公开(公告)号：US09280344B2

公开(公告)日：2016-03-08

申请号：US13628369

申请日：2012-09-27

Applicant: TEXAS INSTRUMENTS INCORPORATED

Inventor： Horst Diewald ,  Johann Zipperer

IPC: G06F9/30 ,  G06F9/38

CPC classification number: G06F9/30007 ,  G06F9/30065 ,  G06F9/30145 ,  G06F9/381 ,  G06F9/3814 ,  G06F9/3885 ,  G06F9/3895

Abstract: A processor includes a plurality of execution units. At least one of the execution units is configured to repeatedly execute a first instruction based on a first field of the first instruction indicating that the first instruction is to be iteratively executed.

Abstract translation: 处理器包括多个执行单元。 执行单元中的至少一个被配置为基于指示要迭代地执行第一指令的第一指令的第一字段来重复执行第一指令。

公开(公告)号：US20140372493A1

公开(公告)日：2014-12-18

申请号：US13918209

申请日：2013-06-14

Applicant: Texas Instruments Incorporated ,  Texas Instruments Deutschland GmbH

Inventor： Brent Everett Peterson ,  Nitya Ramdas ,  Sotirios Christodulos Tsongas ,  Jonathan Zack Albus ,  Johann Zipperer

IPC: G06F7/483

CPC classification number: G06F7/544 ,  G06F2207/5355

Abstract: A system and method for accelerating evaluation of functions. In one embodiment, a method includes receiving, by a processor, a value to be processed, and notification of a function to be applied to the value. The value is represented in a floating point format. The value is converted, by the processor, to a fixed point format. Which of Newton-Raphson and polynomial approximation is to be used to apply the function to the value in the fixed point format is determined by the processor. The function is applied to the value in the fixed point format to generate a result in the fixed point format. The result is converted to the floating point format by the processor.

Abstract translation: 一种加速功能评估的系统和方法。 在一个实施例中，一种方法包括由处理器接收要处理的值以及要应用于该值的功能的通知。 该值以浮点格式表示。 该值由处理器转换为固定点格式。 使用牛顿 - 拉夫森和多项式近似法将函数应用于固定点格式的值由处理器决定。 该函数应用于固定点格式的值，以生成固定点格式的结果。 结果由处理器转换为浮点格式。