Release 0.4.0-rc4 #2717
Merged
Release 0.4.0-rc4 #2717
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
sbastrakov
reviewed
Oct 5, 2018
include/picongpu/version.hpp
Outdated
| @@ -1,4 +1,5 @@ | |||
| /* Copyright 2015-2018 Axel Huebl | |||
| /* Copyright 2015-2018 Axel Hueblrc3 | |||
There was a problem hiding this comment.
Yes, thx. Just wanted open it already. Will fix
ax3l
force-pushed
the
release-0.4.0-rc4
branch
from
550e6a8 to
3b1ba07
Compare
ax3l
added
component: third party
replace `map()` by list comprehension, correct spelling error in comment
Fix readthedocs sphinx to version 1.7 since the latest 1.8 release line has a bug rendering overloaded C++ code with breathe.
Document more modern compilers for Spack install method. By default, spack takes the latest supported (CUDA) version which supports GCC 7. Document older releases with according older GCC as alternatives.
fix ComputationalRadiationPhysics#2714 Boost is shipping there swap implementation with support for the device side if `BOOST_GPU_ENABLED` is `__host__ __device__` but is calling a pure host function `std::swap` within the device code. Even if swap is not called on the device this implementation can pull host only code inside the device compile path of CUDA. - provide a device side empty implementation for swap if the arguments are `std:.string`
21050ab1b Merge pull request ComputationalRadiationPhysics#17 from ComputationalRadiationPhysics/fix-nvmlUnsupportedDevice 86303be74 NVML: Handle Unsupported GPU git-subtree-dir: thirdParty/cuda_memtest git-subtree-split: 21050ab1b851944e3f9f64348a43abe966ac5379
- add tbg templates for hemera (HZDR) cluster CPU/GPU - add hemera profiles - update documentation
`cuda_memtest` can currently only be used if the node is exclusive allocated by the user and no other job is running on it. All hypnos template files for hypnos supports that the user can allocate only a subset of a node. In this case `cuda_memtest` will crash if an other user/job is already using gpu zero. This PR will disable the GPU memory test if the job has not alloacted all GPUs. - remove PBS option `-n` (exclusive node usage) because it is not working on hypnos - disable the test `cuda_memtest` if node is not exclusive allocated
309787260 Merge pull request ComputationalRadiationPhysics#684 from ComputationalRadiationPhysics/release-0.3.4 af5f0046c Merge pull request ComputationalRadiationPhysics#678 from psychocoderHPC/topic-backPortQueueReg fcea5e924 Fixed broken `alpaka::math::min` for non-integral types 3908b778d Remove noexcept(false) from destructor 4eee8a54a Allow to run alpaka OpenMP 2 block accelerated kernels within existing parallel region 0216e925f Remove explicit queue deregistration from device because this could throw in destructors dd5da1a3c Further improve compile time a00b128bb Improve compile-time 510d94c5a Merge pull request ComputationalRadiationPhysics#669 from ax3l/bp-034-part2 f5193bd68 AppVeyor: Update from dev f2b7cc3a5 Check definition of __GLIBCXX__ first. Fixes ComputationalRadiationPhysics#671. 82c7a6d8a ViewStdContainers: Predef Work-Around b3b786c47 Assert: Fix Usage of Unused af06b72fe Fix warning about comparison unsigned < 0 f73c9fd37 Fix tests using std::int16_t overflowing e1178b3c1 Fix static_casts leading to overflows. bfb42b35b Add a check for OpenMP version f3168f596 Glibc < 2.18: Fix Missing Macros 431aea324 Added `alpaka::ignore_unused` for unused parameter efa121609 Added prepareForAsyncCopy trait and specialization for cpu and cuda memory, see https://github.com/ComputationalRadiationPhysics/alpaka/issues/620 4f8def8aa CUDA: Math & Public Headers 3011db8ef Merge pull request ComputationalRadiationPhysics#657 from psychocoderHPC/topic-backport_Dev_To_0.3.4 d1ec82961 fix variable nameing 6660a7d40 re-add `BOOST_ARCH_CUDA_DEVICE` 813d7d18f Fix empty(StreamCpuAsync) returning true even though the last task is still executing ad1140611 incorporate review comments db321f917 Use internal BoostPredef.hpp b6b3ceb1d Add comment for intel workaround 098b2da67 Work around BOOST_COMP_NVCC detection setting BOOST_COMP_NVCC_EMULATED ae1b11d85 Fix crt/math_functions.hpp workaround being based on BOOST_LANG_CUDA git-subtree-dir: thirdParty/alpaka git-subtree-split: 3097872604996f437d6acb7db42bad4237c5d1f3
Warn in PMacc config on newer versions of both, since likely troublesome.
Move to `data/` subdirectory. Adjust manuals accordingly.
Allow Numpy-style Python autodocs for classes, modules and members with Napoleon.
Add section on postproc tools (PNG, Energy Histogram, PS). Devel: Architecture of postprocessing tools.
Update projects around openPMD and link openPMD-api.
Changed to "PIConGPU - particle-in-cell simulations for the exascale era" Thanks everyone! :)
This pull request fixes a configuration typo.
Fix module init file and link new docs into main sphinx document.
Co-authored-by: PrometheusPi <r.pausch@hzdr.de>
remove mapping display and tag output from startup. make output less verbose
OpenMPI: Use 2.1.2 Multi-Rank MPI support and thus multi-GPU support requires for in-node communication a BTL such as "sm" which was replaced with "vader" in OpenMPI 3.0.0. "vader" requires CMA support from the kernel which seems to be something that is not working in a docker container. We therefore switch back to an older release (pre-3.0) of OpenMPI that still has the (slower) "sm" transport. Build for SM_70 (V100) Docker Readme: MPI BTL shared Mem Overwrite exising output with tbg -f Configurable output directory and print to user. Use non-ISAAC examples for now. Add _live LWFA examples for later testing of ISAAC.
psychocoderHPC
approved these changes
Oct 18, 2018
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.
Collection of all relevant PRs for the
release-0.4.0branch in the next days/weeks.Update to
0.4.0-rc4.Bug Fixes
Misc
0.4.0-rc4CHANGELOG.mdwith rc2, rc3 and rc4 changesPython: update all libs and manual docs to latest
devlevels: