The company behind the ATX 3.0 specs adopts the new power connector.
Data Center GPU Max 1100 GPU with 12VHPWR connector, Source: Intel
The so-called PCIe Gen5 or 16-pin or 12VHPWR power connector is not technically a requirement for ATX 3.0 power supplies. However, modern ATX 3.0 PSUs that have been announced thus far feature such connector for at least one graphics card.
NVIDIA was first to adopt this power connector for its RTX 40 GPUs. It can replace up to four 8-pin cables worth of 600W of power. This revolutionary design is not entirely a success for NVIDIA, though, as a few cases of melting connectors and adapters have already been reported by users. NVIDIA is now set to launch its second RTX 40 GPU (4080) next week, while the company’s investigation on the matter continues.
Meanwhile, Intel announced its new Data Center GPU Max 1000 GPUs based on Ponte Vecchio processor. The company will be offering various implementations of this graphics architecture, based on OAM form factor or PCIe. Interestingly, the latter is equipped with 12VHPWR connector, meaning NVIDIA will no longer be the only company using it.
Data Center GPU Max 1100 GPUs, Source: Intel
The 12VHPWR connector will remain exclusive to NVIDIA until January 2023, which is when Intel is planning to launch its Max 1100 PCIe series. However, no desktop gaming products besides GeForce are now expected to feature this connector. Neither AMD with their Radeon RX 7000 series, not Intel with Arc Alchemist, were eager to join NVIDIA in adopting the standard.
Multiple sources now claim that AMD will not be adding a new PCIe Gen5 power connector to its new Radeon GPUs.
Kyle Bennett recently revealed RDNA3 Navi 31 GPU will support unannounced (at the time) DisplayPort 2.1 specifications, only for the VESA consortium to formally announce 2.1 specs a few days later.
According to Kyle’s sources, AMD is not planing to add PCIe Gen5 power connector to new Navi 31 reference cards, in fact, no board partner card is now confirmed to be using such connector either.
After the @NVIDIAGeForce melting drama, I have verified through multiple sources that @Radeon Navi 31 ref cards will NOT use the 12VHPWR power adapter, and I could not verify any AIBs using 12VHPWR on N31 either. Picture in case you don’t know what a smoked 12VHPWR looks like. pic.twitter.com/hLWhjqSm4v
— Kyle Bennett (@KyleBennett) October 25, 2022
This news comes just as NVIDIA is facing reports about melting 16-pin power connectors on their 450W GeForce RTX 4090 graphics cards. The company adopted 12-pin power connector for its RTX 30 Founders Edition GPUs back in 2020, only for the new ‘Ada’ series to feature the full implementation with 12+4pin and defined as 12VHPWR spec and offering up to 600W of power.
As a matter of fact, Kyle’s claim is not the only one. It was Angstronomics who were first to break the news that AMD is not planning to use the new power connector on their reference designs. The company would rely on dual 8-pin power connectors on their Navi 3X based model:
The reference card appears to have an updated 3-fan design that is slightly taller than the previous generation, with a distinctive 3 red stripe accent on a section of the heatsink fins near the dual 8-pin connectors.
— Angstronomics
The site correctly mentioned 3 red stripes on the reference design, which was revealed by AMD in late August. However, AMD’s official render did not show any power connector:
AMD RDNA3 Reference Design, Source: AMD
There is also a report from Igor’sLAB who revealed a PCB design for the upcoming RDNA3 GPU, possibly a custom variant. That card reportedly features triple 8-pin power connectors. With that in mind, there are now three sources with relatively good track record claiming that AMD is not using 12VHPWR connector on RDNA3 GPUs.
If these reports turn out true, then NVIDIA will remain the only company using this new high-power connector. And that’s despite Intel and AMD launching new desktops cards almost at the same time.
Power supply manufacturers are working around the clock to be ready for next-gen graphics cards.
In just a few weeks time, we should expect major updates from NVIDIA and AMD to their graphics card lineups. Thus far, nothing suggest AMD will be joining the party by introducing PCIe Gen5 16-power connector, but this should be the case for all high-end NVIDIA RTX 40 GPUs.
For this reason, power supply companies are set to introduce products compatible with the latest ATX 3.0 standard and equipped with 12VHPWR GPU power connector. Given how rarely PSU get updated, the following products may serve for many years to come.
Seasonic Vertex 1000/1200W
First from the list is Seasonic Vertex series, featuring 80+Gold and Platinum certification and 1000 and 1200W power. At least four models are planned, all fully modular. Their pricing ranges from $231 USD to $305 according to early listings. This PSU is to feature one 16-pin power connector, as per leaked photo.
Silverstone announced its HELA 850R Platinum supply and what is important it has been certified by Cybernetics so probably as good as it gets in terms of PSU certification. This means it passed the rigorous power transient test, and it is fully compatible with ATX 3.0 specs. It’s also a full modular design with single 135 mm fan design and support for 0 dB operation under low load. This particular model is rated for 850W power with 80+Platinum efficiency certification.
Silverstone 850R, Source: Silverstone
ASUS Loki in white
ASUS will be updating its ROG Loki power supplies, now to be offered in white. Compared to ROG Thor series, Loki is ASUS’ first PSU series to feature native PCIe Gen5 power connector. The model pictured below is rated for 850W. The Loki series are designed for Small Form Factor PCs (SFF) and have a 10-year warranty.
ASUS ROG LOKI 850W in white, Source: @harukaze5719
The company recently announce the availability of the black/silver Loki PSUs, featuring 750/800/1000/1200W power ratings. These are 80+ Titanium certified and ATX 3.0 power supplies according to Overclock3D.
Multiple power delivery products have already been announced featuring PCIe Gen5 connector, including: MSI, Thermaltake, Cooler Master or Gigabyte. What is important, though, is that not all of them are fully ATX 3.0 compatible.
Over the last couple of months, the rumor mill surrounding AMD’s impending Ryzen 7000 processors for desktops has been in overdrive. Although Lisa Su unveiled Zen 4 back at CES 2022, it’s been anticipated that the new AM5 platform would include multiple chipsets, much like AM4 has over 500+ motherboard lifespan from X370, X470, X570, and every chipset in between.
AMD announced its X670E, X670, and B650 chipsets during the AMD Keynote at Computex 2022, and this evening, AMD has announced a fourth chipset for Ryzen 7000, the B650E chipset. The B650E chipset will run alongside the already announced B650 chipset, but as it’s part of AMD’s ‘Extreme’ series of chipsets, it will benefit from PCIe 5.0 lanes to at least one M.2 slot, as well as optional support for PCIe 5.0 to a PCIe graphics slot, features not available with standard B650 boards.
During AMD’s Keynote at Computex 2022, AMD’s CEO Lisa Su unveiled three AM5 chipsets designed to harness the power of its 5 nm Zen 4 cores within the Ryzen 7000 processors. We already knew the AM5 socket was based around a Lane Grid Array (LGA) socket with 1718 pins, aptly named LGA1718. Some of the significant benefits coming to AM5 include native PCIe 5.0 support from the CPU, not just for use with the PCIe slots, but also in the way of PCIe 5.0 storage, where the first consumer drives are expected to start rolling out in November 2022.
AMD’s latest announcement of the B650E (Extreme) chipset gives motherboard vendors and users the option of a lower-cost platform but without sacrificing the longevity and expansion support of PCIe 5.0. The X670E chipset is reserved for its most premium models, such as the flagship ASUS ROG Crosshair X670E Extreme motherboard, unveiled at Computex 2022.
AMD AM5 Chipset Comparison
Feature
X670E
X670
B650E
B650
CPU PCIe (PCIe)
5.0 (Mandatory)
2 x16 Slots
4.0
(5.0 Optional)
4.0
(5.0 Optional)
4.0
(5.0 Optional)
CPU PCIe (M.2 Slots)
At Least 1 PCIe 5.0 Slot
PCIe 4.0
(5.0 Optional)
Total CPU PCIe Lanes
24
SuperSpeed USB 20Gbps
(USB 3.2 Gen 2×2)
Up To 14
DDR5 Support
Quad Channel (128-bit bus)
Speeds TBD
Wi-Fi 6E
Yes
Overclocking Support
Y
Y
Y
Y
Available
September 2022
October 2022
Using PCIe 5.0 lanes requires a more premium PCB, usually with more layers which allows the tracks to keep signal integrity, but this typically adds cost. The existence of the B650E chipset will enable vendors to use more expensive PCIe 5.0 laning with more modest controller sets, which allow vendors to offset the cost. Ideally, it gives users a broader and more future-proof platform to upgrade with, but without breaking the bank on unnecessary controller sets; users wanting the best controller sets should opt for X670 or X670E.
This ultimately means that AMD will have a mainstream platform that has PCIe 5.0 by default (B650E) and a lower-cost alternative with just PCIe 4.0 lanes to the PEG and M.2 slots. AMD is strongly prodding motherboard vendors to offer at least one PCIe 5.0 M.2 slot for storage on most of their boards, as this is one of the main benefits of AMD’s AM5 platform.
As announced by AMD during its together we advance_PCs event, the Ryzen 7000 processors for desktop will launch on September 27th, with both motherboards from the X670E and X670 chipsets. The motherboards featuring the B650E and B650 chipsets will be available to purchase at a later date in October.
AMD is working on four 600-series chipsets for its AM5 platform which includes X670E, X670, B650E & B650 motherboards. While X670E & X670 have been the main talk and B650 has been official, the latest leaks bring us the final confirmation of the B650E chipset too.
AMD B650E Chipset Motherboards: Bringing PCIe Gen 5.0 Slot & Gen 5.0 M.2 Support At Mainstream Prices
We reported back at Computex 2022 that the B650E series motherboards offer more PCB layers to efficiently offer better signaling due to PCIE’s rigid Gen5 protocol specifications. Right now, there is the Extreme X670 chipset has been announced officially, adding to the capability of PCIe Gen 5 slot for graphics support and PCIe Gen 5 M.2 for storage.
In an internal presentation leaked by @wxnod, we can see that a manufacturer has listed the B650E (E For Extreme) chipset in one of its slides. The main advantage of B650E motherboards will be that since they feature a singular Promontory 21 chipset, they will definitely be aimed at the mainstream consumer segment with more affordable prices compared to the X670E and the X670 lineup.
While losing a Promontory 21 chipset will lead to decreased I/O capabilities, this implementation will allow for more feasible mATX and mITX designs. We have seen ASUS’s ROG Maximus X670E Gene and ROG STRIX X670E-I Gaming WiFi which feature an mATX & mITX design, respectively.
Both motherboards are based on the X670E chipset which means that they will be priced higher. But a board with a B650E chipset can retain the two most crucial aspects of the Extreme series platform and that’s support for a PCIe Gen 5.0 slot and PCIe Gen 5.0 M.2. At the same time, the pricing compared to the standard B650 (Non-E) motherboards will be slightly higher for the B650E offerings considering they will pack more PCB layers to support the necessary signaling interface for Gen 5 slot and M.2 support.
B650E will give AMD an edge in the mainstream segment where they do lack DDR4 support versus the Intel offerings but having proper Gen 5 slot and M.2 port support can have better longevity, especially considering that Gen 5 SSDs and the DirectStorage API are going to be a major deal in the upcoming years.
There have so far been no product announcements regarding either, the B650E or B650 boards. But, we expect to see products in October as they were previously meant to launch in early Q4 2022. Till then, you can feast your eyes upon the various yet more expensive X670E offerings in our roundup here. AMD will be hosting its official Ryzen 7000 & AM5 unveil in a few hours so make sure you tune in with us during the Livestream here.
Announcing the PCIe® 7.0 Specification: Doubling the Data Rate to 128 GT/s for the Next Generation of Computing
For the past 30 years, PCI-SIG® has been at the forefront of technology innovation. Our PCI Express®(PCIe®) specification has maintained its position as the established de-facto interconnect of choice and a crucial component of the compute continuum. At the PCI-SIG Developers Conference 2022, we celebrated our 30-year anniversary with the announcement of the next evolution of PCIe technology: PCIe 7.0 specification. The forthcoming PCIe 7.0 specification is planned to once again deliver a speed increase in three years, expanding the data rate of the recently released PCIe 6.0 specification to 128 GT/s. The PCIe 7.0 specification is targeted for release to members in 2025.
PCI-SIG technical workgroups will be developing the PCIe 7.0 specification with the following feature goals:
Delivering 128 GT/s raw bit rate and up to 512 GB/s bi-directionally via x16 configuration
Utilizing PAM4 (Pulse Amplitude Modulation with 4 levels) signaling
Focusing on the channel parameters and reach
Continuing to deliver the low-latency and high-reliability targets
Improving power efficiency
Maintaining backwards compatibility with all previous generations of PCIe technology
Companies planning their roadmaps can include the next generation of PCIe technology with the assurance that it will meet their needs for a reliable, high-speed, low latency I/O interconnect. PCIe 7.0 technology will expand the PCI-SIG roadmap to include data-intensive applications and markets, including 800 Gig Ethernet, Artificial Intelligence and Machine Learning (AI/ML), High Performance Computing (HPC), Quantum Computing, Hyperscale Data Centers and Cloud.
During the AMD Keynote at Computex 2022, its CEO, Dr. Lisa Su officially unveiled their next generation of Ryzen processors and the successor to the highly successful Ryzen 5000 series. The new family, the Ryzen 7000 series, will feature up to 16 Zen 4 cores using TSMC’s optimized 5 nm manufacturing process.
