TrendForce reports that mass production of new server platforms—such as Intel Sapphire Rapids and AMD Genoa—is imminent. However, recent market reports have indicated a PMIC compatibility issue for server DDR5 RDIMMs; DRAM suppliers and PMIC vendors are working to address the problem. TrendForce believes this will have two effects: First, DRAM suppliers will temporarily procure more PMICs from Monolithic Power Systems (MPS), which supplies PMICs without any issues. Second, supply will inevitably be affected in the short term as current DDR5 server DRAM production still uses older processes, which will lead to a convergence in the price decline of DDR5 server DRAM in 2Q23—from the previously estimated 15~20% to 13~18%.

As previously mentioned, PMIC issues and the production process relying on older processes are all having a short-term impact on the supply of DDR5 server DRAM. SK hynix has gradually ramped up production and sales of 1α-nm, which, unlike 1y-nm, has yet to be fully verified by consumers. Current production processes are still being dominated by Samsung and SK hynix's 1y-nm and Micron's 1z-nm; 1α and 1β-nm production is projected to increase in 2H23.

Amid the push for technology independence, Chinese companies are pushing out more products to satisfy the need for the rapidly soaring demand for domestic data processing silicon. Today, we have information that Chinese Loongson has launched a 3D5000 CPU with as many as 32 cores. Utilizing chiplet technology, the 3D5000 represents a combination of two 16-core 3C5000 processors based on LA464 cores, based on LoongArch ISA that follows the combination of RISC and MIPS ISA design principles. The new chip features 64 MB of L3 cache, supports eight-channel DDR4-3200 ECC memory achieving 50 GB/s, and has five HyperTransport (HT) 3.0 interfaces. The TDP configuration of the chip is officially 300 Watts; however, normal operation is usually at around 150 Watts, with LA464 cores running at 2 GHz.

Scaling of the new chip goes beyond the chiplet, and pours over into system, as 3D5000 supports 2P and 4P configurations, where a single motherboard can become a system of up to 128 cores. To connect them, Loongson uses a 7A2000 bridge chip that is reportedly 400% faster than the previous solution, although we have no information about the last chip bridge. Based on the LGA-4129 package, the chip size is 75.4x58.5×6.5 mm. Regarding performance, Loongson compares it to the average Arm chip that goes into smartphones and claims that its designs are up to four times faster. In SPEC2006, performance reaches 425 points, while maintaining a single TeraFLOP at dual-precision 64-bit format. On the other hand, the processor was built for security, as the chip has a custom hardware-baked security to prevent Spectre and Meltdown, has an on-package Trusted Platform Module (TPM), and has a secret China-made security algorithm with an embedded custom security module that does encryption and decryption at 5 Gbps.

AMD and JEDEC are collaborating to create a new industry standard for DDR5 memory called MRDIMMs (multi-ranked buffered DIMMs). The constant need for bandwidth in server systems provides trouble that can not easily be solved. Adding more memory is difficult, as motherboards can only get so big. Incorporating on-package memory solutions like HBM is expensive and can only scale to a specific memory capacity. However, engineers of JEDEC, with the help of AMD, have come to make a new standard that will try and solve this challenge using the new MRDIMM technology. The concept of MRDIMM is, on paper, straightforward. It combines two DDR5 DIMMs on a single module to effectively double the bandwidth. Specifically, if you take two DDR5 DIMMs running at 4,400 MT/s and connect them to create a single DIMM, you get 8,800 MT/s speeds on a single module. To efficiently use it, a special data mux or buffer will effectively take two Double Data Rate (DDR) DIMMs and convert them into Quad Data Rate (QDR) DIMMs.

