Optimisation of loops and data flow sections
First Claim
Patent Images
1. A method for compiling code for a multi-core processor, comprising:
- detecting and optimizing a loop,partitioning the loop into partitions executable and mappable on physical hardware with optimal instruction level parallelism,optimizing the loop iterations and/or loop counter for ideal mapping on hardware,chaining the loop partitionsgenerating a list representing the execution sequence of the partitions.
1 Assignment
0 Petitions
Accused Products
Abstract
The present invention relates to a method for compiling code for a multi-core processor, comprising: detecting and optimizing a loop, partitioning the loop into partitions executable and mappable on physical hardware with optimal instruction level parallelism, optimizing the loop iterations and/or loop counter for ideal mapping on hardware, chaining the loop partitions generating a list representing the execution sequence of the partitions.
89 Citations
3 Claims
-
1. A method for compiling code for a multi-core processor, comprising:
-
detecting and optimizing a loop, partitioning the loop into partitions executable and mappable on physical hardware with optimal instruction level parallelism, optimizing the loop iterations and/or loop counter for ideal mapping on hardware, chaining the loop partitions generating a list representing the execution sequence of the partitions.
-
-
2. A method for compiling code for a multi-core processor, comprising:
-
detecting and optimizing dataflow sections of the code, partitioning the dataflow sections into partitions executable and mappable on physical hardware with optimal instruction level parallelism, optimizing the outer control structure of the dataflow sections for ideal mapping on hardware, chaining the dataflow partitions generating a list representing the execution sequence of the partitions.
-
-
3. A method for operating a processor comprising:
-
scheduling by a first scheduler the available processing hardware resource, providing a thread and/or microthread a list of respectively allocated hardware resources, scheduling and mapping partitioned dataflow code onto the allocated hardware resources, and configuring the interconnection between the hardware resources.
-
Specification