search for: narayanaswami

Displaying 9 results from an estimated 9 matches for "narayanaswami".

Did you mean: narayanaswamy
2019 Jun 06
2
Webpage to track implementation status of OpenMP features
Yes, I understand. I just don't understand why there are 15 review links. as to the format of the list, we previously had a list of feature for 4.5 (before it was fully supported), we can reuse this old format. Best regards, Alexey Bataev > 6 июня 2019 г., в 19:12, Narayanaswamy, Ravi <ravi.narayanaswamy at intel.com> написал(а): > > Alexey, > Johannes want to put all
2019 Jun 06
2
Webpage to track implementation status of OpenMP features
I don't know where it comes from, currently there is just 2 patches with the new functionality : mapper implementation in clang and in the runtime. Plus the patch for unified memory. Best regards, Alexey Bataev > 6 июня 2019 г., в 19:03, Doerfert, Johannes <jdoerfert at anl.gov> написал(а): > >> On 06/06, Alexey Bataev via llvm-dev wrote: >> Hmm, it is
2019 Jun 06
2
Webpage to track implementation status of OpenMP features
Hmm, it is interesting. What's missing? and why it is "a lot". It is the status for clang 8.0. There were not too many changes in trunk since last release. Best regards, Alexey Bataev 6 июня 2019 г., в 8:24, Doerfert, Johannes via llvm-dev <llvm-dev at lists.llvm.org<mailto:llvm-dev at lists.llvm.org>> написал(а): Thanks for pointing that one out to me! It's a
2018 Mar 01
0
libomptarget code owner.
Haven't seen any discussions here. Does that mean that everybody agree on appointing George Rokos to be the code owner for the projects/openmp/libomptarget source tree? If so, can we have kind of formal approval so that the code_owners.txt file is updated and questions on libomptarget go to the right person then. BTW, the nominee was discussed at the libomptarget developers meeting,
2018 Jan 24
2
libomptarget code owner.
Hi, Currently libomptarget has no code owner. Although it is part openmp project the expertise required for libomptarget is different from openmp. Georgios Rokos from IBM has agreed to be the owner of libomptarget source, so I would like to nominate Georgios Rokos who is a major contributor to libomptarget. Thanks Ravi -------------- next part -------------- An HTML attachment was
2019 Jun 06
5
Webpage to track implementation status of OpenMP features
Long story short: We want to create a webpage under llvm.org that shows the implementation status of OpenMP features, similar to https://clang.llvm.org/cxx_status.html . Please let me know if you have wishes, questions, or concerns. Cheers, Johannes
2018 Apr 27
2
[LLVM][RFC] Representing the target device information in the LLVM IR
On 04/26/2018 07:03 PM, Narayanaswamy, Ravi wrote: > > Hi Hal, > >    We are not trying to address issues where the object mapped are of > different sizes between host and target with different ABI. > Why are you not trying to address that issue?  -Hal > The issue is when the objects are of same size like double which is > 8bytes on both 32bit and 64bit
2018 Apr 27
0
[LLVM][RFC] Representing the target device information in the LLVM IR
Hi Hal, We are not trying to address issues where the object mapped are of different sizes between host and target with different ABI. The issue is when the objects are of same size like double which is 8bytes on both 32bit and 64bit platform. If a double is used in a first_private on a target clause, the 64 bit side will pass it as value whereas on the 32bit side since the value does not
2018 Apr 26
4
[LLVM][RFC] Representing the target device information in the LLVM IR
For the firstprivate clause, the compiler generates code to pass it by value or by reference to the outlined function. The reason the first private scalars is generally passed by value is for the performance reason. For this particular case, the compiler cannot generate code to pass the double @gg by value under i386-pc-linux-gnu since the value is 64 bit while the architecture is 32bit. For the