The design also allows simultaneous access to both ranks of memory, thanks to the added mux. First-generation MRDIMMs can produce speeds of up to 8,800 MT/s, while the second and third generations modules can go to 12,800 MT/s and 17,600 MT/s, respectively. We expect third-generation MRDIMMs after 2030, so the project is still far away. Additionally, Intel has a similar solution called Multiplexer Combined Ranks DIMM (MCRDIMM) which uses a similar approach. However, Intel's technology is expected to see the light of the day as early as 2024/2025 and beyond the generation of servers, with Granite Rapids likely representing a contender for this technology. SK Hynix already makes MCRDIMMs, and you can see the demonstration of the approach below.

TrendForce reports that several suppliers, such as Micron and SK hynix, have started scaling back DRAM production. The ASP of DRAM plunged 20% in 1Q23, and this price decline is predicted to slow down to 10~15% next quarter. It's uncertain whether or not demand will recover in 2H23. Therefore, the ASP of DRAM has continued to fall as inventory levels are high from the suppliers' side, and prices will only rebound if there is a significant decrease in production.

PC DRAM: Purchase quantity from buyers has fallen drastically over the past three quarters; buyers have around 9~13 weeks of PC DRAM stock remaining. Despite suppliers having already cut production in the PC DRAM segment, DDR4 8 GB module is still likely to fall by more than 10% in 2Q23. There is a possibility that PC OEMs may purchase more DRAM because prices have been down to a relatively low level, but it is still under observation whether or not this can mitigate the inventory overstock situation from the suppliers' side. TrendForce predicts the ASP of PC DRAM will fall between 10~15%.

Today, thanks to Yuuki_Ans on the Chinese Bilibili forum, we have more information about the upcoming "Avenue City" platform that powers Granite Rapids and Sierra Forest. Intel's forthcoming Granite Rapids and Sierra Forest Xeon processors will diverge the Xeon family into two offerings: one optimized for performance/core equipped with P-cores and the other for power/core equipped with E-cores. The reference platform Intel designs and shares with OEMs internally is a 16.7" x 20" board with 20 PCB layers, made as a dual-socket solution. Featuring two massive LGA-7529 sockets, the reference design shows the basic layout for a server powered by these new Xeons.

Capable of powering Granite Rapids / Sierra Forest-AP processors of up to 500 Watts, the platform also accommodates next-generation I/O. Featuring 24 DDR5 DIMMs with support for 12-channel memory, with memory speeds of up to 6400 MT/s. The PCIe selection includes six PCIe Gen 5 x16 links supporting CXL cache coherent protocol and 6x24 UPI links. Additionally, we have another piece of information that Granite Rapids will come with up to 128 cores and 256 threads in both regular and HBM-powered Xeon Max flavoring. You can see storage and reference platform configuration details on the slides below.

In response to the increasing demand for powerful computing that can be relied on in a wide range of even the most challenging installation environments, leading industrial computing manufacturer and solution provider, OnLogic (www.onlogic.com), has unveiled their Helix 401 fanless industrial computer. The compact device is designed for use in edge computing, industry 4.0, Internet of Things (IoT), and many other emerging applications and will make its public debut at Embedded World 2023.

"You may never see them, but industrial computers are everywhere, working diligently to power technology solutions of every shape and size. These systems need to be small and reliable while still being just as powerful as high-end desktop machines," says Mike Walsh, Senior Product Manager at OnLogic. "The Helix 401 balances size and performance while providing a wide range of configuration possibilities to help users tailor it to their specific application. It's small enough to fit in your hand, similar in size to Intel's popular NUC, but capable enough to drive advanced automation solutions and power the next great smart agriculture, building automation or energy management innovation."

According to TrendForce's research, global DRAM revenue fell by 32.5% QoQ to US$12, 281 million for 4Q22. The QoQ decline for 4Q22 is larger than the QoQ decline of 28.8% for 3Q22 and comes close to the QoQ decline of 36% for the final quarter of 2008, when the global economy was in the midst of a major financial crisis. The main cause of the steep revenue drop in 4Q22 was the plummeting overall ASP. DRAM suppliers experienced a rapid accumulation of inventory in 3Q22 due to a freeze in buyers' demand. Subsequently, suppliers were much more energetic in price negotiations for 4Q22 contracts as they were struggling for market share. Among the major categories of DRAM products, server DRAM suffered the sharpest price drop in 4Q22. Contract prices of DDR4 and DDR5 server DRAM products registered QoQ drops of 23~28% and 30~35% respectively.

