The Hot Take: Yeah looks like that CZ market is going to get a new avenue of revenue soon enough. Hoping the prices can be kept down is my only concern.
MSI has shown off new cooling and power tricks for future Nvidia RTX graphics cards.
The outfit has said that since the company is not expecting a major gamer GPU launch this year, it used the gap to show what might land on future Nvidia RTX cards and what it will have to come up with to match.
MSI said that it is working on three main areas for its next designs: cooling, power delivery and the PCB. The cooling work includes new fans, heat pipes, thermal pads and baseplates, all dressed up as an advanced thermal architecture. The fan design uses ultra-thin metal blades rather than the usual plastic jobs.
MSI says the seven-blade all-metal design can deliver up to 40 per cent better airflow. The trick is a high-rigidity metal structure packed into a 0.8mm blade, which should resist deformation at higher speeds.
Thinner blades give more effective airflow area, while wider paths reduce resistance during high-speed operation.
MSI is also working on advanced spiral-groove heat pipes. These increase contact area compared with conventional heat pipes, which should help shift heat away from the GPU more efficiently.
The company has added diamond-composite thermal pads for memory modules to improve heat dissipation. There is also a diamond-copper composite baseplate, with a diamond-copper layer stacked between two copper layers.
MSI says this creates a high-conductivity path from the GPU to the heatsink. All these parts come together in a fully integrated cooling module.
One early design was shown as a next-generation Gaming Trio graphics card. MSI displayed it on an existing RTX 5090 32GB GPU, although it remains a prototype rather than a finished retail card.
The final version is expected to arrive with future Nvidia GPUs, so for now, it is more engineering peep show than shopping list.
MSI is bringing its Safeguard technology directly to high-end graphics cards. The feature first appeared on the companyâs MPG power supply line.
The same protection and control, handled through software and hardware, will now work from the 16-pin connector on the graphics card. That means users will not need a compatible PSU to get the feature working.
MSI is still validating the technology with more power supplies and is expected to give it a new name. The company is also adding server-grade reusable fuses, called eFuse, to future GPUs. These are designed to protect the card from electrical damage using an internal gate-based reset mechanism.
The company says the fuses are resettable and reusable, with a short-circuit response of about 200ns. That should help long-term reliability, although anyone who has watched 16-pin connector drama will know reassurance is doing plenty of work here.
MSI showed the design on its RTX 5090 SUPRIM Safeguard card. As with the cooling module, these technologies are intended for future graphics cards rather than the shelves today.
It all points to GPU makers preparing for more power, more heat and more expensive lumps of hardware that need not cook themselves while running the next AI-slathered benchmark.
Â
Read the full article
The Hot Take: New P-Cores and bus, sounds like Intel is trying to innovate again. Which is good for all of us, healthy competition will help bring/keep prices down for CPUs at least.
Intel has officially confirmed its next-gen Xeon 7 Diamond Rapids CPUs are coming in 2027, featuring 50% higher core counts and twice the memory bandwidth of Xeon 6 in a bid to compete against AMDâs upcoming EPYC Venice CPUs.
Read the full article
The Hot Take: Well have to see if this claim holds up on launch.
Intel is putting its 18A node into the data center with new Xeon 6+ Clearwater Forest CPUs, which pack up to 288 E-cores for dense compute.
Read the full article
The Hot Take: CISC monsters coming from owner of the x86 ISA.
COMPUTEX 2026 Intelâs upcoming Diamond Rapids Xeon will boost core counts to 192, a 50 percent increase over last generation, the x86 giant revealed at Computex in Taipei this week. But while core counts continue to rise, in doing so Intel has managed to cut thread counts by a quarter. Yep, Hyperthreading â Intel's marketing for simultaneous multithreading â is officially dead. Intel first added support for SMT all the way back in 2002. The technology boosted utilization by enabling two threads to harness idle execution units during a single cycle. While SMT doesnât double throughput, for certain applications it can deliver double-digit percentage gains. After slowly abandoning the tech across its consumer product lineup, Intel's Xeons are latest to get the cut. Except, wait! It seems Intel may have seen the error of its ways, and is already reversing course on the decision. Intelâs next next Xeon, codenamed Coral Rapids, will bring SMT back. The jump from 128 to 192 is a big jump for Intel, but still smaller than the AMD is making with its 256-core Venice Epycs. If that werenât enough, it looks like AMD could beat Intel to market by as much as a year. Diamond Rapids is now slated for release sometime in 2027. Echos of Epyc, notes of Monaka In addition to core count, we also got our first look at how Intel will stitch the chip together. It turns out AMD might have been onto something when it started gluing silicon together back in 2017, because Intelâs next round Xeons look more like an Epyc under the hood than ever. We know the chip will be fabbed using Intelâs 18A-P process tech, a refined version of its 2nm-class process tech. Beyond this details get a little fuzzy. From the renders shared in Intelâs press deck, we can see what appear to be two I/O dies serving four vertically stacked compute assemblies assembled using its Foveros packaging tech. This isnât the first time weâve seen something like this from Intel. Intelâs Clearwater Forest, which is finally launching after years of teasing, also used a similar arrangement, with four 24-core compute tiles sitting atop a base die containing the memory controller and L3 cache. Moving the L3 cache to the base die frees up a lot of die area on the compute chiplet. In this case, we're looking at four 48-core compute chiplets. In this respect, Diamond Rapids looks a lot like another CPU weâve looked at recently: Fujitsuâs Monaka. That chip uses an almost identical chip layout, albeit with one I/O die rather than