Quote:TDP is being shown as increased with Intel's Ice Lake designs, with an "up to" 230 W TDp - more than the Skylake or Cascade Lake-based platforms, which just screams at higher core counts (and other features such as OmniPath or on-package FPGAs).

Digging a little deeper into the documentation released by the PSA shows Intel's Ice Lake natively supporting 8-channel memory as well, which makes sense, considering the growing needs in both available memory capacity, and actual throughput, that just keeps rising. More than an interesting, unexpected development, it's a sign of the times.

Quote:Apparently, the 300-series chipset, led by the Z390 Express, will support Intel's 9th generation, 10 nanometer "Ice Lake" silicon with 8 physical cores. The generational successor to the i7-8700K will hence be an 8-core/16-thread chip. This also presents Intel with an opportunity to make its next Core i5 parts either 8-core/8-thread or 6-core/12-thread, and Core i3 either 6-core/6-thread or 4-core/8-thread.

Quote:Intel processor integrated graphics will get its first major hardware update in 4 years since Gen 9.5 "Skylake," with the introduction of the Gen11 architecture that debuts with the company's "Ice lake" processors. The company confirmed in an XDC 2018 conference presentation that the iGPU will support DisplayPort 1.4a along with VESA DSC (display stream compression), enabling it to support display resolutions as high as 5K (5120 x 2880 pixels) with 120 Hz refresh-rate.

Without DSC, 5K-120 Hz requires 42.4 Gbps of bandwidth (not counting interconnect and protocol overheads), which even DisplayPort with HBR3 cannot provide, as it caps out at 32.4 Gbps. DSC offers "visually lossless" compression of the 5K-120 display stream down to roughly 14 Gbps, which can be comfortably handled by DisplayPort 1.4a. 8K (8192 x 4320 pixels) at 60 Hz also becomes possible. Merely supporting these new high resolutions doesn't imply Gen11 iGPUs can game at those resolutions. Support for them is necessitated by rapid increases in resolutions (pixel densities) and refresh-rates of high-end notebooks and ultra-portable devices.

Quote:Intel's next major CPU microarchitecture being designed for the 10 nm silicon fabrication process, codenamed "Ice Lake," could introduce the first major core redesign in over three years. Keen observers of Geekbench database submissions of dual-core "Ice Lake" processor engineering samples noticed something curious - Intel has increased its L1 and L2 cache sizes from previous generations.

The L1 data cache has been enlarged to 48 KB from 32 KB of current-generation "Coffee Lake," and more interestingly, the L2 cache has been doubled in size to 512 KB, from 256 KB. The L1 instruction cache is still 32 KB in size, while the shared L3 cache for this dual-core chip is 4 MB. The "Ice Lake" chip in question is still a "mainstream" rendition of the microarchitecture, and not an enterprise version, which has had a "re-balanced" cache hierarchy since "Skylake-X," which combined large 1 MB L2 caches with relatively smaller shared L3 caches.

Quote:Today, Intel is revealing major details about its upcoming CPU and graphics architectures to select audience. A big scoop VideoCardz landed is the company's next-generation Gen11 integrated graphics core, the first major upgrade to the company's 4-year old Gen9 architecture. According to them, a Gen11 (default GT2 trim we assume) graphics core should offer a compute throughput of 1 TFLOP/s, which is in the league of the Radeon Vega 8, with its 1.12 TFLOP/s throughput. The Vega 8 is part of AMD's Ryzen 3 2200G processor.

Raw compute power only paints half the picture, the iGPU reportedly also supports tile-based rendering. This is a highly publicized method of rendering that made its consumer debut with NVIDIA "Pascal." Also mentioned are redesigned FPU interfaces, support for half-precision FP16, 2x pixel/clock pipelines, display stream compression that lets it support 5K and 8K displays, and adaptive sync. Intel will debut its Gen11 iGPU with its upcoming Core "Ice Lake" processors that debut on the company's 10 nm silicon fabrication process.