Thanks to the attribution of Puget Systems, we have a preview of Intel's latest Xeon W-3400 and Xeon W-2400 workstation processors based on Sapphire Rapids core technology. Delivering up to 56 cores and 112 threads, these CPUs are paired with up to eight TeraBytes of eight-channel DDR5-4800 memory. For expansion, they offer up to 112 PCIe 5.0 lanes come with up to 350 Watt TDP; some models are unlocked for overclocking. This interesting HEDT family for workstation usage comes at a premium with an MSRP of $5,889 for the top-end SKU, and motherboard prices are also on the pricey side. However, all of this should come as no surprise given the expected performance professionals expect from these chips. Puget Systems has published test results that include: Photoshop, After Effects, Premiere Pro, DaVinci Resolve, Unreal Engine, Cinebench R23.2, Blender, and V-Ray. Note that Puget Systems said that: "While this post has been an interesting preview of the new Xeon processors, there is still a TON of testing we want to do. The optimizations Intel is working on is of course at the top, but there are several other topics we are highly interested in." So we expect better numbers in the future.Below, you can see the comparison with AMD's competing Threadripper Pro HEDT SKUs, along with power usage using different Windows OS power profiles:

With the once-lucrative business of cryptocurrency mining now slowly falling out of favor for discrete graphics, crypto miners are turning their heads to creative solutions to "refurbish" and sell their remaining inventory to third-party users. When GPU components, such as the die or GDDR memory, overheat, they can produce visual signs of damage, such as discoloration or melting. Some miners have started painting the memory on their GPU's boards with special thermal paint to hide the wear and tear from the naked eye and make the GDDR chips appear new in hopes that no one would notice. According to Iskandar Souza and TecLab, their cases are now getting debunked.

As these reports note, miners are removing the stock cooling systems from GPUs to install a third-party solution or recently tried to resolder failed GPU dies back in place and paint the yellowish GDDR memory chips. According to the testing done by Iskandar Souza, you can see below the difference between a worn-out yellowish GDDR chip and its painted deception standing next to one another. Below you can also see the process of resoldering failed GPUs back in place. Crypto miners have been very careful to make them look almost as brand new, so GPU buyers from third-party sources need to be extra cautious before making a purchase.

Qualcomm has been working on its Snapdragon SoCs for quite some time now, with massive success in the mobile phone space. However, the company's processors needed to be up to the task regarding laptops. For a user to not look at x86 offerings, the only remaining performant alternatives are Apple's M processors. In 2021 Qualcomm purchased the Nuvia team that was developing massively efficient and high-performance IP for laptops, similar to Apple M processors. Today, according to the insights from Kuba Wojciechowski (@Za_Raczke) on Twitter, we have some potential information about the upcoming Nuvia-powered SoC codenamed Hamoa.

According to the Twitter thread, Qualcomm's Hamoa processors are part of the Snapdragon 8xc Gen 4 compute platform and feature up to eight high-performance P-cores and four low-power E-cores, all based on Nuvia's IP. Allegedly the P-cores are being tested at 3.4 GHz, while the E-cores are tested at 2.5 GHz. The SoC splits CPU cores into blocks, each being a four-core group with 12 MB of shared L2 cache. There is also an 8 MB L3 cache structure; it needs to be clarified whether it is per core block or for the entire SoC. The chip employs 12 MB of system-level cache, with 4 MB of memory for graphics-related tasks handled by iGPU. The iGPU of choice is Adreno 740, with all modern APIs supported. Discrete graphics solutions are supported by the top-end SKUs, which allow eight PCIe 4.0 lanes to be directed toward dGPU, along with an additional four PCIe 4.0 lanes for NVMe SSD. For RAM, the chip uses up to 64 GBs of LPDDR5X eight-channel memory with up to 4.2 GHz speeds. Chip's media engines are structured to support decoding up to 4K120 and encode up to 4K60 with AV1.