AMD Ryzen 7000 also officially marks the end of its long-serving AM4 socket, with the new AM5 LGA1718 socket replacing it with a freshly announced trio of new performance-driven chipsets, including X670E, X670, and B650.
AMD Ryzen: A Brief Recap of Five Years Reinvigorating the Desktop
Since AMD’s original Ryzen (Zen) debuted back in 2017, AMD has consistently innovated and progressed its core architecture in a way that before Zen, no one other than AMD itself thought possible. Some of the main advancements that came with Zen included the new AM4 socket, which is undoubtedly one of the most successful in its history and brought DDR4 memory to the mainstream market. In 2018, AMD shipped its updated Zen+ microarchitecture through the Ryzen 2000, based on GlobalFoundries more efficient and optimized 12 nm architecture, along with a notable uplift in IPC performance gains to boot.
Moving forward into 2019, AMD debuted the Zen 2 architecture, which was used as the basis for the Ryzen 3000 series of CPUs. Switching to TSMC’s high-performance 7 nm manufacturing process, AMD delivered higher performance levels over Zen/Zen+, with double-digit gains in IPC performance and a completely new design shift through the use of chiplets.
This continued into 2020 when AMD started shipping its Zen 3 core with monumental gains over Zen 2, with up to 19% gains in IPC over Zen 2, as well as the introduction of its Resizable BAR feature, higher levels of L3 cache than ever before, and the introduction of PCIe 4.0 to desktop.
AMD Ryzen 7000: Bringing Zen 4 and 5 nm to Consumer Desktop
The latest in AMD’s arsenal, and perhaps one of the most highly anticipated processor announcements of the year, the AMD Ryzen 7000 family has finally been announced with some new features designed to deliver a premium desktop experience. We’ve known for a long time that the Zen 4 microarchitecture is based on an optimized TSMC 5 nm manufacturing process, but we haven’t learned some of the more detailed intricacies until now.
Although the TSMC 5 nm manufacturing process was initially found in smartphones, with Apple and Huawei both championing the transition, Zen 4 marks the first use of 5 nm for desktop systems. The AMD Ryzen 7000 and Zen 4 are similar to Zen 3, including a chiplet-based design, with two Core Complex Dies (CCDs) based on TSMC’s 5 nm manufacturing process.
While AMD isn’t going into great detail on the Zen 4 architecture today – they have to save something to disucss for later in the year – for now the company is disclosing that Zen 4 will come with 1MB of L2 cache per CPU core, which is twice the amount of L2 cache as found on Zen 3 (and Zen 2) CPU cores. Meanwhile L3 cache will remain a subject for another day; AMD isn’t offering details on its L3 cache or whether we will see Zen 4 models with its 3D V-cache stacked packaging.
Coupled with that L2 cache improvement, AMD is aiming for higher clockspeeds, thanks to their architectural design and TSMC’s 5nm process. Officially the company is only claiming “5GHz+” max turbo clockspeeds for now, but in a demo video shown by Dr. Su, AMD’s pre-production 16 core Ryzen 7000 chip was shown to be boosting to above 5.5GHz, which is a significant uplift from the sub-5GHz speeds of AMD’s current Ryzen 5000 desktop chips.
As a result of these cache, architectural (IPC), and clockspeed improvements, AMD is touting a greater than 15% increase in single-threaded performance. And, checking AMD’s disclosure notes, this is based on early Cinebench R23 notes, comparing their pre-production 16C Ryzen 7000 chip to a 16C 5950X. Given the significant clockspeed increases that AMD has demoed on this chip, this does imply that most of AMD’s performance improvements are coming from the clockspeed improvements rather than IPC uplift. However Cinebench is a single benchmark, and for the moment we don’t have any further information on what core architectural changes AMD has made.
Though AMD is disclosing that Zen 4/Ryzen 7000 is getting AI acceleration instructions. Like so many other aspects of the chip, more details are to come, but it sounds like AMD is adding some instructions for manipulating data with common AI data formats such as bfloat16 and int8/int4.
For Ryzen 7000, AMD is also introducing a new 6 nm I/O die (IOD), which replaces the 14 nm IOD used in previous Zen 3 designs. Marking a first for AMD, the new IOD is incorporating an iGPU, in this case based on AMD’s RDNA2 architecture. So with the Ryzen 7000 generation, all of AMD’s CPUs will technically be APUs as well, as graphics is a basic part of the chip’s construction. What this means for the future of AMD’s monolithic desktop APUs is uncertain, but at a minimum, it means that all (or virtually all) of AMD’s CPUs will be suitable for use in systems without discrete graphics, which although not a huge deal for consumer systems, is very much a big deal for corporate/commercial systems.
