Serious Question: What about the Apple M[x] series things?
The M2 integrates an Apple designed ten-core (or eight-core) graphics processing unit (GPU). Each GPU core is split into 32 execution units, which each contain eight arithmetic logic units (ALUs). In total, the M2 GPU contains up to 320 execution units or 2,560 ALUs, which have a maximum floating point (FP32) performance of 3.6 TFLOPs.