Code Scheduling & Loop Unrolling Explained + VLIW (Why It Failed in Modern CPUs)

In this video, we explore how compilers and architectures improve performance using code scheduling and loop unrolling, and then connect it to VLIW (Very Long Instruction Word). You’ll learn: What is code scheduling and why it matters How loop unrolling increases parallelism Combining scheduling + loop unrolling for better performance How VLIW architecture works with a complete example Why VLIW is not used in modern CPUs and smartphones This video focuses on building intuition step-by-step so you can clearly understand how instruction-level parallelism is actually achieved in real systems. 0:00 Intro 1:24 Code Scheduling 3:33 Loop unrolling 6:36 Loop Unrolling + Code Scheduling 7:42 Compiler checklist 9:15 Why we cant roll 1000 times ? 11:08 VLIW 14:23 VLIW Example 17:34 Example 2 #CodeScheduling #LoopUnrolling #vliw #ILP #computerarchitecture #CPUDesign #superscalar #CompilerOptimization #pipeline #csstudents #intel #rayzen #amd