The new IOD also affords AMD the opportunity for some significant platform power savings. Not only is TSMC’s 6nm process well ahead of GlobalFoundries’ old 14nm process, but the design process has allowed AMD to incorporate many of the power-saving technologies that were first developed for the Ryzen 6000 Mobile series, such as additional low power states and active power management capabilities. As a result, Ryzen 7000 should fare much better at idle and low utilization workloads, and it’s a reasonable assumption to see the IOD drawing less power at load, as well (at least with graphics disabled). Though at full load, with up to 16 cores running at over 5GHz, the CCDs are still going to draw a lot of power.
On the matter of power, it’s also noteworthy that AMD is indicating that Ryzen 7000 will operate at higher TDPs. While AMD isn’t announcing official SKUs at this point, they are explicitly noting that the new AM5 platform allows for TDPs (CPU Package Power) up to 170 Watts in this generation, which is up from the 105W TDPs of the AM4-based Ryzen 5000 series.
Last, but certainly not least, AMD’s Zen 4 microarchitecture combined with the new IOD also brings about a host of new features, including official support for PCIe 5.0, much like Intel introduced with its Alder Lake (12th Gen Core) architecture. Combining AMD Ryzen 7000 with an X670E, X670, or B650 motherboard will provide up to 24x PCIe lanes split between slots and storage devices. Based on AMD’s disclosures, it sounds like all of the lanes coming off of the Ryzen 7000 chip itself will be PCIe 5.0-capable, but it will be up to motherboard manufacturers to actually design their boards to support PCIe lanes at the highly-sensitive 5.0 speeds. As a result, Ryzen 7000 chips plugged into some lower-end motherboards will only offer a far more limited number of lanes at PCie 5.0 speeds, with the rest operating at PCIe 4.0 speeds.
AMD’s AM5 Platform: Socket LGA1718 with Three New Chipsets – X670E, X670, and B650
As the announcement of AMD’s Ryzen 7000 family of processors officially brings the previous AM4 platform to an end. Ryzen 7000 will be the first family of processors using AMD’s new AM5 platform, which AMD is also disclosing the first deals of today. Using a LGA-type socket with 1718 pins, AM5 is the other piece of the puzzle in introducing DDR5 and PCIe 5.0 support, as well as higher processor TDPs.
The big news on the I/O front is of course PCIe 5.0 support. This is intended to be used to drive next-generation video cards (and other accelerators) as well as next-generation SSDs, with AMD expecting the first PCIe 5 consumer SSDs to be avaialble just in time for the AM5 platform launch. With up to 32GB/sec of bandwidth in each direction, PCIe 5.0 will offer a lot of bandwidth, but its very tight signal integrity requirements are also in part what required AMD to move to a new socket, with LGA apparently being a better fit.
AM5 also brings quad-channel (128-bit) DDR5 support to AMD’s platforms, which promises a significant boost in memory bandwidth. And, in an interesting move, AMD is offering only DDR5 support. Unlike Intel, whom we saw support both DDR5 and DDR4 with its Alder Lake platform last year, AMD is not including any kind of support for older memory formats here.
Given the high-level nature of today’s disclosures, AMD unsurprisingly isn’t talking about supported memory speeds. But based on their testing footnotes for their pre-release processor performance claims, we see that AMD did test with DDR5-6000 memory. So while almost certianly using overclocked (XMP) memory there, it implies AM5/Ryzen 7000 has some memory overclocking headroom to offer.
One interesting thing that we’ve already mentioned is that AMD Ryzen 7000 will move to support processors up to 170 W on Zen 4, as opposed to 105 W TDP found on processors such as AMD’s previous Ryzen 9 5950X. AMD is also using a new heat spreader (IHS) design on Ryzen 7000, which AMD has done to allow compatibility with previous socket AM4 coolers. This means that theoretically, users looking to upgrade to Ryzen 7000 will be able to use pre-existing coolers with socket AM4 support.
Supporting the new AM5 platform will be a trio of new new motherboard chipsets: X670E, X670, and B650. Starting with the flagship X670E ‘Extreme’ chipset, this is designed for its most premium models, focusing on extreme overclocking, with a full loadout of PCIe 5.0 support – meaning support for two PCIe 5.0 graphics slots, as well as at least one PCIe 5.0 M.2 slot for storage. Which from AMD’s specifications we can infer would be in a x8/x8/x4 loadout, using PCIe lane bifurcation to split off 8 lanes from a first PCIe x16 slot to a second slot when both are in use.
