Сразу скажу кому лень весь лог читать, максимум - 46 мегакеев.
--** Started logging **-------------------------------------
v12.12
Benchmarking
Initializing enviroment...
Loading IL program
Found RV630 device at 725 MHz (3 SIMDs, wavefront size=64)
28 MB of cached, 256 MB uncached RAM available
Compiling...
Linking...
Allocating LOCAL buffers
Program info:
Scratch regs needed: 0
Number of shared GPRs: 0
Number of shared GPRs total: 0
Slow mode: no
Number of wavefronts per SIMD: 0
Is max wavefronts per SIMD?: no
---Benchmarking core, peak size (no readback)---
Using optimal size (8x24)
Iters: 8192, time=156 ms, 52512 iters/sec, 40 Mkeys/sec
Iters: 16384, time=328 ms, 49951 iters/sec, 38 Mkeys/sec
Iters: 32768, time=657 ms, 49875 iters/sec, 38 Mkeys/sec
Using optimal size (24x8)
Iters: 8192, time=172 ms, 47627 iters/sec, 36 Mkeys/sec
Iters: 16384, time=328 ms, 49951 iters/sec, 38 Mkeys/sec
Iters: 32768, time=657 ms, 49875 iters/sec, 38 Mkeys/sec
---Trying grid (24x24)---
Iters: 4096, time=219 ms, 18703 iters/sec, 43 Mkeys/sec
Iters: 8192, time=422 ms, 19412 iters/sec, 44 Mkeys/sec
Iters: 16384, time=828 ms, 19787 iters/sec, 45 Mkeys/sec
---Trying grid (32x32)---
Iters: 2048, time=203 ms, 10088 iters/sec, 41 Mkeys/sec
Iters: 4096, time=406 ms, 10088 iters/sec, 41 Mkeys/sec
Iters: 8192, time=781 ms, 10489 iters/sec, 42 Mkeys/sec
---Trying grid (40x40)---
Iters: 1024, time=141 ms, 7262 iters/sec, 46 Mkeys/sec
Iters: 2048, time=297 ms, 6895 iters/sec, 44 Mkeys/sec
Iters: 4096, time=609 ms, 6725 iters/sec, 43 Mkeys/sec
---Trying grid (48x48)---
Iters: 512, time=109 ms, 4697 iters/sec, 43 Mkeys/sec
Iters: 1024, time=203 ms, 5044 iters/sec, 46 Mkeys/sec
Iters: 2048, time=422 ms, 4853 iters/sec, 44 Mkeys/sec
Iters: 4096, time=844 ms, 4853 iters/sec, 44 Mkeys/sec
---Trying grid (56x56)---
Iters: 512, time=141 ms, 3631 iters/sec, 45 Mkeys/sec
Iters: 1024, time=297 ms, 3447 iters/sec, 43 Mkeys/sec
Iters: 2048, time=562 ms, 3644 iters/sec, 45 Mkeys/sec
---Trying grid (64x64)---
Iters: 512, time=188 ms, 2723 iters/sec, 44 Mkeys/sec
Iters: 1024, time=391 ms, 2618 iters/sec, 42 Mkeys/sec
Iters: 2048, time=765 ms, 2677 iters/sec, 43 Mkeys/sec
---Trying grid (72x72)---
Iters: 256, time=125 ms, 2048 iters/sec, 42 Mkeys/sec
Iters: 512, time=235 ms, 2178 iters/sec, 45 Mkeys/sec
Iters: 1024, time=468 ms, 2188 iters/sec, 45 Mkeys/sec
Iters: 2048, time=953 ms, 2149 iters/sec, 44 Mkeys/sec
---Trying grid (80x80)---
Iters: 256, time=141 ms, 1815 iters/sec, 46 Mkeys/sec
Iters: 512, time=313 ms, 1635 iters/sec, 41 Mkeys/sec
Iters: 1024, time=593 ms, 1726 iters/sec, 44 Mkeys/sec
****Calculating readback speed***** Using optimal size (8x24)
Iters: 1024, time=1047 ms, 978 iters/sec
Using optimal size (24x8)
Iters: 1024, time=1047 ms, 978 iters/sec
---Trying grid (24x24)---
