Reconfigurable hardware structures for functional pipelining of on-chip special purpose functions

• US 10,055,224 B2
• Filed: 12/10/2015
• Issued: 08/21/2018
• Est. Priority Date: 10/02/2012
• Status: Active Grant

• Current Assignee: Oracle International Corporation (Oracle Corporation)
• Original Assignee: Oracle International Corporation (Oracle Corporation)
• Inventors: Aingaran, Kathirgamar, Swart, Garret F.
• Primary Examiner(s): Misiura, Brian T
• Application Number:
  US14/964,805
• Publication Number:
  US 20160098364A1
• Time in Patent Office: 985 Days
• Field of Search: 707713-719
• CPC Class Codes: G06F 12/0804 with main memory updating G06F12/0806 takes precedence
• CPC Class Codes: G06F 12/082 Associative directories G06F12/0822 takes precedence
• CPC Class Codes: G06F 12/12 Replacement control
• CPC Class Codes: G06F 12/1408 by using cryptography for digital transmission H04L9/00
• CPC Class Codes: G06F 12/1475 in a virtual system, e.g. with translation means
• CPC Class Codes: G06F 13/102 where the programme performs an interfacing function, e.g. device driver G06F13/105 takes precedence; scheduling within device drivers G06F9/52; contention policies within device drivers G06F9/4881
• CPC Class Codes: G06F 13/362 with centralised access control
• CPC Class Codes: G06F 13/4068 Electrical coupling
• CPC Class Codes: G06F 15/17331 Distributed shared memory [DSM], e.g. remote direct memory access [RDMA]
• CPC Class Codes: G06F 15/7889 Reconfigurable logic implemented as a co-processor instruction execution using a coprocessor G06F9/3877
• CPC Class Codes: G06F 16/2237 Vectors, bitmaps or matrices
• CPC Class Codes: G06F 16/2453 Query optimisation
• CPC Class Codes: G06F 16/24553 of query operations
• CPC Class Codes: G06F 16/24558 Binary matching operations
• CPC Class Codes: G06F 16/2456 Join operations
• CPC Class Codes: G06F 16/24561 Intermediate data storage techniques for performance improvement
• CPC Class Codes: G06F 16/24569 Query processing with adaptation to specific hardware, e.g. adapted for using GPUs or SSDs
• CPC Class Codes: G06F 16/273 Asynchronous replication or reconciliation
• CPC Class Codes: G06F 16/284 Relational databases
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 21/6209 : to a single file or object, e.g. in a secure envelope, encrypted and accessed using a key, or with access control rules appended to the object itself
• CPC Class Codes: G06F 9/30065 : Loop control instructions; iterative instructions, e.g. LOOP, REPEAT
• CPC Class Codes: G06F 9/381 : Loop buffering
• CPC Class Codes: G06F 9/3851 : from multiple instruction streams, e.g. multistreaming
• CPC Class Codes: G06F 9/3867 : using instruction pipelines
• CPC Class Codes: G06F 9/546 : Message passing systems or structures, e.g. queues
• CPC Class Codes: H04L 69/14 : Multichannel or multilink protocols
• CPC Class Codes: Y02D 10/00 : Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

A method and apparatus for reconfiguring hardware structures to pipeline the execution of multiple special purpose hardware implemented functions, without saving intermediate results to memory, is provided. Pipelining functions in a program is typically performed by a first function saving its results (the “intermediate results”) to memory, and a second function subsequently accessing the memory to use the intermediate results as input. Saving and accessing intermediate results stored in memory incurs a heavy performance penalty, requires more power, consumes more memory bandwidth, and increases the memory footprint. Due to the ability to redirect the input and output of the hardware structures, intermediate results are passed directly from one special purpose hardware implemented function to another without storing the intermediate results in memory. Consequently, a program that utilizes the method or apparatus, reduces power consumption, consumes less memory bandwidth, and reduces the program'"'"'s memory footprint.

