xSCOPE performance figures#

Data transferred from the xCORE device to the XTAG can be set to lossless, where the target application may be stalled, or to lossy where the target application is not stalled but data packets may be dropped.

Data packets transferred from the XTAG to the host computer may be dropped if the host is unable to keep pace with the transmit rate of the target application.

Transfer rates between the xCORE Tile and XTAG-3 or XTAG-4#

The recommended xCONNECT target-to-XTAG link inter- and intra-token delay for most target hardware is approcimately 10ns between transitions.

For a tile frequency of 500MHz this can be achieved by setting the link inter- and intra-token delay to 5 cycles (see Link). The latencies and maximum call rates for the probe functions using an xCONNECT Link at this speed are given in xSCOPE performance figures for xCONNECT Link with 5-cycle intra-token delay.

xSCOPE performance figures for xCONNECT Link with 5-cycle intra-token delay#

Probe function

Latency (core cycles)

Max calls/sec

xscope_probe_data_pred

15 (always)

666,000

xscope_probe

20 (with no contention)

999,000

xscope_probe_cpu

27 (with no contention)

666,000

xscope_probe_data

22 (with no contention)

666,000

xscope_probe_cpu_data

28 (with no contention)

555,000

If two subsequent calls are made, the second call may be delayed in line with the maximum frequency. For example, if xscope_probe_data_pred is called twice, the second call is delayed by approximately 1.5 us.

The maximum call rates can be increased by reducing the inter- and intra-token delay (see Link). A small delay requires careful layout of the link and choice of cabling, since it increases link frequency.

Transfer rates between the XTAG-3 or XTAG-4 and Host PC#

The host PC has a limit at which it can receive trace data from the XTAG. If the PC is unable to keep up with the rate at which the target is transmitting, it will drop trace data records.