Commit Graph

281 Commits

Author SHA1 Message Date
mwojcik f281112779 satman: add 100mhz si5324 settings
siphaser: add calculated vco for 100mhz comment
2021-12-03 17:19:11 +08:00
mwojcik eec3ea6589 siphaser: add support for 100mhz rtio 2021-12-03 17:19:11 +08:00
occheung c6e0e26440 drtio: accept 32b/64b bus 2021-11-08 16:59:08 +08:00
mwojcik 7879d3630b made kc705/gtx interface more similar to kasli/gtp 2021-08-10 18:53:52 +08:00
Harry Ho a0fd5261ea kc705: cleanup 2021-01-22 11:11:13 +08:00
Harry Ho 88b14082b6 drtio/transceiver/gtx: delete obsolete modules 2021-01-20 15:05:32 +08:00
Harry Ho 52afd4ef6b kc705: add GTX multilane support, add multichannel support on master
* One DRTIO master channel is enabled by default.
* User can set the SMA as the 2nd master channel (by passing --drtio-sma to the argparser).
* Multi-channel (i.e. with repeaters) on KC705 satellite is supported but has not been implemented yet.
2021-01-20 15:05:32 +08:00
Harry Ho f25e86e934 kc705: revive DRTIO satellite with updated syntax, update GTX
* Multi-channel has not been implemented yet.
2021-01-20 11:25:38 +08:00
Harry Ho cff7bcc122 Merge branch 'master' (43be383c86) into k7-drtio 2020-12-31 13:30:46 +08:00
Harry Ho dc7addf394 Revert "drtio: remove KC705/GTX support"
This reverts commit ebdbaaad32.
2020-12-31 13:29:50 +08:00
Sebastien Bourdeauducq ea95d91428 wrpll: separate collector reset 2020-11-09 17:57:13 +08:00
Sebastien Bourdeauducq d185f1ac67 wrpll: fix mulshift (2) 2020-10-17 00:32:02 +08:00
Sebastien Bourdeauducq 3f076bf79b wrpll: fix mulshift 2020-10-16 22:05:37 +08:00
Sebastien Bourdeauducq db62cf2abe wrpll: convert tests to self-checking unittests 2020-10-08 18:38:01 +08:00
Sebastien Bourdeauducq 07d43b6e5f wrpll: babysit Vivado DSP retiming
Design now passes timing.
2020-10-08 17:51:27 +08:00
Sebastien Bourdeauducq 6248970ef8 wrpll: clean up matlab comparison test 2020-10-08 15:40:15 +08:00
hartytp cd8c2ce713 wrpll: add test to compare collector+filter against Matlab simulation 2020-10-08 15:36:56 +08:00
hartytp d780faf4ac wrpll.si549: initialize the clock divider to a sensible value 2020-10-08 15:32:27 +08:00
hartytp 7d7be6e711 wrpll.core: move collector into helper CD so we can get tags out while the filters are reset 2020-10-08 15:32:27 +08:00
Sebastien Bourdeauducq 3fa5d0b963 wrpll: clean up sign extension 2020-10-08 15:32:27 +08:00
hartytp 87911810d6 wrpll.core: add CSRs to monitor the collector outputs 2020-10-08 15:32:27 +08:00
hartytp f2f942a8b4 wrpll.ddmtd: remove CSRs from DDMTD
We will gather then from the collector output so we can get all tags on the same cycle
2020-10-08 15:32:27 +08:00
hartytp 85bb641917 wrpll.ddmtd: fix first edge deglitcher
The blind counter should be held in reset whenever the input is high,
not just when there is a rising edge (otherwise the counter runs down
during the main pulse and can then re-trigger on jitter from the falling edge)
2020-10-08 15:32:27 +08:00
hartytp f3cd0fc675 wrpll.filters: the helper clipping threshold is currently way too low. Move clipping after the bitshift to increase a bit.
TODO: think about this and pick a sensible threshold (and also think about integrator anti windup)
2020-10-08 15:32:27 +08:00
hartytp e5e648bde1 wrpll: add bit shift for collector helper output 2020-10-08 15:32:27 +08:00
hartytp c9ae406ac6 wrpll: change the DDMTD helper frequency to match CERN, improve docs 2020-10-08 15:32:27 +08:00
hartytp f6f6045f1a wrpll.thls: fix make 2020-10-08 15:32:27 +08:00
hartytp b44b870452 wrpll.filters: update to match Weida's MatLab simulations 2020-10-08 15:32:27 +08:00
hartytp e9ab434fa7 wrpll.core: update for modified collector 2020-10-08 15:32:27 +08:00
Sebastien Bourdeauducq 17c952b8fb wrpll: style 2020-10-08 15:32:27 +08:00
hartytp ebb7ccbfd1 wrpll: document DDMTD collector and fix unwrapping 2020-10-08 15:32:27 +08:00
cw-mlabs e4b16428f5 wrpll: fix run signal 2020-07-27 13:02:02 +08:00
cw-mlabs 8dd9a6d024 wrpll: fix scl signal 2020-07-27 12:59:32 +08:00
Sebastien Bourdeauducq 61d4614b61 sayma: fix/cleanup DRTIO-DAC sync interaction 2020-04-06 22:34:05 +08:00
Sebastien Bourdeauducq dfa033eb87 wrpll: new collector from Weida/Tom 2020-01-24 10:31:52 +08:00
Sebastien Bourdeauducq dee16edb78 wrpll: DDMTD sampler double latching 2020-01-22 19:16:26 +08:00
Sebastien Bourdeauducq 6c3e71a83a wrpll: cleanup 2020-01-18 09:43:43 +08:00
Sebastien Bourdeauducq 344f8bd12a wrpll: collector patch from Weida 2020-01-18 09:42:58 +08:00
Sebastien Bourdeauducq 50302d57c0 wrpll: more careful I2C timing 2020-01-14 20:03:46 +08:00
Sebastien Bourdeauducq 105dd60c78 wrpll: ADPLLProgrammer mini test bench and fixes 2020-01-14 16:52:25 +08:00
Sebastien Bourdeauducq 3242e9ec6c wrpll: loop test 2020-01-13 22:31:57 +08:00
Sebastien Bourdeauducq 8ec0f2e717 wrpll: implement ADPLLProgrammer 2020-01-13 22:30:11 +08:00
Sebastien Bourdeauducq d685619bcd wrpll: collector code modifications from Weida 2020-01-13 20:42:41 +08:00
Sebastien Bourdeauducq a666766f38 wrpll: add ADPLL offset registers 2019-12-30 22:19:42 +08:00
Sebastien Bourdeauducq 5c6e394928 ddmtd: add collector 2019-12-30 22:17:44 +08:00
Sebastien Bourdeauducq f57f235dca wrpll: new frequency meter
As per Mattermost discussion with Tom.
2019-12-30 19:47:57 +08:00
Sebastien Bourdeauducq 9e15ff7e6a wrpll: improve DDMTD deglitcher 2019-12-30 16:56:06 +08:00
Sebastien Bourdeauducq 307a6ca140 gth_ultrascale: make OBUFDS_GTE3 work
https://www.xilinx.com/support/answers/67919.html
2019-12-09 18:13:22 +08:00
Sebastien Bourdeauducq 05e2e1899a wrpll: update OBUFDS_GTE2 comment
Seems O can fan out simultaneously to transceiver and fabric.
Kasli is using ODIV2 for no particular reason.
2019-12-09 11:58:54 +08:00
Sebastien Bourdeauducq 4148efd2ee wrpll: implement filters and connect to Si549 2019-12-09 11:47:29 +08:00