Claims

1. A device comprising:

a first multiplexer operatively coupled between a first streaming functional unit and a first plurality of potential input sources;

wherein the first streaming function unit is dynamically configurable to perform any one of a first plurality of functions;

wherein the first plurality of functions includes a first function;

a second multiplexer operatively coupled between a second streaming functional unit and a second plurality of potential input sources;

wherein the second streaming function unit is dynamically configurable to perform any one of a second plurality of functions;

wherein the second plurality of functions includes a second function;

wherein output of the first streaming functional unit is one potential input source, of the second plurality of potential input sources;

a scheduler configured to perform the following in response to a request to perform an operation that involves the first function and the second function;

determine how to configure the first multiplexer and second multiplexer to make use of the first streaming functional unit and the second streaming functional unit in performing the operation;

send one or more first signals to the first streaming functional unit to dynamically configure the first streaming functional unit to perform the first function;

send one or more second signals to the second streaming functional unit to dynamically configure the second streaming functional unit to perform the second function; and

send signals to the first multiplexer and the second multiplexer to dynamically configure the first multiplexer and second multiplexer to make use of the first streaming functional unit and the second streaming functional unit in performing the operation.

2. The device of claim 1, wherein the scheduler is configured to send signals to:

cause the first multiplexer to pass streaming input from a first selected input source, of the first plurality of potential input sources, to the first streaming functional unit; and

cause the second multiplexer to pass streaming input from output of the first streaming functional unit to the second streaming functional unit.

3. A device comprising:

a first multiplexer operatively coupled between a first streaming functional unit and a first plurality of potential input sources;

a second multiplexer operatively coupled between a second streaming functional unit and a second plurality of potential input sources;

wherein output of the first streaming functional unit is one potential input source, of the second plurality of potential input sources;

a scheduler configured to;

determine how to configure the first multiplexer and second multiplexer to make use of the first streaming functional unit and the second streaming functional unit in processing data; and

send signals to dynamically configure the first multiplexer and second multiplexer to make use of the first streaming functional unit and the second streaming functional unit in processing the data;

wherein the scheduler is further configured to;

cause the first multiplexer to pass streaming input from a first selected input source, of the first plurality of potential input sources, to the first streaming functional unit; and

cause the second multiplexer to pass streaming input from output of the first streaming functional unit to the second streaming functional unit;

cause the first streaming functional unit to perform a first function, of a first plurality of functions that the first streaming functional unit is capable of performing, on data from data passed to the first streaming functional unit from the first multiplexer; and

cause the second streaming functional unit to perform a second function, of a second plurality of functions that the second streaming functional unit is capable of performing, on output from the first streaming functional unit that is passed to the second streaming functional unit from the second multiplexer.

4. The device of claim 3, wherein the first streaming functional unit performs the first function, for at least a portion of time, while the second streaming function unit performs the second function.

5. A device further comprising:

a first multiplexer operatively coupled between a first streaming functional unit and a first plurality of potential input sources;

a second multiplexer operatively coupled between a second streaming functional unit and a second plurality of potential input sources;

wherein output of the first streaming functional unit is one potential input source, of the second plurality of potential input sources;

a third multiplexer operatively coupled between a third streaming functional unit and a third plurality of potential input sources;

wherein the third multiplexer is dynamically configurable to pass streaming input from selected one of the third plurality of potential input sources to the third streaming functional unit;

a fourth multiplexer operatively coupled between a fourth streaming functional unit and a fourth plurality of potential input sources;

wherein output of the third streaming functional unit is one potential input source, of the fourth plurality of potential input sources;

a scheduler configured to;

determine how to configure the first multiplexer and second multiplexer to make use of the first streaming functional unit and the second streaming functional unit in processing data; and

send signals to dynamically configure the first multiplexer and second multiplexer to make use of the first streaming functional unit and the second streaming functional unit in processing the data;

wherein the scheduler is further configured to send signals to;

cause the first multiplexer to pass streaming input from a first selected input source, of the first plurality of potential input sources, to the first streaming functional unit;

cause the second multiplexer to pass streaming input from output of the first streaming functional unit to the second streaming functional unit;

cause the third multiplexer to pass streaming input from a second selected input source, of the third plurality of potential input sources, to the third streaming functional unit; and

cause the fourth multiplexer to pass streaming input from output of the third streaming functional unit to the fourth streaming functional unit.

