File: AMDGPU.cpp

package info (click to toggle)
rocblas 5.5.1%2Bdfsg-7
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid, trixie
  • size: 565,372 kB
  • sloc: cpp: 198,491; python: 44,792; f90: 25,111; sh: 24,429; asm: 8,954; xml: 222; makefile: 147; ansic: 107; awk: 14
file content (82 lines) | stat: -rw-r--r-- 2,618 bytes parent folder | download
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
/*******************************************************************************
 *
 * MIT License
 *
 * Copyright (C) 2019-2022 Advanced Micro Devices, Inc. All rights reserved.
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this software and associated documentation files (the "Software"), to deal
 * in the Software without restriction, including without limitation the rights
 * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 * copies of the Software, and to permit persons to whom the Software is
 * furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
 * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 * SOFTWARE.
 *
 *******************************************************************************/

#include <Tensile/AMDGPU.hpp>

namespace Tensile
{
    TENSILE_API std::string AMDGPU::type() const
    {
        return Type();
    }

    TENSILE_API AMDGPU::AMDGPU() {}

    TENSILE_API AMDGPU::AMDGPU(AMDGPU::Processor p, int cus, std::string const& name)
        : processor(p)
        , computeUnitCount(cus)
        , deviceName(name)
    {
    }

    TENSILE_API AMDGPU::~AMDGPU() = default;

    TENSILE_API bool AMDGPU::runsKernelTargeting(AMDGPU::Processor other) const
    {
        if(other > this->processor)
            return false;
        if(other == this->processor)
            return true;

        if(other == Processor::gfx803)
            return false;

        if(other == Processor::gfx900)
            return true;

        return false;
    }

    std::ostream& operator<<(std::ostream& stream, AMDGPU::Processor p)
    {
        stream << AMDGPU::toString(p);
        return stream;
    }

    TENSILE_API std::string AMDGPU::description() const
    {
        std::ostringstream rv;

        rv << deviceName << "(" << computeUnitCount << "-CU " << processor << ")";

        return rv.str();
    }

    TENSILE_API std::ostream& operator<<(std::ostream& stream, AMDGPU g)
    {
        return stream << g.description();
    }
} // namespace Tensile