Checklist - xilinx-u55c-gen3x16-xdma-3¶
Table of content
Package information¶
xbtest information |
|
---|---|
Release Number |
3522912 |
Description (what’s new) |
Initial Release |
Platform information |
|
---|---|
Development platform (XSA) |
xilinx-u55c-gen3x16-xdma-3-202210-1-dev-1-3514517 |
Deployment platform (shell, CMC, SC) |
xilinx-cmc-u55-1.5.25-3395704 xilinx-sc-fw-u55-7.1.17-1.f7275be xilinx-u55c-gen3x16-xdma-base-3-3494559 xilinx-u55c-gen3x16-xdma-validate-3-3506150 |
System information¶
System information |
|
---|---|
OS |
CentOS / 7.8.2003 |
Architecture |
x86_64 |
Server type |
PowerEdge R740 |
AUX cable |
yes |
Card S/N |
XFL1BO3WZCH5 |
XRT version |
2.13.449 |
Measured download time |
10.5 seconds |
Requirement - Platform high level features¶
Platform and card requirements¶
Platform and card requirements |
|
---|---|
FPGA part |
xcu55c-fsvh2892-2L-e |
PCIe speed and width |
gen3x16 |
DMA type |
xdma |
DDR: speed, size and quantity |
N/A |
HBM: size, quantity and power rail |
32 Pseudo-Channels; 16,384MB, 12v_pex |
Host memory support |
yes |
P2P support |
yes |
GTs: type, quad, SLR location |
GT[0]: GTY, Quad_X0Y6 (SLR1) GT[1]: GTY, Quad_X0Y7 (SLR1) |
Power rails requirements¶
Power rail |
Card limit (W) |
Note |
---|---|---|
|
69W |
Powers HBM |
|
10.4W |
|
|
78W |
User Selectable |
|
N/A |
Fatal Limit/Card Shutdown @60A per phase (8 phases with full AUX power) |
Calibration - Power CU - Results¶
Description |
Results |
|
---|---|---|
Power, temperature & toggle rate graph |
![]() |
|
Maximum toggle rate reached (%) |
84 Board reboot due to 12v_aux threshold. Last measured power at the 12v_aux was :78.568776 W |
|
Power consumption balance achieved:
|
No Historically, it is difficult to reach maximum 150W limit for u55c. |
|
|
Measurement |
1.577 |
Critical limit |
3.15 |
|
|
Measurement |
4.264 |
Critical limit |
5.75 |
|
|
Measurement |
6.457 |
Critical limit |
6.5 |
Calibration - Memory CU power¶
Memory |
Description |
|
|
|
---|---|---|---|---|
HBM |
Is there enough power for memory? |
Yes. The U55C card is capable of supplying full power to the HBM memories. |
||
Power graph |
![]() |
![]() |
![]() |
|
BW graph |
![]() |
![]() |
![]() |
|
Latency graphs |
![]() ![]() |
![]() |
![]() |
Calibration - Memory bandwidth and latency¶
Note
N/A: not applicable
- 1
The outstanding write/read is the maximum number of outstanding reads just before the read pipeline is full, giving the best BW and latency results.
Memory |
Description |
|
|
|
---|---|---|---|---|
HBM |
QoS / power reduction rate |
Write rate = 33 %; read rate = 33 % ![]() |
|
|
Best write BW (MBps) |
6008 |
N/A |
12255 |
|
Best write latency (ns) |
143 |
N/A |
203 |
|
Best read BW (MBps) |
6008 |
12292 |
N/A |
|
Best read latency (ns) |
681 |
952 |
N/A |
|
Outstanding write/read 1 |
Write = 2 / read = 21 |
4 |
3 |
|
BW/latency graphs (do one for read and one for write) |
![]() ![]() |
![]() |
![]() |
Checklist questionnaire¶
Runtime¶
Question |
Answer / justification / problem tracker reference number |
---|---|
Have you updated the default download time?
|
Yes "download_time": 13
Measured download time is 10.5 sec. Extra padding added to give time for HBM calibration. |
Sensors¶
Question |
Answer / justification / problem tracker reference number |
---|---|
Do you need to monitor more mechanical sources than the default one
(
|
No |
Do you need to monitor more thermal sources than the default one (
|
No |
Do you need to monitor more electrical sources than the default ones
(
|
No |
GT¶
Question |
Answer / justification / problem tracker reference number |
|
---|---|---|
GT |
GT[0] |
GT[1] |
Have you updated GT default settings to maximize signal integrity?