6. The device of claim 5, wherein the first selected input source of the first plurality of potential input sources and the second selected input source of the third plurality of potential input sources are the same input source.

7. The device of claim 5, wherein:

output of the first streaming functional unit is one potential input source, of the third plurality of potential input sources;

the second selected input source of the third plurality of potential input sources is the output of the first streaming functional unit.

8. The device of claim 5, wherein the scheduler is further configured to cause the first multiplexer to pass streaming input from the first selected input source to the first streaming functional unit, and the third multiplexer to pass streaming input from the second selected input source to the third streaming functional unit, in parallel, for at least a first portion of time.

9. The device of claim 8, wherein the scheduler causes the first streaming functional unit to perform a first function, and the third streaming functional unit to perform a second function, in parallel, for at least a second portion of time.

10. The device of claim 8, wherein the scheduler is further configured to:

receive an execution plan that identifies a first function and a second function;

determine that the first streaming functional unit is capable of performing the first function, but not the second function, and in response, send one or more first signals to the first streaming functional unit to cause the first streaming functional unit to perform the first function;

determine that the second streaming functional unit is capable of performing the second function, but not the first function, and in response, send one or more second signals to the second streaming functional unit to cause the second streaming functional unit to perform the second function.

11. A system comprising:

a memory;

a processor coupled to the memory; and

a specialized coprocessor, coupled to the processor and the memory, wherein the specialized coprocessor comprises;

a first multiplexer operatively coupled between a first streaming functional unit and a first plurality of potential input sources;

wherein the first streaming function unit is dynamically configurable to perform any one of a first plurality of functions;

wherein the first plurality of functions includes a first function;

a second multiplexer operatively coupled between a second streaming functional unit and a second plurality of potential input sources;

wherein the second streaming function unit is dynamically configurable to perform any one of a second plurality of functions;

wherein the second plurality of functions includes a second function;

wherein output of the first streaming functional unit is one potential input source, of the second plurality of potential input sources;

a scheduler configured to perform the following in response to a request to perform an operation that involves the first function and the second function;

determine how to configure the first multiplexer and second multiplexer to make use of the first streaming functional unit and the second streaming functional unit in performing the operation;

send one or more first signals to the first streaming functional unit to dynamically configure the first streaming functional unit to perform the first function;

send one or more second signals to the second streaming functional unit to dynamically configure the second streaming functional unit to perform the second function; and

send signals to the first multiplexer and the second multiplexer to dynamically configure the first multiplexer and second multiplexer to make use of the first streaming functional unit and the second streaming functional unit in performing the operation.

12. The system of claim 11, wherein the specialized coprocessor is configured to send signals to:

cause the first multiplexer to pass streaming input from a first selected input source, of the first plurality of potential input sources, to the first streaming functional unit; and

cause the second multiplexer to pass streaming input from output of the first streaming functional unit to the second streaming functional unit.