Quote:This "Ice Lake-U" chip, with its TDP in the ballpark of 15 W, was shown ripping through 7-zip and "Tekken 7." With 7-zip, Intel was trying to demonstrate vector-AES and SHA-NI improving archive encryption performance by 75 percent over "Skylake." The Gen11 iGPU was shown providing a smoother gameplay than Skylake with Gen9, although the company neither mentioned resolution, nor frame-rates. Anandtech wagers it's above 30 fps.

Quote:According to one of the latest Geekbench leaks, Ice Lake reportedly features an increased L1 cache and twice the L2 cache per core. The quad-core Ice Lake chip from the Geekbench entry shows an L1 cache that has been bumped up to 48KB and the L2 cache doubled to 512KB. In recent years, Intel processors have been maintaining the 32KB per L1 cache and 128KB per L2 cache configurations from the Core 2 and Nehalem days, respectively. It would be good to see Intel finally give its processors a deserved cache upgrade.

The quad-core, eight-thread processor also exhibited a base clock in the range of 1.9GHz and a boost clock up to 2.29GHz. The chip is probably an engineering sample (ES), so there's still room for further tuning.

The upcoming Ice Lake processors will utilize the latest Gen11 integrated graphics engine. Gen11 will stick to the GT2 configuration and feature up to 64 execution units (EUs). It's slated to deliver over one TFLOP of performance and open the door to gaming without a discrete graphics card. It's a little too early to know for sure, but we expect Gen11 to perform in the ballpark of AMD's Radeon Vega 8 Graphics processor, which pumps out around 1.12 TFLOPs of performance.

Quote:Benchmarks of Intel's Gen11 iGPU (Integrated Graphics Processing Unit) in GFXBench and CompuBench have finally surfaced. The mysterious processor with Iris Plus Graphics 940 reportedly blows past other 15W chips, such as the Intel's own Core i5-8250U and AMD's Ryzen 2700U and Ryzen 5 2400G offerings.
...
As always, you should take synthetic benchmarks, and leaked ones for the matter, with a grain of salt as they are not a definite indication of real-world performance. However, you can't deny that Gen11 posts some very promising results.
...
Overall the results are impressive and imply that Intel's next generation of integrated graphics could be a game changer that puts the pressure on AMD's Ryzen chips with integrated graphics and Nvidia's low-end discrete graphics cards for notebooks. According to Intel's latest estimates, the Ice Lake processors packing Gen11 graphics should come to market in time for the holiday shopping season.

Quote:But according to purportedly leaked Lenovo documents, we could see the mythical Ice Lake processors on shelves as soon as June.

As with any leaked documents, we need to take the information with a grain of salt, but the timeline for the Ice Lake-powered laptops lines up nicely with Dell's recent revelation that it will reveal new 10nm-powered XPS laptops by "mid-year."
...
Intel's possible early launch of Ice Lake processors would make sense for the notebook market, largely because it comprises two-thirds of the overall PC processor market. The early launch of 10nm processors would also give Intel an advantage over AMD's increasingly-threatening Ryzen Mobile processors that continue to slowly chew away market share from Intel.

The purported June launch for Ice Lake lands squarely in the crosshairs of the Computex trade show that major vendors use to announce new products, so we could learn more as we get closer to the annual trade show. Of course, launching its 10nm processors would also help Intel in the marketing war, as AMD is widely expected to unveil its 7nm desktop processors at the event.