TYAN, an industry-leading server platform design manufacturer and a MiTAC Computing Technology Corporation subsidiary, today introduced 4th Gen Intel Xeon Scalable processor-based server platforms highlighting built-in accelerators to improve performance across the fastest-growing workloads in AI, analytics, cloud, storage, and HPC.

"Greater availability of new technology like 4th Gen Intel Xeon Scalable processors continue to drive the changes in the business landscape", said Danny Hsu, Vice President of MiTAC Computing Technology Corporation's Server Infrastructure Business Unit. "The advances in TYAN's new portfolio of server platforms with features such as DDR5, PCIe 5.0 and Compute Express Link 1.1 are bringing high levels of compute power within reach from smaller organizations to data centers."

Inspur Information, a leading IT infrastructure solutions provider, announced that its G7 server platform fully supports 4th Gen Intel Xeon Scalable Processors. The 16 servers making up the brand-new lineup are industry-leading in terms of performance, openness, intelligent operation & maintenance, and sustainability. Compared with the previous generation of Intel-based products, these servers have 61% higher performance and up to 30% higher computing performance per unit of power consumption. The server platform is designed to be deployed in general-purpose computing, critical computing, AI, and other application scenarios.

Inspur Information's brand-new G7 platform was designed with green technology, open-source solutions, security, and intelligence as priorities. It is an industry-leading example of system design, energy efficiency, and operation & maintenance management. G7 servers support diversified computing, with the most comprehensive product lineup in the industry. With a focus on green energy, this product line supports cold plate and immersion cooling schemes, and has unique cooling designs such as T-shaped radiator and advance heat detection with intelligent regulation, which all work together to reduce energy consumption by up to 30%. The new series also supports cloud operation and maintenance for intelligent fault diagnosis with an accuracy rate up to 95%.

TrendForce's latest analysis of the DRAM market finds that the inventory pressure on suppliers remain significant due to the persistently weak demand for consumer electronics. Among the top three DRAM suppliers, only Samsung has seen a slight drop in inventory level thanks to its highly competitive pricing strategy. To prevent DRAM prices as a whole from making another sharp dive, a few suppliers such as Micron have been cutting production. Therefore, the QoQ decline in DRAM prices are projected to shrink to around 13~18% for 1Q23. However, the slump will have yet to reach the bottom at that time. Regarding the QoQ changes in the prices of the major categories of DRAM products for 1Q23, PC DRAM and server DRAM are projected to again register a drop that is near 20%. Conversely, mobile DRAM will experience the smallest price decline because its profit margin is ready the thinnest.

Netac, a Chinese maker of memory and storage devices, has developed DDR5 memory modules with impressive speeds. The company has used SK Hynix A-type dies to create DDR5 memory with up to 8000 MT/s rates. With incredible speeds comes significant latency, whereas the DDR5-8000 memory kit comes with a CAS latency of 38-48-48-128. Netac has determined that these DRAM modules require as much as 1.5 Volts to power it. The base kit starts at 6000 MT/s, with 6200/6600/7200/7600 and 8000 MT/s variations mentioned above. Available in silver and black, these memory modules are equipped with an ARGB strip at the top that works with every RGB control software of motherboard makers.

You can check out the images and specification table below.

TechPowerUp in partnership with Team Group are giving away six pieces of Team Group T-Force gaming hardware. We've actually been at this since November 14, and entries close tomorrow, November 25. That leaves you with a day to fill up a tiny form and answer a couple of quizzy questions on Team Group; for a chance to win a T-Force Delta RGB DDR5-6400 CL40 32 GB (2x 16 GB) memory kit, or one of five Vulcan Z 1 TB SSDs! The Delta RGB DDR5 would be a great addition to your next-generation desktop build, as its DDR5-6400 frequency goes great with the latest "Raptor Lake" and "Zen 4" processors! The Vulcan Z 1 TB makes for a decent game storage drive to add some room to your game library. Both look great when powered up and viewed through a tempered glass panel! Hurry up!

