[libc] Add Kernel Resource Usage to nvptx-loader (#97503)
This PR allows `nvptx-loader` to read the resource usage of `_start`,
`_begin`, and `_end` when executing CUDA binaries.
Example output:
```
$ nvptx-loader --print-resource-usage libc/benchmarks/gpu/src/ctype/libc.benchmarks.gpu.src.ctype.isalnum_benchmark.__build__
[ RUN ] LlvmLibcIsAlNumGpuBenchmark.IsAlnumWrapper
[ OK ] LlvmLibcIsAlNumGpuBenchmark.IsAlnumWrapper: 93 cycles, 76 min, 470 max, 23 iterations, 78000 ns, 80 stddev
_begin registers: 25
_start registers: 80
_end registers: 62
```
---------
Co-authored-by: Joseph Huber <huberjn@outlook.com>
