12-08-2025 03:15 PM
I am trying to run the benchmark_rate utility on the x440 with 2 TX channels at a 125 MHz sample/master clock rate, but cannot get it to work properly. It seems UHD times out while configuring the x440. I have tried this using both the CG_400 and CG_1600 images and saw the same error. The strange thing is it works perfectly fine using a 250 MHz master clock rate. My understanding is that a 125 MHz master clock rate is supported by both of these images. Below is the terminal output from the benchamark_rate utility at 125 MHz:sudo ./benchmark_rate --tx_rate 125e6 --tx_subdev "A:0 B:0" --tx_channels 0,1 --args "addr=192.168.20.2,mgmt_addr=192.168.1.123,master_clock_rate=125e6,use_dpdk=1"
[INFO] [UHD] linux; GNU C++ version 13.3.0; Boost_108300; DPDK_23.11; UHD_4.8.0.main-0-81dac6ce
EAL: Detected CPU lcores: 32
EAL: Detected NUMA nodes: 1
EAL: Detected shared linkage of DPDK
EAL: Multi-process socket /var/run/dpdk/rte/mp_socket
EAL: Selected IOVA mode 'VA'
EAL: Probe PCI driver: mlx5_pci (15b3:1017) device: 0000:07:00.0 (socket -1)
TELEMETRY: No legacy callbacks, legacy socket not created
[00:00:00.000241] Creating the usrp device with: addr=192.168.20.2,mgmt_addr=192.168.1.123,master_clock_rate=125e6,use_dpdk=1...
[INFO] [MPMD] Initializing 1 device(s) in parallel with args: mgmt_addr=192.168.1.123,type=x4xx,product=x440,serial=33B79AE,name=ni-x4xx-33B79AE,fpga=CG_1600,claimed=False,addr=192.168.20.2,master_clock_rate=125e6,use_dpdk=1
[INFO] [MPMD] Rebooting MPM before device initialization!
[INFO] [MPM.PeriphManager] init() called with device args `fpga=CG_1600,master_clock_rate=(125000000.0, 125000000.0),mgmt_addr=192.168.1.123,name=ni-x4xx-33B79AE,product=x440,use_dpdk=1,clock_source=internal,time_source=internal,initializing=True'.
[INFO] [MPM.RPCServer] Resetting peripheral manager.
[INFO] [MPM.PeriphManager] Device serial number: 338A4C8
[INFO] [MPM.PeriphManager.Clk_Policy] Bypassing RFDC PLL
[INFO] [MPM.PeriphManager.Clk_Policy] Bypassing RFDC PLL
[INFO] [MPM.PeriphManager.Clk_Policy] Bypassing RFDC PLL
[INFO] [MPM.PeriphManager.ClkMgr] Using Clock Configuration:
DB0: Master Clock Rate: 368.64 MSps @Converter Rate 2.94912 GHz
DB1: Master Clock Rate: 368.64 MSps @Converter Rate 2.94912 GHz
[INFO] [MPM.PeriphManager] Initialized 2 daughterboard(s).
[INFO] [MPM.PeriphManager] init() called with device args `boot_init=True,clock_source=internal,time_source=internal,initializing=True'.
[INFO] [MPM.PeriphManager.Clk_Policy] Using RFDC PLL
[INFO] [MPM.PeriphManager.Clk_Policy] Bypassing RFDC PLL
[INFO] [MPM.PeriphManager.ClkMgr] Using Clock Configuration:
DB0: Master Clock Rate: 125.0 MSps @Converter Rate 1.0 GHz
DB1: Master Clock Rate: 125.0 MSps @Converter Rate 1.0 GHz
[INFO] [MPM.PeriphManager] init() called with device args `fpga=CG_1600,master_clock_rate=(125000000.0, 125000000.0),mgmt_addr=192.168.1.123,name=ni-x4xx-33B79AE,product=x440,use_dpdk=1,clock_source=internal,time_source=internal,initializing=True'.
[INFO] [0/Radio#0] Clocking reconfigured, running ADC Self Cal on DB0...
[INFO] [0/Radio#0] Calibrated 1 channels.
[ERROR] [RFNOC::GRAPH] Error during initialization of block 0/Radio#1!
[ERROR] [RFNOC::GRAPH] Caught exception while initializing graph: RfnocError: OpTimeout: Control operation timed out waiting for space in command buffer
Error: RuntimeError: Failure to create rfnoc_graph.
If anyone could provide any information on why this is occuring, it would be greatly appreciated.
12-08-2025 11:39 PM
Hello!
On the X440, UHD often times out when running benchmark_rate at 125 MHz with two TX channels because the RFDC PLL bypass and calibration sequence can stall, causing RFNoC graph creation to fail. Although 125 MHz is listed as supported, multi‑channel operation at that rate is unstable in UHD 4.8.0, while 250 MHz works reliably. The workaround is to test single‑channel at 125 MHz, use higher clock rates like 200/250 MHz, or update UHD/FPGA images and seek support from Ettus if dual‑channel at 125 MHz is required.
12-09-2025 06:51 AM
Thank you for the response. Do you know if multi-channel operation at 125 MHz is stable in UHD 4.9?