CR-1214433, CR-1214577 and CR-1215195

[AShivangi]

Problem solved by the commit

• CR-1214433 Error message when gemm test fails appears to be confusing
• CR-1214577 xrt-smi validate does not printing power mode properly or help message is not clear
• CR-1215195 validate with "--run=" doesn't print the help
• add returns to mark the tests failed correctly

Bug / issue (if any) fixed, which PR introduced the bug, how it was discovered

DSV testing

How problem was solved, alternative solutions (if any) and why they were rejected

• Check the context creation failed error ID coming from the driver and wrap it in the userspace
• Add some messages in verbose mode and improve help verbiage. After some internal discussion, we have decided to make this a hidden option as this was requested internally
• add try/catch

Risks (if any) associated the changes in the commit

Low

What has been tested and how, request additional testing if necessary

Tested on Strix
CR 1:

> xrt-smi validate -r latency --pmode default --verbose
Verbose: Enabling Verbosity
Verbose: Sub command: --pmode
Verbose: Setting power mode to `default`

Validate Device           : [00c5:00:01.1]
    Platform              : NPU
    Power Mode            : Default
-------------------------------------------------------------------------------
Test 1 [00c5:00:01.1]     : latency
    Description           : Run end-to-end latency test
    Benchmarks            : <>
    Details               : Threshold is <> us
    Xclbin                : <>
    Details               : Kernel name is 'DPU_PDI_0'
                            Instruction size: 20 bytes
                            No. of iterations: 10000
                            Average latency: <> us
    Test Status           : [PASSED]
-------------------------------------------------------------------------------
Validation completed


>xrt-smi validate -r latency --verbose
Verbose: Enabling Verbosity
Verbose: Setting power mode to `performance`

Validate Device           : [00c5:00:01.1]
    Platform              : NPU
    Power Mode            : Performance
-------------------------------------------------------------------------------
Test 1 [00c5:00:01.1]     : latency
    Description           : Run end-to-end latency test
    Benchmarks            : <>
    Details               : Threshold is <> us
    Xclbin                : <>
    Details               : Kernel name is 'DPU_PDI_0'
                            Instruction size: 20 bytes
                            No. of iterations: 10000
                            Average latency: <> us
    Test Status           : [PASSED]
-------------------------------------------------------------------------------
Validation completed

CR 2:

>xrt-smi validate -r gemm
Validate Device           : [00c5:00:01.1]
    Platform              : NPU
    Power Mode            : Performance
-------------------------------------------------------------------------------
Verbose: Enabling Verbosity
Test 1 [00c5:00:01.1]     : gemm
    Description           : Measure the TOPS value of GEMM operations
    Benchmarks            : <>
    Details               : Threshold is <> TOPS
    Xclbin                : <>
    Details               : Kernel name is 'DPU_1x4'
    Error(s)              : Not enough columns available. Please make sure not other
                            workload is running on the device.
    Test Status           : [FAILED]
-------------------------------------------------------------------------------
Validation failed

CR 3:

$ xrt-smi validate --run=
the argument for option '--run' should follow immediately after the equal sign

DESCRIPTION: The Xilinx (R) Run Time - System Management Interface (xrt-smi) is a standalone
             command line utility that is included with the Xilinx Run Time (XRT) installation
             package. It includes multiple commands to identify and validate the installed card(s).
             
             This information can be used for both card administration and application debugging.

USAGE: xrt-smi[--help] [--version] [--verbose] [--batch] [--force] [command [commandArgs]]

AVAILABLE COMMANDS:
  configure  - Device and host configuration
  examine    - Status of the system and device
  program    - Download the acceleration program to a given device
  reset      - Resets the given device
  validate   - Validates the basic shell acceleration functionality

OPTIONS:
  --help             - Help to use this application
  --version          - Report the version of XRT and its drivers
  --verbose          - Turn on verbosity
  --batch            - Enable batch mode (disables escape characters)
  --force            - When possible, force an operation

Documentation impact (if any)

N/A

[rchane]

Looks good to me!

[aktondak]

Looks Good