processor-to-logic latency, AXI link: one board, the engine at its measured clock timer: CNTVCT_EL0 at 99.999 MHz, one tick 10.0 ns the timer alone (two reads, an ISB each) median 10 ns p10 10 p90 20 p99 20 max 20 mean 11 (n 20000) EMIO signature read (a processor GPIO register) median 230 ns p10 230 p90 240 p99 240 max 89851 mean 237 (n 100000) AXI-Lite read, a link register median 230 ns p10 230 p90 230 p99 230 max 19920 mean 233 (n 100000) AXI-Lite read, an engine register median 240 ns p10 240 p90 240 p99 240 max 25680 mean 242 (n 100000) a DSB alone median 10 ns p10 10 p90 110 p99 150 max 10470 mean 28 (n 100000) AXI-Lite write and its response (DSB), a link register median 250 ns p10 250 p90 350 p99 380 max 22460 mean 269 (n 100000) AXI-Lite write and its response (DSB), an engine register median 250 ns p10 250 p90 350 p99 380 max 56791 mean 269 (n 100000) AXI-Lite writes back to back, no DSB between: 51 ns each over 100000 AXI-Lite write then read (select a cell, read its field) median 460 ns p10 460 p90 580 p99 600 max 53021 mean 481 (n 100000) guarded read, as every job access goes (signature, then read) median 470 ns p10 460 p90 470 p99 470 max 21530 mean 470 (n 100000) a 1-entry write list by DMA, kick to done (4 writes, polls) median 7640 ns p10 7570 p90 7790 p99 9340 max 25820 mean 7775 (n 5000) a 512-entry write list by DMA (one page), kick to done median 20310 ns p10 20010 p90 20480 p99 23510 max 54711 mean 20433 (n 2000) = 39.7 ns an entry, 25.2 M register writes/s 128 chains' results written back (one page), kick to read median 37550 ns p10 37240 p90 37990 p99 47880 max 49670 mean 37825 (n 2000) = 293 ns a chain AXI, DMA and sequencer: a full table (64 levels x 128 fields, 32835 register writes): median 3.81 ms of 6, 116 ns a write AXI, DMA and sequencer: 65536 chains of 8 cells x 4 sweeps: 0.285 s, 4.34 us a chain, 230153 chains/s AXI, plain register accesses: a full table (64 levels x 128 fields, 32835 register writes): median 17.46 ms of 6, 532 ns a write AXI, plain register accesses: 16384 chains of 8 cells x 4 sweeps: 0.154 s, 9.42 us a chain, 106113 chains/s AXI accesses 1174977, DMA lists 8862, sequencer batches 257, write-backs 2714