Interestingly, AMD differentiates X670 into two market segments compared to previous iterations such as X570, X470, and the X370 chipsets. While both the X670E and X670 cater to enthusiasts, X670 is designed to be a slightly downmarket offering, taking a step back in the amount of functionality motherboard vendors are expected to offer with those boards. In particular, X670 does not require PCIe 5.0 support for the PCIe x16 slots – while many boards will offer it, an X670 board would also be allowed to implement PCIe 4.0 instead. Do note, however, the PCIe 5.0 is still required for at least one M.2 slot for NVMe SSDs.
Between the two versions of the X670 chipset, it seems as though the most premium models such as ASUS’s ROG Crosshair series, MSI’s MEG series, and GIGABYTE’s Aorus Xtreme series will be based on X670E, in order to separate it from the more mid-range focused and more widely affordable X670 options.
Finally, we have the B650 chipset. As with previous AMD B-series chipsets, will target mainstream users with more affordable options. Like the rest of the AM5 chipsets, B650 requires PCIe 5.0 support for at least one M.2 slot for storage, while it does away with PCIe 5.0 support for PCIe slots entirely. It also doesn’t have any overclocking support explicitly mentioned. At a high level B650 sounds a lot like X670 with overclocking enabled, but we’ll have to wait to hear from AMD and motherboard vendors for more explicit details.
Along with the announcement of X670E, X670, and the B650 chipsets, AMD has announced some of the most premium motherboards we can expect to see for the launch of Ryzen 7000. This includes a range of flagship and premium X670E boards from families we’ve seen many times before, including the ASRock X670E Taichi, the ASUS ROG Crosshair X670E Extreme, the Biostar X670E Valkyrie, the GIGABYTE X670 Aorus Xtreme, and the MSI MEG X670E Ace motherboards.
We don’t have any official specifications from motherboard vendors regarding the announced models at the time of writing. Still, we expect to start receiving specifications, controller sets, and power delivery information very soon.
On the power delivery front, AMD has confirmed that AM5 will support AMD’s Serial Voltage 3 (SVI3) standard. First introduced as part of the Ryzen 6000 Mobile series, SVI3 allows for finer grained power control and significantly faster voltage response capabilities. And for desktop boards in particular, SVI3 also supports a larger number of power phases, which will be especially useful for high-end X670E motherboards.
Rounding out the AM5 platform, since all of AMD’s Ryzen 7000 CPUs will have integrated graphics, AM5 as a whole has graphics support baked into every tier of motherboards. AM5 motherboards will be able to support up to four display outputs using a mix of HDMI 2.1 and DisplayPort 2.
Finally, the platform will come with an upgrade to AMD’s USB capabilities, though seemingly not as much as we had first hoped. According to AMD, the platform supports up to 14 SuperSpeed USB 20Gbps (USB 3.2 Gen 2×2) Type-C ports. Notably, AMD isn’t saying anything about USB4 here, so while 20Gbps ports are nothing to sneeze at, it doesn’t look like AM5 will offer the higher speeds and other perks of USB4 – at least not with this first generation of products.
AMD Ryzen 7000 Processors: Coming Fall 2022
Despite AMD essentially opting for a paper launch of its latest Ryzen 7000 family of processors, it hasn’t actually provided any details surrounding its SKUs or expected pricing. From the AMD Keynote during Computex 2022 hosted by CEO Dr. Lisa Su, we know AMD is planning to offer Ryzen 7000 with up to 16 cores, but it remains to be seen if AMD will go for even more cores in the coming months.
We know that on AM4 over the progression from 2017 to 2020 of AMD’s Ryzen family, Zen initially came with 8C/16T options (Ryzen 7 1800X), while we saw AMD double this capability with 16C/32T options such as the Ryzen 9 3950X.
It remains to be seen if we will see Ryzen 7000 with more than 16C models, but for now, that’s what AMD is sticking with, at least for Computex 2022. AMD did say we will get more information on its Ryzen 7000 family of processors and Zen 4 and the AM5 socket in the coming months as we head towards a full retail launch in the fall of 2022.
We received a photo of the upcoming new variant of the A100 Tensor Core GPU.
The A100 based on GA100 “Ampere” GPU is a predecessor to H100 Hopper data-center accelerator. The new liquid-cooled variant is based on A100 PCIe based model released in June last year. This is not the SXM variant which is used for the HGX/DGX A100 systems.
