US6499028B1
Expired / Lapsed
US
⏱️ 0.0 years remaining
Efficient identification of candidate pages and dynamic response in a NUMA computer
Assignee: International Business Machines Corp
•
Filing: 1999-03-31
•
Granted: 2002-12-24
•
Expires: 2019-03-31
Abstract
Abstract A performance monitor configured to count memory transactions and to issue an interrupt to the computer system if the monitor detects a specified number of transactions associated with a particular segment of the physical address space of the system. The monitor includes an interface suitable for coupling to an interconnect network of a computer system and configured to extract physical address information from a transaction traversing the interconnect network, a translation module adapted for associating the extracted physical address with one of a plurality of memory blocks and, in response thereto, incrementing a memory block counter corresponding to the memory block, and an interrupt unit configured to assert an interrupt if the block counter exceeds a predetermined value. The interface unit is configurable to selectively monitor either incoming or outgoing transactions and the translation unit preferably includes a plurality of region filters each comprising one or more of the memory blocks. In the preferred embodiment, the plurality of block counters are implemented with a random access memory device. In one embodiment useful for simulating operation of the system and for checking the design of the performance monitor, the monitor further includes a transaction generator coupled to the interconnect network and configured to issue specified remote memory transactions at specified intervals if a monitor enable bit of the performance monitor is disabled. In one embodiment, the transaction generator is configurable to issue either outgoing transactions or incoming transactions.
Inventors
- 👤 Bishop Chapman Brock
- 👤 Eli Chiprout
- 👤 Elmootazbellah Nabil Elnozahy
- 👤 David Brian Glasco
- 👤 Ramakrishnan Rajamony
- 👤 Freeman Leigh Rawson, III
- 👤 Ronald Lynn Rockhold
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-05 14:45
CPC Classifications
G; G06; G06F; G06F11/00; G06F11/30; G06F11/34; G06F11/3409; G06F11/3466; G06F11/3471; G06F12/00; G06F12/02; G06F12/08; G06F11/3414; G06F11/3495; G06F12/0802; G06F12/0806; G06F12/0813; G06F2201/00; G06F2201/81; G06F2201/86; G06F2201/87; G06F2201/88; G06F2212/00; G06F2212/25; G06F2212/254; G06F2212/2542; Y; Y10; Y10S; Y10S707/00; Y10S707/99931; Y10S707/99933; Y10S707/99934
Claims Analysis
Total Claims: 23
Claim 1
Independent Claim
103 words
A performance monitor, comprising: an interface suitable for coupling to an interconnect network of a computer system, the interconnect network linking a local node of the computer with at least one remote node of the computer, wherein the interface is configured to extract physical address information from a transaction traversing the interconnect network; a translation module adapted for associating the physical address with one of a plurality of memory blocks and, responsive thereto, incrementing a memory block counter corresponding to the memory block; and an interrupt unit configured to assert an interrupt if the at least one block counter exceeds a predetermined value.
Claim 2
Dependent Claim
103 words
A performance monitor, comprising: an interface suitable for coupling to an interconnect network of a computer system, the interconnect network linking a local node of the computer with at least one remote node of the computer, wherein the interface is configured to extract physical address information from a transaction traversing the interconnect network; a translation module adapted for associating the physical address with one of a plurality of memory blocks and, responsive thereto, incrementing a memory block counter corresponding to the memory block; and an interrupt unit configured to assert an interrupt if the at least one block counter exceeds a predetermined value.
Claim 3
Dependent Claim
21 words
The performance monitor of claim 1 , wherein the interface unit is configurable to selectively monitor either incoming or outgoing transactions.
Claim 4
Dependent Claim
60 words
The performance monitor of claim 1 , wherein the translation module includes a plurality of region filters configured to receive the physical address, wherein each of the region filters is associated with a contiguous region of physical address space and further wherein an output of each of the filters is indicative of whether the physical address lies within the region.
Claim 5
Dependent Claim
25 words
The performance monitor of claim 3 , wherein each of the regions is comprised of at least one of the plurality of the memory blocks.
Claim 6
Dependent Claim
56 words
The performance monitor of claim 4 , wherein the size and number of memory blocks comprising each of the regions is programmably defined by a region descriptor, wherein the region descriptor includes a base address and wherein the region descriptor is programmably alterable via a programming interface coupled to an I/O bus of the local node.
Claim 7
Dependent Claim
19 words
The performance monitor of claim 1 , wherein the block counters are comprised of a random access memory device.
Claim 8
Dependent Claim
37 words
The performance monitor of claim 1 , wherein each of the block counters is associated with a programmable interrupt disable bit operable to prevent the interrupt unit from asserting an interrupt corresponding to the associated block counter.
