US2017364338A1PendingUtilityA1

Tool-level and hardware-level code optimization and respective hardware modification

56
Assignee: HYPERION CORE INCPriority: Jun 8, 2011Filed: Jul 7, 2017Published: Dec 21, 2017
Est. expiryJun 8, 2031(~4.9 yrs left)· nominal 20-yr term from priority
Inventors:Martin Vorbach
G06F 8/4434G06F 30/3323G06F 8/443G06F 8/447G06F 8/41G06F 9/3001G06F 30/34G06F 30/30G06F 17/5054G06F 17/504G06F 17/5045
56
PatentIndex Score
0
Cited by
0
References
0
Claims

Abstract

The present invention related to a method for compiling high-level software code into hardware, transforming each instruction into a respective hardware block and using an execution control signal representing the program pointer for triggering the execution within each respective hardware block.

Claims

exact text as granted — not AI-modified
1 . (canceled) 
     
     
         2 - 8 . (canceled) 
     
     
         9 . A method for translating high-level software code into a hardware representation, the method comprising:
 analyzing the high-level software code by analyzer software;   splitting the high-level software code into blocks, including mapping a plurality of software instructions of the high-level software code to hardware routines,
 one or more blocks of the plurality of blocks comprising one main routine and at least one subordinate code block, the plurality of blocks being defined by jump and call instructions to code sections or subroutines of the high-level software code, 
 each block of the plurality of blocks having a unique identifier, 
 wherein software instructions in each block are mapped to hardware functions and are arranged in an execution order, at least some of the software instructions in each block configured to execute at least one of concurrently and asynchronously, wherein particular instructions of the software instructions that depend on other instructions of the high-level software code receive input data from results produced by the other instructions, 
 wherein the plurality of blocks are configured such that, upon completion of execution of the software instructions in a respective block, the respective block returns a pointer matching the unique identifier of a next block to execute; and 
   generating the hardware representation based on the plurality of blocks.

Cited by (0)

No later patents cite this yet.

References (0)

No backward citations on record.