New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Anton/experimental fpga #298
Open
ShanoToni
wants to merge
22
commits into
codeplaysoftware:fpga-support
Choose a base branch
from
ShanoToni:anton/experimental_fpga
base: fpga-support
Could not load branches
Branch not found: {{ refName }}
Could not load tags
Nothing to show
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Open
Anton/experimental fpga #298
ShanoToni
wants to merge
22
commits into
codeplaysoftware:fpga-support
from
ShanoToni:anton/experimental_fpga
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
ProGTX
requested changes
Sep 22, 2021
mehdi-goli
approved these changes
Nov 19, 2021
mehdi-goli
requested changes
Nov 19, 2021
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The change in the Benchmark and test are radical, we need to find a better way to remove the queue creation
ShanoToni
force-pushed
the
anton/experimental_fpga
branch
from
December 3, 2021 16:01
3d340cc
to
757dc56
Compare
* Rudimentary hipSYCL build integration. * Don't always use CPU profile for GEMM and set samples C++17 standard for hipSYCL. * Allow overriding HIPSYCL_TARGETS by environment variable as well. And output the selected SYCL implementation. * Move setting HIPSYCL_TARGETS to SYCL.cmake and add docs. * Clarify comment about HIPSYCL_TARGETS
Co-authored-by: Kumudha <kumudha.narasimhan@codeplay.com> Co-authored-by: Mehdi Goli <mehdi.goli@codeplay.com>
CMake supports having export files which describe the library to users seeking it in either the build tree or an installed directory. This means users can now specify `-Dsycl_blas_DIR=$install_path` during configuration and CMake will be able to locate the library and headers.
Instead of adding an absolute path to the interface include dirs, we should use the PUBLIC link, since any SYCL-BLAS target will transitively depend on ComputeCpp or some other SYCL implementation as well (SYCL-BLAS uses SYCL constructs in its public headers). Without this change, packages created by installing the project will have absolute paths of the machine it was built on, making the package unrelocatable. With it, a requisite of the SYCL library is added to the targets. The SDK includes are still propagated for the export file, but removed for installs, as the headers are installed alongside the SYCL-BLAS headers so can be found in the same location.
Co-authored-by: Kumudha KN <kumudha.narasimhan@codeplay.com>
- Enable testing of Product Reduction and fix issues with it - Remove testing of Division Reduction since the Division operator is not commutative
ShanoToni
force-pushed
the
anton/experimental_fpga
branch
from
December 6, 2021 12:50
757dc56
to
63e6900
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Added modifications to the tests and benchmarks in order to use the ComputeCPP runtime fpga fix in the queue constructor.
When compiling with the SYCL_BLAS_FPGA flag the queue is constructed in the .hpp file included in the benchmark or test .cpp file so it passes in trough the compute++ compiler and has access to the new dummy kernel from the queue constructor. (Required for the FPGA)