Processors - Page 73

AMD's next-gen Zen 4 "Raphael" LGA1718 package has been teased, this time through a new mockup that will eventually be what we'll see as the Ryzen 7000 series CPUs.

The new Raphael CPUs will reportedly have a flagship 170W TDP model, but for the most part will be 120W TDP designs. AMD will have DDR5 support with its new AM5-based motherboards, meanwhile, Intel will support DDR5 on its higher-end boards, but will offer DDR4 support on other Intel 600-series chipsets.

Zen 4 will have 28 PCIe 4.0 lanes on offer, an upgrade over the 24 PCIe 4.0 lanes on the Zen 3 series. Intel will have next-gen PCIe 5.0 connectivity on its upcoming 12th Gen Core "Alder Lake-S" processors, which will be directly battling against AMD's new Zen 4 "Raphael" CPUs.

We last heard about AMD's next-gen Zen 4-powered EPYC processors a few months ago now back in February 2021, and now there's a new (but old) roadmap teasing Zen 4 embedded products.

The roadmap is sold old here that the Zen 3-based EPYC 7003 series processors are a "concept" yet they have already been released, so the roadmap is a few years old. On this roadmap, we can see the Zen 1-based EPYC 7001 series CPUs with their planned up to 32 cores and 64 threads meanwhile the Zen 2-based EPYC 7003 series had up to 64 cores and 128 threads.

But AMD wasn't finished there, as you can see the Zen 4-based EPYC 7004 series will have over 64 cores, with previous rumors pegging it to offer a monstrous 96 cores and 192 threads. You will also notice the new Zen 4-based EPYC 7004 series has a TDP of between 120W and 230W+ or more, while the other EPYC chips tapped out at 225W.

It wasn't too long ago that the AMD 4700S PC Desktop Kit was spotted online, and now it's out in the wild in some markets at least -- and someone has taken some pictures of the motherboard

The pictures were posted on Twitter by "DISCLOSUZEN" but the CPU cooler wasn't removed, so we don't have a juicy shot of the chip itself. They are the first pictures of the AMD 4700S PC Desktop Kit, with the AMD 4700S processor based on the Zen 2 architecture and packing 8 cores and 16 threads at up to 4GHz.

AMD also has 16GB of GDDR6 memory on its 4700S processor, which should be on the back of the motherboard and under what looks to be a custom heat sink. There's a PCIe 3.0 x16 slot for a discrete GPU, which makes sense given that AMD has most likely disabled the integrated GPU, or it defective and thus, disabled anyway.

Intel has just launched its new 11th Gen Core "Tiger Lake-H" processors with the shining star of the show being the flagship Core i9-11980HK processor, which promises ultra-performance inside of the next generation wave of laptops in 2021.

The new Intel Core i9-11980HK offers up 8 cores and 16 threads on the new Willow Cove architecture, on Intel's in-house 10nm SuperFin technology. We have a fully unlocked processor with Intel Extreme Tuning Utility (XTU) for "enthusiast overclocking" and Intel Speed Optimizer for easy overclocking.

There's 20 PCIe 4.0 lanes on the Core i9-11980HK as well as 24 PCIe 3.0 lanes, more than enough to cover the fastest discrete GPU that can go alongside the new CPU -- being NVIDIA's GeForce RTX 3080 GPU -- as well as a couple of ultra-fast PCIe 4.0 SSDs.

Intel has finally rolled out its new Tiger Lake-H processors in both 6-core and 8-core CPU form and all on the new 10nm node. The new flagship Core i9-11980HK processor is an 8-core, 16-thread chip at up to 5.0GHz and is the first overclockable 10nm CPU from Intel.

Intel is debuting its new Willow Cove core architecture inside of the new 11th Gen Core-H series CPUs and on its 10nm SuperFin technology. The company is touting a 19% performance improvement over the previous generation, with Intel using a 45W power envelope on the new 11th Gen CPUs -- except for the flagship Core i9-11980HK processor which has a TDP between 45-65W. The rest of the stack are 35-45W offerings with between 6 and 8 cores.