While it’s nothing extraordinary for a data-center GPU to get liquid cooling, this model appears to be NVIDIA’s own sleek design with tubing connectors on the rear, right next to the 8-pin power connector.
A100 with NVIDIA liquid-cooling, Source: VideoCardz/NVIDIA
One should note that liquid-cooling for A100 accelerators is already widely available, except it requires manual replacement of the passive dual-slot cooler. Passive cooling may not be ideal for workstation systems where sufficient airflow is required. This is probably why NVIDIA opted for the A100 SXM variant for its DGX A100 Station, using sophisticated refrigerant cooling.
A100 with custom liquid-cooling, Source: VideoCardz
Intel’s upcoming 12th Gen Alder Lake-HX CPU lineup for enthusiast workstations & gaming laptops has leaked out over at Videocardz. The lineup includes various SKUs which are aimed at the fastest laptops for content creators and gamers.
Intel 12th Gen Alder Lake-HX CPU Lineup Leaks Out: Designed For High-End Workstation & Gaming Laptops With Up To 16 Cores, 5 GHz Clocks, & PCIe 5.0
The Alder Lake-HX lineup is Intel bringing the desktop 12th Gen dies to the laptop segment in a BGA form factor. For this purpose alone, Intel will be using the Alder Lake ‘C0’ die which rocks a total of 8 P-Cores and 8 E-Cores. These chips will come in the same package size as the desktop parts which are 45 x 37.5mm but have been thinned out to reduce the height from 4.4mm, down to 2.0mm.
Intel Visual Compute Accelerator 2 dissected by Der8auer, features trio of Xeon CPUs
Since these are based on the same silicon as the desktop parts, one should also expect similar core count, cache sizes, and clock speeds. One major feature is that Intel’s Alder Lake-HX CPUs are going to be the first PCIe Gen 5.0 platform for laptops, featuring a total of 48 PCIe lanes. These comprise 16 PCIe Gen 5, 20 PCIe Gen 4, and 12 PCIe Gen 3. As one would guess, these would allow for better I/O capabilities than the existing Alder Lake-H lineup which only offers 28 PCIe lanes which include 16 Gen 4 and 12 Gen 3.
The full specifications of Intel’s 12th Gen Alder Lake-HX CPUs for workstations & gaming laptops have been leaked. (Image Credits: Videocardz)
As for the other significant feature of the Intel Alder Lake-HX lineup, we are looking at full overclock support for both the CPU and DDR5 memory. These will be made possible through an updated ETU (Extreme Tuning Utility) while XMP 3.0 profiles will be available across a wide range of mobility HX platforms.
Finally, let’s talk SKUs, there are 7 in total which starts from 8 cores and goes all the way up to 16 cores. There’s not a single SKU that doesn’t feature E-cores enabled on die. What’s really interesting is that certain top-tier SKUs in each segment are ECC and vPRO compliant while the 2nd tier SKUs offer full memory and unlimited core overclocks while the rest feature limited core OC.
Now coming to the SKUs, the Intel Core i9 segment will include the i9-12950HX and i9-12900HX with 16 cores and 24 threads (8+8) design, offering boost clocks of up to 5.0 GHz, 30 MB cache & TDP figures ranging between 55W (PL1) and 157W (PL2).
The Core i7 segment is the most crowded with three SKUs that include the i7-12850HX, i7-12800HX, and the i7-12650HX. The top i7 SKUs come with 16 cores but feature 25 MB of cache, and up to 4.8 GHz clocks while the 12650Hx is equipped with 14 cores and 20 threads (6+8) for a total of 24 MB cache clocking up to 4.7 GHz.
Intel representative teases the new Ponte Vecchio compute GPU for AI & HPC applications of the future
Lastly, we have the entry-level Intel Alder Lake-HX Core i5 segment which includes the 12 core i5-12600HX (4+8) and the 8 core i5-12450HX (4+4). These CPUs feature 18 MB and 12 MB cache and the clocks are rated up to 4.6 / 4.4 GHz, respectively. The only department where these chips lack against the Alder Lake-H lineup is the 32-16 EU iGPU which is similar to the desktop parts. We can expect these chips to land in several laptops in the coming months leading to Computex 2022 & a formal announcement is expected at Inte’s Vision Event next week.
In a new blog posted by Phison, the DRAM controller manufacturer has reiterated how PCIe Gen 5 NVMe SSDs will feature higher temperatures and require active cooling solutions.
Phison Sets Up To 125C Thermal Limit For PCIe Gen 5 NVMe SSD Controller, Active Cooling & New Connector In Talks
Last year, Phison revealed a good bunch of details regarding PCIe Gen 5 NVMe SSDs. Phison’s CTO, Sebastien Jean revealed that the first Gen 5 solutions will start shipping to customers by the end of this year.