Iters: 1024, time=1062 ms, 964 iters/sec
---Trying grid (32x32)---
Iters: 1024, time=1109 ms, 923 iters/sec
---Trying grid (40x40)---
Iters: 1024, time=1156 ms, 885 iters/sec
---Trying grid (48x48)---
Iters: 1024, time=1188 ms, 861 iters/sec
---Trying grid (56x56)---
Iters: 1024, time=1266 ms, 808 iters/sec
---Trying grid (64x64)---
Iters: 1024, time=1359 ms, 753 iters/sec
---Trying grid (72x72)---
Iters: 1024, time=1422 ms, 720 iters/sec
---Trying grid (80x80)---
Iters: 1024, time=1500 ms, 682 iters/sec
****Benchmarking full cycle (1b4****** Using optimal size (8x24)
Iters: 8192, time=171 ms, 47906 iters/sec, 36 Mkeys/sec
Iters: 16384, time=329 ms, 49799 iters/sec, 38 Mkeys/sec
Iters: 32768, time=656 ms, 49951 iters/sec, 38 Mkeys/sec
Using optimal size (24x8)
Iters: 8192, time=156 ms, 52512 iters/sec, 40 Mkeys/sec
Iters: 16384, time=328 ms, 49951 iters/sec, 38 Mkeys/sec
Iters: 32768, time=656 ms, 49951 iters/sec, 38 Mkeys/sec
---Trying grid (24x24)---
Iters: 2048, time=109 ms, 18788 iters/sec, 43 Mkeys/sec
Iters: 4096, time=219 ms, 18703 iters/sec, 43 Mkeys/sec
Iters: 8192, time=422 ms, 19412 iters/sec, 44 Mkeys/sec
Iters: 16384, time=828 ms, 19787 iters/sec, 45 Mkeys/sec
---Trying grid (32x32)---
Iters: 1024, time=110 ms, 9309 iters/sec, 38 Mkeys/sec
Iters: 2048, time=203 ms, 10088 iters/sec, 41 Mkeys/sec
Iters: 4096, time=390 ms, 10502 iters/sec, 43 Mkeys/sec
Iters: 8192, time=797 ms, 10278 iters/sec, 42 Mkeys/sec
---Trying grid (40x40)---
Iters: 1024, time=141 ms, 7262 iters/sec, 46 Mkeys/sec
Iters: 2048, time=312 ms, 6564 iters/sec, 42 Mkeys/sec
Iters: 4096, time=610 ms, 6714 iters/sec, 42 Mkeys/sec
---Trying grid (48x48)---
Iters: 512, time=109 ms, 4697 iters/sec, 43 Mkeys/sec
Iters: 1024, time=219 ms, 4675 iters/sec, 43 Mkeys/sec
Iters: 2048, time=422 ms, 4853 iters/sec, 44 Mkeys/sec
Iters: 4096, time=843 ms, 4858 iters/sec, 44 Mkeys/sec
---Trying grid (56x56)---
Iters: 512, time=156 ms, 3282 iters/sec, 41 Mkeys/sec
Iters: 1024, time=281 ms, 3644 iters/sec, 45 Mkeys/sec
Iters: 2048, time=579 ms, 3537 iters/sec, 44 Mkeys/sec
---Trying grid (64x64)---
Iters: 256, time=109 ms, 2348 iters/sec, 38 Mkeys/sec
Iters: 512, time=187 ms, 2737 iters/sec, 44 Mkeys/sec
Iters: 1024, time=391 ms, 2618 iters/sec, 42 Mkeys/sec
Iters: 2048, time=781 ms, 2622 iters/sec, 42 Mkeys/sec
---Trying grid (72x72)---
Iters: 256, time=125 ms, 2048 iters/sec, 42 Mkeys/sec
Iters: 512, time=235 ms, 2178 iters/sec, 45 Mkeys/sec
Iters: 1024, time=468 ms, 2188 iters/sec, 45 Mkeys/sec
Iters: 2048, time=954 ms, 2146 iters/sec, 44 Mkeys/sec
---Trying grid (80x80)---
Iters: 256, time=140 ms, 1828 iters/sec, 46 Mkeys/sec
Iters: 512, time=313 ms, 1635 iters/sec, 41 Mkeys/sec
Iters: 1024, time=593 ms, 1726 iters/sec, 44 Mkeys/sec
Deallocating resources
|