About a month ago, we reported about the AMD Ryzen 7 9800X3D "Zen 5" processor with 3D V-Cache that is flying off the shelves, with scalpers trying to make a profit from buying the retail inventory. The processor continues to face widespread availability issues more than a month after its launch, though the company assures consumers that relief is on the horizon. "We are working diligently to get as much supply to market as possible, with more processors being shipped every week," an AMD spokesperson told Tom's Hardware. "We expect availability to get better as shipments ramp throughout the quarter." The CPU is not only hard to find but also proves to be one of the most sought-after processors on Amazon.

The supply shortage has created opportunities for scalpers, who are listing the processor at prices reaching $1,000—more than double its retail price. Even established retailers like Walmart have listed the chip at inflated prices, approaching $800. Adding to consumers' challenges, some third-party sellers have posted fraudulent listings, making it crucial for buyers to verify seller credibility. While major retailers like Amazon, Newegg, Best Buy, and B&H Photo maintain the official $479 price point when in stock, securing a unit at this price has proven challenging for most consumers. As the holiday season is here, AMD's promised production ramp-up is much needed, as gamers have been planning their upgrade months in advance and are in dire need of pushing the performance of their systems up another notch.

We are days away from the official November 7 launch of AMD's Ryzen 7 9800X3D CPU with 3D V-Cache, and we are already seeing some estimates of the speedup compared to the last-generation Ryzen 7 7800X3D CPU. According to a Geekbench submission discovered by Everest (Olrak29_) on X, the upcoming AMD Ryzen 7 9800X3D has been spotted running at a clock speed of 5.46 GHz. This is a 260 MHz increase from the official boost frequency of 5.2 GHz, which indicates overclocking has been applied. If readers recall, the last generations of X3D processors had overclocking disabled, and this time, things are looking different thanks to the compute die being placed on top of SRAM. AMD attributes this to CCD being closer to the heat spreader instead of memory and allowing it to spread heat more effectively, ensuring a stable overclock.

Regarding performance, the Ryzen 7 9800X3D outperforms its predecessor, the Ryzen 7 7800X3D, by an impressive 27.4% in the single-core Geekbench v6 test and 26.8% in the multicore test. The last generation CPU scored 2,726 points in single-core and 15,157 points in multicore tests, while the new Zen 5 design has managed to produce 3,473 points in single-core and 19,216 in multicore tests. These results are approximately 27% improvement over the Zen 4, suggesting that the Zen 5 architecture benefits greatly from better SRAM bandwidth and capacity. While these results only come from synthetic benchmarks, they give us a picture of what to expect from this CPU. We have to wait for more real-world test cases to fully conclude the improvement factor.

Gabriel Ferraz, maintainer of the TechPowerUp SSD database and content creator, recently published an article that shows the relationship between SLC (Single-Level Cell) cache technology and its performance impact on SSDs. Using a Pichau Aldrin Pro 2 TB SSD featuring an Innogrit IG5236 controller and YMTC 128-layer TLC NAND, Gabriel has uncovered both the advantages and potential drawbacks of this feature. The article reveals that with SLC cache enabled, which acts as a high-speed buffer, the SSD achieved remarkable write speeds of up to 6.5 GB/s, but only until 691 GB had been written. Beyond that, speeds dropped to 2.2 GB/s and then to 860 MB/s as the drive filled up.

Disabling the SLC cache delivers more consistent performance results that are 2.1 GB/s across the whole capacity of the SSD, but with lower peak performance. Testing also examined the impact on power consumption and efficiency. With the SLC cache active, the SSD consumed approximately 5 W of power while achieving over 3000 MB/s bandwidth. Disabling the cache reduced power consumption but at the cost of halving the bandwidth to around 1900 MB/s, resulting in lower overall efficiency. Maximum power consumption with cache enabled peaked at 7.3 W, compared to a lower figure when operating in constant TLC mode. Below, you can see some performance benchmarks published on The Overclock Page.

