Adaptive channel for algorithms with different latency and performance points

1. A method for processing requests in a channel, the method comprising:

receiving a first request in the channel;

based on determining that no subsequent requests are received in a predetermined time window, running calculations on the first request in a processing time TP; and

based on receiving at least one of a plurality of subsequent requests prior to the expiration of the predetermined time window:

creating a batch;

adding the first request and each of the plurality of subsequent requests to the batch; and

processing the batch in a time TB, in response to at least one of a timeout of the batch and a capacity of the channel is reached,

wherein the predetermined time window is equal to TQ−TB, where TQ is a Quality of Service (QoS) time requirement in which at least one of the processed first request and the processed batch is returned.

2. The method as claimed in claim 1 wherein the channel is a Quality of Service (QoS) channel.

3. The method as claimed in claim 2 further comprising returning the first request as a processed request.

4. The method as claimed in claim 3 wherein the processed request is returned in a QoS time TQ, wherein TP<TQ.

5. The method as claimed in claim 4 further comprising launching the batch in response to a time T being equal to TQ−TB, where T is the time after receipt of the first request in the channel.

6. The method as claimed in claim 4 wherein the calculations are run on the first request in response to a determination that no other of the plurality of subsequent requests were received in a time TQ−TB.

7. The method as claimed in claim 1 further comprising delaying running calculations on the plurality of subsequent requests in response to receiving one or more of the plurality of subsequent requests while running calculations on the first request.

8. The method as claimed in claim 1 further comprising initiating pre-computation calculations on the first request.

9. A computer program product for processing requests in a channel, the computer program product including a non-transitory computer readable medium having instructions for causing a computer to implement a method, the method comprising:

receiving a first request in the channel;

based on determining that no subsequent requests are received in a predetermined time window, running calculations on the first request in a processing time; and

based on receiving at least one of a plurality of subsequent prior to the expiration of the predetermined time window:

creating a batch;

adding the first request and each of the plurality of subsequent requests to the batch; and

processing the batch in a time TB, in response to at least one of a timeout of the batch and a capacity of the channel is reached,

wherein the predetermined time window is equal to TQ−TB, where TQ is a Quality of Service (QoS) time in which at least one of the processed first request and the processed batch is returned.

10. The computer program product as claimed in claim 9 wherein the channel is a Quality of Service (QoS) channel.

11. The computer program product as claimed in claim 10 wherein the method further comprises returning the first request as a processed request.

12. The computer program product as claimed in claim 11 wherein the processed request is returned in a QoS time TQ, wherein TP<TQ.

13. The computer program product as claimed in claim 12 further comprising launching the batch in response to a time T being equal to TQ−TB, where T is the time after receipt of the first request in the channel.

14. The computer program product as claimed in claim 12 wherein the calculations are run on the first request in response to a determination that no other of the plurality of subsequent requests were received in a time TQ−TB.

15. The computer program product as claimed in claim 9 wherein the method further comprises delaying running calculations on the plurality of subsequent requests in response to receiving one or more of the plurality of subsequent requests while running calculations on the first request.

16. The computer program product as claimed in claim 9 further comprising initiating pre-computation calculations on the first request.

17. A system for processing requests in a channel, the system comprising:

a processor configured to:

receive a first request in the channel;

based on determining that no subsequent requests are received in a predetermined time window, run calculations on the first request in a processing time TP; and

based on receiving at least one of a plurality of subsequent requests prior to the expiration of the predetermined time window:

create a batch;

add the first request and each of the plurality of subsequent requests to the batch; and

process the batch in a time TB, in response to at least one of a timeout of the batch and a capacity of the channel is reached;

wherein the batch is launched in response to a time T being equal to TQ−TB, where T is the time after receipt of the first request in the channel and where TQ is a Quality of Service (QoS) time in which the processed request is returned.

18. The system as claimed in claim 17 wherein the channel is a Quality of Service (QoS) channel.

19. The system as claimed in claim 18 wherein the calculations are run on the first request in response to a determination that no other of the plurality of subsequent requests were received in a time TQ−TB.

20. The system as claimed in claim 18 wherein the processor is further configured to:

initiate pre-computation calculations on the first request;

delay running calculations on the plurality of subsequent requests in response to receiving one or more of the plurality of subsequent requests while running calculations on the first request; and

return the first request as a processed request,

wherein the processed request is returned in a QoS time TQ, wherein TP<TQ.