Processors - Page 38

Intel has finally detailed its next-generation Lunar Lake architecture, with "breakthrough" x86 power efficiency, a "massive leap" in graphics performance for "great" mobile gaming, and unmatched future-ready AI compute.

The next-generation Lunar Lake architecture features 32GB of on-package memory, support for LPDDR5X DRAM, all-new Performance-cores (P-cores) and Efficient-cores (E-cores) that deliver a "significant performance and energy efficiency improvements".

The fourth-generation Intel NPU has up to 48 TOPS of AI performance, with Intel reiterating that the powerful NPU inside of Lunar Lake delivers 4x the AI compte performance over the previous generation (Meteor Lake). There's an all-new GPU design with Battlemage, combining two new innovations: Xe2 GPU cores for graphics, and Xe Matrix Extension (XMX) arrays for AI.

Intel's Arrow Lake desktop processors are going to be out in October, or at least that's the word from Computex 2024.

This comes from Wccftech which has been tapping motherboard makers at Computex, firms that are showing off their Z890 boards - and have inside info on the Arrow Lake release timeframe.

Note that the mentioned October date is for Arrow Lake CPUs to be on shelves, not just some kind of initial reveal. In fact, the announcement of the next-gen desktop processors is planned to happen at Intel Innovation in September (which has been previously mentioned via the rumor mill).

Qualcomm held its Computex 2024 keynote earlier today, hyping both the Copilot+ PC ecosystem and its new Snapdragon X Series processors.

In the Qualcomm Computex 2024 keynote YouTube video above, at the 11:34 mark Neowin reports that Qualcomm President and CEO Cristiano Amon said that these initial laptops being released are just the first wave of Windows PCs that will feature Snapdragon X Elite chips.

Qualcomm teased renders of PCs with Snapdragon X Elite chips inside, with Amon saying that the new Snapdragon X Series chips will be inside all sorts of form factor PC systems. The company had some slides up that showed off tablet designs, Mini-PCs, and even all-in-one PC systems.

Qualcomm has just hosted its Computex 2024 keynote, with president and CEO Cristiano Amon joined by tech industry leaders on stage, including from Acer, ASUS, Dell, HP, Lenovo, Microsoft, and Samsung for the industry shift in the PC space enabled by Copilot+ PCs powered by Qualcomm's new Snapdragon X series processors.

Qualcomm CEO Cristiano Amon said: "The PC is reborn. Copilot+ PCs powered by Snapdragon X Elite are the fastest, most intelligent Windows PCs ever built with AI integrated throughout the system and can deliver multi-day battery life. I am grateful to the partners that joined me on stage today to celebrate this industry shift that puts Snapdragon powered Windows Copilot+ PCs at the forefront of technology innovation. Together, we are redefining the personal computing experience, and enabling developers to efficiently create apps for this new generation".

The new Snapdragon X series chips were the big focus, with Amon highlighting the NPU inside of the new Qualcomm Snapdragon X series processors as the "key differentiator and reason why performance of PCs powered by Snapdragon X Series is superior and makes Copilot+ experiences possible".

AMD has announced its new chips for Copilot+ AI PCs, the latest AMD Ryzen AI 300 Series, at Computex. These chips deliver 50 TOPS of AI performance with next-gen Zen 5 CPU Cores and beefed-up RDNA 3.5 graphics. The latter will make these chips great for PC gaming on compact machines - especially handhelds!

As part of its presentation comparing the performance between the flagship Ryzen AI 9 HX 370 and the Snapdragon X Elite Arm-based SoC with built-in GPU, AMD notes a 60% performance increase in favor of Ryzen using the 3DMark Night Raid Graphics benchmark.

This is partly due to the fact that it's an x86 chip without an emulation layer, but the performance increase also comes from the 16 Compute Units, up from 12 CUs in the previous gen Ryzen 7040 Series and Ryzen 8040 Series.

AMD's AI processing for laptops and portable devices is leveling up big time with the new Ryzen AI 300 Series, powered by Zen 5, XDNA 2, and RDNA 3.5 graphics. Described as the 'World's Best Processor for Copilot+ PCs,' they launch in July with two models - the Ryzen AI 9 HX 370 and the Ryzen AI 9 365.

