Intel Archives - Jet Developers Blog

Intel’s Sierra Forest Chip Revolutionizes Data Center Efficiency

Intel’s latest innovation, the Sierra Forest chip, is set to redefine efficiency standards in the realm of microchips. With a launch projected for 2024, this cutting-edge data center chip boasts an unparalleled double-efficiency feature while maintaining the same power consumption as its counterparts. This development aligns seamlessly with the industry-wide commitment to curbing power usage and enhancing both cost-effectiveness and ecological sustainability.

At a prominent semiconductor technology conference hosted by Stanford University in Silicon Valley, Intel took the wraps off the upcoming “Sierra Forest” chip. What sets this chip apart is its remarkable promise of delivering a remarkable 240% improvement in performance per watt compared to Intel’s current generation of data center chips. This revelation holds profound implications, particularly given the staggering electricity consumption of data centers that drive the modern digital landscape. With mounting pressure on technology firms to rein in energy usage, this breakthrough could be a game-changer.

The insatiable appetite for energy within data centers, mainly driven by server maintenance, prompted Intel’s innovation. To put the figures in perspective, C and C Technology Group estimates that data centers gulp down about 1,000 kWh per square meter—a staggering tenfold more than an average American household. This prodigious energy demand is primarily attributed to server racks, the backbone of data centers, which not only require substantial power to function but also demand extensive energy resources to maintain optimal temperatures. The inefficiency of cooling systems further compounds the issue, accounting for a staggering 70% of a data center’s total energy consumption.

The conspicuous culprits in this energy-intensive scenario are servers and cooling systems, necessitating a concerted drive toward efficiency optimization. The challenge is further exacerbated by outdated servers and network communication tools that remain conspicuous energy hogs. Enter Intel, aiming to maximize computational output per chip to address these challenges head-on.

Notably, the scene isn’t exclusive to Intel; competitors are also in the race to harness efficiency. Ampere Computing, a startup founded by former Intel executives, introduced a cloud-computing-centric chip that effectively handles demanding tasks. Responding to this challenge, both Intel and rival Advanced Micro Devices (AMD) have rolled out comparable offerings, with AMD’s version hitting the market in June of this year.

The spotlight returned to Intel as it unveiled plans for the impending release of the “Sierra Forest” chip in the coming year. What distinguishes this launch is Intel’s strategic segmentation of its data center chip lineup for the first time. The division comprises the high-performance “Granite Rapids” chip, characterized by higher power consumption, and the more energy-efficient “Sierra Forest” chip. This move is a strategic response to Intel’s dwindling market share in the data center sector, an arena where AMD and Ampere have managed to carve out a competitive foothold.

Ronak Singhal, a senior fellow at Intel, underlines the transformative potential of the “Sierra Forest” chip for data centers. By consolidating legacy software onto fewer computers within a data center, substantial power savings become feasible. Singhal’s explanation is simple yet profound: “I may have things that are four or five, six years old. I can get power savings by moving something that’s currently on five, 10 or 15 different servers into a single” new chip. This density-centric approach not only drives down the total cost of ownership but also necessitates fewer systems, embodying a promising stride toward a more sustainable future for data centers.

Intel to Begin Shipping its 12-Qubit Quantum Processor

In a major announcement for the technology industry, U.S. chipmaker Intel has revealed that its highly anticipated 12-qubit quantum processor is now ready for shipment, giving it a significant edge over its competitors. According to a report by Ars Technica, the quantum processor will be dispatched to select research laboratories across the United States.

In recent months, Intel has faced growing scrutiny as companies increasingly turned to Nvidia for their artificial intelligence (AI) requirements or opted for in-house chip designs for upcoming products. Furthermore, with rivals like IBM pushing the boundaries of quantum computing, the pressure on Intel has mounted. Just this week, Interesting Engineering reported on IBM’s quantum computer surpassing a supercomputer in solving complex mathematical problems. In this competitive landscape, the news of Intel’s quantum processor comes as a potential game-changer that could revitalize the company’s position.

