… AMD Ryzen 9 3950X Zen 2’s split lock latency lands above Zen 5’s, though it’s still better than what Intel’s newer architectures achieve. Latencies remain constant regardless of cluster boundaries, mirroring behavior seen with Zen 5 and Arrow Lake. …
… Even then, Zen 5 can mostly feed itself from the op cache rather than the decoders. That’s very much where AMD wants to be, since Zen 5’s decoder setup is weaker than Lion Cove’s when running a single thread. …
Evaluating the Infinity Cache in AMD Strix Halo Strix Halo is the codename for AMD’s highest end mobile chip, which is used in the Ryzen AI MAX series. It combines a powerful CPU with 16 Zen 5 cores and a large GPU with 20 RDNA 3.5 Workgroup Processors WGPs . …