13. A system comprising:

a memory;

a processor coupled to the memory; and

a specialized coprocessor, coupled to the processor and the memory, wherein the specialized coprocessor comprises;

a first multiplexer operatively coupled between a first streaming functional unit and a first plurality of potential input sources;

a second multiplexer operatively coupled between a second streaming functional unit and a second plurality of potential input sources;

wherein output of the first streaming functional unit is one potential input source, of the second plurality of potential input sources;

a scheduler configured to;

determine how to configure the first multiplexer and second multiplexer to make use of the first streaming functional unit and the second streaming functional unit in processing data; and

send signals to dynamically configure the first multiplexer and second multiplexer to make use of the first streaming functional unit and the second streaming functional unit in processing the data;

wherein the coprocessor is further configured to;

cause the first multiplexer to pass streaming input from a first selected input source, of the first plurality of potential input sources, to the first streaming functional unit; and

cause the second multiplexer to pass streaming input from output of the first streaming functional unit to the second streaming functional unit;

cause the first streaming functional unit to perform a first function, of a first plurality of functions that the first streaming functional unit is capable of performing, on data from data passed to the first streaming functional unit from the first multiplexer; and

cause the second streaming functional unit to perform a second function, of a second plurality of functions that the second streaming functional unit is capable of performing, on output from the first streaming functional unit that is passed to the second streaming functional unit from the second multiplexer.

14. The system of claim 13, wherein the first streaming functional unit performs the first function, for at least a portion of time, while the second streaming function unit performs the second function.

15. A system of comprising:

a memory;

a processor coupled to the memory; and

a specialized coprocessor, coupled to the processor and the memory, wherein the specialized coprocessor comprises;

a first multiplexer operatively coupled between a first streaming functional unit and a first plurality of potential input sources;

a second multiplexer operatively coupled between a second streaming functional unit and a second plurality of potential input sources;

wherein output of the first streaming functional unit is one potential input

source, of the second plurality of potential input sources;

a third multiplexer operatively coupled between a third streaming functional unit and a third plurality of potential input sources;

wherein the third multiplexer is dynamically configurable to pass streaming input from selected one of the third plurality of potential input sources to the third streaming functional unit;

a fourth multiplexer operatively coupled between a fourth streaming functional unit and a fourth plurality of potential input sources;

wherein output of the third streaming functional unit is one potential input source, of the fourth plurality of potential input sources;

the specialized coprocessor is further configured to;

determine how to configure the first multiplexer and second multiplexer to make use of the first streaming functional unit and the second streaming functional unit in processing data; and

send signals to dynamically configure the first multiplexer and second multiplexer to make use of the first streaming functional unit and the second streaming functional unit in processing the data;

the specialized coprocessor is further configured to send signals to;

cause the first multiplexer to pass streaming input from a first selected input source, of the first plurality of potential input sources, to the first streaming functional unit;

cause the second multiplexer to pass streaming input from output of the first streaming functional unit to the second streaming functional unit;

cause the third multiplexer to pass streaming input from a second selected input source, of the third plurality of potential input sources, to the third streaming functional unit; and

cause the fourth multiplexer to pass streaming input from output of the third streaming functional unit to the fourth streaming functional unit.

16. The system of claim 15, wherein the first selected input source of the first plurality of potential input sources and the second selected input source of the third plurality of potential input sources are the same input source.

17. The system of claim 15, wherein:

output of the first streaming functional unit is one potential input source, of the third plurality of potential input sources;

the second selected input source of the third plurality of potential input sources is the output of the first streaming functional unit.

18. The system of claim 15, wherein the specialized coprocessor is further configured to cause the first multiplexer to pass streaming input from the first selected input source to the first streaming functional unit, and the third multiplexer to pass streaming input from the second selected input source to the third streaming functional unit, in parallel, for at least a first portion of time.

19. The system of claim 18, wherein the specialized coprocessor is further configured to cause the first streaming functional unit to perform a first function, and the third streaming functional unit to perform a second function, in parallel, for at least a second portion of time.

20. The system of claim 18, wherein the specialized coprocessor is further configured to:

determine an execution plan that identifies a first function and a second function;

determine that the first streaming functional unit is capable of performing the first function, but not the second function, and in response, send one or more first signals to the first streaming functional unit to cause the first streaming functional unit to perform the first function;

determine that the second streaming functional unit is capable of performing the second function, but not the first function, and in response, send one or more second signals to the second streaming functional unit to cause the second streaming functional unit to perform the second function.