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
Add common interface for simple kernels #733
Conversation
The code that triggers the compiler error on Intel: template <typename F, typename... Args>
void run(F f, Args... args) {
#pragma omp parallel for
for (unsigned i = 0; i < 100; i++) {
f(args...);
}
}
int main() {
int a;
run([](auto j) {}, a);
} |
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.
I would not say this reduce the porting effort, but it really reduce a lot code from porting. Thanks!
Originally, our porting script always generates 1 ~ 2 layers to keep the same interface and template usage as CUDA/HIP. Thus, it will gives many layer just for internal, which is somehow annoying.
I think we can leave these kernels launch args to compiler decide and it should not give any performance impact.
Do you have any idea such that we do not need to copy the same thing over different executors?
Instantiating in core directly seems to be impossible because we need different compiler to compile it.
Is putting it in generic folder like common a possible way? but it will increase the complexity to find the actual kernel code
@yhmtsai Yes, that was the idea, we could basically have a core/device/simple_headers.hpp file that includes the correct executor's headers etc. dependent on which executor is being compiled. |
add missing includes for more IWYU-like structure Co-authored-by: Terry Cojean <terry.cojean@kit.edu> Co-authored-by: Thomas Grützmacher <thomas.gruetzmacher@kit.edu>
Kudos, SonarCloud Quality Gate passed! |
Codecov Report
@@ Coverage Diff @@
## develop #733 +/- ##
===========================================
- Coverage 94.38% 93.11% -1.28%
===========================================
Files 400 408 +8
Lines 32253 32621 +368
===========================================
- Hits 30441 30374 -67
- Misses 1812 2247 +435
Continue to review full report at Codecov.
|
The `test_install` folder was moved to `test` with ginkgo-project/ginkgo#733.
The `test_install` folder was moved to `test` with ginkgo-project/ginkgo#733.
Ginkgo release 1.4.0 The Ginkgo team is proud to announce the new Ginkgo minor release 1.4.0. This release brings most of the Ginkgo functionality to the Intel DPC++ ecosystem which enables Intel-GPU and CPU execution. The only Ginkgo features which have not been ported yet are some preconditioners. Ginkgo's mixed-precision support is greatly enhanced thanks to: 1. The new Accessor concept, which allows writing kernels featuring on-the-fly memory compression, among other features. The accessor can be used as header-only, see the [accessor BLAS benchmarks repository](https://github.com/ginkgo-project/accessor-BLAS/tree/develop) as a usage example. 2. All LinOps now transparently support mixed-precision execution. By default, this is done through a temporary copy which may have a performance impact but already allows mixed-precision research. Native mixed-precision ELL kernels are implemented which do not see this cost. The accessor is also leveraged in a new CB-GMRES solver which allows for performance improvements by compressing the Krylov basis vectors. Many other features have been added to Ginkgo, such as reordering support, a new IDR solver, Incomplete Cholesky preconditioner, matrix assembly support (only CPU for now), machine topology information, and more! Supported systems and requirements: + For all platforms, cmake 3.13+ + C++14 compliant compiler + Linux and MacOS + gcc: 5.3+, 6.3+, 7.3+, all versions after 8.1+ + clang: 3.9+ + Intel compiler: 2018+ + Apple LLVM: 8.0+ + CUDA module: CUDA 9.0+ + HIP module: ROCm 3.5+ + DPC++ module: Intel OneAPI 2021.3. Set the CXX compiler to `dpcpp`. + Windows + MinGW and Cygwin: gcc 5.3+, 6.3+, 7.3+, all versions after 8.1+ + Microsoft Visual Studio: VS 2019 + CUDA module: CUDA 9.0+, Microsoft Visual Studio + OpenMP module: MinGW or Cygwin. Algorithm and important feature additions: + Add a new DPC++ Executor for SYCL execution and other base utilities [#648](#648), [#661](#661), [#757](#757), [#832](#832) + Port matrix formats, solvers and related kernels to DPC++. For some kernels, also make use of a shared kernel implementation for all executors (except Reference). [#710](#710), [#799](#799), [#779](#779), [#733](#733), [#844](#844), [#843](#843), [#789](#789), [#845](#845), [#849](#849), [#855](#855), [#856](#856) + Add accessors which allow multi-precision kernels, among other things. [#643](#643), [#708](#708) + Add support for mixed precision operations through apply in all LinOps. [#677](#677) + Add incomplete Cholesky factorizations and preconditioners as well as some improvements to ILU. [#672](#672), [#837](#837), [#846](#846) + Add an AMGX implementation and kernels on all devices but DPC++. [#528](#528), [#695](#695), [#860](#860) + Add a new mixed-precision