Logs for PR #1008 (2026-01-21T20:30:53.397278+00:00):

=== СТАТУС: Успешно выполнены программы: main_aplusb_matrix ===
=== main_aplusb_matrix stdout (exit code: -11 (segfault после выполнения)) ===
Found 1 GPUs in 8.89878 sec (CUDA: 0.115265 sec, OpenCL: 1.55492 sec, Vulkan: 7.22853 sec)
Available devices:
Device #0: API: CUDA+OpenCL+Vulkan. GPU. Tesla T4 (CUDA 12020). Free memory: 14822/14930 Mb.
Using device #0: API: CUDA+OpenCL+Vulkan. GPU. Tesla T4 (CUDA 12020). Free memory: 14822/14930 Mb.
Using OpenCL API...
matrices size: 16384x8192 = 3 * 512 MB
Running BAD matrix kernel...
Kernels compilation done in 3.201 seconds
a + b matrix kernel times (in seconds) - 10 values (min=0.202633 10%=0.202784 median=0.203044 90%=3.40779 max=3.40779)
A + b (bad) median effective memory bandwidth: 7.38756 GB/s
Running GOOD matrix kernel...
Kernels compilation done in 0.059707 seconds
a + b matrix kernel times (in seconds) - 10 values (min=0.00655 10%=0.006551 median=0.006557 90%=0.066356 max=0.066356)
A + b (good) median effective memory bandwidth: 228.763 GB/s