You can keep the array processors fed with low IPC and frequency by having absolutely massive vector lengths, the engineering for that kind of processor isn’t in the pipeline, branch prediction etc. it’s in the APUs and how to stream data into them. Much more like GPUs, in fact RISC-V has instructions for gather/scatter.
You can keep the array processors fed with low IPC and frequency by having absolutely massive vector lengths, the engineering for that kind of processor isn’t in the pipeline, branch prediction etc. it’s in the APUs and how to stream data into them. Much more like GPUs, in fact RISC-V has instructions for gather/scatter.