Claim 9
Dependent Claim
37 words
The performance monitor of claim 1 , further comprising a transaction generator coupled to the interconnect network and operable to issue specified transactions at specified intervals if a monitor enable bit of the performance monitor is disabled.
Claim 10
Dependent Claim
21 words
The performance monitor of claim 8 , wherein the performance monitor is configurable to issue either outgoing transactions or incoming transactions.
Claim 11
Dependent Claim
170 words
A computer system, comprising: a local node including at least one processor coupled to a local memory of the local node via a local bus of the local node; at least one remote node, each including at least one processor coupled to a local memory of the remote node via a local bus of the remote node; an interconnect network coupling the remote node to the local node via which the local node can access the local memory of the remote node and the remote node can access the local memory of the local node; and a performance monitor including an interface suitable for coupling to the interconnect network and configured to extract physical address information from a transaction traversing the interconnect network, a translation module adapted for associating the physical address with one of a plurality of memory blocks and, responsive thereto, incrementing at a block counter corresponding to the memory block, and an interrupt unit configured to assert an interrupt if the block counter exceeds a predetermined value.
Claim 12
Dependent Claim
170 words
A computer system, comprising: a local node including at least one processor coupled to a local memory of the local node via a local bus of the local node; at least one remote node, each including at least one processor coupled to a local memory of the remote node via a local bus of the remote node; an interconnect network coupling the remote node to the local node via which the local node can access the local memory of the remote node and the remote node can access the local memory of the local node; and a performance monitor including an interface suitable for coupling to the interconnect network and configured to extract physical address information from a transaction traversing the interconnect network, a translation module adapted for associating the physical address with one of a plurality of memory blocks and, responsive thereto, incrementing at a block counter corresponding to the memory block, and an interrupt unit configured to assert an interrupt if the block counter exceeds a predetermined value.
Claim 13
Dependent Claim
61 words
The computer system of claim 10 , wherein the translation module includes a plurality of region filters adapted to receive the physical address information, wherein each the region filter is associated with a contiguous region of the system's physical address space and further wherein an output signal of each filter is indicative of whether the physical address lies within the region.
Claim 14
Dependent Claim
24 words
The system of claim 11 , wherein each of the regions is comprised of at least one of the plurality of the memory blocks.
Claim 15
Dependent Claim
27 words
The system of claim 12 , wherein the number and size of the memory blocks comprising each of the regions is programmably alterable via a programming interface.
Claim 16
Dependent Claim
36 words
The system of claim 10 , wherein the computer system is configured to respond to the interrupt from the interrupt unit by decreasing the size of the memory blocks in the region associated with the interrupt.
Claim 17
Dependent Claim
34 words
The system of claim 10 , wherein the computer system is configured to respond to the interrupt by migrating the contents of the memory block responsible for triggering the interrupt to a different node.
Claim 18
Dependent Claim
36 words
The system of claim 10 , further comprising a transaction generator coupled to the interconnect network and operable to issue specified transactions at specified intervals if a monitor enable bit of the performance monitor is disabled.
Claim 19
Independent Claim
91 words
A method of monitoring performance of a computer system comprising: defining physical address boundaries for a plurality of memory blocks; extracting physical address information from transactions traversing an interconnect network of the computer system, the interconnect network linking a local node of the computer system with at least one remote node of the computer system; associating the physical address with one of the plurality of memory blocks and, in response thereto, incrementing a block counter corresponding to memory block; and asserting an interrupt if the block counter exceeds a specified maximum.
Claim 20
Independent Claim
91 words
A method of monitoring performance of a computer system comprising: defining physical address boundaries for a plurality of memory blocks; extracting physical address information from transactions traversing an interconnect network of the computer system, the interconnect network linking a local node of the computer system with at least one remote node of the computer system; associating the physical address with one of the plurality of memory blocks and, in response thereto, incrementing a block counter corresponding to memory block; and asserting an interrupt if the block counter exceeds a specified maximum.
Claim 21
Dependent Claim
50 words
The method of claim 17 , wherein the step of defining the memory blocks comprises: defining a memory region by programming a base address field of a region descriptor; and dividing the memory region into the memory blocks by programming a block size and block count of the region descriptor.
Claim 22
Dependent Claim
28 words
The method of claim 17 , further comprising, in response to the interrupt, migrating the contents of the memory block responsible for the interrupt to a different node.
Claim 23
Dependent Claim
36 words
The method of claim 17 , further comprising, in response to the interrupt, subdividing the memory block responsible for the interrupt into a plurality of smaller memory blocks and repeating the steps of claim 14 .
References Cited (Backward Citations)
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2005-12-23 | 2006-06-24 | 2006-12-24 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2009-12-23 | 2010-06-24 | 2010-12-24 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2013-12-23 | 2014-06-24 | 2014-12-24 | $7700.00 | Window Closed / Lapsed |