Yes, the new naming for AMD's SoCs is real and works like this: Ryzen AI is the new brand name denoting a powerful dedicated NPU (here, it's the third-gen XDNA 2), 300 is the series, and the 9 HX stuff is the model info that AMD traditionally puts at the end of Ryzen CPU model naming.

With AMD's third-generation XDNA 2 NPU technology, Ryzen AI 300 Series processors are Copilot+ ready. The impressive 50 TOPS of AI performance push them past the Snapdragon X Elite, Intel's next-gen Lunar Lake, and Apple's M4 chips. This is a massive increase from the 10 TOPS for the Ryzen 7040 Series and 16 TOPS for the Ryzen 8040 Series.

At Computex 2024, AMD has formally announced its next-generation desktop CPUs, the new Ryzen 9000 Series, which will launch in July with four models. Powered by the next-gen Zen 5 architecture, AMD noted in its presentation to the press that this was more than a "trivial update" for Zen but a "sweeping update" with advances that deliver 2X data and instruction bandwidth and, of course, big performance gains for AI.

AMD says there's an average 16% IPC uplift compared to Zen 4, with the chart outlining the improvement across a range of gaming, rendering, and other CPU workloads. Far Cry 6 sees a 10% uplift on the low-end, and Octane and Cinebench R23 are in the middle with 16% and 17%, respectively. On the high-end, you've got Blender with an impressive 23% uplift and Geekbench 5.4 with a massive 35%. Zen 5 is a definite step up from Zen 4.

The four models that are set to debut in July are AM5 ready: the flagship AMD Ryzen 9 9950X, Ryzen 9 9900X, Ryzen 7 9700X, and Ryzen 5 9600X. One of the other big things with Zen 5 is that the performance increases come with an improvement in power efficiency, with the Ryzen 9 9950X (16 Cores/32 Threads) featuring a 170W TDP, which is on par with the Zen 4 Ryzen 9 7950X.

AMD's Ryzen 9000 launch has been leaked ahead of Computex, although we should add a hefty helping of seasoning with this one.

The leak comes from Wxnod on X (formerly Twitter) and is supposedly a deck of presentation slides from AORUS (GIGABYTE), but separately, CodeCommando has also spilled the specs of AMD's initial Zen 5 desktop CPUs. (Hat tips to Wccftech and VideoCardz respectively here).

While the two leaks appear to match, and show an initial four chips that AMD is set to unleash, we should still be very cautious about all this.

Intel has penciled in its annual Innovation event for September 24 this year, hosted in San Jose, California as usual. We should expect a huge focus on the next-gen Core Ultra CPUs, Arrow Lake, Lunar Lake, Xeon 6, and Gaudi 3 news.

Intel's upcoming Innovation event will run between September 24-25, where we should see the official launch of Intel's next-gen Core Ultra 200 series "Arrow Lake" desktop CPUs, with an update on what's coming to mobile with Arrow Lake and Lunar Lake CPUs. We should expect a hard launch of Intel's new high-end Xeon "Granite Rapids-AP" processors, as well as an update on Intel's Gaudi 3 AI accelerators during the event.

The upcoming Lunar Lake CPUs from Intel will be the big focus of the show, as they'll be the first true AI PC processors after the launch of the Core Ultra 100 series "Meteor Lake" CPUs. We've got Computex 2024 before Intel Innovation, so expect some reveals and teases during the show, with more news during Intel Innovation in September.

NVIDIA and MediaTek are expected to announce their new custom Arm-based "AI PC" processor at Computex 2024 next week.

In a new report from CTEE and picked up by Wccftech, the big cooperation between NVIDIA and MediaTek will be announced. Until now, it has been rumors and whispers... but the big announcement is going to happen at Computex 2024, which is perfect.

NVIDIA CEO Jensen Huang flew into Taiwan this week, where he's meeting the whose-who of the tech industry: TSMC, MediaTek, GIGABYTE, Pegatron, and other manufacturers that aren't as well known in the industry but are invaluable including Wistron and Wiwing.

NVIDIA's next-generation AI PC processor will feature Arm-based Blackhawk CPU cores, Blackwell RTX GPU cores, and next-gen LPDDR6 memory.

