-
NVIDIA
- Sunnyvale, CA
Highlights
- Pro
Popular repositories Loading
-
cppnow_presentations_2016
cppnow_presentations_2016 PublicPresentation materials for C++Now 2016
-
cub_historical_2019_2020
cub_historical_2019_2020 PublicForked from NVIDIA/cub
Cooperative Primitives for CUDA C++ Kernel Authors. This repository contains CUB PRs from Q4 2019 until Q4 2020.
-
wg21_p2300_execution
wg21_p2300_execution Public`std::execution`, the proposed C++ framework for asynchronous and parallel programming.
-
2016_berkeley_cpp_summit_presentations
2016_berkeley_cpp_summit_presentations PublicPresentation materials for the 2016 Berkeley C++ Summit
-
boost.lockfree
boost.lockfree PublicHartmut Kaiser and Bryce Lelbach's version of Boost.Lockfree
156 contributions in the last year
Day of Week | March Mar | April Apr | May May | June Jun | July Jul | August Aug | September Sep | October Oct | November Nov | December Dec | January Jan | February Feb | March Mar | ||||||||||||||||||||||||||||||||||||||||
Sunday Sun | |||||||||||||||||||||||||||||||||||||||||||||||||||||
Monday Mon | |||||||||||||||||||||||||||||||||||||||||||||||||||||
Tuesday Tue | |||||||||||||||||||||||||||||||||||||||||||||||||||||
Wednesday Wed | |||||||||||||||||||||||||||||||||||||||||||||||||||||
Thursday Thu | |||||||||||||||||||||||||||||||||||||||||||||||||||||
Friday Fri | |||||||||||||||||||||||||||||||||||||||||||||||||||||
Saturday Sat |
Contribution activity
March 2025
Created 4 commits in 2 repositories
Created 3 repositories
-
brycelelbach/accelerated-computing-hub
Jupyter Notebook
This contribution was made on Mar 14
-
brycelelbach/2D-wave-equation
Python
This contribution was made on Mar 5
-
brycelelbach/octopus
C++
This contribution was made on Mar 5
Created a pull request in NVIDIA/cccl that received 16 comments
[Thrust] Perform asynchronous allocations by default for the par_nosync
policy
This will make algorithms (like scans) that don't have a computation-dependent result but do temporary allocation properly asynchronous under par_n…
Opened 3 other pull requests in 2 repositories
NVIDIA/cccl
2
merged
-
[thrust, docs] Use the variadic overload of
make_zip_iterator
in thezip_iterator
docsThis contribution was made on Mar 12 -
Fix bad link in Thrust docs landing page
This contribution was made on Mar 10
NVIDIA/accelerated-computing-hub
1
merged
-
[CUDA Python and CUDA C++ Tutorial]: Change the default Google Colab instance to a T4 GPU instance
This contribution was made on Mar 16
Reviewed 2 pull requests in 1 repository
NVIDIA/cccl
2 pull requests
-
[Thrust] Perform asynchronous allocations by default for the
par_nosync
policyThis contribution was made on Mar 22 -
Improve dtype handling.
This contribution was made on Mar 4
Created an issue in NVIDIA/cccl that received 6 comments
Rename cuda::experimental::managed_memory_resource
to cuda::experimental::unified_memory_resource
"Managed memory" is a terrible and unclear name for the CUDA Unified Memory feature, and it may be particularly confusing to C++ users, as there is…
Opened 26 other issues in 2 repositories
NVIDIA/cccl
7
closed
18
open
-
cudax::device_memory_resource
doesn't seem to haveallocate_async
This contribution was made on Mar 19 -
Symlinks to Markdown files in
libcudacxx/
are badThis contribution was made on Mar 19 -
[DOC]: Thrust offset iterator docs are missing from fancy iterator page
This contribution was made on Mar 17
-
_CUB_RETURN_IF_STATUS
macros don't belong in <cub/device/dispatch/dispatch_for_each_in_extents.cuh>This contribution was made on Mar 17 -
Thrust
execution_policy::on
should take a stream_ref in addition to a streamThis contribution was made on Mar 14 -
cudax::stream::wait()
blocks the caller, whilecudax::stream::wait(event_ref)
does notThis contribution was made on Mar 13 -
[FEA] and [DOC]: Diagnostic when
par_nosync
is used but the algorithm will block anyways.This contribution was made on Mar 12 -
[FEA]: Thrust algorithms invoked with
par_nosync
should asynchronously allocate temporary storageThis contribution was made on Mar 12 -
thrust::make_zip_iterator
accepts variadic arguments instead of athrust::tuple
, butthrust::zip_iterator
's constructor does notThis contribution was made on Mar 12 -
[DOC]: "See also" references in Thrust docs do not actually link to the other entity
This contribution was made on Mar 12
-
Range view versions of Thrust/CUB iterators and range-based algorithm interfaces
This contribution was made on Mar 12
-
[DOC]: No docs for
thrust::allocate_unique
This contribution was made on Mar 12 -
[DOC]: No docs for
thrust::universal_vector
,thrust::universal_allocator
, etcThis contribution was made on Mar 12 -
make_buffer
and execution space properties on buffer typesThis contribution was made on Mar 11 -
Experimental feature enablement macros are overkill
This contribution was made on Mar 11
-
[BUG]: Some CUDA experimental memory resource headers do not properly warn if the enable macro is not defined
This contribution was made on Mar 11
-
cudax::*_memory_resource
should be an object not a typeThis contribution was made on Mar 11 -
[DOC]: A bunch of
cudax
memory resources aren't showing up in the docsThis contribution was made on Mar 11 -
[DOC]: Examples of synchronous buffer usage needed
This contribution was made on Mar 11
-
[FEA] We have
async_buffer(mr, count, uninit)
but notbuffer(mr, count, uninit)
This contribution was made on Mar 11 -
[FEA] Missing binary-binary
thrust::transform_reduce
overloadThis contribution was made on Mar 11 -
CUB implicit temp storage algorithm overlodas
This contribution was made on Mar 8
-
thrust::*_into algorithms to expose more asynchrony
This contribution was made on Mar 8
-
<cuda/experimental/buffer.cuh> doesn't include cudax::buffer
This contribution was made on Mar 8
-
Maintain richer docstrings in cuda.cooperative
This contribution was made on Mar 2
NVIDIA/accelerated-computing-hub
1
open
-
[BUG]: Opening the tutorial notebooks in Colab defaults to a runtime that doesn't have CUDA/a GPU installed.
This contribution was made on Mar 14