two. While weâre fairly certain Diamond Rapidâs L3 cache will live on the base die, the memory controller could be housed on the four base dies or it could be on the I/O dies, similar to what AMD has done since Rome launched in 2019. If we had to guess, our bet would be on the I/O die, since it would reduce the number of NUMA nodes to one or two as opposed to four. Not a mainstream part Unlike Intelâs last P-core Xeon, codenamed Granite Rapids, donât expect to see Diamond Rapids deployed widely in enterprise virtualization or storage servers. According to Intel, Diamond Rapids is âoptimized for high-demand IaaS, high-perf/thread,â putting it in the same class as its high-performance-computing (HPC)-centric 6900P-series parts. The lack of SMT complicates hypervisor licensing models. Where you once got two threads for the price of one, Diamond Rapids customers will now be getting half as many for their dollar. There are of course ways of getting around this. Oracle rented out its Ampere-based instances, which also lack SMT, in core-pairs rather than on a core-per-core basis, but something like this would presumably require buy-in from the likes of VMware or RedHat. As with past HP- optimized processors, Diamond Rapids will be packing a much beefier memory bus than most folks are going to be looking for. HPC workloads like their memory bandwidth and the next-gen Xeon will have no shortage of it with 16-channels of DDR5. Intel hasnât disclosed what memory speeds the chip will support out of the box. With that said, Clearwater is already at 8000 MT/s on standard RDIMMS, and Granite could hit 8800 MT/s on MRDIMMS â in fact, 9600 MT/s DIMMS wouldnât be an unreasonable assumption. That works out to 1.2 TB/s of bandwidth per socket, which happens to be the same as Nvidiaâs LPDDR5X-packed Vera CPUs. Thatâs not the only thing we're still in the dark about. Power consumption and instruction per clock gains from the chipâs new architecture are details we expect Intel to trickle out. The good news: we wonât have to wait long for the next round of specifications, as Intel will be presenting on Diamond Rapids at Hot Chips in August.
Read the full article
The Hot Take: I'm interested in the Surface with this chip to get a decent GPU on an ARM setup and play with ARM Windows more personally. Only professionally worked with it and that was only an inch deep.
Computex 2026 and GTC Taipei will go down in history as the moment NVIDIA used to officially announce its entrance into the PC market. During his keynote at the Taipei Music Center, CEO Jensen Huang announced the RTX Spark â formerly codenamed N1 and N1X â which will power an array of premium laptops and small form factor systems coming this
Read the full article
The Hot Take: Intel moving fast to make up lost ground on this front for sure. From the looks trying to hit the $ sweet spot too.
Intel revealed more details of its next-gen Data Center GPU, code-named Crescent Island, at Computex 2026. This inference-optimized chip will feature up to 480GB of LPDDR5X memory for efficient handling of massive AI contexts.
Read the full article
The Hot Take: Will have to see what the final products show us.
The N1X reportedly comes in two SKUs: a top-end 20-core option with 6,144 CUDA cores matching the desktop RTX 5070, and a cut-down 18-core option with 5,120 CUDA cores. The standard N1 also has two configs, one with a 12-core CPU and 2,560 CUDA cores and a 10-core model with 2,048 CUDA cores.
Read the full article
The Hot Take: Domestic manufacturing is key.
Samsung's multi-billion dollar advanced chipmaking factory located in Taylor, Texas, is ready to start mass production of chips for clients.
The company has confirmed that everything is ready and that mass production of advanced chips for customers will begin next year.
2nm process advancement is underway as well
Margaret Han, Vice President of Samsung's foundry division in the US, said during the Samsung Advanced Foundry Ecosystem Forum held at the company's US headquarters yesterday that âWe are ready.â She added that âCustomers will begin production at the Taylor fab starting next year.â
Samsung began construction on this factory back in 2022. Its total investment in the project is expected to exceed $17 billion. The company had previously said during the first quarter earnings call this year that the fab was âunder construction.â It was stated that the goal was to begin operation within the year.
Tesla is among the customers who will have their chips produced at this factory. The carmaker already has a $16.5 billion deal with Samsung for the production of its AI5 and AI6 self-driving chips. Samsung will produce 2nm chips at the facility.
To further improve its technological edge at the US factory, Samsung will start building out the second-generation enhancement of its 2nm process in the near future. This process advancement has been tuned finely for AI workloads, potentially delivering a performance improvement of up to 30%.
Read the full article
The Hot Take: Finally CUDIMMs catching on?
G.Skill demos the capabilities of its DDR5 memory by pushing the Trident Z5 CK "CUDIMM" kit to 9200 MT/s at just 1.1V. G.SKILL Showcases DDR5-9200 1.1V 16GBx2 High-Speed CU-DIMM Memory Kit on MSI Z890 GODLIKE Motherboard Press Release: G.SKILL International Enterprise Co., Ltd, the worldâs leading brand of performance overclock memory, is showcasing an ultra-high-speed DDR5 CU-DIMM 32GB (16GBx2) memory kit operating at an impressive DDR5-9200 CL74-74-74-148 speed with only 1.1V DRAM voltage, validated on the flagship MSI MEG Z890 GODLIKE motherboard platform. Exceptional DDR5 speed at Ultra-Low Voltage As memory performance continues to advance, balancing high frequency and operation voltage has become increasingly important. Demonstrating [âŚ]Read full article at https://wccftech.com/g-skill-pushes-trident-z5-ck-cudimm-ddr5-memory-to-9200-mtps-at-just-1-1v/
Read the full article
By ckasprzak | TkOut | May 29, 2026 |
Hardware
The Hot Take: Definitely want to give this puppy a try, though I'm leaning towards the higher end unit.
Fosi Audio officially launches its first externally focused audio solution with a stronger emphasis on e-sports and gaming, the C3. According to the press release available, the compact USB-C sound card is scheduled to be available from 28 May 2026 and is aimed primarily at players who want not just any louder sound in shooters, [âŚ]
Read the full article