|
"0": {
"name": "top",
"transceiver_settings": {
"module": {
"tx_differential_swing_control": 11,
"tx_pre_emphasis": 0,
"tx_post_emphasis": 0,
"rx_equaliser": "DFE"
},
"cable": {
"tx_differential_swing_control": 11,
"tx_pre_emphasis": 0,
"tx_post_emphasis": 0,
"rx_equaliser": "DFE"
}
}
}
|
"1": {
"name": "bottom",
"transceiver_settings": {
"module": {
"tx_differential_swing_control": 11,
"tx_pre_emphasis": 0,
"tx_post_emphasis": 0,
"rx_equaliser": "DFE"
},
"cable": {
"tx_differential_swing_control": 11,
"tx_pre_emphasis": 0,
"tx_post_emphasis": 0,
"rx_equaliser": "DFE"
}
}
}
|
Memory¶
Question |
Answer / justification / problem tracker reference number |
|
---|---|---|
Memory |
HBM |
HOST |
Have you defined specific DMA bandwidths (
|
No |
N/A |
Have you defined optimum DMA settings (
|
No |
N/A |
Have you defined specific P2P CARD bandwidths (
|
No |
N/A |
Have you defined optimum P2P CARD settings (
|
No |
N/A |
Have you defined specific P2P NVME bandwidths (
|
No |
N/A |
Have you defined optimum P2P NVME settings (
|
No |
N/A |
Have you reduced the CU rate to avoid over-power ( |
No |
No |
Have you defined |
"cu_rate": {
"simul_wr_rd": {
"write": {
"nominal": 33
},
"read": {
"nominal": 33
}
}
}
|
"cu_rate": {
"only_wr": {
"write": {
"nominal": 50
}
}
}
|
Have you defined
For host memory these values are depending on the PCIe speed. |
"cu_bw": {
"only_wr": {
"write": {
"average": 12255
}
},
"only_rd": {
"read": {
"average": 12292
}
},
"simul_wr_rd": {
"write": {
"average": 6008
},
"read": {
"average": 6008
}
}
}
|
"cu_bw": {
"only_wr": {
"write": {
"high": 16000,
"low": 4000
}
},
"only_rd": {
"read": {
"high": 16000,
"low": 4000
}
},
"simul_wr_rd": {
"write": {
"high": 16000,
"low": 4000
},
"read": {
"high": 16000,
"low": 4000
}
}
}
|
Have you defined
|
"cu_latency": {
"only_wr": {
"write": {
"high": 508,
"low": 141
}
},
"only_rd": {
"read": {
"high": 1239,
"low": 666
}
},
"simul_wr_rd": {
"write": {
"high": 232,
"low": 100
},
"read": {
"high": 1007,
"low": 466
}
}
}
|
"cu_latency": {
"only_wr": {
"write": {
"high": 6000,
"low": 1
}
},
"only_rd": {
"read": {
"high": 6000,
"low": 1
}
},
"simul_wr_rd": {
"write": {
"high": 6000,
"low": 1
},
"read": {
"high": 6000,
"low": 1
}
}
}
|
Have you defined
|
"cu_outstanding": {
"only_wr": {
"write": {
"nominal": 3
}
},
"only_rd": {
"read": {
"nominal": 4
}
},
"simul_wr_rd": {
"write": {
"nominal": 2
},
"read": {
"nominal": 21
}
}
}
|
No |
Have you defined
|
No |
No |
Pre-canned tests¶
Question |
Answer / justification / problem tracker reference number |
---|---|
Have you tested all provided pre-canned tests?
|
Yes |
Have you modified the pre-canned test template?
|
No |
Have you saved all pre-canned results?
|
Yes |
Issues tracking¶
Question |
Answer / justification / problem tracker reference number |
---|---|
Did you modify the platform definition limits and range after running the pre-canned tests?
|
No |
Pre-canned tests results¶
Pre-canned test modifications¶
Test name |
Modification from original template |
Justifications |
---|---|---|
/ |
No modification |
/ |
dma
pre-canned test¶
Memory |
Write BW (MBps) |
Read BW (MBps) |
---|---|---|
HBM |
11932 |
12083 |
p2p_card
pre-canned test¶
Memory |
Write BW (MBps) |
Read BW (MBps) |
---|---|---|
HBM |
3723 |
1832 |
p2p_nvme
pre-canned test¶
Memory |
Card mode |
Write BW (MBps) |
Read BW (MBps) |
---|---|---|---|
HBM |
source |
2181 |
2855 |
HBM |
target |
2968 |
1950 |
memory
pre-canned test¶
Memory |
Test mode |
Write BW (MBps) |
Read BW (MBps) |
Write Latency (ns) |
Read Latency (ns) |
---|---|---|---|---|---|
HBM |
|
196608 |
196160 |
208 |
952 |
|
392172 |
N/A |
208 |
N/A |
|
|
N/A |
393369 |
N/A |
952 |
|
|
192263 |
192260 |
144 |
733 |
memory_host
pre-canned test¶
Memory |
Test mode |
Write BW (MBps) |
Read BW (MBps) |
Write Latency (ns) |
Read Latency (ns) |
---|---|---|---|---|---|
HOST |
|
5229 |
5222 |
829 |
3835 |
|
9155 |
N/A |
829 |
N/A |
|
|
N/A |
12178 |
N/A |
3835 |
|
|
9155 |
12006 |
829 |
3890 |