The new details on NVIDIA's next-gen Arm-based AI PC processor comes from @XpeaGPU on X, quoting an article that talked about a new handheld and console SoC designed by NVIDIA based on the same architecture. NVIDIA looks to use multiple next-gen IPs on a single package, similar to how AMD and Intel are rolling out their new processors with CPU cores, GPU cores, NPUs, and even on-package memory.

NVIDIA is reportedly tapping TSMC's new 3nm process node for its Arm processor, with an advanced packaging solution containing Arm-based Cortex A5 Blackhawk CPU cores, and NVIDIA's in-house Blackwell RTX GPU cores, which should make for a potent AI PC processor.

AMD's new EPYC 4004 processors are launching, using the AM5 socket aimed at Small and Medium-Sized Businesses (SMB) and hosting businesses.

The new AMD EPYC 4004 processor will feature up to 16 cores and 32 threads of Zen 4 processing power, made for single-socket operation with a boost clock of up to 5.7GHz. The new EPYC 4004 processor supports DDR5-5200 memory with ECC support, with a maximum capacity of up to 192GB of DDR5 memory. The I/O dies contain PCIe Gen5 and DDR5 controllers, with a built-in RDNA 2-based GPU.

These new processors are using the 40x40 LGA-1718 socket, otherwise known as the AM5 socket, with AMD confirming that the new EPYC 4004 processors even support AM4 cooling solutions, which will be a huge cost-saving factor for SMB customers. The new AMD EPYC 4004 processors have the same TDP range as the regular gaming-focused Ryzen CPUs: between 65W and 170W.

AMD's next-gen "Strix Halo" Zen 5-based APU has been pictured on Chiphell, showing off its chiplet-based deisgn, using 256-bit LPDDR5X memory.

The new Strix Halo APU will feature a chiplet-based design, with one or two Zen 5 CCDs and a huge SoC die that features an oversized integrated RDNA 3+ GPU, and 256-bit LPDDR5X memory controllers not found on the cIOD. AMD is aiming at CPU and GPU performance that competes with Apple's M3 Pro and M3 Max SoCs, at comparable PCB and power consumption.

AMD is using an integrated RDNA 3+ GPU in its next-gen Strix Halo APU, with a huge 40 Compute Units that works out to 2560 Stream Processors, 80 AI accelerators, 40 Ray accelerators, 160 TMUs, and an unknown amount of ROPs, with GPU clock speeds of up to 3.0GHz.

Intel teased its next-gen mobile-focused Lunar Lake CPUs today, but also confirmed its next-gen Arrow Lake-S, Arrow Lake-HX, and Arrow Lake-H processors for both desktop and laptops are coming in Q4 2024.

Intel's new high-performance Arrow Lake CPUs will hit the desktop later this year in Arrow Lake-S form, something that we should see confirmed (and detailed) at Computex 2024 in just a couple of weeks time. Intel has now provided a preview of its next-gen Core Ultra 200 "Arrow Lake-S" desktop CPUs, with a tease of the monolithic design that has multiple tiles inside.

Arrow Lake will feature a CPU, GPU, SoC, and I/O tiles, with the biggest of the tiles being the CPU and SoC which are the larger rectangular-shaped ones at the bottom, and the square one in the middle. There's also a dummy tile used, which is something Intel is also doing with its new Lunar Lake CPUs, too.

Intel has teased its next-generation Lunar Lake CPUs ahead of Computex 2024, teasing the new AI NPU and latest Battlemage "Xe2" integrated GPU.

The next-gen Lunar Lake CPUs will set the foundation for the next-generation AI PC platform, with Intel planning to have the new Lunar Lake CPUs out and in products in Q3 2024. Intel's next-gen Lunar Lake is something truly special: it features all-new architectures across the board with new CPU cores, new GPU cores, new NPU cores, and more thanks to advances in 3D packaging technology and power innovations.

Intel will be using next-gen Lion Cove P-Cores and Skymont E-Cores for Lunar Lake, with some hopefully very delicious IPC improvements. Intel has teased that we'll have 3x the AI performance from Lunar Lake over Meteor Lake, with 45+ TOPS of NPU power for AI workloads. This is just from the NPU alone, while Lunar Lake offers 100+ TOPS of AI performance in total (NPU + CPU + GPU).

