Task07 Панов Антон Александрович ITMO

[LargonG]

Local:

Found 3 GPUs in 0.38049 sec (CUDA: 0.0309575 sec, OpenCL: 0.0786745 sec, Vulkan: 0.269651 sec)
Available devices:
  Device #0: API: OpenCL. GPU. AMD Radeon(TM) Graphics (gfx1035). Free memory: 6073/6153 Mb.
  Device #1: API: OpenCL. CPU. AMD Ryzen 7 6800H with Radeon Graphics         . Intel(R) Corporation. Total memory: 15556 Mb.
  Device #2: API: CUDA+OpenCL+Vulkan. GPU. NVIDIA GeForce RTX 3060 Laptop GPU (CUDA 13000). Free memory: 5120/6143 Mb.
Using device #2: API: CUDA+OpenCL+Vulkan. GPU. NVIDIA GeForce RTX 3060 Laptop GPU (CUDA 13000). Free memory: 5120/6143 Mb.
Using CUDA API...
Evaluating CSR matrix nrows x ncols=1000000x1000000 with values in range [0; 1000]
____________________________________________________________________________________________
Evaluating with NNZ per row in range [32; 32], median NNZ per row=32, total NNZ=32000000...
CPU (multi-threaded via OpenMP) finished in 0.0947064 sec
CPU effective bandwidth: 1.32289 GB/s (332.874 uint millions/s)
GPU SpMV (sparse matrix-vector multiplication) times (in seconds) - 10 values (min=0.0108161 10%=0.0108181 median=0.0112597 90%=0.153456 max=0.153456)
GPU SpMV median effective VRAM bandwidth: 11.249 GB/s (2841.99 uint millions/s)
____________________________________________________________________________________________
Evaluating with NNZ per row in range [128; 128], median NNZ per row=128, total NNZ=128000000...
CPU (multi-threaded via OpenMP) finished in 0.252042 sec
CPU effective bandwidth: 1.91538 GB/s (505.172 uint millions/s)
GPU SpMV (sparse matrix-vector multiplication) times (in seconds) - 10 values (min=0.0151182 10%=0.0151359 median=0.0158202 90%=0.0165051 max=0.0165051)
GPU SpMV median effective VRAM bandwidth: 30.612 GB/s (8090.92 uint millions/s)
____________________________________________________________________________________________
Evaluating with NNZ per row in range [1; 32], median NNZ per row=17, total NNZ=16499998...
CPU (multi-threaded via OpenMP) finished in 0.0570123 sec
CPU effective bandwidth: 1.19578 GB/s (275.84 uint millions/s)
GPU SpMV (sparse matrix-vector multiplication) times (in seconds) - 10 values (min=0.0101825 10%=0.0101991 median=0.0105835 90%=0.0753446 max=0.0753446)
GPU SpMV median effective VRAM bandwidth: 6.51182 GB/s (1511.79 uint millions/s)
____________________________________________________________________________________________
Evaluating with NNZ per row in range [1; 128], median NNZ per row=64, total NNZ=64499934...
CPU (multi-threaded via OpenMP) finished in 0.183316 sec
CPU effective bandwidth: 1.34476 GB/s (346.278 uint millions/s)
GPU SpMV (sparse matrix-vector multiplication) times (in seconds) - 10 values (min=0.0121328 10%=0.0121331 median=0.0121675 90%=0.0122886 max=0.0122886)
GPU SpMV median effective VRAM bandwidth: 20.3601 GB/s (5259.91 uint millions/s)
____________________________________________________________________________________________
Evaluating with NNZ per row in range [32; 128], median NNZ per row=80, total NNZ=79933808...
CPU (multi-threaded via OpenMP) finished in 0.214026 sec
CPU effective bandwidth: 1.4213 GB/s (366.935 uint millions/s)
GPU SpMV (sparse matrix-vector multiplication) times (in seconds) - 10 values (min=0.0129436 10%=0.0129472 median=0.0129765 90%=0.0131224 max=0.0131224)
GPU SpMV median effective VRAM bandwidth: 23.5215 GB/s (6087.93 uint millions/s)

D:\dev\gpu\GPGPUTasks2025\out\build\default\main_sparse_matrix_multiply.exe (process 5580) exited with code 0 (0x0).

