|
Possible NVCC Warp-Aggregated Atomic Issue
|
|
4
|
51
|
October 12, 2026
|
|
Share/Copy memory between two CUDA contexts in the same GPU and process
|
|
0
|
35
|
October 11, 2026
|
|
A correctly rounded implementation of the half-precision function hexpm1()
|
|
0
|
28
|
October 10, 2026
|
|
Driver Incompatibility for Supporting Both Volta and Blackwell Simultaneously on Ubuntu
|
|
3
|
897
|
October 9, 2026
|
|
DCGM 4.7.0 reports Power Health Warning on one L40S but Healthy on identical GPU in same TensorFlow process
|
|
1
|
53
|
October 8, 2026
|
|
Broken code when using std::clamp with no compiler warning
|
|
2
|
56
|
October 6, 2026
|
|
[bug] [nvcc] cicc dies with SIGILL lowering __nvvm_atom_add_gen_d for sm_120
|
|
0
|
28
|
October 6, 2026
|
|
A correctly rounded implementation of the half-precision arctangent function hatan()
|
|
0
|
37
|
October 5, 2026
|
|
Nvlink fatal : Could not open input file '/usr/lib/x86_64-linux-gnu/librt.a'
|
|
1
|
1115
|
October 4, 2026
|
|
CUDA 13.0 on GitHub action runners: 'crt/host_config.h': No such file or directory
|
|
2
|
305
|
October 3, 2026
|
|
cudaHostRegister for read-only shared memory on GeForce RTX: support and alternatives
|
|
2
|
79
|
October 1, 2026
|
|
Performance tuning the half-precision hyperbolic tangent function htanh()
|
|
0
|
36
|
September 30, 2026
|
|
DMA-BUF not supported on RTX 5090 with open kernel module?
|
|
0
|
65
|
September 30, 2026
|
|
Performance tuning the half-precision exponential function hexp()
|
|
1
|
58
|
September 29, 2026
|
|
How should errors reported through an mbarrier be associated with individual fabric operations?
|
|
1
|
47
|
September 29, 2026
|
|
A newbie with an AI reported BUG: ubuntu2604/x86_64 CUDA repo: Packages index has 5 malformed entries, apt update fails
|
|
3
|
308
|
September 29, 2026
|
|
Follow-up: lost 289th bit in the reduction mod 2^256-2^32-977 after nj_umul256wide - correct fix costs 1.2 % on sm_89, cheaper way?
|
|
2
|
96
|
September 25, 2026
|
|
GPU-PV (dxgkrnl): CUDA workload slows ~1.7× over 3–4 days of host uptime with accumulating dxgvmb_send_sync_msg: wait_for_completion failed in dmesg;
|
|
0
|
79
|
September 25, 2026
|
|
CUDA GPU not getting detected after Python environment update
|
|
0
|
41
|
September 24, 2026
|
|
Implementation of CUDA extended precision floating point operations
|
|
11
|
152
|
September 24, 2026
|
|
Linking issues using CUDA 13.2 on NVIDIA Blackwell GB100
|
|
0
|
34
|
September 24, 2026
|
|
New Version Numbers
|
|
0
|
72
|
September 24, 2026
|
|
WSL2 / WDDM: a vectorised (≥64-bit) global load at zero free VRAM takes the Windows host down — ~250-line pure-CUDA reproducer, one flag flips it
|
|
1
|
137
|
September 23, 2026
|
|
CUDA Tiling API and optimal tile shapes
|
|
2
|
60
|
September 23, 2026
|
|
[bug] cuda 13.4.59 crashed: assertion failed: invalid entity code for constraint configuration of attribute device_builtin
|
|
0
|
30
|
September 23, 2026
|
|
cudaGraphLaunch crashes or reports a launch failure for multi-million-node graphs
|
|
0
|
41
|
September 23, 2026
|
|
The tractor driver will return...this time with V-PACK
|
|
4
|
120
|
September 22, 2026
|
|
Announcement: opencl-api-cpp - A 'sister' library to cuda-api-wrappers, but for OpenCL
|
|
0
|
63
|
September 21, 2026
|
|
Prefetch.tensormap: elected lane vs full warp using CUTLASS/CuTe on SM90 and SM100
|
|
1
|
81
|
September 21, 2026
|
|
CUDA Graph updates report success but retain stale cluster dimensions on driver 580.159.03
|
|
0
|
53
|
September 18, 2026
|
Visitar URL original