AMD's next-gen Zen 5 processors will be launched at Computex 2024 next month, while next-next-gen Zen 6 processors are being teased with 32 cores per CCD.

In some new posts on X from leakers "Kepler_L2" and "InstLatX64" we're discovering the Zen 5 and Zen 6 core configurations, with Zen 5 hitting in just a few weeks time. Zen 5 and Zen 5c cores are expected to both be smaller than existing Zen 4 cores, which means there'll be more room to fire more CCDs on the CPU package.

Zen 4 has up to 12 CCDs while Zen 4c had up to 8 CCDs on the flagship EPYC processors, with two CCDs that had each had 8 cores for up to 128 cores and 256 threads of CPU power. The next-generation Zen 5 processors will have up to 16 CCDs on Zen 5 and up to 12 CCDs on Zen 5c, with Zen 5 keeping the same single CCX design within the CCD with a total of 8 cores for up to 128 cores, while Zen 5c processors have a single CCX with up to 16 cores for up to 192 cores in total.

Intel's next-generation Lunar Lake CPUs are still in the ovens inside of their labs, but now we're hearing about the new Core Ultra 5 238V processor with 32GB of LPDDR5X on-package memory.

If you don't know about on-package memory, Intel's new Lunar Lake CPUs will have 16GB or 32GB of on-package memory, right next to the CPU, GPU, and NPU on the chip. Lunar Lake is for low-power devices with 8W to 30W TDP designs, using Intel's latest CPU and GPU architectures combined with a brand-new AI accelerator.

Intel's next-gen Core Ultra 200V series will have LPDDR5X-8533 memory, in either 16GB or 32GB on-package. Intel's new Core Ultra 5 234V processor will reportedly have 16GB, while the newly-found Core Ultra 5 238V has 32GB of on-package LPDDR5X memory.

Intel's next-generation Core Ultra 200 series "Arrow Lake" CPUs have been spotted in new shipping manifestos, in both Arrow Lake-S (desktop) and Arrow Lake-HX (laptop) form.

We've seen new Intel Core Ultra 200 series "Arrow Lake" CPUs in shipping manifestos already, but now we have more of the range: 6-core, 14-core, 16-core, and 24-core variants for both desktops and laptops have been spotted this time. Here's the full list so far:

So we'll have a trio of desktop Arrow Lake-S processors with a 24-core CPU with 36MB of L3 cache, a 14-core CPU with 24MB of L3 cache, and a 6-core CPU with 18MB of L3 cache. On the laptop side of things, we've got the Arrow Lake-HX processors in a 16-core part with 30MB of L3 cache, and a 14-core CPU with 24MB of L3 cache.

Earlier this year, AMD launched its latest Ryzen 8000G Series of desktop processors, which featured built-in Radeon graphics (up to a Radeon 780M), offering PC gamers an entry-level option that doesn't require a discrete graphics card. With the AMD Ryzen 7 8700G, you've got a CPU that can play modern PC games in 1080p without a GPU.

The Ryzen 8000G Series is AMD's first desktop processor lineup to include dedicated AI NPU hardware - with up to 39 TFLOPs of AI processing power. Combining AMD XDNA AI hardware, Zen 4 CPU architecture, and RDNA 3 graphics, you've got a series of AMD chips to suit all workloads.

This week, AMD unveiled two new entries to the lineup: the AMD Ryzen 7 8700F and AMD Ryzen 5 8400F. These variants ship without Radeon graphics and are optimized for efficiency and low-power draw.

NVIDIA and MediaTek are reportedly working on a new Arm-based AI processor, co-developing the new SoC that will be finalized in Q3 2024... just months from now.

The new silicon will support advanced technologies, and will be mass-produced on TSMC's new 3nm process node, and will compete against Apple's new M4 chip, and Qualcomm's upcoming Snapdragon X Elite SoC according to Chinese media outlet UDN.

The site reports that the price of NVIDIA and MediaTek's new Arm-based AI processor will be "as high as $300" adding that this is the first time NVIDIA and MediaTek have cooperated on PC processors, and that it's expected we'll get details on the new AI PC processor during Computex 2024 in just a few weeks' time in Taipei, Taiwan.