[misc] Prettify KernelProfiler outputs

[yuanming-hu]

Before

[  0.18%] copy_dynamic_c24_1_kernel_83_listgen_S24dynamic    min   5.534 ms   avg   5.541 ms   max   5.553 ms   total   0.017 s [      3x]
[  0.01%] copy_dynamic_c24_1_kernel_84_struct_for     min   0.173 ms   avg   0.174 ms   max   0.176 ms   total   0.001 s [      3x]
[  0.00%] copy_dynamic_nd_c22_0_kernel_73_clear_list_S24dynamic    min   0.093 ms   avg   0.111 ms   max   0.133 ms   total   0.000 s [      3x]
[  0.18%] copy_dynamic_nd_c22_0_kernel_74_listgen_S24dynamic    min   5.470 ms   avg   5.524 ms   max   5.553 ms   total   0.017 s [      3x]
[  0.01%] copy_dynamic_nd_c22_0_kernel_75_struct_for    min   0.408 ms   avg   0.411 ms   max   0.417 ms   total   0.001 s [      3x]
[  0.00%] copy_dynamic_nd_c22_1_kernel_76_clear_list_S24dynamic    min   0.093 ms   avg   0.120 ms   max   0.136 ms   total   0.000 s [      3x]
[  0.19%] copy_dynamic_nd_c22_1_kernel_77_listgen_S24dynamic    min   5.472 ms   avg   5.758 ms   max   6.093 ms   total   0.017 s [      3x]

After

CUDA Profiler
=========================================================================
[      %     total   count |      min       avg       max   ] Kernel name
[ 65.90%   2.829 s   2080x |    0.672     1.360     3.494 ms] build_pid_c4_0_kernel_37_struct_for
[  8.04%   0.345 s      1x |  345.204   345.204   345.204 ms] runtime_initialize
[  2.35%   0.101 s   2080x |    0.004     0.048     9.407 ms] snode_deactivate_c50_0_kernel_25_struct_for
[  2.25%   0.097 s   2080x |    0.031     0.046     0.585 ms] p2g_c6_0_kernel_46_struct_for
[  1.61%   0.069 s   2080x |    0.004     0.033     0.333 ms] snode_deactivate_dynamic_c52_0_kernel_17_struct_for
[  1.21%   0.052 s   2080x |    0.023     0.025     1.462 ms] snode_deactivate_c50_1_kernel_31_struct_for

[Click here for the format server]

---

[codecov]

Codecov Report

Merging #1525 into master will decrease coverage by 0.08%.
The diff coverage is n/a.

@@            Coverage Diff             @@
##           master    #1525      +/-   ##
==========================================
- Coverage   86.57%   86.48%   -0.09%     
==========================================
  Files          19       19              
  Lines        3649     3647       -2     
  Branches      648      647       -1     
==========================================
- Hits         3159     3154       -5     
- Misses        358      360       +2     
- Partials      132      133       +1     

Impacted Files	Coverage Δ
python/taichi/lang/meta.py	60.29% <0.00%> (-4.42%)	⬇️
python/taichi/lang/transformer.py	93.11% <0.00%> (-0.40%)	⬇️
python/taichi/lang/ast_checker.py	74.28% <0.00%> (+2.06%)	⬆️

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 1dce5cd...40c660b. Read the comment docs.

[archibate]

Cool! Will we update docs/profiler.rst for this output? (Just copy the PR desc)

[yuanming-hu]

Cool! Will we update docs/profiler.rst for this output? (Just copy the PR desc)

That would be very helpful! Thanks!