You've got Thunderbolt 4 support, up to DDR4-3200 memory support, and Intel Optane Memory H20 offering second-gen Optane + NAND hybrid SSD for what Intel says will deliver "amazing responsiveness in real-world client usages".

Samsung is hard at work on its next-gen Exynos SoC which will be competing against Qualcomm's next-gen SoC, and Apple's current-gen M1 chip and next-gen M2 chip.

But what will be inside of Samsung's new SoC is going to be interesting: it's aimed at notebooks and will pack an integrated custom GPU from AMD which I'm sure is based on the RDNA 2 architecture. The news is coming from The Korean Economic Daily which said an industry source told them: "The new Exynos will offer improved functions, including extraordinary computing power and battery efficiency, by utilizing a 5-nanometer processing technology. It's good for both laptops and smartphones".

We should expect Samsung to unveil a new family of Exynos SoC-powered laptops and smartphones using its new chip, which will be made on the fresh 5nm node. We should see the Exynos SoC scale up from smartphones with lower power and TDP through to laptops with varying power and TDPs.

Intel's largest launch in a very long time will be later this year with its 12th Gen Core "Alder Lake-S" CPU family, which will reportedly be launching in November 2021 according to the latest rumors.

The introduction of Alder Lake-S will usher in Intel as the first with PCIe 5.0 and DDR5 memory support, after AMD held PCIe 4.0 over Intel's head for a couple of years there, Intel will be the first with both PCIe 5.0 and DDR5 support. PCIe 5.0 will be on all 600-series motherboards, but we will see some boards launching with DDR5 or DDR4 support -- some of that will be up to motherboard makers.

Wccftech says that Intel has told its partners that it is "planning to launch Alder Lake S in November of 2021. As with all timelines, this can move backward or forwards depending on a few variables but for now this has been communicated to partners and is mostly fixed".

We are hearing some new rumbles on AMD's next-gen Ryzen 6000 series APUs codenamed Rembrandt, with leaker ExecutibleFix pumping out some new details.

In the tweets we're told that AMD's new Rembrandt APUs will be using the new Zen 3+ architecture, RDNA 2 GPU cores and be on TSMC's new 6nm node. We heard all of this nearly a year ago now with previous rumors: Zen 3+ architecture + RDNA 2 architecture + TSMC 6nm node.

But the new rumors are teasing that the Rembrandt APU packs 12 Compute Units of RDNA 2 GPU cores, which will be interesting to see how gaming performance will end up when the new APUs launch in 2022. The current-gen Cezanne APUs feature 512 stream processors based on the previous-gen Vega GPU architecture, while the new Rembrandt APU cores will pack 768 stream processors -- a 50% increase.

Intel's new Alder Lake-S is currently in the foundry ovens and being tested, with the 12th Gen Core processors being teased in a different form today: codename Core-1800.

The newly-teased Intel Core-1800 processor was spotted by Igor Wallossek that has published a datasheet from HWiNFO for the new Intel 12th Gen Core CPU. The specification sheet for codename Core-1800 shows the engineering sample processor listed with a B0 stepping which is the second revision engineering sample (ES2) with more changes to be made to the chip before it's made final.

Intel's codename Core-1800 in its ES2 form is a 16-core, 24-thread CPU with varying boost clocks. The datasheet for the Core-1800 has 2 of its cores at up to 4.6GHz, 4 cores at up to 4.4GHz, and 6 cores at up to 4.2GHz. Intel has an all-turbo boost CPU clock of 4GHz on the codename Core-1800 chip.

AMD is hard at work on its next-gen Zen 4 and Zen 5 architectures, with recent rumors teasing new Zen 5 APUs codenamed "Strix Point" and now we have new rumors for the upcoming Zen 4 architecture.

The new Zen 4 architecture will be powering AMD's next-gen Ryzen 6000 series CPUs that will be released in the second half of 2022, while we could see an announcement of it by the end of the year. The new Zen 4 architecture is codenamed Raphael and will be made on TSMC's new 5nm process node, with the new CPUs reportedly pack a Navi2-based integrated GPU.