AMD is preparing to release its next generation of high-performance CPUs, the Ryzen 9000X3D series, and rumors are circulating about potential increases in stacked L3 cache. However, a recent report from Wccftech suggests that the upcoming models will maintain the same 64 MB of additional 3D V-cache as their predecessors. The X3D moniker represents AMD's 3D V-Cache technology, which vertically stacks an extra L3 cache on top of one CPU chiplet. This design has proven particularly effective in enhancing gaming performance, leading AMD to market these processors as the "ultimate gaming" solutions. According to the latest information, the potential Ryzen 9 9950X3D would feature 16 Zen 5 cores with a total of 128 (64+64) MB L3 cache, while a Ryzen 9 9900X3D would offer 12 cores with the same cache capacity. The Ryzen 7 9800X3D is expected to provide 96 (32+64) MB of total L3 cache.

Regarding L2, the CPUs feature one MB of L2 cache per core. Perhaps the most exciting development for overclockers is the reported inclusion of full overclocking support in the new X3D series. This marks a significant evolution from the limited options available in previous generations, potentially allowing enthusiasts to push these gaming-focused chips to new heights of performance. While the release date for the Ryzen 9000X3D series remains unconfirmed, industry speculation suggests a launch window as early as September or October. This timing would coincide with the release of new X870 (E) chipset motherboards. PC enthusiasts would potentially wait to match the next-gen CPU and motherboards, so this should be a significant upgrade cycle for many.

MSI, a global leader in gaming PC hardware, is thrilled to announce the release of its highly anticipated SSD powerhouse, the SPATIUM M580 FROZR, ushering in a new era of storage performance. With cutting-edge technology and innovative thermal solutions, this SSD is set to redefine the standards of speed and reliability in storage solutions.

SPATIUM M580 FROZR, Reaching New Heights with Crowned Speeds
The SPATIUM M580 FROZR sets a new benchmark in storage performance with its revolutionary features. Powered by the state-of-the-art PHISON E26 PCIe Gen 5 controller and equipped with advanced 3D NAND flash modules boasting 232 layers, this SSD achieves mind-blowing read speeds of up to 14.6 GB/s and write speeds of up to 12.7 GB/s, up to 2 times faster transfer rates compared to current PCIe 4.0 SSDs. This represents a significant leap in speeds, boosted by a DRAM cache buffer and a SLC Cache, providing users with lightning-fast data access and gaining valuable milliseconds in latency for gaming, content creation, and professional applications. Additionally, the M580 FROZR is fortified with LPDC ECC and E2E Data Protection, ensuring data integrity and reliability. With a high TBW (Terabytes Written) value and backed by a comprehensive 5-year warranty, users can trust in the durability and longevity of the SPATIUM M580 FROZR in 1 TB, 2 TB and 4 TB variants after an easy installation.

Intel's upcoming high-end desktop (HEDT) processor lineup for enthusiasts and prosumers is around the corner, and today, we managed to see the flagship SKU - the Xeon W9-3595X. Spotted recently on Geekbench benchmarks, this new chip packs a whopping 60 cores and 120 threads, making it Intel's highest core count HEDT offering yet. The Xeon W9-3595X is based on Intel's advanced Sapphire Rapids architecture, built using the Intel 7 process node. It succeeds the previous flagship 56-core W9-3495X, with four additional cores crammed into the new 350 Watt TDP envelope. Clock speeds have taken a slight hit to accommodate the extra cores, with the maximum turbo frequency lowered from 4.8 GHz on the 3495X to 4.6 GHz on the new 3595X.

However, with more cores, the 3595X should still offer a significant multi-threaded performance uplift for heavily parallel workloads. The Xeon W9-3595X will drop into existing LGA-4677 motherboards, like the ASUS PRO WS 790-ACE, after a BIOS update. It features 112 MB of L3 cache, 120 MB of L2 cache (2 MB per core), and continues Intel's push towards higher core counts for enthusiasts, content creators, and workstation users who need maximum multi-threaded horsepower. Pricing and availability details remain unannounced as of now. But with an appearance on public databases, an official launch of the 60-core HEDT juggernaut seems imminent. These new Sapphire Rapids SKUs will likely have extra AI features, like dedicated AI acceleration engines, in the same manner that server-class SKUs do.

