IP Library › Granted Patent US 10,037,229
Granted Patent B2
US 10,037,229 · App. 15/152,257 · Granted Jul 31, 2018

Operation of a multi-slice processor implementing a load/store unit maintaining rejected instructions

Inventors: Sundeep Chadha (Austin, TX); Robert A. Cordes (Austin, TX); David A. Hrusecky (Cedar Park, TX); Hung Q. Le (Austin, TX); Elizabeth A. McGlone (Rochester, MN)
Assignee: International Business Machines Corporation
G06F9/5027
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,037,229
App. No.
15/152,257
Granted
Jul 31, 2018
Kind
B2
Abstract

Operation of a multi-slice processor that includes a plurality of execution slices, a plurality of load/store slices, and one or more instruction sequencing units, where operation includes: receiving, at a load/store slice from an instruction sequencing unit, a instruction to be issued; determining, at the load/store slice, a rejection condition for the instruction; and responsive to determining the rejection condition for the instruction, maintaining state information for the instruction in the load/store slice instead of notifying the instruction sequencing unit of a rejection of the instruction.

Claims (42)

1. A multi-slice processor comprising:

an instruction sequencing unit, a plurality of execution slices, and a plurality of load/store slices, wherein the multi-slice processor is configured to carry out:

receiving, at a load/store slice from the instruction sequencing unit, an instruction to be issued;

determining, at the load/store slice, a rejection condition for the instruction; and

responsive to determining the rejection condition for the instruction, maintaining state information for the instruction in the load/store slice instead of notifying the instruction sequencing unit of a rejection of the instruction.

2. The multi-slice processor of claim 1 , wherein the multi-slice processor is further configured to carry out:

determining that the rejection condition for the instruction has resolved or is pending resolution; and

responsive to determining that the rejection condition for the instruction has resolved or is pending resolution, reissuing the instruction from within the load/store slice.

3. The multi-slice processor of claim 2 , wherein the multi-slice processor is further configured to carry out:

responsive to determining that the rejection condition for the instruction has resolved or is pending resolution, notifying the instruction sequencing unit that the instruction is being reissued.

4. The multi-slice processor of claim 2 , wherein the instruction is a load instruction, and wherein the multi-slice processor is further configured to carry out:

determining an arrival of data for the instruction from a lower tier of memory into a data cache on the load/store slice; and

scheduling the instruction to be issued such that the instruction may provide the data for the instruction to a destination without accessing the data cache.

5. The multi-slice processor of claim 1 , wherein the multi-slice processor is further configured to carry out:

determining that the rejection condition is expected to resolve within a quantity of cycles; and

responsive to determining that the rejection condition is expected to resolve within the quantity of cycles, scheduling the instruction to be issued coincident with a lapse of the quantity of cycles.

6. The multi-slice processor of claim 1 , wherein the load/store slice comprises a load/store access queue and a load reorder queue, and wherein receiving the instruction to be issued comprises:

determining that the instruction is a load instruction; and

providing, from the load/store access queue to the load reorder queue, the instruction.

7. The multi-slice processor of claim 1 , wherein the load/store slice comprises a load/store access queue and a store reorder queue, and wherein receiving the instruction to be issued comprises:

determining that the instruction is a store instruction; and

providing, from the load/store access queue to the store reorder queue, the instruction.

8. An apparatus comprising:

a multi-slice processor and computer memory coupled to the multi-slice processor, wherein the multi-slice processor comprises:

an instruction sequencing unit, a plurality of execution slices, and a plurality of load/store slices, wherein the multi-slice processor is configured to carry out:

receiving, at a load/store slice from the instruction sequencing unit, an instruction to be issued;

determining, at the load/store slice, a rejection condition for the instruction; and

responsive to determining the rejection condition for the instruction, maintaining state information for the instruction in the load/store slice instead of notifying the instruction sequencing unit of a rejection of the instruction.

9. The apparatus of claim 8 , wherein the multi-slice processor is further configured to carry out:

determining that the rejection condition for the instruction has resolved or is pending resolution; and

responsive to determining that the rejection condition for the instruction has resolved or is pending resolution, reissuing the instruction from within the load/store slice.

10. The apparatus of claim 9 , wherein the multi-slice processor is further configured to carry out:

responsive to determining that the rejection condition for the instruction has resolved or is pending resolution, notifying the instruction sequencing unit that the instruction is being reissued.

11. The apparatus of claim 10 , wherein the instruction is a load instruction, and wherein the multi-slice processor is further configured to carry out:

determining an arrival of data for the instruction from a lower tier of memory into a data cache on the load/store slice; and

scheduling the instruction to be issued such that the instruction may provide the data for the instruction to a destination without accessing the data cache.

12. The apparatus of claim 8 , wherein the multi-slice processor is further configured to carry out:

determining that the rejection condition is expected to resolve within a quantity of cycles; and

responsive to determining that the rejection condition is expected to resolve within the quantity of cycles, scheduling the instruction to be issued coincident with a lapse of the quantity of cycles.

13. The apparatus of claim 8 , wherein the load/store slice comprises a load/store access queue and a load reorder queue, and wherein receiving the instruction to be issued comprises:

determining that the instruction is a load instruction; and

providing, from the load/store access queue to the load reorder queue, the instruction.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 11, 2016
From: CHADHA, SUNDEEP; CORDES, ROBERT A.; HRUSECKY, DAVID A.; LE, HUNG Q.; MCGLONE, ELIZABETH A.
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 038552/0365 →
Continuity (1)
Related Publication 20170329641A1 · Nov 16, 2017