ATX Version 3.0 Design Guide Reveals PCIe 5.0 Connector Cable Details, Up To 600W Power Input For Next-Gen GPUs
As for what PCIe Gen 5 SSDs bring to the table, it is reported that PCIe Gen 5 SSDs will offer speeds of up to 14 GBps and existing DDR4-2133 memory also offers around 14 GBps speeds per channel. And while SSDs are not going to replace system memory solutions, the storage and DRAM can now operate within the same space and a unique perspective is provided in the form of L4 caching. The current CPU architectures comprise of an L1, L2, and L3 cache so Phison believes that Gen 5 SSDs & beyond with a 4kb cache can operate as an LLC (L4) cache for the CPU owing to similar design architecture.
Phison now states that to keep the power limit in check, they are going down from 16nm to 7nm to reduce the wattage while hitting their performance targets. The reliance on the 7nm and enhanced process nodes can help reduce the power limit and another way to conserve power is to reduce NAND channels on the SSD.
Jean said, “In practical terms, you no longer need eight channels to saturate the Gen4 and even Gen5 PCIe interface. You can potentially saturate the host interface with four NAND channels, and reducing the number of back-end channels reduces the total SSD power by typically 20 to 30 percent.”
via Phison
Temperatures remain the main concern for SSDs as we move forward. As we have seen with PCIe Gen 4 NVMe SSDs, they do tend to get hotter than previous generations and as such, require hefty cooling solutions. Most high-end devices these days are equipped with a heatsink & motherboard makers have also emphasized the use of their own thermal heatsinks, at least for the primary SSD.
According to Phison, NAND typically operates up to 70-85 Degrees Celcius and with Gen 5, the SSD controller limits have been set at up to 125C but NANAD temperatures can only go up to 80C after which they will go into critical shutdown.
Gigabyte States A Single 16-Pin or Triple 8-Pin To 16-Pin Gen 5 Connector Required For Next-Gen GPUs
As an SSD fills up, it becomes much more sensitive to heat. Jean recommends keeping and SSD under 50 degrees Celsius (122 degrees F). “The controller and all the other components … are good up to 125 degrees Celsius (257 degrees F),” he said, “but the NAND isn’t, and the SSD will go into critical shutdown if it detects that the temperature of the NAND is above 80 degrees Celsius (176 degrees F) or so.”
Heat is bad, but extreme cold isn’t great either. “If most of your data was written really hot and you read it really cold, you have a huge cross-temp swing,” said Jean. “The SSD is designed to handle that, but it translates into more error corrections. So lower maximum throughput. The sweet spot for an SSD is between 25 and 50 Celsius (77 to 122 degrees F).”
via Phison
As such, Phison has stated that they advise Gen 4 SSD makers to have a heatsink but for Gen 5, it is a must. There’s also a likelihood that we might even see active fan-based cooling solutions for next-gen SSDs and that’s due to the higher power requirements that result in more heat output. The Gen 5 SSDs are going to average in at around 14W TDP while Gen 6 SSDs are going to average in around 28W TDPs. Furthermore, it is reported that managing heat is a major challenge moving forward.
“I would expect to see heatsinks for Gen5,” he said. “But eventually we’ll need to have a fan that’s pushing air right over the heatsink, too.”
When it comes to server-side form factors, Jean said, “the main thing is to have good airflow through the chassis itself, and the heatsinks essentially reduce the need for crazy, high-speed fans because it gives you a much larger dissipation surface. The EDSFF E1 and E3 specifications have form-factor definitions that include heatsinks. Some hyperscalers are willing to trade off storage density in a chassis for a heatsink and a reduced need for high-speed fans.”
“If you look at the bigger question of where PCs are going, there’s an understanding that, for example, the M.2 PCIe Gen5 card, as it is today, has reached the limit of where it can go. The connector will become a bottleneck for future speed increases,” said Jean. “So new connectors are being developed and they’ll be available in the next few years. They will greatly increase both the signal integrity and the heat dissipation capability through conduction to the motherboard. These new connectors may allow us to avoid putting fans on SSDs.”
via Phison
Currently, 30% of the heat is dissipated via the M.2 connector and 70% via the M.2 screw. This is also where the new interfaces and interface slots will play a huge role. Phison is currently investing in a new type of connector which may allow the use of fans altogether but for users who hunger more speeds, there will still be AICs and NVMe SSDs that will support better cooling designs. It is also mentioned that
