forked from triton-inference-server/python_backend
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathgpu_buffers.cc
More file actions
89 lines (79 loc) · 3.14 KB
/
Copy pathgpu_buffers.cc
File metadata and controls
89 lines (79 loc) · 3.14 KB
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
// Copyright 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
//
// Redistribution and use in source and binary forms, with or without
// modification, are permitted provided that the following conditions
// are met:
// * Redistributions of source code must retain the above copyright
// notice, this list of conditions and the following disclaimer.
// * Redistributions in binary form must reproduce the above copyright
// notice, this list of conditions and the following disclaimer in the
// documentation and/or other materials provided with the distribution.
// * Neither the name of NVIDIA CORPORATION nor the names of its
// contributors may be used to endorse or promote products derived
// from this software without specific prior written permission.
//
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY
// EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
// IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
// PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
// CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
// EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
// PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
// PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
// OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
#include "gpu_buffers.h"
#include "pb_string.h"
namespace triton { namespace backend { namespace python {
GPUBuffersHelper::GPUBuffersHelper()
{
completed_ = false;
}
void
GPUBuffersHelper::AddBuffer(const bi::managed_external_buffer::handle_t& handle)
{
if (completed_) {
throw PythonBackendException(
"It is not possible to add buffers after 'Complete' has been called on "
"a GPUBuffersHelper.");
}
buffers_.emplace_back(handle);
}
void
GPUBuffersHelper::SetError(
std::unique_ptr<SharedMemoryManager>& shm_pool, const std::string& error)
{
error_shm_ = PbString::Create(shm_pool, error);
}
void
GPUBuffersHelper::Complete(std::unique_ptr<SharedMemoryManager>& shm_pool)
{
if (completed_) {
throw PythonBackendException(
"Complete has already been called. Complete should only be called "
"once.");
}
gpu_buffers_shm_ = shm_pool->Construct<GPUBuffersShm>();
if (!error_shm_) {
buffers_handle_shm_ =
shm_pool->Construct<bi::managed_external_buffer::handle_t>(
buffers_.size());
gpu_buffers_shm_.data_->buffer_count = buffers_.size();
gpu_buffers_shm_.data_->success = true;
gpu_buffers_shm_.data_->buffers = buffers_handle_shm_.handle_;
for (size_t i = 0; i < buffers_.size(); ++i) {
buffers_handle_shm_.data_.get()[i] = buffers_[i];
}
} else {
gpu_buffers_shm_.data_->success = false;
gpu_buffers_shm_.data_->error = error_shm_->ShmHandle();
}
completed_ = true;
}
bi::managed_external_buffer::handle_t
GPUBuffersHelper::ShmHandle()
{
return gpu_buffers_shm_.handle_;
}
}}} // namespace triton::backend::python