Github CI:

Found 2 GPUs in 0.049046 sec (CUDA: 7.6513e-05 sec, OpenCL: 0.0225917 sec, Vulkan: 0.0263291 sec)
Available devices:
  Device #0: API: OpenCL. CPU. AMD EPYC 7763 64-Core Processor                . Intel(R) Corporation. Total memory: 15994 Mb.
  Device #1: API: Vulkan. CPU. llvmpipe (LLVM 20.1.2, 256 bits). Free memory: 15994/15994 Mb.
Using device #0: API: OpenCL. CPU. AMD EPYC 7763 64-Core Processor                . Intel(R) Corporation. Total memory: 15994 Mb.
Device AMD EPYC 7763 64-Core Processor                 doesn't support CUDA
Error: Device doesn't support requested API

[GPUcourseBOT]

✅ Результаты тестирования PR #1039

Логи тестирования (нажмите чтобы развернуть)

=== СТАТУС: Успешно выполнены программы: main_sparse_matrix_multiply ===
=== main_sparse_matrix_multiply stdout (exit code: -11 (segfault после выполнения)) ===
Found 1 GPUs in 8.55535 sec (CUDA: 0.115358 sec, OpenCL: 0.706201 sec, Vulkan: 7.73372 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 CUDA API...
Evaluating CSR matrix nrows x ncols=1000000x1000000 with values in range [0; 1000]
____________________________________________________________________________________________
Evaluating with NNZ per row in range [32; 32], median NNZ per row=32, total NNZ=32000000...
CPU (multi-threaded via OpenMP) finished in 0.043668 sec
CPU effective bandwidth: 2.89859 GB/s (732.297 uint millions/s)
GPU SpMV (sparse matrix-vector multiplication) times (in seconds) - 10 values (min=0.0218915 10%=0.0218929 median=0.0219004 90%=0.0247298 max=0.0247298)
GPU SpMV median effective VRAM bandwidth: 5.78346 GB/s (1461.16 uint millions/s)
____________________________________________________________________________________________
Evaluating with NNZ per row in range [128; 128], median NNZ per row=128, total NNZ=128000000...
CPU (multi-threaded via OpenMP) finished in 0.168708 sec
CPU effective bandwidth: 2.87002 GB/s (758.556 uint millions/s)
GPU SpMV (sparse matrix-vector multiplication) times (in seconds) - 10 values (min=0.0168651 10%=0.0172695 median=0.025286 90%=0.0253646 max=0.0253646)
GPU SpMV median effective VRAM bandwidth: 19.1524 GB/s (5062.08 uint millions/s)
____________________________________________________________________________________________
Evaluating with NNZ per row in range [1; 32], median NNZ per row=17, total NNZ=16499998...
CPU (multi-threaded via OpenMP) finished in 0.0225671 sec
CPU effective bandwidth: 3.0495 GB/s (707.936 uint millions/s)
GPU SpMV (sparse matrix-vector multiplication) times (in seconds) - 10 values (min=0.0109355 10%=0.0109367 median=0.0109378 90%=0.0110137 max=0.0110137)
GPU SpMV median effective VRAM bandwidth: 6.30086 GB/s (1462.81 uint millions/s)
____________________________________________________________________________________________
Evaluating with NNZ per row in range [1; 128], median NNZ per row=64, total NNZ=64499934...
CPU (multi-threaded via OpenMP) finished in 0.0847006 sec
CPU effective bandwidth: 2.92367 GB/s (755.301 uint millions/s)
GPU SpMV (sparse matrix-vector multiplication) times (in seconds) - 10 values (min=0.0214121 10%=0.0214138 median=0.0214202 90%=0.0229551 max=0.0229551)
GPU SpMV median effective VRAM bandwidth: 11.5653 GB/s (2987.83 uint millions/s)
____________________________________________________________________________________________
Evaluating with NNZ per row in range [32; 128], median NNZ per row=80, total NNZ=80011495...
CPU (multi-threaded via OpenMP) finished in 0.105854 sec
CPU effective bandwidth: 2.88548 GB/s (755.558 uint millions/s)
GPU SpMV (sparse matrix-vector multiplication) times (in seconds) - 10 values (min=0.0140884 10%=0.0142801 median=0.0236615 90%=0.0237399 max=0.0237399)
GPU SpMV median effective VRAM bandwidth: 12.912 GB/s (3381.02 uint millions/s)

Посмотреть полные логи

[PolarNick239]

4/5 баллов 👍(т.к. дедлайн)