NVIDIA has recently revised its specification sheet for the upcoming GeForce RTX 4070 SUPER GPU—a small mistake was included in their review guide and marketing material. Team Green workers were likely in a rush to get everything ready for RTX 40xx SUPER range's official unveiling at CES 2024, so a typo here and there is not unexpected. The RTX 4070 SUPER's AD104 GPU configuration was advertised as offering a 20% core count upgrade over the vanilla RTX 4070 (non-SUPER), but detail sensitive sleuths were somewhat puzzled with the SUPER's L2 cache designation of 36 MB. Various 2023 leaks suggested that 48 MB was the correct value; representing a 33% jump up from the standard 4070's L2 pool. We must note that TPU's GPU database had the correct spec entry since day one.

AMD's 3D V-Cache technology utilizes blocks of SRAM stacked on top of the CPU logic die, where CPU cores reside, and allows the processor to access massive pools of cache for applications. However, using this extra level 3 (L3) cache as a RAM disk appears possible, where the L3 SRAM behaves similarly to a storage drive. A big disclaimer here is that this is only possible by exposing the L3 to the CrystalDiskMark benchmark, and no real-world applications can do it in a way that CrystalDiskMark. According to X/Twitter user Nemez (@GPUsAreMagic), the steps to replicate this procedure are: Obtaining an AMD Ryzen CPU with 3D V-Cache, installing OSFMount and creating a FAT32 formatted RAM disk, and running CrystalDiskMark, with values set to values to SEQ 256 KB, Queue Depth 1, Threads 16, and data fill to 0s instead of random.

The results of this experiment? Well, they appear to be rather stunning as the nature of L3 SRAM is that the memory is tiny but very fast and accessible to the CPU, so it can help load data locally before going to the system RAM. With AMD Ryzen 7 5800X3D, the speeds of this RAM disk are over 182 GB/s for reading and over 175 GB/s for writing. In another test, shared by Albert Thomas (@ultrawide219), we managed to see RAM disk based on AMD Ryzen 7800X3D V-Cache, which scores a little less with over 178 GB/s read and over 163 GB/s write speeds. Again, CrystalDiskMark only performed these tests on small allocations varying between 16 MiB and 32 MiB, so no real-world workloads are yet able to utilize this.

TYAN, an industry leader in server platform design and a subsidiary of MiTAC Computing Technology Corporation, debuts its new server line-up for 4th Gen AMD EPYC & AMD Ryzen Processors at SC23, Booth #1917, in the Colorado Convention Center, Denver, CO, November 13-16.

AMD EPYC 9004 processor features leadership performance and is optimized for a wide range of HPC, cloud-native computing and Generative AI workloads
TYAN offers server platforms supporting the AMD EPYC 9004 processors that provide up to 128 Zen 4C cores and 256 MB of L3 Cache for dynamic cloud-native applications with high performance, density, energy efficiency, and compatibility.

Intel's next-generation designs are nearing launch, and we are already getting information about the upcoming generations. Today, we have the information that Intel's Arrow Lake-S desktop/client implementations of the Arrow Lake family will feature as much as 3 MB of level two (L2) cache for each performance core. Currently, Intel's latest 13th-generation Raptor Lake and 14th-generation Raptor Lake Refresh feature 2 MB of L2 cache per performance core. However, the 15th generation Arrow Lake, scheduled for launch in 2024, will bump that up by 50% and reach 3 MB. Given that P-cores are getting a boost in capacity, we expect E-cores to do so as well, but at a smaller size.

Arrow Lake will utilize Lion Cove P-core microarchitecture, while the E-core design will be based on Skymont. Intel plans to use a 20A node for this CPU, and more details will be presented next year.

NVIDIA receives a lot of questions about graphics memory, also known as the frame buffer, video memory, or "VRAM", and so with the unveiling of our new GeForce RTX 4060 Family of graphics cards we wanted to share some insights, so gamers can make the best buying decisions for their gaming needs. What Is VRAM? VRAM is high speed memory located on your graphics card.

It's one component of a larger memory subsystem that helps make sure your GPU has access to the data it needs to smoothly process and display images. In this article, we'll describe memory subsystem innovations in our latest generation Ada Lovelace GPU architecture, as well as how the speed and size of GPU cache and VRAM impacts performance and the gameplay experience.

Finding itself embattled with AMD's EPYC "Genoa" processors, Intel is giving its 4th Gen Xeon Scalable "Sapphire Rapids" processor a rather quick succession in the form of the Xeon Scalable "Emerald Rapids," bound for Q4-2023 (about 8-10 months in). The new processor shares the same LGA4677 platform and infrastructure, and much of the same I/O, but brings about two key design changes that should help Intel shore up per-core performance, making it competitive to EPYC "Zen 4" processors with higher core-counts. SemiAnalysis compiled a nice overview of the changes, the two broadest points of it being—1. Intel is peddling back on the chiplet approach to high core-count CPUs, and 2., that it wants to give the memory sub-system and inter-core performance a massive performance boost using larger on-die caches.

The "Emerald Rapids" processor has just two large dies in its extreme core-count (XCC) avatar, compared to "Sapphire Rapids," which can have up to four of these. There are just three EMIB dies interconnecting these two, compared to "Sapphire Rapids," which needs as many as 10 of these to ensure direct paths among the four dies. The CPU core count itself doesn't see a notable increase. Each of the two dies on "Emerald Rapids" physically features 33 CPU cores, so a total of 66 are physically present, although one core per die is left unused for harvesting, the SemiAnalysis article notes. So the maximum core-count possible commercially is 32 cores per die, or 64 cores per socket. "Emerald Rapids" continues to be based on the Intel 7 process (10 nm Enhanced SuperFin), probably with a few architectural improvements for higher clock-speeds.

In the latest Linux Kernel patches, Intel engineers are submitting initial support for Meteor Lake processor generation, with some interesting potential features. In a patch submitted yesterday, the Intel engineer noted, "On MTL, GT can no longer allocate on LLC - only the CPU can. This, along with the addition of support for ADM/L4 cache, calls a MOCS/PAT table update." What this translates to is that starting from Meteor Lake, the integrated graphics can no longer allocate on the last-level cache (LLC), the highest numbered cache accessed by the cores before fetching from memory. Instead, only the CPU cores can allocate to it. Even more interesting is the mention of the Meteor Lake platform's level 4 (L4) cache. For the first time since Haswell and Broadwell, Intel may be planning to bring back the L4 cache and integrate it into the CPU.

Usually, modern processors use L1, L2, and L3 caches where the L1 version is the fastest and smallest, while the others are larger but slower. The inclusion of L4 caches often is unnecessary, as this type of cache can consume a big area on the processor die while bringing little benefit, translating to the cost of manufacturing drastically soaring. However, with Meteor Lake and its multi-die tile design, we wonder where the L4 cache will end up. We could see integration into the base tile, which holds the compute cores and essential compute elements. This makes the most sense since the logic needs access to fast memory, and L4 could improve the performance in specific applications.

AMD's EPYC lineup already features the new Zen 4 core designed for better performance and efficiency. However, since the release of EPYC Milan-X processors with 3D V-cache integrated into server offerings, we wondered if AMD will continue to make such SKUs for upcoming generations. According to the report from Wccftech, we have a leaked table of specifications that showcase what some seemingly top-end Genoa-X SKUs will look like. The two SKUs listed here are the "100-000000892-04" coded engineering sample and the "100-000000892-06" coded retail sample. With support for the same SP5 platform, these CPUs should be easily integrated with the existing offerings from OEM.

As far as specifications, this processor features 384 MBs of L3 cache coming from CCDs, 768 MBs of L3 cache from the 3D V-Cache stacks, and 96 MBs of L2 cache for a total of 1248 MBs in the usable cache. A 3 MB stack of L1 cache is also dedicated to instructions and primary CPU data. Compared to the regular Genoa design, this is a 260% increase in cache sizes, and compared to Milan-X, the Genoa-X design also progresses with 56% more cache. With a TDP of up to 400 Watts, configurable to 320 Watts, this CPU can boost up to 3.7 GHz. AMD EPYC Genoa-X CPUs are expected to hit the shelves in the middle of 2023.

An alleged AMD client product roadmap slide leaked to the web confirms the Ryzen 7000X3D series. This also builds on a confirmation by Robert Hallock that 3DV Cache technology remains a continued part of the company's client processor roadmap. The 3DV Cache tech played in instrumental role in shoring up gaming performance of AMD's previous-generation "Zen 3" microarchitecture to levels matching or exceeding those of the Intel "Alder Lake," with a performance uplift in the range of 10 to 25 percent. The expectations for 3DV Cache to work a similar miracle with "Zen 4" are set rather high.

While "Zen 4" has achieved gaming performance parity with "Alder Lake," Intel's next-generation "Raptor Lake" is right around the corner, with the company claiming 10-15% single-threaded performance uplifts that should restore the its gaming performance leadership over AMD. The alleged AMD roadmap does not specify when exactly the Ryzen 7000X3D comes out, but is part of the block that spans Q3-2022, deep into 2023. Rumors are abuzz that the company could unveil the 7000X3D in the first half of 2023.

AMD's next-generation Ryzen 7000-series "Phoenix" mobile processors are all the rage these days. Bound for 2023, these chips feature a powerful iGPU based on the RDNA3 graphics architecture, with performance allegedly rivaling that of a GeForce RTX 3060 Laptop GPU—a popular performance-segment discrete GPU. What's more, AMD is also taking a swing at Intel in the CPU core-count game, by giving "Phoenix" a large number of "Zen 4" CPU cores. The secret ingredient pushing this combo, however, is a large cache.

AMD has used large caches to good effect both on its "Zen 3" processors, such as the Ryzen 7 5800X3D, where they're called 3D Vertical Cache (3D V-cache); as well as its Radeon RX 6000 discrete GPUs, where they're called Infinity Cache. The only known difference between the two is that the latter is fully on-die, while the former is stacked on top of existing silicon IP. It's being reported now, that "Phoenix" will indeed feature a stacked 3D V-cache.

The next-generation "Ada Lovelace" graphics architecture powering NVIDIA's GeForce RTX 40-series graphics cards, could see a significant increase in on-die cache memory, according to leaked source-code related to drivers or firmware, seen by XinoAssassin on Twitter. The source-code leak emanates from the recent large-scale cyber-attack on NVIDIA. When comparing source files related to Ampere and Ada architectures, XinoAssassin noticed lines that reference large cache slices.

From this, it was analyzed that the top-of-the-line AD102 silicon will have 96 MB of last-level cache on the silicon; the AD103 and AD104 chips have 64 MB; the AD106 has 48 MB, and the smallest AD107 has 32 MB. Compare this to the 6 MB on the GA102, puny 4 MB on the GA103 and GA104; 3 MB on the GA106, and 2 MB on the GA107. NVIDIA is known to make innovations in generational memory bandwidth increase and memory management, with each new architecture. The company could tap into even faster versions of GDDR6X memory it co-developed with Micron (GDDR6 with PAM4 signaling).

Intel's next-generation Xeon processors code-named Sapphire Rapids are on track to hit the market this year. These new processors are supposed to bring a wide array of new and improved features and a chance for Intel to show off its 10 nm SuperFin manufacturing process in the server market. Thanks to the Twitter user YuuKi_AnS, we have some of the first tests run in AIDA64 and Cinebench R15 benchmark suites. Yuuki managed to get ahold of DDR5-enabled Sapphire Rapids Xeon with 48 cores and 96 threads, equipped with a base frequency of 2.3 GHz and boost speeds of 3.3 GHz. The processor tested was an engineering sample with a Q-SPEC designation of "QYFQ" and made for Intel Socket E (LGA-4677). This CPU sample was locked at 270 Watt TDP.

Below, you can see the performance results of this processor, tested in the AIDA64 cache and memory benchmark and Cinebench R15 bench test. There is a comparison between AMD's Milan-X and Xeon Platinum 8380, so the numbers are more in check of what you can expect from the final product.

To meet the market demand for large-capacity data storage, TEAMGROUP today announced two high-performance, huge-capacity storage products: the TEAMGROUP MP34Q M.2 PCIe SSD, which utilizes QLC Flash and the PCIe Gen3x4 interface and comes with capacities up to 8 TB; and the HIGH ENDURANCE CARD designed for high-resolution surveillance systems. Whether it is for computer equipment or security systems used at home or a business, TEAMGROUP provides reliable upgrade solutions for those who seek the best performance and stability.

Today the company announced the TEAMGROUP MP34Q M.2 PCIe SSD, which utilizes QLC Flash and the PCIe Gen3x4 interface. It also supports NVMe 1.3 and the Dual Cache technologies: SLC Caching and DRAM Cache Buffer. The MP34Q M.2 PCIe SSD offers a massive capacity of up to 8 TB, excellent read/write speeds of up to 3,400/3,000 MB/s, and an official five-year warranty with purchase, so consumers can buy and upgrade with confidence.

AMD Socket AM5 motherboards are set to arrive in Q2-2022, according to PJ, the editor of Uniko's Hardware. This would mean that the Zen 3 + 3D Vertical Cache chiplet AMD CEO Dr Lisa Su showed off in her Computex keynote, could very well be built in the Socket AM4 package, compatible with existing motherboards. The prototype Dr Su showed off appeared Socket AM4, too. AMD claims that the 3D Vertical Cache feature, when paired with a "Zen 3" chiplet, improves gaming performance by a significant 15 percent, helping AMD catch up with Intel's "Rocket Lake-S" processor at gaming. Elsewhere across the landscape, PJ predicts that the Z690 chipset, which goes with "Alder Lake-S" processors in the LGA1700 package, will arrive by Q4 2021, with cost-effective chipsets such as the B660 and H610 in Q1-2022.

Graphics cards have been developed over the years so that they feature multi-level cache hierarchies. These levels of cache have been engineered to fill in the gap between memory and compute, a growing problem that cripples the performance of GPUs in many applications. Different GPU vendors, like AMD and NVIDIA, have different sizes of register files, L1, and L2 caches, depending on the architecture. For example, the amount of L2 cache on NVIDIA's A100 GPU is 40 MB, which is seven times larger compared to the previous generation V100. That just shows how much new applications require bigger cache sizes, which is ever-increasing to satisfy the needs.

Today, we have an interesting report coming from Chips and Cheese. The website has decided to measure GPU memory latency of the latest generation of cards - AMD's RDNA 2 and NVIDIA's Ampere. By using simple pointer chasing tests in OpenCL, we get interesting results. RDNA 2 cache is fast and massive. Compared to Ampere, cache latency is much lower, while the VRAM latency is about the same. NVIDIA uses a two-level cache system consisting out of L1 and L2, which seems to be a rather slow solution. Data coming from Ampere's SM, which holds L1 cache, to the outside L2 is taking over 100 ns of latency.

AMD on April 1st published a new patent application that seems to show the way its chiplet GPU design is moving towards. Before you say it, it's a patent application; there's no possibility for an April Fool's joke on this sort of move. The new patent develops on AMD's previous one, which only featured a passive bridge connecting the different GPU chiplets and their processing resources. If you want to read a slightly deeper dive of sorts on what chiplets are and why they are important for the future of graphics (and computing in general), look to this article here on TPU.

The new design interprets the active bridge connecting the chiplets as a last-level cache - think of it as L3, a unifying highway of data that is readily exposed to all the chiplets (in this patent, a three-chiplet design). It's essentially AMD's RDNA 2 Infinity Cache, though it's not only used as a cache here (and for good effect, if the Infinity Cache design on RDNA 2 and its performance uplift is anything to go by); it also serves as an active interconnect between the GPU chiplets that allow for the exchange and synchronization of information, whenever and however required. This also allows for the registry and cache to be exposed as a unified block for developers, abstracting them from having to program towards a system with a tri-way cache design. There are also of course yield benefits to be taken here, as there are with AMD's Zen chiplet designs, and the ability to scale up performance without any monolithic designs that are heavy in power requirements. The integrated, active cache bridge would also certainly help in reducing latency and maintaining chiplet processing coherency.

MSI, a world-leading motherboard manufacturer, announces the release of AGESA COMBO PI V2 1.2.0.1 beta BIOS for its AMD 500 series motherboards to add SMART ACCESS MEMORY support to AMD RYZEN 3000 desktop processors. Now both RYZEN 5000 and RYZEN 3000* desktop processors support SMART ACCESS MEMORY. AGESA COMBO PI V2 1.2.0.1 BIOS also improves L3 Cache bandwidth in AIDA64 for RYZEN 5000 desktop processors.

SMART ACCESS MEMORY is an innovative feature that allows the system to access the full capacity of the VRAM on the graphics card. Compare to the current solution which has a 256 MB access limitation, this feature will provide the users a better gaming experience.

On December 31st, AMD's Radeon group has filed a patent for a chiplet architecture of the GPU, showing its vision about the future of Radeon GPUs. Currently, all of the GPUs available on the market utilize the monolithic approach, meaning that the graphics processing units are located on a single die. However, the current approach has its limitations. As the dies get bigger for high-performance GPU configurations, they are more expensive to manufacture and can not scale that well. Especially with modern semiconductor nodes, the costs of dies are rising. For example, it would be more economically viable to have two dies that are 100 mm² in size each than to have one at 200 mm². AMD realized that as well and has thus worked on a chiplet approach to the design.

AMD reports that the use of multiple GPU configuration is inefficient due to limited software support, so that is the reason why GPUs were kept monolithic for years. However, it seems like the company has found a way to go past the limitations and implement a sufficient solution. AMD believes that by using its new high bandwidth passive crosslinks, it can achieve ideal chiplet-to-chiplet communication, where each GPU in the chiplet array would be coupled to the first GPU in the array. All the communication would go through an active interposer which would contain many layers of wires that are high bandwidth passive crosslinks. The company envisions that the first GPU in the array would communicably be coupled to the CPU, meaning that it will have to use the CPU possibly as a communication bridge for the GPU arrays. Such a thing would have big latency hit so it is questionable what it means really.

As we are nearing the launch of AMD's highly hyped, next-generation RDNA 2 GPU codenamed "Big Navi", we are seeing more details emerge and crawl their way to us. We already got some rumors suggesting that this card is supposedly going to be called AMD Radeon RX 6900 and it is going to be AMD's top offering. Using a 256-bit bus with 16 GB of GDDR6 memory, the GPU will not use any type of HBM memory, which has historically been rather pricey. Instead, it looks like AMD will compensate for a smaller bus with a new technology it has developed. Thanks to the new findings on Justia Trademarks website by @momomo_us, we have information about the alleged "infinity cache" technology the new GPU uses.

It is reported by VideoCardz that the internal name for this technology is not Infinity Cache, however, it seems that AMD could have changed it recently. What does exactly you might wonder? Well, it is a bit of a mystery for now. What it could be, is a new cache technology which would allow for L1 GPU cache sharing across the cores, or some connection between the caches found across the whole GPU unit. This information should be taken with a grain of salt, as we are yet to see what this technology does and how it works, when AMD announces their new GPU on October 28th.