335 Commits

Author SHA1 Message Date
shawnz
7f5390cec3 Bug 5323124: Waive simpleAWBarrier on QNX 2025-06-10 15:14:33 +08:00
shawnz
5f6d46dfea Bug 5323018: Update the CMakeLists.txt and Common/helper_multiprocess.cpp of ptxjit and memMapIPCDrv for QNX cross build 2025-06-09 19:53:25 +08:00
shawnz
49307463b5 Bug 5133216: Add QNX tooltrain and cross build support 2025-05-29 16:57:28 +08:00
Rob Armstrong
9c0d5aaae6 Merge branch 'shawnz_bug_fix' into 'master'
Bug 5305842 and 5305854: Update CMakeLists for SBSA CUDA Toolkit support on aarch64-linux platforms

See merge request cuda-samples/cuda-samples!115
2025-05-28 08:26:16 -07:00
shawnz
0d08748ffa Bug 5305842: Update CMakeLists.txt for cdp samples for sbsa CUDA Toolkit supporting on aarch64-linux platforms 2025-05-28 11:42:49 +08:00
Rob Armstrong
27f47634a0 Merge branch 'shawnz_bug_fix' into 'master'
Bug 5300528: Add MPI_C_LIBRARIES for user defined MPI path

See merge request cuda-samples/cuda-samples!114
2025-05-23 07:57:54 -07:00
shawnz
40d297dfe7 Bug 5300528: Add MPI_C_LIBRARIES for user defined MPI path 2025-05-23 14:47:55 +08:00
Rob Armstrong
20b90b5063 Merge public 12.9 changes into 13.0 dev 2025-05-22 11:45:07 -07:00
Rob Armstrong
8a9e2c830c
Update 1_Utilities/README.md to redirect bandwidthTest to NVBandwidth (#371) 2025-05-22 11:43:14 -07:00
Rob Armstrong
f47f06f077 Merge branch 'shawnz_bug_fix' into 'master'
Update the CMAKE_CUDA_ARCHITECTURES from 50 to 75 for Samples/7_libNVVM/cuda-c-linking

See merge request cuda-samples/cuda-samples!113
2025-05-22 08:16:44 -07:00
shawnz
0c78a3e0de Update the CMAKE_CUDA_ARCHITECTURES from 50 to 75 for Samples/7_libNVVM/cuda-c-linking 2025-05-22 15:52:51 +08:00
Rob Armstrong
8219570c15 Merge branch 'shawnz_bug_fix' into 'master'
Bug fix for 5280038, 5277193, 5281036 and 5294720

See merge request cuda-samples/cuda-samples!112
2025-05-21 10:51:12 -07:00
Rob Armstrong
fc88988f23 Merge public changes to internal ToT 2025-05-21 09:28:35 -07:00
shawnz
1141dd7af4 Bug 5281036: Limit the register number of debug version for cdpAdvancedQuicksort 2025-05-20 14:47:44 +08:00
shawnz
da3b7a2b3c Update the vulkanImageCUDA/vulkanImageCUDA.cu for Windows headers 2025-05-19 17:43:08 +08:00
shawnz
5987a9e9fa Update transpose for code format check 2025-05-19 17:38:42 +08:00
shawnz
107f3f537f Update the include files sequence for vulkan samples on Windows 2025-05-19 17:38:22 +08:00
shawnz
c1b03b9f81 Bug 5277193: Remove the CUFFT_LICENSE_ERROR checking as it is deprecated since CUDA13.0 2025-05-16 11:21:07 +08:00
shawnz
ee0ee417c9 Update the sample list for API changes in CHANGELOG 2025-05-14 16:02:17 +08:00
shawnz
ebc1078379 Bug 5280038: Update cuda-c-linking as per CUDA 13.0 API change 2025-05-14 15:54:41 +08:00
Rob Armstrong
2861e78272 Merge branch 'peggyt_bug_fix' into 'master'
Bug 5056055: limit register usage to 128 per thread in debug mode

See merge request cuda-samples/cuda-samples!110
2025-05-12 08:55:45 -07:00
shawnz
8f33cc6094 Bug 5274280: Enable 8_Platform_Specific/Tegra/EGLSync_CUDAEvent_Interop 2025-05-12 15:02:31 +08:00
shawnz
2ec9cf394a Bug 5272236: Update the include file copy path as path changes on 13.0 2025-05-12 15:00:52 +08:00
Peggy Tian
770e433a9e Bug 5056055: limit register usage to 128 per thread in debug mode to comply with the maximum number of 32-bit registers per SM 2025-05-12 06:04:22 +00:00
Rob Armstrong
c6af90553e Merge branch 'master' into 'master'
Bug 5236593: Increase the pending kernel launch limit to 4096