capability solver, Compressed Basis GMRES (CB-GMRES). [#693](#693), [#763](#763) + Add the IDR(s) solver. [#620](#620) + Add a new fixed-size block CSR matrix format (for the Reference executor). [#671](#671), [#730](#730) + Add native mixed-precision support to the ELL format. [#717](#717), [#780](#780) + Add Reverse Cuthill-McKee reordering [#500](#500), [#649](#649) + Add matrix assembly support on CPUs. [#644](#644) + Extends ISAI from triangular to general and spd matrices. [#690](#690) Other additions: + Add the possibility to apply real matrices to complex vectors. [#655](#655), [#658](#658) + Add functions to compute the absolute of a matrix format. [#636](#636) + Add symmetric permutation and improve existing permutations. [#684](#684), [#657](#657), [#663](#663) + Add a MachineTopology class with HWLOC support [#554](#554), [#697](#697) + Add an implicit residual norm criterion. [#702](#702), [#818](#818), [#850](#850) + Row-major accessor is generalized to more than 2 dimensions and a new "block column-major" accessor has been added. [#707](#707) + Add an heat equation example. [#698](#698), [#706](#706) + Add ccache support in CMake and CI. [#725](#725), [#739](#739) + Allow tuning and benchmarking variables non intrusively. [#692](#692) + Add triangular solver benchmark [#664](#664) + Add benchmarks for BLAS operations [#772](#772), [#829](#829) + Add support for different precisions and consistent index types in benchmarks. [#675](#675), [#828](#828) + Add a Github bot system to facilitate development and PR management. [#667](#667), [#674](#674), [#689](#689), [#853](#853) + Add Intel (DPC++) CI support and enable CI on HPC systems. [#736](#736), [#751](#751), [#781](#781) + Add ssh debugging for Github Actions CI. [#749](#749) + Add pipeline segmentation for better CI speed. [#737](#737) Changes: + Add a Scalar Jacobi specialization and kernels. [#808](#808), [#834](#834), [#854](#854) + Add implicit residual log for solvers and benchmarks. [#714](#714) + Change handling of the conjugate in the dense dot product. [#755](#755) + Improved Dense stride handling. [#774](#774) + Multiple improvements to the OpenMP kernels performance, including COO, an exclusive prefix sum, and more. [#703](#703), [#765](#765), [#740](#740) + Allow specialization of submatrix and other dense creation functions in solvers. [#718](#718) + Improved Identity constructor and treatment of rectangular matrices. [#646](#646) + Allow CUDA/HIP executors to select allocation mode. [#758](#758) + Check if executors share the same memory. [#670](#670) + Improve test install and smoke testing support. [#721](#721) + Update the JOSS paper citation and add publications in the documentation. [#629](#629), [#724](#724) + Improve the version output. [#806](#806) + Add some utilities for dim and span. [#821](#821) + Improved solver and preconditioner benchmarks. [#660](#660) + Improve benchmark timing and output. [#669](#669), [#791](#791), [#801](#801), [#812](#812) Fixes: + Sorting fix for the Jacobi preconditioner. [#659](#659) + Also log the first residual norm in CGS [#735](#735) + Fix BiCG and HIP CSR to work with complex matrices. [#651](#651) + Fix Coo SpMV on strided vectors. [#807](#807) + Fix segfault of extract_diagonal, add short-and-fat test. [#769](#769) + Fix device_reset issue by moving counter/mutex to device. [#810](#810) + Fix `EnableLogging` superclass. [#841](#841) + Support ROCm 4.1.x and breaking HIP_PLATFORM changes. [#726](#726) + Decreased test size for a few device tests. [#742](#742) + Fix multiple issues with our CMake HIP and RPATH setup. [#712](#712), [#745](#745), [#709](#709) + Cleanup our CMake installation step. [#713](#713) + Various simplification and fixes to the Windows CMake setup. [#720](#720), [#785](#785) + Simplify third-party integration. [#786](#786) + Improve Ginkgo device arch flags management. [#696](#696) + Other fixes and improvements to the CMake setup. [#685](#685), [#792](#792), [#705](#705), [#836](#836) + Clarification of dense norm documentation [#784](#784) + Various development tools fixes and improvements [#738](#738), [#830](#830), [#840](#840) + Make multiple operators/constructors explicit. [#650](#650), [#761](#761) + Fix some issues, memory leaks and warnings found by MSVC. [#666](#666), [#731](#731) + Improved solver memory estimates and consistent iteration counts [#691](#691) + Various logger improvements and fixes [#728](#728), [#743](#743), [#754](#754) + Fix for ForwardIterator requirements in iterator_factory. [#665](#665) + Various benchmark fixes. [#647](#647), [#673](#673), [#722](#722) + Various CI fixes and improvements. [#642](#642), [#641](#641), [#795](#795), [#783](#783), [#793](#793), [#852](#852) Related PR: #857
The `test_install` folder was moved to `test` with ginkgo-project/ginkgo#733.
