• In computing, minifloats are floating-point values represented with very few bits. This reduced precision makes them ill-suited for general-purpose numerical...
    25 KB (2,050 words) - 13:17, 3 October 2024
  • floating-point format with 8 bits of exponent and 7 bits of mantissa Minifloat: small floating-point formats IEEE 754: IEEE standard for floating-point...
    21 KB (1,875 words) - 00:13, 3 October 2024
  • (binary128), decimal128 256-bit: Octuple (binary256) Extended precision Other Minifloat bfloat16 TensorFloat-32 Microsoft Binary Format IBM floating-point architecture...
    901 bytes (94 words) - 12:47, 23 May 2024
  • 754 ISO/IEC 10967, Language Independent Arithmetic Primitive data type Minifloat Google Brain Lawsuit against Google for its use of bfloat16 in TPU Teich...
    30 KB (1,800 words) - 18:15, 10 September 2024
  • Thumbnail for Floating-point arithmetic
    Architecture Kahan summation algorithm Microsoft Binary Format (MBF) Minifloat Q (number format) for constant resolution Quadruple-precision floating-point...
    117 KB (14,091 words) - 00:35, 5 October 2024
  • (binary128), decimal128 256-bit: Octuple (binary256) Extended precision Other Minifloat bfloat16 TensorFloat-32 Microsoft Binary Format IBM floating-point architecture...
    17 KB (1,894 words) - 05:42, 1 September 2024
  • (binary128), decimal128 256-bit: Octuple (binary256) Extended precision Other Minifloat bfloat16 TensorFloat-32 Microsoft Binary Format IBM floating-point architecture...
    12 KB (1,133 words) - 20:19, 11 April 2023
  • (binary128), decimal128 256-bit: Octuple (binary256) Extended precision Other Minifloat bfloat16 TensorFloat-32 Microsoft Binary Format IBM floating-point architecture...
    29 KB (3,672 words) - 01:52, 6 September 2024
  • fully in hardware ISO/IEC 10967, language-independent arithmetic (LIA) Minifloat, low-precision binary floating-point formats following IEEE 754 principles...
    63 KB (7,511 words) - 07:13, 16 September 2024
  • Thumbnail for G.711
    (binary128), decimal128 256-bit: Octuple (binary256) Extended precision Other Minifloat bfloat16 TensorFloat-32 Microsoft Binary Format IBM floating-point architecture...
    15 KB (1,816 words) - 19:17, 6 September 2024