See merge request cuda-samples/cuda-samples!109
2025-05-07 09:47:51 -07:00
Peggy Tian
611008fa86 Bug 5236593: Increase the pending kernel launch limit to 4096 2025-05-07 17:38:52 +08:00
shawnz
bf628887f1 Bug 5217339: Replace SM 101 with 110 for Thor 2025-05-07 14:10:35 +08:00
Rob Armstrong
330dd8472f Merge external PR #363 2025-05-05 08:45:01 -07:00
Francesco Rizzi
b530f1cf42
Fix bug in 6_Performance/transpose: copy sharedmem kernel (#363)
Update kernel loop bounds handling, main loop data copy to avoid incorrect reuse of output results.

---------

Authored-by: Francesco Rizzi <francesco.rizzi@ng-analytics.com>
2025-05-05 08:43:23 -07:00
Rob Armstrong
f2645c5df8 Final merge of 12.9 changes into cuda_a_dev 2025-05-01 09:55:03 -07:00
Rob Armstrong
c70d79cf3b Final 12.9 README updates 2025-05-01 09:39:06 -07:00
Rob Armstrong
9ac81370fa Update 12.9 changes from 'master' into 'cuda_a_dev' 2025-04-30 09:48:21 -07:00
Rob Armstrong
14b1bfdcc4 Replace README references to "CUDA Toolkit 12.5" with general "CUDA Toolkit" 2025-04-30 09:46:45 -07:00
shawnz
b27b55ec70 Bug 5241914: Fix the error message for cuSolverDn_LinearSolver 2025-04-27 16:57:02 +08:00
shawnz
49159f3739 Bug 5164417 and 5097376: Fix the OpenMP issue finding issue for MSVC and Glang 2025-04-27 16:50:12 +08:00
Rob Armstrong
93cafa8fe9 Update 12.9 changes from 'master' into 'cuda_a_dev' 2025-04-21 09:22:29 -07:00
shawnz
a45fd3bd7c Bug 5199167: Fix the includes issue for 5_Domain_Specific\simpleD3D12 2025-04-21 11:52:33 +08:00
shawnz
7e90d36120 Bug 5196362: Update parameters of cuCtxCreate for vectorAddMMAP 2025-04-17 10:53:03 +08:00
shawnz
2c0b36a967 Bug 5214721: Correct the path of nvvm64_40_0.dll 2025-04-15 14:27:58 +08:00
shawnz
640b566412 Bug 5214721: Update path for nvvm64_40_0.dll on CUDA 13.0 2025-04-14 16:34:24 +08:00
shawnz
5384563c57 Remove SM < 75 for cudaNvSci 2025-04-11 15:06:52 +08:00
shawnz
01a62e2bc0 Bug 5184356: Update the computeMode for remaining 3 samples 2025-04-11 10:40:35 +08:00
shawnz
02fdb070ad Bug 5196362, 5184356, 5212196, 5214258 and 5214259: Update sameples for CUDA13.0 API changes 2025-04-10 18:27:18 +08:00
Rob Armstrong
278f4adbd2 Merge branch 'master' into cuda_a_dev 2025-04-09 08:33:37 -07:00
shawnz
4672b8ba2b Bug 5163983: Remove SM < 75 in CMakeLists.txt of some samples 2025-04-09 15:10:40 +08:00
shawnz
e77d6eb5ab Bug 5207005: Append pid in shmName for Linux only as this is for MIG scenario 2025-04-07 17:17:17 +08:00
Rob Armstrong
ac700327a2 Add folders to CMakeLists.txt for supporting generators and IDEs 2025-04-05 09:54:24 -07:00
shawnz
a1b5a6f6e3 Bug 5163983: Remove SM < 75 in CMakeLists.txt of some samples 2025-04-03 15:51:59 +08:00
shawnz
a32d5badf7 Bug 5196977: Update includes for nbody 2025-04-03 15:30:05 +08:00
Rob Armstrong
1fd22429c3 Merge branch 'shawnz_bugs_fix' into 'master'
Change for fixing bugs: 5196977, 4914019, 4191696 and 5199167 .

See merge request cuda-samples/cuda-samples!97
2025-04-02 22:28:17 -07:00