The axi-pcie-devel package is supplied with a test application to verify KCU/GPU interaction. It is comprised of the interCardGui
application and the test_dma
program. These are used with the InterCardTest
firmware that should be loaded on the KCU. The interCardGui
brings up a devGui
-like GUI that provides access to the registers provided by the InterCardTest
firmware on the KCU.
Running the test
After building and installing the datagpu
driver using comp_and_load_drivers.sh (in the aes-stream-drivers package), go to the gpu
directory in a axi-pcie-devel
check-out to launch the interCardGui
:
cd ~/git/axi-pcie-devel/software/gpu/ ../scripts/interCardGui
There was an issue launching it from another directory at one point, but this may have been fixed. The GUI connects with the /dev/datagpu_0
device by default, but another may be select by using the --dev
option. The following GUI should come up:
Depending on the state of the system, it may be desirable to reset the firmware state by opening the AxiPcieCore.AxiVersion blocks and clicking on UserRst to clear out any previous state:
From another prompt, start the test_dma program:
cd ~/git/axi-pcie-devel/software/gpu/ sudo ./bin/test_dma
This program also interacts with /dev/datagpu_0
by default. Another device may be selected using the -d
option. The program will print some stuff and then pause:
(rogue_v6.1.3) claus@drp-srcf-gpu001:gpu$ sudo ./bin/test_dma [sudo] password for claus: Total devices 1 Selected device: NVIDIA RTX A5000 Global memory: 24026 MB 64-bit Memory Address support Setting write pointer: 0x7f9885600000 - 65536 Setting read pointer: 0x7f9885610000 - 65536 Done with pointers Mapping FPGA registers swFpgaRegs = 0x7f98a36bd000 Enabling IO memory for FPGA registers Mapping write start register Mapping read start register Mapped FPGA registers Create stream write memory Trigger write Wait memory value
At this point it is useful to click Read All
at the bottom of the interCardGui to verify that various registers look reasonable. The dmesg
program also shows some output from the datagpu
driver that might be of interest.
To trigger a DMA sequence, click on the OneShot
Exec
button in the PrbsTx
block of the interCardGui
. This should result in additional printout from test_dma
:
Done waiting Stream Sync Context sync data: 0 0x 2000000 - 0x 1 data: 1 0x 2000 - 0x 0 data: 2 0x 0 - 0x 0 data: 3 0x 0 - 0x 0 data: 4 0x 0 - 0x 0 data: 5 0x 0 - 0x 0 data: 6 0x 0 - 0x 0 data: 7 0x 0 - 0x 0 data: 8 0x 1 - 0x ff data: 9 0x 0 - 0x 0 ...
Click on Read All
in interCardGui
again to update the register values. The AxiGpuAsyncCore
block shows some statistics that may be of interest. Here it indicates that both the write
and read
DMAs completed successfully:
Problems encountered
When we started working with the InterCardTest
, we found that the DMAs worked fine on some machines but would not occur on others. The systems that worked fine are ones used by the TID development group, rdsrv419
, rdsrv403
, etc. These run the Ubuntu 22.04 OS. On the LCLS nodes drp-srcf-gpu001
and daq-tst-dev06
, the test would fail. These hosts run RHEL7 3.10.0-1160.
Further, when we modified the test_dma.cu
source code to write to the AxiPcieCore.AxiVersion.ScratchPad
register, it would succeed fro gpu001
and fail for dev06
.
A number of things were tried to try and resolve the issue. This may be an incomplete list:
- Install CUDA 12.3 on all machines
- Unsuccessful on gpu001, which went to 12.4
- Install the NVIDIA open drivers v545 on all machines
- Unsuccessful on gpu001, which went to v550
- Disable the IOMMU using
iommu=off
,amd_iommu=off
and/orintel_iommu=off
onGRUB_CMDLINE_LINUX
- Ensure Rogue is at the latest version (v6.1.3)
- Place the KCU and GPU in dev06 with just one PCIe bridge between them (adjacent slots)
- Remove all but one KCU from dev06
- Turn off the Access Control System (ACS) using
setpci
or the BIOS setting- Disabling the ACS Control parameter in the dev06 BIOS appeared to allow the GPU in dev06 to access the KCU's registers. However, doing the equivalent with
setpci
seemed to have no effect in gpu001 (which doesn't appear to have such a BIOS parameter)
- Disabling the ACS Control parameter in the dev06 BIOS appeared to allow the GPU in dev06 to access the KCU's registers. However, doing the equivalent with
Resolution
It appeared that gpu001 and dev06 were able to access the KCU's registers and the DMA was being started. This was surmised by the latency counters in the interCardGui
starting to count when the DMA was triggered by the test_dma
code. By modifying the code, both the write and read DMAs could be started. Judging by the counters never stopping, neither ever completed. The read DMAs caused the ReadAxiErrorCnt
to count and a value of 3 was seen in ReadAxiErrorVal
. Sometimes this was also seen for the write DMAs. Changing the DMA sizes (even down to 0) had no effect on the behavior.
There is a parameter in AxiPcieCore.AxiVersion
block shown by interCardGui
called AXI_PCIE_CONFIG_C_ADDR_WIDTH_C
. Its value was originally 40. Looking at the addresses displayed in AxiGpuAsyncCore
and in the datagpu
driver output in dmesg
, it was noted that on the TID machines the PCI addresses are 40 bits wide and on gpu001 they are 42 bits wide. On dev06
, they are 47 bits wide. Larry updated all affected firmware to allow up to 64-bit PCIe addresses. This allowed the test to work correctly on gpu001
and dev06
. The AXI_PCIE_CONFIG_C_ADDR_WIDTH_C
parameter now has a value of 64 in interCardGui
.