For more details, and to participate, visit this page. Entries close November 25 (tomorrow).

Intel Core i9-13900K processor has just been launched, and overclockers worldwide got their hand on a few samples to make history. According to the HWBot submission, a Swedish overclocker named "elmor" has pushed Intel's top-end consumer SKU to a fantastic 8.812 GHz. For more than eight years, the record for the single-highest overclocking speed was held by AMD FX-8370, from the now-bygone era of AMD Black Edition processors. The overclocking attempt was performed using liquid nitrogen (LN2) that cools the chip using its −195.8 °C temperature. Pushing core voltage to 1.850 Volts and VCCIN to 2 Volts, multiplier set to x88, and a bus speed of 100.15 MHz. In addition to the Core i9-13900K CPU, elmor used ASUS ROG Maximus Z790 APEX motherboard and 32 GB DDR5 GSKILL memory running at 4808 MT/s.

As a reminder, the FX-8370 CPU was holding the number one sport for eight years with a speed of 8.722 GHz. Beating the FX-8370 by just 90 MHz, it will be interesting to see if any of the upcoming CPU SKUs can match this overclocking record, and we are curious if any contender will come to beat elmor's current record.

In December of 2021, we covered the appearance of Russia's home-grown Baikal-S processor, which has 48 cores based on Arm Cortex-A75 cores. Today, thanks to the famous chip photographer Fritzchens Fritz, we have the first die shows that show us exactly how Baikal-S SoC is structured internally and what it is made up of. Manufactured on TSMC's 16 nm process, the Baikal-S BE-S1000 design features 48 Arm Cortex-A75 cores running at a 2.0 GHz base and a 2.5 GHz boost frequency. With a TDP of 120 Watts, the design seems efficient, and the Russian company promises performance comparable to Intel Skylake Xeons or Zen1-based AMD EPYC processors. It also uses a home-grown RISC-V core for management and controlling secure boot sequences.

Below, you can see the die shots taken by Fritzchens Fritz and annotated details by Twitter user Locuza that marked the entire SoC. Besides the core clusters, we see that a slum of cache connects everything, with six 72-bit DDR4-3200 PHYs and memory controllers surrounding everything. This model features a pretty good selection of I/O for a server CPU, as there are five PCIe 4.0 x16 (4x4) interfaces, with three supporting CCIX 1.0. You can check out more pictures below and see the annotations for yourself.

GIGABYTE Technology, (TWSE: 2376), an industry leader in high-performance servers and workstations, today announced supporting products for the new AMD AM5 platform starting with two GIGABYTE motherboards, MC13-LE0 & MC13-LE1, that pair a consumer CPU with IPMI management functionalities via BMC. Additionally, a new desktop workstation, W332-Z00, was released using the same motherboard series platform that supports remote management, but the W332 does so with a Realtek NIC that enables DASH.

The new GIGABYTE products designed to support host systems are deceivingly powerful with a small micro-ATX form factor motherboard and enterprise rich out-of-band management features on top of PCIe Gen 5 and DDR5 technologies. These new client friendly products will be found in office settings under a desk rather than a rack in a data center, as they be managed from anywhere, provided there is a network connection. Furthermore, these new products are purpose built for the mainstream AMD B650E chipset with AMD Zen 4 architecture for AMD Ryzen 7000 Series desktop processors.

According to TrendForce research, rising inflation has weakened demand for consumer products, flattening the peak of peak season. In 3Q22, memory bit consumption and shipments continued to exhibit quarterly decline. Due to a significant decline in memory demand, terminal buyers also delayed purchases, leading to further escalation of supplier inventory pressure. At the same time, the strategies of various DRAM suppliers to increase their market share remain unchanged. There have been cases of "consolidated Q3/Q4 price negotiations" or "negotiating quantity before pricing" in the market, which are the reasons leading to a ballooning of declining DRAM prices to 13~18% in 4Q22.