In the meantime, Intel will be introducing its next-gen Alder Lake platform, with the new 600-series chipset and 12th Gen Core processors supporting next-gen technologies with DDR5 memory and PCIe 5.0 connectivity. AMD won't have a response to Alder Lake until Raphael, with AMD including DDR5 and PCIe 5.0 support with Zen 4... Intel will launch with DDR5 + PCIe 5.0 first, AMD will be a few months behind.

The situation between China, Taiwan, the United States and pretty much the entire world right now -- but those 3 countries specifically, is tense AF and it is only getting worse.

Taiwan Semiconductor Manufacturing Company (TSMC) is the crown jewel of not just Taiwan, but the world. If Taiwan was invaded by China it would mean the end of technology as we know it for many years, as TSMC is the only place that can make some of the world's most advanced chips that if it were invaded it would bring the entire world to its knees.

Now we have TSMC chairman Dr. Mark Liu talking about possible armed conflict in Taiwan due to TSMC strategic importance in a recent interview with CBS. He said that TSMC is one of only 3 companies in the world manufacturing semiconductors on advanced, leading edge process nodes but access to that technology has been limited by the United States Department of Commerce to entities that act against American national security interests.

TSMC has announced that it is using AMD EPYC processors in its general workload, and even R&D teams to make the very latest technology on the planet.

In a new post on AMD's website titled "TSMC optimizes workloads with AMD EPYC CPUs" the company explains how it has been deploying AMD's industry-leading EPYC processors across its company. It started off with pushing the high core count beasts into their general workload, and then quickly into the R&D heart of TSMC.

Simon Wang, Director of Infrastructure and Communication Services Division at TSMC explains: "We first introduced AMD EPYC processors into the general workload and they are being deployed with our research and development team".

We are very close to the reveal of Intel's next-gen Tiger Lake-H processors, with the new Core i9-11950H turning up to the party a little early.

Intel's new Core i9-11950H processor is an 8-core, 16-thread offering that will have boost clocks of up to 4.9GHz according to the new leaks. The new CPU was spotted inside of the HP ZBook Studio 15.6 G8 Mobile workstation PC which normally features an NVIDIA Quadro RTX mobile GPU.

We might see this particular Intel Core i9-11950H processor being exclusive to HP for the time being, with some Geekbench 5 benchmarks run on it and throwing out a single-core score of 1365 while we have a multi-core score of 6266. Intel will be fully unveiling and detailing its new Tiger Lake-H series on May 11, which is just over a week away now.

Intel's next-gen Sapphire Rapids Xeon CPU has been spotted with an MCM (multi-chip module) design packing an insane 80 cores in a new shot of an engineering sample of the CPU.

The new photo turned up on Bilibili with the 4th Gen Sapphire Rapids Xeon CPU featuring an MCM design with 5x4 configuration -- which works out that each die has up to 80 cores, but we probably won't see the full 80-core silicon ever being released due to the mesh layout.

Wccftech reports that theoretically, the new Intel Sapphire Rapids-SP Xeon CPUs "could feature" a maximum of 72 cores and 144 threads, but we could see them tap out at 56 cores and 112 threads. Another leak pointed to the fact of an engineering sample with 60 cores (15 cores per die, with a 5x3 layout) while the CPU itself had just 56 cores and 112 threads enabled (14 cores per die).

Apple's next-gen M2 chip has reportedly entered production, with the new M2 processor set to power the next-gen Apple MacBook and MacBook Pro laptops planned for later this year.

The new Apple M2 system-on-a-chip will be made by TSMC and should be on its new 5nm+ process, which is a performance-enhanced version of the 5nm process that the M1 was made on. Apple's new M2 chip will have improved performance and power efficiency over its predecessor.

Apple is expected to use the next-gen M2 chip inside of its future MacBook and MacBook Pro laptops that will be unveiled later this year, a move that will see it pushing away from relying on Intel for its CPUs inside of its popular and high-end MacBook and MacBook Pro lines.

AMD currently has its Zen 3 architecture powering its Ryzen 5000 series CPUs and while the Zen 4 architecture is in the oven, the Zen 5 architecture is right behind it and now we have some juicy new rumors about AMD's next-next-gen Zen 5 APUs.

