Cuda - improve variable name clarity

CUDA - drop double negation

CUDA - clean up logic for collograd in cuda/gen, should be based on all bases with interp/grad

Merge pull request #617 from CEED/jeremy/travis-occa-arm

Travis - drop OCCA testing from ARM64 until memory bug is fixed

Travis - drop OCCA testing from ARM64 until memory bug is fixed

Merge pull request #613 from CEED/jeremy/extra-casts

CUDA - drop extra casts

CUDA - drop extra casts

Update 'factored form' link in README.rst (#615)

Point to more appropriate page in documentation.

Merge pull request #614 from CEED/yohann/fix-cuda-gen

Fix a bug in the Cuda-gen backend

Merge branch 'main' into yohann/fix-cuda-gen

Access the restriction before using it.

Merge pull request #612 from jrwrigh/patch-1

Update API documentation link on README

Update other link

Update API link on README

Merge pull request #609 from CEED/jeremy/release-notes

Doc - update release notes

Doc - update release notes to include OCCA update

Doc - update release notes

OCCA Backend Update (#305)

* [Docs] Update docs for new OCCA backend

* [Fortran] CeedVectorRestoreArray fix

* [Test] Updates t002-ceed test to support query params

* [Make] Adds tidy for cp

OCCA Backend Update (#305)

* [Docs] Update docs for new OCCA backend

* [Fortran] CeedVectorRestoreArray fix

* [Test] Updates t002-ceed test to support query params

* [Make] Adds tidy for cpp files

* [OCCA] Updates OCCA backend

* PR feedback: Update StrideType naming

* PR feedback: Fixed USER_STRIDES vs BACKEND_STRIDES usage

* [OCCA] Add comments to code generation

* [CI] Removes commit from OCCA build

* PR Feedback: Update README

* PR Feedback: Removed compiler warnings

* Fix restriction function changes

* occa: track AssembleLinear -> LinearAssemble

* [OCCA][Vector] Adds takeArray method

* [OCCA][Restriction] Fixes restriction strides

* [OCCA][Operator] Adds point block diagonal registration

* [OCCA][Operator] Fixes

* OCCA - update debug color for visability

* Travis - fix extra fi

* OCCA - adjust kernel, multi component derivatives are expected as [dim][comp][q]

* OCCA - adjust basis kernel args in operator kernel to agree with expected [dim][comp][q] ordeing

* OCCA - fix uninitalized memory in grad transpose 3d kernel

* OCCA - fix Elayout description

* OCCA - fix bad dimensions in basis kernel

* OCCA - fix TakeArray to sync before returning array pointer

* MFEM - print error when test fails

* OCCA - fix 2d grad kernels

* OCCA - flag digonal of composite operators unsupported

* OCCA - fix restoreArray logic

* OCCA - minor cleanup with GPU

* Travis - add 'make info' where able for debugging

* OCCA - explictily test OpenCL mode

* OCCA - drop restrict for ElemRestriction kernels, OpenCL doesn't like it

* OCCA - explicitly test cuda and hip versions of OCCA backend

* OCCA - explicitly test OpenMP mode in OCCA

* Tests - modify check for VLA support for OCCA to catch all OCCA modes

* WIP - test possible OCCA fix for PowerPC

* OCCA - separate CPU modes for testing as well

* Readme - update list of OCCA backend modes

* Makefile - fix unterminated addprefix

* OCCA - enable direct access to OCCA Serial mode

* OCCA - add comments to registration

* Makefile - remove extra )

* OCCA - remove pass by reference C++ syntax for OpenCL compatability

* OCCA - drop use of @restrict for OpenCL

* OCCA - remove OpenCL mode, not fully supported in OCCA (see OCCA issue #166)

* OCCA - fixing rebase issues

* OCCA - Fix implementation of QFunctionContext

* OCCA - move GetContextSize so ierr check actually works

* Travis - use libOCCA instead of jeremylt/occa

* Junit - update OCCA test skip list

* Make - simplify OCCA check for enabled modes

Co-authored-by: Jed Brown <jed@jedbrown.org>
Co-authored-by: Jeremy L. Thompson <jeremy.thompson@colorado.edu>

show more ...

Merge pull request #608 from CEED/jeremy/hip-short

Hip - shorten up resource strncmp

Hip - shorten up resource strncmp to remove requirement for trailing slash with /gpu/hip

Merge pull request #607 from CEED/jeremy/more-hash

Hash - add additional hash key lengths

Hash - simplify multi key equality check

Hash - add additional hash key lengths

QFunction Context Data Object (#596)

* Ctx - create context object for QFunction context data

* Context - rename UserContext -> QFunctionContext

* Ctx - add lcov markers

* Ctx - fix leak in

QFunction Context Data Object (#596)

* Ctx - create context object for QFunction context data

* Context - rename UserContext -> QFunctionContext

* Ctx - add lcov markers

* Ctx - fix leak in identity QFunctions

* Hip/Cuda - rename sync functions for vector/context

* Tests - lcov marker update

* QFunction - drop unused function

* Python - fix copy-paste errors

* Ctx - update notes for Fortran usage

* Fortran - drop unneeded cast

Co-authored-by: Jed Brown <jed@jedbrown.org>

* Interface - use void* for SetData interfaces

* Make - use call quiet for NVCC

* Interface - use void* for GetData interfaces

* Make - add quiet call option for examples

* Makefile - create common makefile to reduce duplication/complexity in example makefiles

Co-authored-by: Jed Brown <jed@jedbrown.org>

show more ...

README: fix alt-text for badges