In terms of PC DRAM, due to weak demand for notebooks, PC OEMs will remain focused on destocking DRAM inventory. While the DRAM supply side has not actually reduced production since operating profit remains favorable, bit output continues to rise and pressure on suppliers' inventory becomes increasingly obvious. From the perspective of DDR4 and DDR5, the price drop forecast in 4Q22 is 13~18% with DDR5 declining more than DDR4. However, as the penetration rate of DDR5 continues to rise, coupled with a higher unit price, the penetration rate of DDR5 in the PC DRAM sector will increase 13~15% in 4Q22, which will buoy the average unit price of overall PC DRAM (combined DDR5 and DDR4) marginally and PC DRAM pricing in 4Q22 is estimated to drop by approximately 10~15%.

The two gaming product leaders, Team Group and BIOSTAR, have joined forces to release the T-FORCE DELTA RGB DDR5 VALKYRIE Edition DESKTOP MEMORY, the first collaboration of T-FORCE brand from Team Group and VALKYRIE series from BIOSTAR. The design is based on the popular DELTA RGB DDR5 DESKTOP MEMORY and its stealth fighter-influenced look, featuring the signature wide-angled heatspreader with dazzling RGB lightning. On top are the logos of T-FORCE's iconic wing and the classic golden wings of the BIOSTAR VALKYRIE series, also integrating the concept of the warriors' majestic wings in the form of a streamlined design spread across the heatspreader. Gamers can enjoy the memory's striking visuals and legendary performance as T-FORCE and VALKYRIE carry them further in the gaming arena.

T-FORCE DELTA RGB DDR5 VALKYRIE Edition DESKTOP MEMORY is equipped with a next-generation RGB smart control chip, allowing gamers to use BIOSTAR's Advanced VIVID LED DJ software to create a unique RGB setup for their PC. With both outstanding hardware and software supports, users can control and synchronize lighting effects any way they like, making it easy to create a divine look all will admire. The VALKYRIE Edition DDR5 supports the latest Intel XMP 3.0, allowing gamers to enjoy the thrill and performance of overclocking in just a few simple clicks. Furthermore, its special thermally conductive silicone and power management chip (PMIC) cooling design significantly reduce heat, providing stable performance while it runs at high speeds.

Qualcomm is a company well known for designing processors going inside a vast majority of smartphones. However, the San Diego company has been making attempts to break out of its vision to focus on smartphones and establish new markets where it could show its potential for efficient processor design. According to Bloomberg's insights, Qualcomm is planning to re-enter the server market and try again to compete in the now very diverse space. In 2014, Qualcomm announced that the company is developing an Arm ISA-based CPU that will target servers and be an excellent alternative for cloud service providers looking at efficient designs called Centriq. Later on, in November of 2017, the company announced the first CPU Centriq 2400, which had 48 custom Falkor cores, six-channel DDR4 memory, and 60 MB of L3 cache.

What happened later is that the changing management of the company slowly abandoned the project, and the Arm CPU market was a bit of a dead-end for many projects. However, in recent years, many companies began designing Arm processors, and now the market is ready for a player like Qualcomm to re-enter this space. With the acquisition of Nuvia Inc., which developed crazy fast CPU IPs under the leadership of industry veterans, these designs could soon see the light of the day. It is reported that Qualcomm is in talks with Amazon's AWS cloud division, which has agreed to take a look at Qualcomm's offerings.

According to TrendForce investigations into the DRAM market, under pressure from ever-increasing output, Korean manufacturers have significantly increased their willingness to compromise on pricing in order to stimulate buying from distributors and customers, leading to a steady expansion of falling prices. In addition to Korean manufacturers enthusiastically slashing prices, low-priced chips from the spot market are also circulating in the market. Other suppliers have no choice but to follow suit and fervently reduce pricing for sales, rapidly exacerbating the 3Q consumer DRAM price drop from the original estimate of 8~13% to a quarterly decline of 13-18%.

