Nuno Nobre
Nuno Nobre
Alternatives for non-standard sub_group::shuffle_up/down/xor and yet-to-be-implemented atomic_fence
Hi @illuhad, I've been trying to compile a project written in SYCL which also uses a few DPC++ extensions. 1) I'm aware [`sub_group::shuffle_up/down/xor`](https://intel.github.io/llvm-docs/doxygen/structcl_1_1sycl_1_1ext_1_1oneapi_1_1sub__group.html) are not part of the standard, but...
In addition to these small typos I found while revising #1554, I also noticed that the [example](https://github.com/stfc/PSyclone/blob/ba35a86a1e13f1f266d2ba4e637621d1ae39939c/src/psyclone/transformations.py#L2606-#L2632) we give for ACCEnterDataTrans wouldn't actually add the directive by lack of a...
Hi, I'm a bit confused so I'll try my best to not make a mess of this... 1) When compiling with the Intel classic compilers, CMake uses -O3 whereas the...
In the following excerpt, `kjcnt` changes on different calls to `mpp_init_readbot_strip` causing a runtime error with the current implementation. In addition to checking if the array is allocated, we should...
This is a compilation of the outstanding issues and unimplemented features in the OpenACC enter data and update directives implementation efforts in #310 and #1554. 1) Distinguishing between array accesses...
Hi Alex (@lindsayad), I thought it'd be a good idea to read a bit on AD, since it's been such a stone in my shoe recently. 😅 So, why do...
Hi Alex, The idea here is to try to strongly impose Dirichlet boundary conditions on problems in H(div) because nobody likes penalties that much. It's our understanding the only support...
Hi @jwpeterson, Regarding the warning messages you're seeing in the newest vector examples: > As discussed over slack with @roystgnr, we may have a missing FE pre-request somewhere which is...
Forgot this when we initially implemented H(div) conforming elements, but I'm pretty sure the tangential component would need to be averaged in the same way the normal component needs to...
Hi Aksel, Less than a year later, I'm trying to bring it full circle here. 🥳 This (properly) closes #767. Let me know what you think so far. I haven't...