVersion = 32;
  }

  return *this;
}

NVPTXSubtarget::NVPTXSubtarget(const Triple &TT, const std::string &CPU,
                               const std::string &FS,
                               const NVPTXTargetMachine &TM)
    : NVPTXGenSubtargetInfo(TT, CPU, FS), PTXVersion(0), SmVersion(20), TM(TM),
      InstrInfo(), TLInfo(TM, initializeSubtargetDependencies(CPU, FS)),
      FrameLowering() {}

bool NVPTXSubtarget::hasImageHandles() const {
  // Enable handles for Kepler+, where CUDA supports indirect surfaces and
  // textures
  if (TM.getDrvInterface() == NVPTX::CUDA)
    return (SmVersion >= 30);

  // Disabled, otherwise
  return false;
}

bool NVPTXSubtarget::allowFP16Math() const {
  return hasFP16Math() && NoF16Math == false;
}