Looking forward to Q4, it will be difficult for stocking momentum to recover before terminal inventories have been completely depleted. TrendForce expects the price of consumer DRAM to continue to fall until oversupply in the market is alleviated. Thus, consumer DRAM pricing will carry on moving lower by another 3~8% in Q4 and the possibility of sustained decline cannot be ruled out.

As we approach the launch of Intel's upcoming Raptor Lake desktop processors, we are getting more leaks of testing performed by system integrators and 3rd parties that have early access to the engineering sample (ES) chips. A few days ago, we saw an Intel Core i7-13700K CPU run Geekbench 5 benchmark with the older DDR4 memory on ASRock Z690 Steel Legend WiFi 6E. Today, we are seeing a similar test performed on the same processor, with ASRock Z690 Steel Legend WiFi 6E/D5 equipped with DDR5 memory. While the previous DDR4 testing used modules running at 3200 MT/s, the DDR5 testing uses 5200 MT/s rated DRAM with unknown timings and setup.

As far as performance goes, the single-core result of the 16-core Intel Core i7-13700K processor was 2090 points with DDR4, while DDR5 showed a slight regression of 2069 points. Of course, this could be attributed to the margin of error. As far as multi-core performance goes, the DDR4 testing managed to produce 16542 points, whereas the DDR5-equipped platform scored 19811 points. This is an immediate 20% performance uplift in multi-core score. It shows that all the cores present in Raptor Lake processors are starving for bandwidth, and a faster memory protocol can bring quite an improvement. As usual, we have to wait to confirm this information with our testing so that we can draw more conclusions.

With Intel Raptor Lake-S desktop processors around the corner, we see an ever-increasing number of entries to the popular synthetic benchmark databases. Yesterday we had an Intel Core i5-3600K CPU, while today, we are presented with Core i7-13700K SKU. The new 13th generation Core i7-13700K CPU features eight P-cores and eight E-cores. Compared to the 12th generation Core i7-12700K, this is a step up with eight P-cores and four E-cores. According to Geekbench 5 benchmark, the new Qualification Sample (QS) of Core i7-13700K CPU was running at the minimum clock of 5.289 GHz, maximum clock of 5.381 GHz, and average speed of 5.36 GHz. It was tested on the same configuration as yesterday's i5 SKU with ASRock Z690 Steel Legend WiFi 6E motherboard with 32 GB of DDR4 memory.

As far as the results are concerned, the 13th gen i7-13700K SKU scored 2090 points in the single-core test, while the multi-core score totaled 16542 points. If we compare this to the 12th gen i7-12700K CPU that it replaces, the new model leads by about 10% and 17% in single-core and multi-core tests, respectively.

Amazon's AWS division has been making Graviton processors for a few years now, and the company recently announced its Graviton3 design will soon to available in the cloud. Today, we are witnessing a full launch of the Graviton3 CPUs with the first instances available in the AWS Cloud. In theC7g instances, AWS customers can now scale their workloads across 1-64 vCPU instance variants. Graviton3's 64 cores run at 2.6 GHz clock speed, 300 GB/sec maximum memory bandwidth, DDR5 memory controller, 64 cores, seven silicon die chiplet-based design, 256-bit SVE (Scalable Vector Extension), all across 55 billion transistors. Paired with up to 128 GiB of DDR5 memory, these processors are compute-intensive solutions. AWS noted that the company used a monolithic computing and memory controller logic design to reduce latency and improve performance.

One interesting thing to note is the motherboard that AWS hosts Graviton3 processors in. Usually, server motherboards can be single, dual, or quad-socket solutions. However, AWS decided to implement a unique solution with three sockets. This tri-socket setup is designed to see each CPU as an independent processor, managed by a Nitro Card, which can handle exactly three CPUs. The company notes that the CPU is now in general availability with C7g instances and you can see it below.