The next-next-gen AMD Zen 5 APUs are reportedly codenamed "Strix Point" -- with no affiliation to ASUS that I'm aware of -- which will be made on TSMC's new 5nm process and rock next-gen DDR5 memory support. The new codenamed Strix Point APUs would use the AMD Zen 5 architecture and will fill out the Ryzen 8000 series of CPUs in 2024.

Moepc has the scoop here, explaining: "Zen 5 APU "Strix Point" belongs to Ryzen 8000 series (at the time of writing), and it will adopt big.LITTLE like Intel's Alder Lake and Raptor Lake, with 8 big Zen 5 cores and 4 little cores. It's scheduled to be launched in 2024".

Inside of Microsoft's next-gen Xbox Series X/S consoles is an 8-core, 16-thread semi-custom APU powered by the AMD Zen 2 and RDNA 2 architectures -- but now the CPU-only AMD 4700S processor has turned up.

What the hell is the AMD 4700S processor, and why isn't the Ryzen branding there? Well, manufacturers in China are now selling the AMD 4700S processor as an ITX compatible solution that is used on an "AMD Cardinal" motherboard, which as VideoCardz explains "would suggest that AMD developed the motherboard themselves".

The motherboard doesn't have any DDR4 memory slots, as there is 16GB of GDDR6 memory on the sides of the AMD 4700S processor -- just like the 16GB of GDDR6 memory that surrounds the Xbox Series X chip. But this new AMD 4700S processor doesn't feature on-board graphics like the Xbox Series X and Xbox Series S consoles, which have 16GB of shared GDDR6 memory -- the 16GB of GDDR6 on the AMD 4700S is used purely as system RAM.

After announcing the new ROG Ryujin II AIO CPU cooler in January 2021, ASUS have now launched it into the wild.

The new ASUS ROG Ryujin II AIO CPU cooler comes in two flavors: 240mm and 360mm, with the AIO cooler rocking a 3.5-inch LCD display and beautifully styled all-black Noctua fans. ASUS uses the Seventh Gen Astek pump which is virtually silent, with a base operating speed of 840RPM.

ASUS Chief Operating Officer Joe Hsieh explains: "When developing the next generation of our premium Ryujin coolers, we again looked to Asetek and its most advanced technology to date which provides extreme performance, silent operation and industry-recognized quality and reliability. With ROG Ryujin II 240/360, not only did we want to max out performance, we wanted to enhance aesthetics while upgrading the screen to an LCD panel and retaining the FanXpert controls".

Cerebras revealed its next-gen WSE-2 (Wafer Scale Engine) chip last year during the Hot Chips 2020 conference, but the company has now provided more details at the Linley Spring Processor Conference.

We already knew that the next-gen Cerebras WSE-2 packed an insane 850,000 cores ready for AI work, and an even-more-insane 2.6 trillion transistors (yeah that's trillion with a T). Cerebras' new details on the WSE-2 include the fact that it has 40GB of on-chip SRAM, 20 petabytes of memory bandwidth, and 220 petabits of aggregate fabric bandwidth.

The new WSE-2 is the largest chip ever made, packing 2.6 trillion transistors and 850,000 AI-optimized, fully programmable cores. Cerebras crams all of that into a single silicon wafer, all on TSMC's 7nm process. The entire chip is simply gigantic -- and while it's the same 46,225mm2 as its predecessor in the WSE-1, the new WSE-2 packs some gigantic upgrades.

Intel's new 11th Gen Core CPUs are now floating out into the wild with the folks at Silicon Lottery offering some pre-binned Rocket Lake-S processors for your OC and gaming pleasure.

It all starts with the pre-binned Core i5-11600K offering 4.8GHz all-core boost for $250, while 4.9GHz costs you $260, and then 5GHz costs $340. Next up we have the higher-end and flagship Rocket Lake-S chip with Intel's new Core i9-11900K at 4.9GHz offered by Silicon Lottery for $620, 5GHz costs you $700 while 5.1GHz bumps up to $880.

Silicon Lottery is only offering the 6-core Intel Core i5-11600K and 8-core Core i9-11900K, with no factory pre-binned Core i7-11700K on offer at all.