Fix for CR-1219310 : Spatial sharing overhead test failure on linux

[aktondak]

Problem solved by the commit

This PR fixes CR-1219310

• The problem was identified as missing init_buffer call which made the instruction buffer all zeros and causing the device to behave in-deterministically.
• This PR also cleans up some utility code in TestRunner class and correctly moves it to ValidateUtilities.

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

CR-1219310
Discovered through testing on Linux by the Linux folks.

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

The problem was solved through correctly using the df-bw control code and modifying the buffer sizes accordingly.

Risks (if any) associated the changes in the commit

None

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

Tested on Windows and linux platforms. Updated metric numbers after testing :
Windows :

Z:\Repos\XRT-MCDM-FORK\XRT-MCDM\build\WRelease\xilinx\xrt>xrt-smi validate --run spatial-sharing-overhead
Validate Device           : [00c5:00:01.1]
    Platform              : NPU
    Power Mode            : Performance
-------------------------------------------------------------------------------
Test 1 [00c5:00:01.1]     : spatial-sharing-overhead
    Details               : **Overhead: 654.9 ms**
    Test Status           : [PASSED]
Z:\Repos\XRT-MCDM-FORK\XRT-MCDM\build\WRelease\xilinx\xrt>xrt-smi validate --run temporal-sharing-overhead
Validate Device           : [00c5:00:01.1]
    Platform              : NPU
    Power Mode            : Performance
-------------------------------------------------------------------------------
Test 1 [00c5:00:01.1]     : temporal-sharing-overhead
    Details               : **Overhead: '682.7' ms**
    Test Status           : [PASSED]

Documentation impact (if any)

N/A

[gbuildx]

Can one of the admins verify this patch?

[mamin506]

The description is not accurate.
The problem was identified as missing init_buffer call which made the instruction buffer all zeros and causing the device to behave in-deterministically.

Just to clarify,
On Linux, missing init_buffer() will not made the instruction buffer all zeros. The true statement is that the instruction buffer will be garbage.
Instead, all zero instruction buffer is the behavior of Windows. It makes the test on Windows run as a no-op kernel. That is why the issue is not exposed on Windows.