Skip to content

Manohar/dyn dev select - #8

Merged
smkarlap merged 4 commits into
openvino-ep-v2from
manohar/dyn-dev-select
Mar 6, 2020
Merged

Manohar/dyn dev select#8
smkarlap merged 4 commits into
openvino-ep-v2from
manohar/dyn-dev-select

Conversation

@smkarlap

@smkarlap smkarlap commented Mar 6, 2020

Copy link
Copy Markdown

Description: Enables selection of target device dynamically via ORT API's

Motivation and Context

  • A single build of ORT can be run on multiple hardware accelerators

@smkarlap smkarlap self-assigned this Mar 6, 2020

@psfoley psfoley left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Looks great overall. The only thing I would add is documentation that explains how to select the device from python.

@smkarlap

smkarlap commented Mar 6, 2020

Copy link
Copy Markdown
Author

Looks great overall. The only thing I would add is documentation that explains how to select the device from python.

Done

Comment thread onnxruntime/core/providers/openvino/openvino_execution_provider.cc
@smkarlap
smkarlap requested a review from suryasidd March 6, 2020 22:25

@suryasidd suryasidd left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@psfoley psfoley left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

👍

@smkarlap
smkarlap merged commit c946545 into openvino-ep-v2 Mar 6, 2020
@smkarlap
smkarlap deleted the manohar/dyn-dev-select branch March 6, 2020 22:28
MaajidKhan pushed a commit that referenced this pull request Mar 9, 2022
ARM a55 micro-architecture (with dot product instructions), similar to a53, is widely used as little cores in big.Little configurations. A55 has a narrower memory load/store hardware, where a 128b load instruction would block the pipeline for 2 whole cycles, during which no other instructions can be executed. On the other hand, a 64b load instruction can be duo issued with many other instructions.

This change adds a Symmetric QGEMM kernel for a55 micro-architecture, where we replace

ldr q4,[x1],#16

with

ldr d4,[x1],#8
ldr x11,[x1],#8
ins v4.d[1],x11

so that we can try to hide the memory load cycles behind computing cycles in the kernel.

Co-authored-by: Chen Fu <fuchen@microsoft.com>
lavanyax pushed a commit that referenced this pull request Mar 29, 2022
ARM a55 micro-architecture (with dot product instructions), similar to a53, is widely used as little cores in big.Little configurations. A55 has a narrower memory load/store hardware, where a 128b load instruction would block the pipeline for 2 whole cycles, during which no other instructions can be executed. On the other hand, a 64b load instruction can be duo issued with many other instructions.

This change adds a Symmetric QGEMM kernel for a55 micro-architecture, where we replace

ldr q4,[x1],#16

with

ldr d4,[x1],#8
ldr x11,[x1],#8
ins v4.d[1],x11

so that we can try to hide the memory load cycles behind computing cycles in the kernel.

Co-authored-by: Chen Fu <fuchen@microsoft.com>
sfatimar pushed a commit that referenced this pull request Aug 28, 2023
### Description
Release OrtEnv before main function returns. Before this change, OrtEnv
is deleted when C/C++ runtime destructs all global variables in ONNX
Runtime's core framework.
The callstack is like this:
```
  * frame #0: 0x00007fffee39f5a6 libonnxruntime.so.1.16.0`onnxruntime::Environment::~Environment(this=0x00007fffee39fbf2) at environment.h:20:7
    frame #1: 0x00007fffee39f614 libonnxruntime.so.1.16.0`std::default_delete<onnxruntime::Environment>::operator()(this=0x00007ffff4c30e50, __ptr=0x0000000005404b00) const at unique_ptr.h:85:2
    frame #2: 0x00007fffee39edca libonnxruntime.so.1.16.0`std::unique_ptr<onnxruntime::Environment, std::default_delete<onnxruntime::Environment>>::~unique_ptr(this=0x5404b00) at unique_ptr.h:361:17
    frame #3: 0x00007fffee39e2ab libonnxruntime.so.1.16.0`OrtEnv::~OrtEnv(this=0x00007ffff4c30e50) at ort_env.cc:43:1
    frame #4: 0x00007fffee39fa96 libonnxruntime.so.1.16.0`std::default_delete<OrtEnv>::operator()(this=0x00007fffefff8f78, __ptr=0x00007ffff4c30e50) const at unique_ptr.h:85:2
    frame #5: 0x00007fffee39f394 libonnxruntime.so.1.16.0`std::unique_ptr<OrtEnv, std::default_delete<OrtEnv>>::~unique_ptr(this=0x7ffff4c30e50) at unique_ptr.h:361:17
    frame #6: 0x00007ffff78574b5 libc.so.6`__run_exit_handlers + 261
    frame #7: 0x00007ffff7857630 libc.so.6`exit + 32
    frame #8: 0x00007ffff783feb7 libc.so.6`__libc_start_call_main + 135
    frame #9: 0x00007ffff783ff60 libc.so.6`__libc_start_main@@GLIBC_2.34 + 128
    frame #10: 0x0000000000abbdee node`_start + 46
```
After this change, OrtEnv will be deleted before the main function
returns and nodejs is still alive.
RyanMetcalfeInt8 pushed a commit to RyanMetcalfeInt8/onnxruntime that referenced this pull request Jul 25, 2025
hdharpure9922 pushed a commit that referenced this pull request Jul 28, 2026
…rosoft#29880)

