TorchLean API

FloatLib.Floats.Formats.OCP.MX.E2M3

OCP MX E2M3 #

E2M3 is a six-bit finite floating element from the OCP microscaling specification. The runtime carrier is a UInt8 with an erased proof that the code is below 64. For addition, subtraction, multiplication, division, and square root, balanced and throughput planning select exhaustive proved tables; latency planning selects arithmetic kernels. Fused multiply-add keeps both a table and the generic proved kernel: throughput planning selects the table, while balanced and latency-oriented planning avoid its larger lookup footprint.

Reference #

OCP MX E2M3 six-bit element format with byte-backed storage.

    Instances For

      Certified E2M3 fused-multiply-add table.

      Its generation equation is opaque, so importing this package does not normalize the 262,144 entries.

      Instances For
        @[instance_reducible, always_inline]
        @[inline]

        Construct E2M3 from a natural pattern, reduced to six bits.

        Instances For
          @[inline]

          Read the byte whose low six bits contain the E2M3 code.

          Instances For