Release 1.4.0 to master The Ginkgo team is proud to announce the new Ginkgo minor release 1.4.0. This release brings most of the Ginkgo functionality to the Intel DPC++ ecosystem which enables Intel-GPU and CPU execution. The only Ginkgo features which have not been ported yet are some preconditioners. Ginkgo's mixed-precision support is greatly enhanced thanks to: 1. The new Accessor concept, which allows writing kernels featuring on-the-fly memory compression, among other features. The accessor can be used as header-only, see the [accessor BLAS benchmarks repository](https://github.com/ginkgo-project/accessor-BLAS/tree/develop) as a usage example. 2. All LinOps now transparently support mixed-precision execution. By default, this is done through a temporary copy which may have a performance impact but already allows mixed-precision research. Native mixed-precision ELL kernels are implemented which do not see this cost. The accessor is also leveraged in a new CB-GMRES solver which allows for performance improvements by compressing the Krylov basis vectors. Many other features have been added to Ginkgo, such as reordering support, a new IDR solver, Incomplete Cholesky preconditioner, matrix assembly support (only CPU for now), machine topology information, and more! Supported systems and requirements: + For all platforms, cmake 3.13+ + C++14 compliant compiler + Linux and MacOS + gcc: 5.3+, 6.3+, 7.3+, all versions after 8.1+ + clang: 3.9+ + Intel compiler: 2018+ + Apple LLVM: 8.0+ + CUDA module: CUDA 9.0+ + HIP module: ROCm 3.5+ + DPC++ module: Intel OneAPI 2021.3. Set the CXX compiler to `dpcpp`. + Windows + MinGW and Cygwin: gcc 5.3+, 6.3+, 7.3+, all versions after 8.1+ + Microsoft Visual Studio: VS 2019 + CUDA module: CUDA 9.0+, Microsoft Visual Studio + OpenMP module: MinGW or Cygwin. Algorithm and important feature additions: + Add a new DPC++ Executor for SYCL execution and other base utilities [#648](#648), [#661](#661), [#757](#757), [#832](#832) + Port matrix formats, solvers and related kernels to DPC++. For some kernels, also make use of a shared kernel implementation for all executors (except Reference). [#710](#710), [#799](#799), [#779](#779), [#733](#733), [#844](#844), [#843](#843), [#789](#789), [#845](#845), [#849](#849), [#855](#855), [#856](#856) + Add accessors which allow multi-precision kernels, among other things. [#643](#643), [#708](#708) + Add support for mixed precision operations through apply in all LinOps. [#677](#677) + Add incomplete Cholesky factorizations and preconditioners as well as some improvements to ILU. [#672](#672), [#837](#837), [#846](#846) + Add an AMGX implementation and kernels on all devices but DPC++. [#528](#528), [#695](#695), [#860](#860) + Add a new mixed-precision capability solver, Compressed Basis GMRES (CB-GMRES). [#693](#693), [#763](#763) + Add the IDR(s) solver. [#620](#620) + Add a new fixed-size block CSR matrix format (for the Reference executor). [#671](#671), [#730](#730) + Add native mixed-precision support to the ELL format. [#717](#717), [#780](#780) + Add Reverse Cuthill-McKee reordering [#500](#500), [#649](#649) + Add matrix assembly support on CPUs. [#644](#644) + Extends ISAI from triangular to general and spd matrices. [#690](#690) Other additions: + Add the possibility to apply real matrices to complex vectors. [#655](#655), [#658](#658) + Add functions to compute the absolute of a matrix format. [#636](#636) + Add symmetric permutation and improve existing permutations. [#684](#684), [#657](#657), [#663](#663) + Add a MachineTopology class with HWLOC support [#554](#554), [#697](#697) + Add an implicit residual norm criterion. [#702](#702), [#818](#818), [#850](#850) + Row-major accessor is generalized to more than 2 dimensions and a new "block column-major" accessor has been added. [#707](#707) + Add an heat equation example. [#698](#698), [#706](#706) + Add ccache support in CMake and CI. [#725](#725), [#739](#739) + Allow tuning and benchmarking variables non intrusively. [#692](#692) + Add triangular solver benchmark [#664](#664) + Add benchmarks for BLAS operations [#772](#772), [#829](#829) + Add support for different precisions and consistent index types in benchmarks. [#675](#675), [#828](#828) + Add a Github bot system to facilitate development and PR management. [#667](#667), [#674](#674), [#689](#689), [#853](#853) + Add Intel (DPC++) CI support and enable CI on HPC systems. [#736](#736), [#751](#751), [#781](#781) + Add ssh