mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-07-28 20:11:22 +00:00
4f2096be38
### Description
<!-- Describe your changes. -->
Update XNNPACK to latest version
- adds fp16 kernels and various other improvements
- requires pthreadpool update as well
Most code updates in the XNNPACK EP are to adjust to the new XNNPACK API
- 'setup' is split into 'reshape' and 'setup'
- some ops use a workspace buffer
- copied workspace allocation from XNNPACK unit test code
- some suffixes changed
Added wrapper for XNNPACK caches to base XNNPACK EP kernel
- simplifies usage
- XNNPACK split out the code and weights caches, but the code cache
isn't currently usable via the public API
- we could use the internal types if we think it's required for
performance reasons. non-trivial though as we'd need to propagate ifdef
values from the XNNPACK build up to the ORT build.
- using XNNPACK internals would also mean we would not be able to
support using a pre-build XNNPACK package
- not an issue currently
Fixed opset registration for internal NHWC domain
- was not being tied to the ONNX version, so nodes inserted by layout
transformation had the incorrect opset
- a number of other places needed updating once this issue was fixed
Remove support for NCHW Resize from XNNPACK EP so it's NHWC only
- we only supported NCHW for fp32,
- doing so adds complexity in multiple places (XNNPACK EP kernel
implementation, layout transformation and transpose optimization)
- unclear if that complexity provides any benefit. can add back if
required by production scenario
### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
We're looking at enabling fp16 support for CoreML and NNAPI. If we do
that we need a good fallback story if the CPU EP will be used. The
XNNPACK fp16 kernels will hopefully provide that.
NOTE: This PR doesn't add fp16 support to the XNNPACK EP kernels. That
can be done as required in separate EPs and should be relatively simple
to do.
27 lines
1.8 KiB
Diff
27 lines
1.8 KiB
Diff
diff --git a/CMakeLists.txt b/CMakeLists.txt
|
|
index dba9b4687..bcaa18ad7 100755
|
|
--- a/CMakeLists.txt
|
|
+++ b/CMakeLists.txt
|
|
@@ -122,7 +122,7 @@ ENDIF()
|
|
# ---[ Build flags
|
|
IF(NOT CMAKE_SYSTEM_NAME)
|
|
MESSAGE(FATAL_ERROR "CMAKE_SYSTEM_NAME not defined")
|
|
-ELSEIF(NOT CMAKE_SYSTEM_NAME MATCHES "^(Android|Darwin|iOS|Linux|Windows|CYGWIN|MSYS|QURT)$")
|
|
+ELSEIF(NOT CMAKE_SYSTEM_NAME MATCHES "^(Android|Darwin|iOS|Linux|Windows|CYGWIN|MSYS|QURT|Emscripten|iOS)$")
|
|
MESSAGE(FATAL_ERROR "Unrecognized CMAKE_SYSTEM_NAME value \"${CMAKE_SYSTEM_NAME}\"")
|
|
ENDIF()
|
|
IF(CMAKE_SYSTEM_NAME MATCHES "Windows")
|
|
@@ -534,7 +534,12 @@ IF(XNNPACK_BUILD_LIBRARY)
|
|
TARGET_LINK_LIBRARIES(operator-utils PRIVATE logging)
|
|
TARGET_LINK_LIBRARIES(post-operation PRIVATE logging)
|
|
TARGET_LINK_LIBRARIES(subgraph PRIVATE allocator logging memory mutex operators operator-run)
|
|
- TARGET_LINK_LIBRARIES(XNNPACK PRIVATE allocator cache hardware-config indirection jit logging memory microkernel-utils microparams-init mutex normalization operators operator-run operator-utils packing post-operation microkernels-prod subgraph)
|
|
+ IF(CMAKE_SYSTEM_NAME STREQUAL "Emscripten")
|
|
+ # omit microkernels-prod as the list is manually created by ORT in cmake/external/xnnpack.cmake
|
|
+ TARGET_LINK_LIBRARIES(XNNPACK PRIVATE allocator cache hardware-config indirection jit logging memory microkernel-utils microparams-init mutex normalization operators operator-run operator-utils packing post-operation subgraph)
|
|
+ ELSE()
|
|
+ TARGET_LINK_LIBRARIES(XNNPACK PRIVATE allocator cache hardware-config indirection jit logging memory microkernel-utils microparams-init mutex normalization operators operator-run operator-utils packing post-operation microkernels-prod subgraph)
|
|
+ ENDIF()
|
|
SET_TARGET_PROPERTIES(XNNPACK PROPERTIES C_EXTENSIONS YES)
|
|
ENDIF()
|
|
IF(NOT MSVC)
|