Wednesday, March 30, 2005
Torvalds: Put Linux to the test | CNET News.com
Torvalds: Put Linux to the test | CNET News.com: "The issue was raised when Intel employee Kenneth Chen announced some performance figures for various versions of the 2.6 kernel. The tests found that versions 2.6.11, 2.6.9, 2.6.8 and 2.6.2 of the kernel performed 13, 6, 23 and 1 percent slower respectively than the Red Hat Enterprise Linux 3 baseline--which runs on version 2.4 of the kernel, with some added features from version 2.6. "
Tuesday, March 29, 2005
Linux-Kernel Archive: measure time less than 1 jiffie?
Linux-Kernel Archive: measure time less than 1 jiffie?: "because 1 jiffie is 10ms"
Monday, March 28, 2005
Intel desktop crib sheet guide arrives
Intel desktop crib sheet guide arrives: "Intel desktop crib sheet guide arrives "
Friday, March 25, 2005
adaptive path � ajax: a new approach to web applications
adaptive path � ajax: a new approach to web applications: "Google Suggest and Google Maps are two examples of a new approach to web applications that we at Adaptive Path have been calling Ajax. The name is shorthand for Asynchronous JavaScript + XML, and it represents a fundamental shift in what�s possible on the Web."
Thursday, March 24, 2005
Multicore computing, multithreaded programming, and gaming
Multicore computing, multithreaded programming, and gaming: "'implementing a multithreaded system requires two to three times the development and testing effort of implementing a comparable non-multithreaded system.' "
Wednesday, March 23, 2005
Windows System Resource Manager�Frequently Asked Questions
Windows System Resource Manager�Frequently Asked Questions: "Windows System Resource Manager"
Monday, March 21, 2005
Detecting Hyper-Threading Technology and Counting Processors in Multicore Systems
Detecting Hyper-Threading Technology and Counting Processors in Multicore Systems: "Detecting Hyper-Threading Technology and Counting Processors in Multicore Systems"
Friday, March 18, 2005
Cooking with Lisp
Cooking with Lisp: "Robert W. Floyd's 1978 Turing Award Lecture, hosted by Markus Fix here, and he has a great quote about Lisp:
I have seen numerous examples of the programming power which Lisp programmers obtain from having a single data structure, which is also used as a uniform syntactic structure for all the functions and operations which appear in programs, with the capability to manipulate programs as data. Although my own previous enthusiasm has been for syntactically rich languages like the Algol family, I now see clearly and concretely the force of Minsky's 1970 Turing lecture, in which he argued that Lisp's uniformity of structure and power of self reference gave the programmer capabilities whose content was well worth the sacrifice of visual form. "
I have seen numerous examples of the programming power which Lisp programmers obtain from having a single data structure, which is also used as a uniform syntactic structure for all the functions and operations which appear in programs, with the capability to manipulate programs as data. Although my own previous enthusiasm has been for syntactically rich languages like the Algol family, I now see clearly and concretely the force of Minsky's 1970 Turing lecture, in which he argued that Lisp's uniformity of structure and power of self reference gave the programmer capabilities whose content was well worth the sacrifice of visual form. "
Wednesday, March 16, 2005
Supported System Configurations
Supported System Configurations: "J2SE 5.0 does not provide support for Itanium 2 -- Itanium 2 support may be added in subsequent update releases"
Myrinet Overview
Myrinet Overview: "Messages can be sent and received without system calls, resulting in measured message latencies at the MPI level with the 'E card' and 'F card' NICs of ~2.7�s with MX, and ~6.5�s with GM. Message latencies using the popular, low-cost, 'D card' NICs are ~0.8�s higher. Thanks to the OS-pass mode of operation and to protocol processing being offloaded to the firmware, the host-CPU overhead is minimal, ~0.15�s per message for sending or receiving.
For either GM or MX, and with single-port NICs, measured, user-level, one-way, data rates are ~1.98 Gb/s (248 MBytes/s), and two-way (summed bidirectional) data rates are ~3.92 Gb/s (490 MBytes/s). With the high-end, dual-port NICs, the firmware takes care of distributing and reassembling packet data across the two ports. The measured, user-level, one-way data rate of ~3.9 Gb/s (~490 GBytes/s) approaches the capacity of the two links. On hosts with good PCI-X throughput, the two-way (summed bidirectional) data rate approaches 6.4 Gb/s (800 MBytes/s)."
For either GM or MX, and with single-port NICs, measured, user-level, one-way, data rates are ~1.98 Gb/s (248 MBytes/s), and two-way (summed bidirectional) data rates are ~3.92 Gb/s (490 MBytes/s). With the high-end, dual-port NICs, the firmware takes care of distributing and reassembling packet data across the two ports. The measured, user-level, one-way data rate of ~3.9 Gb/s (~490 GBytes/s) approaches the capacity of the two links. On hosts with good PCI-X throughput, the two-way (summed bidirectional) data rate approaches 6.4 Gb/s (800 MBytes/s)."
Tuesday, March 15, 2005
Monday, March 14, 2005
Sun Microsystems Contrarian Minds: Guy Steele
Sun Microsystems Contrarian Minds: Guy Steele: "Called Fortress, the new language is part of a larger Sun Labs effort to come up with a design for the supercomputer of the future, an effort funded in part by DARPA, t"
Tuesday, March 08, 2005
Peeking Into Google
Peeking Into Google: "Google replicates the Web pages it caches by splitting them up into pieces it calls 'shards.' The shards are small enough that several can fit on one machine. And they're replicated on several machines, so that if one breaks, another can serve up the information. The master index is also split up among several servers, and that set also is replicated several times. The engineers call these 'chunk servers.'
As a search query comes into the system, it hits a Web server, then is split into chunks of service. One set of index servers contains the index; one set of machines contains one full index. To actually answer a query, Google has to use one complete set of servers. Since that set is replicated as a fail-safe, it also increases throughput, because if one set is busy, a new query can be routed to the next set, which drives down search time per box. "
As a search query comes into the system, it hits a Web server, then is split into chunks of service. One set of index servers contains the index; one set of machines contains one full index. To actually answer a query, Google has to use one complete set of servers. Since that set is replicated as a fail-safe, it also increases throughput, because if one set is busy, a new query can be routed to the next set, which drives down search time per box. "
Subscribe to:
Posts (Atom)