debugging for Github Actions CI. [#749](#749) + Add pipeline segmentation for better CI speed. [#737](#737) Changes: + Add a Scalar Jacobi specialization and kernels. [#808](#808), [#834](#834), [#854](#854) + Add implicit residual log for solvers and benchmarks. [#714](#714) + Change handling of the conjugate in the dense dot product. [#755](#755) + Improved Dense stride handling. [#774](#774) + Multiple improvements to the OpenMP kernels performance, including COO, an exclusive prefix sum, and more. [#703](#703), [#765](#765), [#740](#740) + Allow specialization of submatrix and other dense creation functions in solvers. [#718](#718) + Improved Identity constructor and treatment of rectangular matrices. [#646](#646) + Allow CUDA/HIP executors to select allocation mode. [#758](#758) + Check if executors share the same memory. [#670](#670) + Improve test install and smoke testing support. [#721](#721) + Update the JOSS paper citation and add publications in the documentation. [#629](#629), [#724](#724) + Improve the version output. [#806](#806) + Add some utilities for dim and span. [#821](#821) + Improved solver and preconditioner benchmarks. [#660](#660) + Improve benchmark timing and output. [#669](#669), [#791](#791), [#801](#801), [#812](#812) Fixes: + Sorting fix for the Jacobi preconditioner. [#659](#659) + Also log the first residual norm in CGS [#735](#735) + Fix BiCG and HIP CSR to work with complex matrices. [#651](#651) + Fix Coo SpMV on strided vectors. [#807](#807) + Fix segfault of extract_diagonal, add short-and-fat test. [#769](#769) + Fix device_reset issue by moving counter/mutex to device. [#810](#810) + Fix `EnableLogging` superclass. [#841](#841) + Support ROCm 4.1.x and breaking HIP_PLATFORM changes. [#726](#726) + Decreased test size for a few device tests. [#742](#742) + Fix multiple issues with our CMake HIP and RPATH setup. [#712](#712), [#745](#745), [#709](#709) + Cleanup our CMake installation step. [#713](#713) + Various simplification and fixes to the Windows CMake setup. [#720](#720), [#785](#785) + Simplify third-party integration. [#786](#786) + Improve Ginkgo device arch flags management. [#696](#696) + Other fixes and improvements to the CMake setup. [#685](#685), [#792](#792), [#705](#705), [#836](#836) + Clarification of dense norm documentation [#784](#784) + Various development tools fixes and improvements [#738](#738), [#830](#830), [#840](#840) + Make multiple operators/constructors explicit. [#650](#650), [#761](#761) + Fix some issues, memory leaks and warnings found by MSVC. [#666](#666), [#731](#731) + Improved solver memory estimates and consistent iteration counts [#691](#691) + Various logger improvements and fixes [#728](#728), [#743](#743), [#754](#754) + Fix for ForwardIterator requirements in iterator_factory. [#665](#665) + Various benchmark fixes. [#647](#647), [#673](#673), [#722](#722) + Various CI fixes and improvements. [#642](#642), [#641](#641), [#795](#795), [#783](#783), [#793](#793), [#852](#852) Related PR: #866
What?
This PR adds the capability to implement simple kernels with a uniform syntax across all executors:
Why?
This might help simplify our solver porting efforts for SYCL, and also allow us to execute custom operations on our data in examples transparently across executors, like I am doing in #701 on the CPU.
How?
It works in
twothree steps:alpha, x, y
to intermediate device representations. The mappings right now are:matrix::Dense<ValueType>*
->matrix_accessor<ValueType>
Array<ValueType>*
->ValueType*
T*
->T*
(the disambiguation here is currently a bit hacky and limited to arithmetic types)compact(...)
andvector(...)
which omit (vector -> ValueType*
) or infer the stride from kernel dimensions (compact -> matrix_accessor<ValueType>
)By wrapping the input objects in wrapper types, we could implement more specific semantics like
pointwise
for(row, col)
, colwise for(0, col)
, rowwise for(row, 0)
or scalar for(0, 0)
. This could simplify the example toor even
if we added optional
row_index()
andcolumn_index()
pseudo parameters torun_kernel
I had to re-implement a tiny accessor replacement, since the value semantics implemented by
gko::range
don't work well in this generic context.Finally,
GKO_KERNEL
is defined to be empty for CPU and SYCL or__device__
for CUDA and HIP.TODO
We now specify a different stride for each matrix parameter. Does that matter, or is constant memory fast enough anyways?This is no longer true, we use compact representations now