FP8
An 8-bit floating-point format that roughly doubles throughput and halves memory versus 16-bit for AI workloads.
Current numbers
~2.9 EF FP4AMD Helios (72× MI455X) rack-scale FP4 (1.4 EF FP8), 31 TB HBM4, ORW double-wide
192 GBHBM3E per Ironwood (TPU v7) chip @ 7.37 TB/s; 4,614 FP8 TFLOPS; 6x memory vs Trillium
9,216chips per Ironwood pod = 42.5 FP8 ExaFLOPS, ~1.77 PB pooled HBM, OCS 3D-torus