add RMSNorm kernel to roofline plots in the latency-demo notebook

[yuhaohaoyu]

Lineage and Dependency

• Sub-task from EPIC [Docs] Add latency estimation demo notebook #94
• Sister-task: for a static multiple-core rmsnorm kernel def: create rmsnorm_fwd_ktir.mlir #164

what's the goal

Add synthetic latency experiments in to the roofline sections of the latency_demo notebook.

What's the benefit

RMSNorm is an important normalization kernel used in IBM's Granite, Llama-3, Gemma, etc. Including it in ktir-cpu's latency demo notebook is great addition to showcase the usefulness of ktir-cpu.

how to assess completion

1. Update codes under notebooks/, with codes to parameterization of the kernel to full fill the 4-core, 32-core-strong-scaling, and 32-core-weak-scaling setup for the roofline section of latency_demo notebook.
2. Notebook run output (capture into html) for visual verification.