By delivering its 12-qubit quantum processor ahead of schedule, Intel aims to reassert its prominence and solidify its position in the market. The successful shipment of this advanced technology could provide Intel with the much-needed boost it requires to stay at the forefront of the evolving technology landscape.

Intel’s quantum processor

Intel’s quantum offering has been dubbed Tunnel Falls, much like its other processors named after water bodies. Unlike its competitors, Intel has been working to build silicon-based qubits. In its opinion, this helps it facilitate a transition from silicon chip to quantum chip in the future with the least effort possible.

Intel’s qubits are, therefore, small quantum dots that can capture individual electrons and store information. This makes Intel’s job a lot tougher since it has to focus on getting the hardware and the software right for its quantum processor.

By shipping its quantum processors to research laboratories, Intel hopes to get some more hands and brains to work on what it takes to get its quantum processors to work for everybody.

Currently, the processor needs a dilution refrigeration system to get temperatures down to absolute zero degrees before it can begin work. Intel’s partnership with research laboratories is seeking remedies for such real-world problems of quantum computers. At the same time, the company uses its fabrication expertise to build better quantum chips with more qubits at par with its competitors.

Dropping the ‘i’ to gain visibility

The Santa Clara, California-based company is also working on its branding to remain visible amidst the cloud of chipmakers that have sprung up over the years. In a recent move, Intel has decided to drop the ‘i” in its processor’s nomenclature and simply call them Core3/5/7/9 in the future.

Intel will soon start shipping its 12-qubit quantum processor — Intel’s new branding for its processorsIntel

This is being done to make it difficult for people to shorten the processor name, company executives told The Verge. Instead, users will have to call them Core 3 or Core 5 processors in the near future, allowing the company to differentiate its latest flagship chips that will also carry the Ultra branding.

Intel has surely made life a bit more complicated for those keen on knowing the generation of the processor they are investing in. Users will have to dig deep to see if they buy devices with the latest chips or some leftover inventory from the previous year.

Until the quantum range of processors becomes available, there is only Intel, Core, and Core Ultra ranges for die-hard users. Intel says tiering within these ranges will continue in the future as well.

Intel and Microsoft Collaborate to Democratize AI with Meteor Lake Chips

Intel showcased details of its upcoming Meteor Lake chips of PC processors during Microsoft’s Build 2023 conference. With a “chiplet” system-on-chip (SoC) design, Intel aims to deliver advanced intellectual properties (IPs) and segment-specific performance while maintaining lower power consumption. Meteor Lake will introduce Intel’s first PC platform with a built-in neural VPU, enabling efficient AI model execution.

The integrated VPU will collaborate with existing AI accelerators on the CPU and GPU, allowing for accessible and impactful AI features for PC users. Intel asserts that its product is at the forefront of the AI trend, positioning Meteor Lake as a key player.

At Computex, Intel disclosed that the VPU in Meteor Lake is derived from Movidius’s third-generation Vision Processing Unit (VPU) design. By leveraging this acquisition from 2016, Intel aims to establish itself as an AI market leader. Although specific performance figures and VPU specifications have not been revealed, it is anticipated that Intel’s VPU will surpass Movidius’s previous throughput rating of 1 TOPS (tera operations per second).

As the VPU is integrated into the SoC, AI capabilities will be a standard feature across all Meteor Lake SKUs, rather than a differentiating factor. Intel seeks to achieve similar energy efficiency levels as smartphone SoCs, enabling tasks like dynamic noise suppression and background blur.

Collaborating closely with Microsoft, Intel aims to scale Meteor Lake and Windows 11 across the ecosystem. Through partnerships and leveraging the ONNX Runtime—an open-source library for deploying machine learning models—Intel plans to optimize AI model execution on the Windows platform.

Intel envisions shifting server-based AI workloads to client devices, offering benefits such as reduced costs, lower latency, and enhanced privacy. By pursuing this vision, Intel aims to gain a competitive advantage in the market.