SUBQ $7, (BX)                           // 48832b07
	SUBQ $7, (R11)                          // 49832b07
	SUBQ $7, DX                             // 4883ea07
	SUBQ $7, R11                            // 4983eb07
	SUBQ DX, (BX)                           // 482913
	SUBQ R11, (BX)                          // 4c291b
	SUBQ DX, (R11)                          // 492913
	SUBQ R11, (R11)                         // 4d291b

t2) // Z3 := b * t2 x3.Sub(y3, z3) // X3 := Y3 - Z3 z3.Add(x3, x3) // Z3 := X3 + X3 x3.Add(x3, z3) // X3 := X3 + Z3 z3.Sub(t1, x3) // Z3 := t1 - X3 x3.Add(t1, x3) // X3 := t1 + X3 y3.Mul({{.p}}B(), y3) // Y3 := b * Y3 t1.Add(t2, t2) // t1 := t2 + t2 t2.Add(t1, t2) // t2 := t1 + t2 y3.Sub(y3, t2) // Y3 := Y3 - t2 y3.Sub(y3, t0) // Y3 := Y3 - t0 t1.Add(y3, y3) // t1 := Y3 + Y3 y3.Add(t1, y3) // Y3 := t1 + Y3 t1.Add(t0, t0) // t1 := t0 + t0 t0.Add(t1, t0) // t0 := t1 + t0 t0.Sub(t0, t2) // t0 := t0 -...

*   Enable JIT-compiled i64-indexed kernels on GPU for large tensors with more than 2**32 elements.
    *   Unary GPU kernels: Abs, Atanh, Acos, Acosh, Asin, Asinh, Atan, Cos, Cosh, Sin, Sinh, Tan, Tanh.
    *   Binary GPU kernels: AddV2, Sub, Div, DivNoNan, Mul, MulNoNan, FloorDiv, Equal, NotEqual, Greater, GreaterEqual, LessEqual, Less.

* `tf.lite`
    * Add experimental supports conversion of models that may be larger than 2GB before buffer deduplication

browsers\n\nsmall {\n  @include font-size($small-font-size);\n}\n\n\n// Mark\n\nmark {\n  padding: $mark-padding;\n  background-color: var(--#{$prefix}highlight-bg);\n}\n\n\n// Sub and Sup\n//\n// Prevent `sub` and `sup` elements from affecting the line height in\n// all browsers.\n\nsub,\nsup {\n  position: relative;\n  @include font-size($sub-sup-font-size);\n  line-height: 0;\n  vertical-align: baseline;\n}\n\nsub { bottom: -.25em; }\nsup { top: -.5em; }\n\n\n// Links\n\na {\n  color: rgba(var(--#{$prefix}link-color-rgb),...