### Description

`import onnxruntime` segfaults during `dlopen` of
`onnxruntime_pybind11_state.so` on Linux. This removes the global
initializer in `onnxruntime_pybind_state.cc` that eagerly calls
`Env::Default()`, and resolves the platform `Env` on first use at its
two call sites instead.

### Motivation and Context

The module has a namespace-scope dynamic initializer:

```cpp
static Env& platform_env = Env::Default();
```

Since POSIX telemetry landed (microsoft#27379), `Env::Default()` constructs
`PosixEnv`, whose `PosixTelemetry` member initializes the 1DS SDK in its
constructor. That path reads `defaultRuntimeConfig`, a namespace-scope
`static ILogConfiguration` defined in the 1DS SDK's
`RuntimeConfig_Default.hpp`, which lives in a **different translation
unit of the same shared library**.

Dynamic initialization order across translation units is unspecified,
and the pybind TU's initializer runs first. `Variant::merge_map`
therefore iterates a still zero-initialized `std::map`: `_M_node_count
== 0`, but `_M_header._M_left` is `nullptr` rather than self-pointing,
so `begin() != end()` and the loop dereferences null.

Textbook static initialization order fiasco. Backtrace (Release build
relinked without `--strip-all` to recover symbols):

```
#0  std::map<..., Variant>::lower_bound        stl_map.h:1307
#1  std::map<..., Variant>::operator[]         stl_map.h:509
#2  Variant::merge_map                         VariantType.hpp:508
#3  RuntimeConfig_Default::RuntimeConfig_Default  RuntimeConfig_Default.hpp:97
#4  LogManagerImpl::LogManagerImpl             LogManagerImpl.cpp:183
#5  LogManagerFactory::Create                  LogManagerFactory.cpp:36
#6  LogManagerFactory::lease
#7  LogManagerFactory::Get                     LogManagerFactory.hpp:71
#8  LogManagerProvider::Get                    LogManagerProvider.cpp:16
#9  onnxruntime::PosixTelemetry::Initialize()
#10 onnxruntime::PosixTelemetry::PosixTelemetry()
#11 onnxruntime::(anonymous namespace)::PosixEnv::PosixEnv()
#12 onnxruntime::Env::Default()
#13 _GLOBAL__sub_I_onnxruntime_pybind_state.cc
#14 call_init                                  elf/dl-init.c:74
...
#21 _dl_open                                   elf/dl-open.c:905
```

The crash is independent of `LD_LIBRARY_PATH` and `CUDA_VISIBLE_DEVICES`
— it happens before any ORT runtime code runs. `libonnxruntime.so` is
unaffected because it contains no global initializer that reaches
`Env::Default()`, which is why C/C++ and onnxruntime-genai consumers do
not see it.

Both remaining uses of `platform_env` are inside pybind lambdas that run
long after load, so calling `Env::Default()` there is safe. This also
removes the now-stale `TODO: we may delay-init this variable` and a
pre-existing `#pragma warning(push)` that should have been `pop`.

Note for follow-up: `Env::Default()` is now unsafe to call from any
dynamic initializer. This was the only such call site in the tree, but
hardening `PosixTelemetry` to defer SDK initialization out of its
constructor would remove the hazard entirely.

### Tests

Verified on a Linux CUDA 13 Release build (`onnxruntime_USE_TELEMETRY`
enabled):

- `dlopen` of `onnxruntime_pybind11_state.so` succeeds (previously
SIGSEGV).
- `import onnxruntime` reports the version and
`['CUDAExecutionProvider', 'CPUExecutionProvider']`.
- `onnxruntime.enable_telemetry_events()` / `disable_telemetry_events()`
— the two call sites changed here — work.
- CPU and CUDA inference sessions produce correct results.
- Reproduced and verified with `LD_LIBRARY_PATH` unset and
`CUDA_VISIBLE_DEVICES` empty.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants