An intriguing offshoot of Intel's Meteor Lake generation of processors has been discovered by hardware sleuth momomo_us—an iBase MI1002 motherboard specification sheet contains references to a 14th Gen Core Ultra (Meteor Lake-PS) family, with a next-gen LGA1851 socket listed as the desktop platform. The industrial iBase Mini-ITX workstation board is "coming soon" according to a promotional image—this could signal a revival of Meteor Lake outside of laptop platforms. 2023 was a bit of a rollercoaster year for MTL-S SKUs (on socket LGA1851)—one moment Team Blue confirmed that it was happening, then a couple of days later it was disposed of. The upcoming Arrow Lake processor generation seems to be the logical taker of this mantle, but the (leaked) existence of Meteor Lake-PS throws a proverbial spanner into the works.

iBase's MTL-PS-ready boards will be niche "industrial/embedded" items—according to Tom's Hardware: "Intel hasn't officially revealed Meteor Lake PS, but given the "PS" designation, these upcoming processors target the IoT market, similar to Alder Lake PS. Therefore, it's safe to assume that Intel is bringing the mobile Meteor Lake processors to the LGA1851 socket...Although the motherboard has (this) socket, no chipset is present because Meteor Lake PS is the spitting image of the Meteor Lake chip and doesn't need a PCH." Team Blue is hyping up Arrow Lake (ARL-S) as its next-gen mainstream desktop platform, with a launch window set for later in 2024—by sharp contrast, Meteor Lake PS parts are highly unlikely to receive much fanfare upon release.

Intel is quietly working on second generation Arc GPUs—we have not heard much about Xe2 "Battlemage" since CES 2024. Back in January, Tom "TAP" Petersen—an Intel fellow and marketing guru—casually revealed during an interview conducted by PC World: "I'd say about 30% of our engineers are working on Battlemage, mostly on the software side because our hardware team is on the next thing (Celestial)...Battlemage has already has its first silicon in the labs which is very exciting and there's more good news coming which I can't talk about right now." Intel appears to be targeting a loose late 2024 launch window; Petersen stated that he would like to see second generation products arrive at retail before CES 2025's commencement. The SiSoftware Sandra database was updated around mid-March with two very intriguing new Intel GPU entries—test systems (built on an ASUS PRIME Z790-P WIFI mainboard) were spotted running graphics solutions "equipped with 20 Xe-Core (160 EU) and 24 Xe-Cores (160 EU)."

Michael/miktdt commented on the freshly discovered database entries: "some smaller versions are on Sisoft...I guess they are coming. Single-float GP Compute looks quite good for just 160 VE/192 VE. Doesn't tell much about the release though, I guess anything between Q4 2024 and Q2 2025 is a possibility." Both models seem to sport 11.6 GB VRAM capacities—likely 12 GB—and 8 MB of L2 cache. Wccftech has guesstimated potential 192-bit memory bandwidth for these speculative lower-level GPUs. Team Blue has a bit more tweaking to do—based on leaked figures—but time is on their side: "the performance per core for Alchemist currently sits an average of 16% faster than the alleged Battlemage GPU which isn't a big deal since driver-level optimizations and final silicon can give a huge boost when the retail products come out."

NVIDIA completed its last round of GeForce NVIDIA RTX 40-series GPU refreshes at the very end of January—new evidence suggests that another wave is scheduled for imminent release. MEGAsizeGPU has acquired and shared a tabulated list of new Ada Lovelace GPU variants—the trusted leaker's post presents a timetable that was supposed to kick off within the second half of this month. First up is the GeForce RTX 4070 GPU, with a current designation of AD104-251—the leaked table suggests that a new variant, AD103-175-KX, is due very soon (or overdue). Wccftech pointed out that the new ID was previously linked to NVIDIA's GeForce RTX 4070 SUPER SKU. Moving into April, next up is the GeForce RTX 4060 Ti—jumping from the current AD106-351 die to a new unit; AD104-150-KX. The third adjustment (allegedly) affects the GeForce RTX 4060—going from AD107-400 to AD106-255, also timetabled for next month. MEGAsizeGPU reckons that Team Green will be swapping chips, but not rolling out broadly adjusted specifications—a best case scenario could include higher CUDA, RT, and Tensor core counts. According to VideoCardz, the new die designations have popped up in freshly released official driver notes—it is inferred that the variants are getting an "under the radar" launch treatment.

The "iVRy VR" community-backed project has slowly chipped away at unlocking the PlayStation VR2's full potential—Sony's $550 (MSRP) virtual reality headset is locked into the PlayStation 5 ecosystem, but many gamers have requested that it become compatible with PC platforms. iVRy's progress on this front could be surpassed by first-party efforts—a month ago, Sony indicated that it was exploring new avenues: "we're pleased to share that we are currently testing the ability for PS VR2 players to access additional games on PC to offer even more game variety in addition to the PS VR2 titles available through PS5. We hope to make this support available in 2024, so stay tuned for more updates." Reports suggest that Sony's second generation product has not met sales expectations—insiders posit that company leadership has requested a pause of production. An entry into the PC market could boost the PS VR2's popularity, but it will face plenty of competition within an already "niche" segment.

iVRy has monitored Sony's progress with great interest—the former's social media account has disclosed the discovery of a new development milestone: "(their) latest firmware update enables PC access! This means it's no longer necessary to use driver/hardware workarounds to make it work on Windows. Still to be confirmed whether this update enables NVIDIA use, but all indications are that Sony's 'PC games' plans involve direct connection." The iVRy VR project has—so far—managed to (successfully) connect the PS VR2 to AMD GPU-based systems. Sony is expected to produce an official means of hooking up their headset to PCs. iVRy discussed this provision in their follow-up post: "a 'VirtualLink' adapter of some kind is still required due to PS VR2 hardware design. If Sony does intend to make 'official' PC drivers, they would need to provide this adapter to end-users."

Yesterday, South Korea's National Radio Research Agency certified a brand new and very mysterious Xbox Development Kit—naturally, the "Xbox News for Koreans" social media account took credit for this intriguing discovery: "this means that you can use the device in Korea. It is likely to be distributed to game developers in Korea soon." The model's serial code—2089—does not correspond to any of Microsoft's current Xbox Series (X|S) development kits. The tipster shared a short history lesson: "Xbox Series X|S dev kit consoles were certified by the National Radio Research Agency on June 10-11, 2020. The release of the Xbox Series X|S console in Korea was on November 10, 2020." By referencing the current generation's five-month gap—between registration and release of finalized retail units—it is speculated that something new could be arriving around August time.

Industry experts reckon that the leaked devkit is not linked to a rumored "All-Digital" White Xbox Series X Refresh—the latter likely contains unchanged basic hardware designs. Windows Central posited that an Xbox handheld is another possibility—leaked product roadmaps (of 2022 vintage) revealed that Microsoft was considering a move into portable gaming segments. A month ago, Xbox leadership discussed the platform's future—Sarah Bond stated: "there's some exciting stuff coming out in hardware that we're going to share this holiday, and we're also invested in the next generation roadmap...and what we're really focused on there, is delivering the largest technical leap you will have ever seen in a hardware generation." Many media outlets believed that an Xbox Series "Pro" model was teased during the special Official Xbox Videocast.

Insider Gaming's Tom Henderson believes that Sony PlayStation leadership will tighten up development conditions, following recent leaks pertaining to the technological underpinnings of the heavily rumored "PS5 Pro" home console. An IGN report and another Henderson-authored article posit that last week's revelations are "legit," according to their respective networks of industry moles. Apparently top secret information was extracted from a technical document—reports suggest that Sony sent this paper to its third-party development partners, alongside a new batch of development kits.

Industry experts think that (slated) repercussions could affect smaller development houses—Henderson tweeted: "as expected, Sony has launched an internal investigation into the leaked documents on Trinity as it leaked during a third-party rollout...Not sure on the implications yet as I don't think they can catch one individual, but Sony could reduce its third-party developer pool for new tech as a result." Rumors of a "mid-gen hardware refresh" have been swirling for almost a year and a half, but PlayStation bosses seem to be rattled into action (this week). Microsoft maintained a cool exterior following the leak of next-gen Xbox details, but that information emerged from unredacted court documents. Phil Spencer and his colleagues claim that future Xbox product roadmaps are in constant flux.

The International Data Corporation (IDC) has been tracking sales of Sony's PlayStation VR2 virtual reality headset since launch time (February 2023)—a new report claims that a backlog of unsold units has accumulated. Bloomberg's analysis of IDC data reveals that PS VR2 sales have consistently declined each quarter, despite promising early numbers—the publication alleges that Sony Group Corporation has paused production of its ($550 MSRP) PS VR2 headset: "until it clears a backlog of unsold units, according to people familiar with its plans, adding to doubts about the appeal of virtual reality gadgets." Anonymous industry moles reckon that manufacturing facilities have pumped out over two million examples since launch time. Sony is unlikely to admit, publicly, that it is having a tough time shifting its second generation virtual reality headset—Bloomberg's network of insiders believe that "stocks of the device are building up."

The lack of AAA content, developed exclusively for the PS VR2's ecosystem, is cited as big stumbling block—Bloomberg (alongside numerous publications) reckons that sales have suffered due to an absence of system-selling titles. Horizon: Call of the Mountain (2023) was an impactful launch title, but the headset's software portfolio contains a lot of "novelty" items, casual experiences and glorified tech demos (according to community feedback). Late last month, Sony admitted that it was exploring options beyond the VR2's normal mode of operation (PS5 acting as host): "We're pleased to share that we are currently testing the ability for PS VR2 players to access additional games on PC to offer even more game variety in addition to the PS VR2 titles available through PS5. We hope to make this support available in 2024, so stay tuned for more updates." This surprising announcement arrived mere days before the firing of (around) 900 PlayStation employees. Company leadership revealed that Firesprite's headcount would be reduced. This VR-oriented studio collaborated with Guerrilla Games on the development of Horizon: Call of the Mountain. Sony's London Studio will be closed down—its team had previously worked on PlayStation VR Worlds (2016) and Blood & Truth (2019)—compatible with Sony's first generation headset.

TSMC is experiencing unprecedented demand from AI chip customers—unnamed parties have (fancifully) requested the construction of entirely new fabrication facilities. Taiwan's leading semiconductor contract manufacturer seems to concentrating on "sensible" expansions, mainly in the area of CoWoS packaging output—according to an Economic Daily report, company leadership and local government were negotiating over the construction of four new advanced packaging plants. Insiders propose that plans have been revised—an investment in excess of 500 billion yuan ($16 billion) will enable the founding of six new CoWoS-focused facilities. TSMC is expected to make an official announcement next month—industry moles reckon that construction work will start in April. Two (of the six total) advanced packaging plants could become fully operational before the conclusion of 2024.

Lately, TSMC has initiated an ambitious recruitment drive—targeting around 6000 new workers. A touring entity is tasked with the attraction of "talents with high enthusiasm for semiconductors." The majority of new recruits are likely heading to new or expanded Taiwan-based facilities. The Economic Daily report proposes that Chiayi City's technological hub will play host to TSMC's new CoWoS packaging plants. A DigiTimes Asia news piece (from January) posited that TSMC leadership anticipates CoWoS output reaching 44,000 units by the end of 2024. This predicted tally could grow, thanks to the (rumored) activation of additional factories. CoWoS packaging is considered to be a vital aspect of AI accelerators—insiders believe that TSMC's latest investment will boost production of NVIDIA H100 GPUs. The combined output of six new CoWoS plants will assist greatly in the creation of next-gen B100 chips.

Jensen Huang's opening GTC 2024 keynote is scheduled to happen tomorrow afternoon (13:00 Pacific time)—many industry experts believe that the NVIDIA boss will take the stage and formally introduce his company's B100 "Blackwell" GPU architecture. An enlightened few have been treated to preview (AI and HPC) units—including Dell's CEO, Jeff Clarke—but pre-introduction leaks have not flowed out. Team Green is likely enforcing strict conditions upon a fortunate selection of trusted evaluators, within a pool of ecosystem partners and customers.

Today, a brave soul has broken that silence—tech tipster, AGF/XpeaGPU, fears repercussions from the leather-jacketed one. They revealed a handful of technical details, a day prior to Team Green's highly anticipated unveiling: "I don't want to spoil NVIDIA B100 launch tomorrow, but this thing is a monster. 2 dies on (TSMC) CoWoS-L, 8x8-Hi HBM3E stacks for 192 GB of memory." They also crystal balled an inevitable follow-up card: "one year later, B200 goes with 12-Hi stacks and will offer a beefy 288 GB. And the performance! It's... oh no Jensen is there... me run away!" Reuters has also joined in on the fun, with some predictions and insider information: "NVIDIA is unlikely to give specific pricing, but the B100 is likely to cost more than its predecessor, which sells for upwards of $20,000." Enterprise products are expected to arrive first—possibly later this year—followed by gaming variants, maybe months later.

Samsung Electronics is all set to discuss the future of AI, alongside Jensen Huang, at NVIDIA's upcoming GTC 2024 conference. South Korean insiders have leaked the company's intentions, only days before the event's March 18 kickoff time. Their recently unveiled 36 GB HBM3E 12H DRAM product is expected to be the main focus of official presentations—additionally, a new storage subscription service is marked down for a possible live introduction. An overall "Redefining AI Infrastructure" presentation could include—according to BusinessKorea—a planned launch of: "petabyte (PB)-level SSD solution, dubbed 'PBSSD,' along with a subscription service in the US market within the second quarter (of 2024) to address the era of ultra-high-capacity data."

A Samsung statement—likely sourced from leaked material—summarized this business model: "the subscription service will help reduce initial investment costs in storage infrastructure for our customers and cut down on maintenance expenses." Under agreed upon conditions, customers are not required to purchasing ultra-high-capacity SSD solutions outright: "enterprises using the service can flexibly utilize SSD storage without the need to build separate infrastructure, while simultaneously receiving various services from Samsung Electronics related to storage management, security, and upgrades." A special session—"The Value of Storage as a Service for AI/ML and Data Analysis"—is alleged to be on the company's GTC schedule.

Industry insiders reckon that Samsung Electronics is transitioning to molded underfill (MR-MUF) production techniques—rival memory manufacturer, SK Hynix, champions this chip making technology. A Reuters exclusive has cited claims made by five industry moles—they believe that Samsung is reacting to underwhelming HBM production yields. The publication proposes that: "one of the reasons Samsung has fallen behind (competing producers) is its decision to stick with chip making technology called non-conductive film (NCF) that causes some production issues, while Hynix switched to the mass reflow molded underfill (MR-MUF) method to address NCF's weakness." The report suggests that Samsung is in the process of ordering new MUF-related equipment.

One anonymous source stated: "Samsung had to do something to ramp up its HBM (production) yields... adopting MUF technique is a little bit of swallow-your-pride type thing for (them), because it ended up following the technique first used by SK Hynix." Reuters managed to extract a response from the giant South Korean multinational—a company spokesperson stated: "we are carrying out our HBM3E product business as planned." They indicated that NCF technology remains in place as an "optimal solution." Post-publication, another official response was issued: "rumors that Samsung will apply MR-MUF to its HBM production are not true." Insiders propose a long testing phase—Samsung is rumored to be sourcing MUF materials, but mass production is not expected to start this year. Three insiders allege that Samsung is planning to "use both NCF and MUF techniques" for a new-generation HBM chip.

Rumors from last week pointed to a possible $3.5 billion government defense-related investment—Intel was linked to this very lucrative semiconductor supply contract. Insiders posited that the US Department of Commerce was readying a rough $1 billion investment, while the Pentagon prepared around $2.5 billion. The latter has scrapped those plans, according to anonymous sources—Bloomberg believes that this: "move threatens to limit the total amount that Intel has been expecting to get in federal funding, setting up a contentious situation." The publication's moles have requested complete anonymity, due to the secretive nature of policy negotiations.

The US Department of Commerce deliberates over the nation's CHIPS Act—this fund could be utilized to "make up for the shortfall," following the Pentagon's reported last minute course change. The Department of Commerce could be forced to foot the entire bill—of $3.5 billion—if Intel's services are secured. Negotiations over a so-called "Secure Enclave" project have been ongoing since last year, according to insiders. It is possible that the "fast-moving" military spending bill set off alarms at the Pentagon—the Department of Defense's reasonings were not revealed by Bloomberg's investigation. Several media outlets have requested official comments from the two arms of government. Yesterday, Intel shares fell by 3%—as reported Investopedia—with the market reacting to rumors of cancelled plans.

JEDEC is currently presiding over standards for 6th generation high bandwidth memory (AKA HBM4)—the 12 and 16-layer DRAM designs are expected to reach mass production status in 2026. According to a ZDNET South Korea report, involved manufacturers are deliberating over HBM4 package thicknesses—allegedly, decision makers have settled on 775 micrometers (μm). This is thicker than the previous generation's measurement of 720 micrometers (μm). Samsung Electronics, SK Hynix and Micron are exploring "hybrid bonding," a new packaging technology—where onboard chips and wafers are linked directly to each other. Hybrid bonding is expected to be quite expensive to implement, so memory makers are carefully considering whether HBM4 warrants its usage.

ZDNET believes that JEDEC's agreement—settling on 775 micrometers (μm) for 12-layer and 16-layer stacked HBM4—could have: "a significant impact on the future packaging investment trends of major memory manufacturers. These companies have been preparing a new packaging technology, hybrid bonding, keeping in mind the possibility that the package thickness of HBM4 will be limited to 720 micrometers. However, if the package thickness is adjusted to 775 micrometers, 16-layer DRAM stacking HBM4 can be sufficiently implemented using existing bonding technology." A revised schedule could delay the rollout of hybrid bonding—perhaps pushed back to coincide with a launch of seventh generation HBM. The report posits that Samsung Electronics, SK Hynix and Micron memory engineers are about to focus on the upgrading of existing bonding technologies.

Naughty Dog's remaster of "The Last of Us Part II" released on January 16 of this year—the PlayStation 4-era survival horror classic was spruced up and released exclusively on Sony's current-generation console. Segments of the gaming community have continued to question the company's PS5/PS4-to-PC porting policy—timing remains the key sticking point here. PC platform enthusiasts have often waited around two to three years for expirations of PlayStation exclusivity. Sony leadership has absorbed some of this feedback—a small wave of PC ports have emerged in recent times, following a series of insider leaks. Crucially, Horizon Forbidden West Complete Edition's PC version is due to launch on March 21, followed by Ghost of Tsushima Director's Cut—almost two months later.

Iron Galaxy ported "The Last of Us Part 1" to PC platforms—their collaboration—with Naughty Dog—launched last March. Naturally, discussions immediately focused on the sequel's speculated release date—one year later, a "reliable" tipster has thrown in their two cents. Silknigth's recent track record includes the outing of Sucker Punch's Ghost of Tsushima Director's Cut PC port. The leaker stated: "Sony's upcoming PC game is The Last Of Us Part 2 Remastered. Its announcement is expected next month, although the exact date is unknown. There will be a longer-than-usual period between the announcement date and the release day." Reports suggest that Sony could unveil another batch of PC ports in the near future—these titles include: God of War Ragnarok, Gran Turismo 7 and Demon's Souls.

Qualcomm's Weibo social media account has teased an upcoming new product launch: "the spring dragon raises its head, and everything is reborn! The new Snapdragon flagship is about to be released. Let's welcome the New Year and the new era. On March 18, please stay tuned for the Snapdragon flagship new product launch conference." News outlets believe that a variant of the current top-of-the-line Snapdragon 8 Gen 3 (SM8650-AB) chipset will be introduced next week. Smartphone tech tipster, Digital Chat Station, revealed that a mysterious Qualcomm Snapdragon "SM8635" model was in the pipeline. Early February speculation pointed to a possible "Snapdragon 8s Gen 3" moniker—the added "s" implies that this mobile processor could emerge as a cheaper "sub-flagship" model.

Geekbench 6.2.2 results—posted by a trio of Realme "RMX3851" android smartphones—revealed speculated "8s Gen 3" specifications, including a 3.01 GHz "Big" Core clock, an Adreno 735 integrated GPU, and a 1+3+4 cluster configuration. The pre-release samples could not keep up with finalized Snapdragon 8 Gen 3 hardware in performance gauntlets. A mid-range "Snapdragon 7+ Gen 3" SoC could make an appearance on March 18, but tipsters believe that the event will be dedicated to a single new product. Digital Chat Station reckons that Qualcomm will market the Snapdragon 8s Gen 3 "as a Little 8G3."

Speculative NVIDIA GeForce RTX 50-series "GB20X" GPU memory interface details appeared online late last week—as disclosed by the kopite7kimi social media account. The inside information aficionado—at the time—posited that the "memory interface configuration of GB20x (Blackwell) is not much different from that of AD10x (Ada Lovelace)." It was inferred that Team Green's next flagship gaming GPU (GB202) could debut with a 384-bit memory bus—kopite7kimi had "fantasized" about a potentially monstrous 512-bit spec for the "GeForce RTX 5090." A new batch of follow-up tweets—from earlier today—rips apart last week's insights. The alleged Blackwell GPU gaming lineup includes the following SKUs: GB202, GB203, GB205, GB206, GB207.

Kopite7kimi's revised thoughts point to Team Green's flagship model possessing 192 streaming multiprocessors and a 512-bit memory bus. VideoCardz decided to interact with the reliable tipster—their queries were answered promptly: "According to kopite7kimi, there's a possibility that the second-in-line GPU, named GB203, could sport half of that core count. Now the new information is that GB203 might stick to 256-bit memory bus, which would make it half of GB202 in its entirety. What this also means is that there would be no GB20x GPU with 384-bit bus." Additional speculation has NVIDIA selecting a 192-bit bus for the GB205 SKU (AKA GeForce RTX 5070). The GeForce RTX 50-series is expected to arrive later this year—industry experts are already whispering about HPC-oriented Blackwell GPUs being unveiled at next week's GTC 2024 event. A formal gaming family announcement could arrive many months later.

JEDEC is expected to announce a next-gen low-power RAM memory (LPDDR) standard specification by the third quarter of this year. Earlier today, smartphone technology watcher—Revegnus—highlighted insider information disclosed within an ETnews article. The International Semiconductor Standards Organization (JEDEC) has recently concluded negotiations regarding "next-generation mobile RAM standards"—the report posits that: "more than 60 people from memory, system semiconductor, and design asset (IP) companies participated" in a Lisbon, Portugal-situated meeting. A quoted participant stated (to ETnews): "We have held various discussions to confirm the LPDDR6 standard specification...(Details) will be released in the third quarter of this year."

The current generation LPDDR5 standard was secured back in February 2019—noted improvements included 50% performance and 30% power efficiency jumps over LPDDR4. Samsung Electronics and SK Hynix are in the process of mass-producing incremental improvements—in the form of LPDDR5X and LPDDR5T. A second source stated: "Technology development and standard discussions are taking place in a way to minimize power consumption, which increases along with the increase in data processing." A full-fledged successor is tasked with further enhancing data processing performance. Industry figures anticipate that LPDDR6 will greatly assist in an industry-wide push for "on-device AI" processing. They reckon that "large-scale AI calculations" will become the norm on smartphones, laptops, and tablet PCs. Revegnus has heard (fanciful) whispers about a potential 2024 rollout: "support may be available starting with Qualcomm's Snapdragon 8 Gen 4, expected to be released as early as the second half of this year." Sensible predictions point to possible commercialization in late 2025, or early 2026.

According to TPU's SSD database, the Microsoft Z1000 M.2 22110 form factor solid-state drive launched back in 2020—last week, well-known hardware tipster, yuuki_ans, leaked a set of photos and specifications. Their March 7 social media post showcases close-ups of a potential enterprise product—sporting a CNEX Labs CNX-2670AA-CB2T controller, Toshiba BiCS4 96-layer eTLC NAND flash dies and 1 GB Micron MT40A1G8SA-075:E DDR4 RAM cache. The mysterious storage device appears to be an engineering sample (PV1.1)—an attached label lists a possible manufacturing date of May 18, 2020, but its part number and serial code are redacted in yuuki's set of photos. PCIe specifications are not disclosed, but experts reckon that a 4.0 standard is present here (given the prototype's age).

The long form factor and presence of a CNEX Labs controller suggest that Microsoft has readied a 960 GB capacity model for usage in data servers. Unoccupied spaces on the board provide evidence of different configurations. Extra BGA mounting points could introduce another DRAM chip, and there is enough room for additional capacitors—via solder pads on both sides of the Z1000's PCB. It is speculated that 2 TB and 4 TB variants exist alongside the leaked 960 GB example—a "broad portfolio" of finalized Z1000 products could be in service right now, but the wider public is unlikely to see these items outside of Microsoft facilities.

Earlier in the week it was revealed that NVIDIA had distributed next-gen AI GPUs to its most important ecosystem partners and customers—Dell's CEO expressed enthusiasm with his discussion of "Blackwell" B100 and B200 evaluation samples. Team Green's next-gen family of gaming GPUs have received less media attention in early 2024—a mid-February TPU report pointed to a rumored PCIe 6.0 CEM specification for upcoming RTX 50-series cards, but leaks have become uncommon since late last year. Top technology tipster, kopite7kimi, has broken the relative silence on Blackwell's gaming configurations—an early hours tweet posits a slightly underwhelming scenario: "although I still have fantasies about 512 bit, the memory interface configuration of GB20x is not much different from that of AD10x."

Past disclosures have hinted about next-gen NVIDIA gaming GPUs sporting memory interface configurations comparable to the current crop of "Ada Lovelace" models. The latest batch of insider information suggests that Team Green's next flagship GeForce RTX GPU—GB202—will stick with a 384-bit memory bus. The beefiest current-gen GPU AD102—as featured in GeForce RTX 4090 graphics cards—is specced with a 384-bit interface. A significant upgrade for GeForce RTX 50xx cards could arrive with a step-up to next-gen GDDR7 memory—kopite7kimi reckons that top GPU designers will stick with 16 Gbit memory chip densities (2 GB). JEDEC officially announced its "GDDR7 Graphics Memory Standard" a couple of days ago. VideoCardz has kindly assembled the latest batch of insider info into a cross-generation comparison table (see below).

A Qualcomm Snapdragon X Elite "X1E80100" processor model was leaked in late February—it is likely that several SKUs have been distributed for evaluation purposes. Geekbench Browser is normally a good source of pre-release information—a benched Lenovo "83ED" laptop was spotted last week. That entry outed a "Snapdragon X Elite-X1E78100" processor, sporting twelve cores with maximum frequencies of 3.42 GHz. The latest exposures arrive courtesy of a Baidu forum post. Qualcomm has publicly revealed its "X Elite" range of Nuvia-designed Oryon core CPUs, but insiders have uncovered an additional "X Plus" family—probably a series of less expensive/lower spec alternatives.

The leaked list of SKUs does not include any detailed information—it reconfirms the existence of Qualcomm's top-tier X1E80100 and X1E78100 models and the presence of Adreno iGPUs. Driver information points to Qualcomm's next-gen integrated graphics solutions being readied for modern APIs: DX11, DX12, and OpenGL. The firm's ARM-based mobile PC CPUs are expected to launch within a mid-2024 period, according to the company's official statements—insiders believe that the NPU-enhanced Snapdragon X processors are destined to debut within next-gen "Windows 12" AI-centric notebooks.

Taiwan's Commercial Times has published coverage of a newly launched TSMC recruitment drive—proceedings kicked off last weekend with company representatives heading to the National Taiwan University campus. On the second of March, TSMC set up an outdoor booth on the grounds of Taipei's public research university—where the national comprehensive institute organized a Talent Recruitment Enterprise Expo. Unsurprisingly, TSMC recruiters are seeking potential "talents with high enthusiasm for semiconductors." Ctee's reporter found out that Taiwan's premier foundry is expecting to: "recruit approximately 6,000 new colleagues in Taiwan in 2024, including engineers and technicians." TSMC is reportedly responding to business growth and technology development demands—so much so, that its native manufacturing plants require a fresh influx of workers.

According to Ctee's report, TSMC's March recruitment tour is due to snake through Taiwan and then head over to mainland China: "Tsinghua University, National Cheng Kung University, National Yang-Ming Jiaotong University, Central China University, Zhongxing University, Zhongshan, National Chung Cheng University, Beijing University of Science and Technology, etc., totaling 19 physical activities and four online talent recruitment briefings." A parallel "2024 DNA Summer Internship Program" has also been rolled out: "inviting interested students to join and use internships to personally experience the environment and culture of TSMC." The company's growing global layout also provides opportunities for new employees to work overseas—the article highlights TSMC's newly opened semiconductor fabrication plant in Kumamoto Prefecture, Japan as the preferred choice for "internal employees." The multinational firm's Arizona facilities did not get a shout out, despite recent good news. Reports from mid-2023 suggest that TSMC's core values are at odds with North American work culture.

Electronic Arts revealed a workforce reduction program last week—reportedly impacting around 670 employees—alongside announcements regarding a number of major development project cancellations and reassignments. Laura Miele, President of EA Entertainment and Technology, disclosed that Respawn Entertainment's mysterious "Star Wars FPS Action game" had been axed, with staffers moving onto "new projects based on our owned brands" instead of licensed material. Industry insider reports suggested that an internal Respawn team—not assigned to a "Star Wars: Jedi" sequel—had started work on a Mandalorian/bounty hunter-themed first-person shooter IP. The official announcement of a renewed focus on Respawn's "rich library of owned brands" has generated plenty of internet speculation—Titanfall franchise fans have long demanded a proper third entry in the series. Studio boss, Vince Zampella, has teased revisits in the past—an Axios interview revealed that veteran Titanfall game director, Steve Fukuda, was incubating "something new" with a very small skunkworks-type team.

Earlier this week, Giant Bomb's Jeff Grubb addressed rumored goings-on at Respawn. His "Game Mess Mornings 03/04/24" videocast—co-hosted by Emma Fyffe—included a segment dedicated to EA's adjusted development strategies. Grubb reiterated insider information about "Titanfall Legends" getting canned early on last year—allegedly a single-player Apex/Titanfall crossover experience. Giant Bomb's News Editor has reached out to his network of moles—he shared this inside info during Monday's broadcast: "They're not making Titanfall 3. They just straight up aren't. They do have another team that has been kicking around a project that is very early. There's been a very small team in the prototyping phase and now they're going to go to wider. This is a real project now, but still in the prototyping phase. This game, as it stands today, as far as I understand, is a Titanfall game. It's in the Titanfall universe. But everyone I talk to keeps saying, don't get in your mind that it's Titanfall 3, a game with online multiplayer and a single player campaign."

South Korean tech insiders believe that SK Hynix has sent "12-layer DRAM stacked HBM3E (5th generation HBM)" prototype samples to NVIDIA—according a ZDNET.co.kr article, initial examples were shipped out last month. Reports from mid-2023 suggested that Team Green had sampled 8-layer HBM3E (4th gen) units around summer time—with SK Hynix receiving approval notices soon after. Another South Korean media outlet, DealSite, reckons that NVIDIA's memory qualification process has exposed HBM yield problems across a number of manufacturers. SK Hynix, Samsung and Micron are competing fiercely on the HBM3E front—with hopes of getting their respective products attached to NVIDIA's H200 AI GPU. DigiTimes Asia proposed that SK Hynix is ready to "commence mass production of fifth-generation HBM3E" at some point this month.

SK Hynix is believed to be leading the pack—insiders believe that yield rates are good enough to pass early NVIDIA certification, and advanced 12-layer samples are expected to be approved in the near future. ZDNET reckons that SK Hynix's forward momentum has placed it an advantageous position: "(They) supplied 8-layer HBM3E samples in the second half of last year and passed recent testing. Although the official schedule has not been revealed, mass production is expected to begin as early as this month. Furthermore, SK Hynix supplied 12-layer HBM3E samples to NVIDIA last month. This sample is an extremely early version and is mainly used to establish standards and characteristics of new products. SK Hynix calls it UTV (Universal Test Vehicle)... Since Hynix has already completed the performance verification of the 8-layer HBM3E, it is expected that the 12-layer HBM3E test will not take much time." SK Hynix's Vice President recently revealed that his company's 2024 HBM production volumes for were already sold out, and leadership is already preparing innovations for 2025 and beyond.

AMD Linux engineers have been working on "GFX1150" and "GFX1151" targets for a while—official references to "Strix 1/Strix Point" and "Strix Point Halo" have appeared several times on official development channels. Phoronix's head honcho—Michael Larabel—monitors these activities with keen interest, his latest finding indicates that Team Red is preparing open-source RadeonSI/RADV driver support for the GFX1151 IP. Their MESA 24.1 update merges in GPU enablement for possible high-end "Strix Point Halo" laptop processors—tech tipsters believe that these chiplet variants could sport up to sixteen Zen 5 CPU cores and forty RDNA 3.5 GPU cores.

AMD's enablement of the "GFX1150/Strix Point" GPU appeared online late last month—these monolithic laptop chips are alleged to sit below "Strix Point Halo" in Team Red's product hierarchy. Insiders suggest that the best configurations could house twelve Zen 5 CPU cores and sixteen RDNA 3.5 GPU cores. Phoronix posited that the "RDNA 3 refresh" graphics solution: "is just rumored for select APUs, while ultimately we'll see where this GFX 11.5.1 IP is found if for some further upgraded APU or something more special. In any event the open-source Linux driver support is coming together." According to official product roadmaps, the initial batch of "Strix Point" mobile chips are expected ship later this year—representing a proper next-gen upgrade over current "Hawk Point" offerings.

The existence of Intel's upcoming Core i9-14900KS processor has been confirmed by a series of insider leaks and premature retail listings—an "alleged" example was photographed and appeared online right at the start of 2024. French e-tail listings produced evidence of two packages—a traditional retail box version, and a barebones tray option for OEM purposes. Earlier today, the I_Leak_VN social media account uploaded proof of a single "Special Edition" box sitting in an unnamed Vietnamese warehouse—it is not immediately clear whether units have reached retail facilities, or have just arrived on Southeast Asian shores. The embargo-busting post seemingly corroborates global insider information/whispers about distribution networks receiving stock—possibly in preparation for a rumored mid-March launch. VideoCardz believes that Vietnamese customers will be paying roughly $765 a pop—30% pricier than the current cost of 14th Gen Core flagship ownership.