Skip to main content

AMD Rolls Out 45nm Quad-Core Opteron CPUs

AMD Rolls Out 45nm Quad-Core Opteron CPUs

Chipmaker AMD has formally rolled out its new 45nm Quad-Core Opteron processors. Dubbed “Shanghai” and aimed at the high performance workstation and server market, the new CPUs are designed to offer advanced virtualization capabilities—so one processor can, in effect, host several systems, potentially running different operating systems—and more efficient operation: according to AMD, the new chips offer up to 35 percent more performance than previous AMD processors, while running on up to 35 percent less power. Although the chip comes almost a year after Intel shipped its 45 nm workstation and server processors, AMD is hoping to capture additional marketshare by offering a more efficient chip designed to handle virtualization more easily.

“Flawless execution in bringing the 45nm Quad-Core AMD Opteron processor to market early results in new performance leadership on x86 servers,” said AMD senior VP for computing solutions Randy Allen, in a statement. “In concert with our OEM and solution provider partners, AMD is addressing the need for enterprises to focus on their bottom line while giving them the innovations they need to build for the future.”

Note AMD’s emphasis on “flawless” after a hamstrung launch of its previous Barcelona and Phenonm processors, which were hit by a design flaw that could cause the processors to lock up.

The new Shanghai processors bump on-boar cache to 6 MB, offer integrated DDR2-800 memory support, and significantly higher clock speeds than their predecessors. AMD is touting the Shanghai processors as an easier upgrade than competing Intel processor, since it can be slotted into the same Socket 1207 architecture that rolled out with previous CPUS; AMD also plans to use Socket 1207 with its next line of Opterons, codenamed “Istanbul.” Two versions of the Shanghai chip are available now, and AMD says enhanced versions, due in January 2009, should be able to push 17.68GB/s between processors.

Dell, Hewlett-Packard, Sun Microsystems, and IBM are already on-board to produce systems build around Shanghai; initial offerings are expected to be aimed at data centers and workstations, but high-end consumer-oriented systems aren’t inconceivable.

Geoff Duncan
Former Digital Trends Contributor
Geoff Duncan writes, programs, edits, plays music, and delights in making software misbehave. He's probably the only member…
A dangerous new jailbreak for AI chatbots was just discovered
the side of a Microsoft building

Microsoft has released more details about a troubling new generative AI jailbreak technique it has discovered, called "Skeleton Key." Using this prompt injection method, malicious users can effectively bypass a chatbot's safety guardrails, the security features that keeps ChatGPT from going full Taye.

Skeleton Key is an example of a prompt injection or prompt engineering attack. It's a multi-turn strategy designed to essentially convince an AI model to ignore its ingrained safety guardrails, "[causing] the system to violate its operators’ policies, make decisions unduly influenced by a user, or execute malicious instructions," Mark Russinovich, CTO of Microsoft Azure, wrote in the announcement.

Read more