Work-around for not applying -fsycl-device-code-split=per_kernel on Windows#1083
Work-around for not applying -fsycl-device-code-split=per_kernel on Windows#1083oleksandr-pavlyk merged 4 commits intomasterfrom
Conversation
|
View rendered docs @ https://intelpython.github.io/dpctl/pulls/1083/index.html |
|
Array API standard conformance tests for dpctl=0.14.1dev2=py310h76be34b_44 ran successfully. |
|
Array API standard conformance tests for dpctl=0.14.1dev2=py310h76be34b_43 ran successfully. |
|
Array API standard conformance tests for dpctl=0.14.1dev2=py310h76be34b_45 ran successfully. |
|
Array API standard conformance tests for dpctl=0.14.1dev2=py310h76be34b_46 ran successfully. |
|
Array API standard conformance tests for dpctl=0.14.1dev2=py310h76be34b_47 ran successfully. |
|
Array API standard conformance tests for dpctl=0.14.1dev2=py310h76be34b_48 ran successfully. |
|
Array API standard conformance tests for dpctl=0.14.1dev2=py310h76be34b_49 ran successfully. |
|
Array API standard conformance tests for dpctl=0.14.1dev2=py310h76be34b_50 ran successfully. |
|
Array API standard conformance tests for dpctl=0.14.1dev2=py310h76be34b_52 ran successfully. |
|
Array API standard conformance tests for dpctl=0.14.1dev2=py310h76be34b_54 ran successfully. |
e0d5720 to
86a26c5
Compare
|
Array API standard conformance tests for dpctl=0.14.1dev2=py310h76be34b_46 ran successfully. |
Use semicolon to specify multiple linker flags in SYCL_LDFLAGS
In cmake 3.22 using target_link_options result in option inserted in LINK_FLAGS which places it after -link option and passed directly to the underlying linker where it is ignored. This is fixed in cmake 3.25 Also make sure to apply -fsycl-link-huge-device-code on Linux only, the option is not supported on Windows.
86a26c5 to
73437f6
Compare
|
Array API standard conformance tests for dpctl=0.14.1dev2=py310h76be34b_49 ran successfully. |
|
Deleted rendered PR docs from intelpython.github.com/dpctl, latest should be updated shortly. 🤞 |
|
Array API standard conformance tests for dpctl=0.14.1dev2=py310h76be34b_49 ran successfully. |
Tweaked
bld.batto account for possible folder names inLibrary\lib\clang.Made the logic of patching
Windows-IntelLLVM.cmakein conda package for cmake 3.22 dependent of existence of the folder.Modified
CMakeLists.txtto ensure that SDL flags/NXCompat /DynamicBaseare correctly applied on Windows.Worked around issue of oneAPI DPC++ integration with cmake 3.22 to ensure that
-fsycl-device-code-split=per_kernelis correctly passed to the linker driver.Also ensure that
-fsycl-link-huge-device-codeis only added on Linux (option is not supported on Windows).The following line
python -c "import dpctl.tensor as dpt; print(dpt.arange(10))can now execute on Windows machine with Iris Xe card.