Quote:When reading through the Gen11 GT2 whitepaper by Intel, which describes their upcoming integrated graphics architecture, we may have found a groundbreaking piece of information that concerns the memory architecture of computers running 10 nm "Ice Lake" processors. The whitepaper mentions the chip to feature a 4x32-bit LPDDR4/DDR4 interface as opposed to the 2x64-bit LPDDR4/DDR4 interface of current-generation chips such as "Coffee Lake." This is strong evidence that Intel's new architecture will have unganged dual-channel memory controllers (2x 64-bit), as opposed to the monolithic 128-bit IMC found on current-generation chips.
...
AMD has been supporting unganged dual-channel memory interfaces for over a decade now. The company's first Phenom processors introduced unganged memory with a BIOS option to force the CPU to interleave all data, called ganged mode. The consensus among the tech-community over the past ten years and the evolution of the modern processor toward more parallelism favors unganged mode. With CPU core counts heading north of 8 for mainstream-desktop processors, and integrated GPUs becoming the norm, it was natural for Intel to add support for an unganged memory interface.

Quote:In yet another sign that Ice Lake processors are coming to market soon, Intel removed the alpha support flag for the upcoming Gen11 graphics in the latest pull request for its open-source developers. That signals that the drivers are now considered mature enough to be enabled by default. On previous kernels, this flag was required for users to acknowledge the early alpha hardware support. Intel also added support for Comet Lake's aging Gen9 graphics.

Quote:Swan also reported that the company has begun qualifying its 10nm Ice Lake processors, which is a critical first step towards volume production, and maintains the company's previous projections that systems with those chips will hit retail shelves in volume in time for the holidays. “As I shared earlier, our confidence in 10nm is also improving. In addition to the manufacturing velocity improvement I described earlier, we expect to qualify our first volume 10nm product, Ice Lake, this quarter and are increasing our 10nm volume goals for the year,” said Swan.

Swan also noted that the company's Ice Lake server chips would come in 2020, "earlier versus later" in the year.

Quote:On the flipside, the Ice Lake (ICL) chipset, which is set to replace Cannon Lake (CNL), will carry the 495-series branding. We don't blame you if you've never heard of (or forgotten) about Cannon Lake. Other than being the first processor to be produced under the 10nm manufacturing process, Cannon Lake has nothing else to its name. As far as we know, the Intel Core i3-8121U dual-core processor is (or was) the only Cannon Lake chip to see the light of day.
...
Intel's most recent desktop client roadmap suggests that Comet Lake will land in the last quarter of the year while Ice Lake won't arrive until 2020.

Quote:Intel also provided a series of gaming benchmarks pitting the Vega-powered 25W Ryzen 7 3700U against a pre-production 25W Ice Lake processor. Intel declined to specify if this processor will come to market, but Intel's benchmarks, when normalized for power consumption, show the Ice Lake processor beating the Ryzen 7 3700U in most benchmarks, albeit by margins that range from near-ties (and one loss) to a 15% advantage.

In either case, if backed by independent third-party benchmarks, an Intel processor beating AMD's APU would reverse years of AMD's dominance in integrated graphics. That isn't entirely unbelievable given the extent of Intel's reworking of the architecture, but we're sure AMD isn't standing still, either.

Quote:Intel’s specific claim to fame is an 18 percent IPC uplift for Ice Lake relative to Skylake, but that claim is balanced against some frequency losses. For example, Ice Lake is specifically stated to offer up to 4.1GHz clock speeds. Intel’s 14nm Core i7-8665U (Whiskey Lake) has a boost clock of 4.8GHz. Without knowing how Ice Lake’s per-core frequencies are implemented we don’t know which chip will end up holding higher sustained clocks or offering better total performance, but the 700MHz top-end gap is large. In fact, it’s large enough to almost totally offset the IPC gain.

I want to emphasize that this doesn’t mean Ice Lake CPUs will be slower than their Whiskey Lake counterparts. It just means that based on the information we have right now, it isn’t clear what the relative clock speeds will actually be or how that will impact performance. Intel’s IPC slide also states, in the fine print: “Performance results are based on testing as of dates shown in configuration and may not reflect all publicly available security updates.” This appears, however, to be a boilerplate insertion.
...
All of which is to say: Of the estimated 1.36x improvement in SPECint_rate_base2006 between the SKL and ICL parts, roughly 1.2x should be coming from clock speed, leaving about 1.16x to come from IPC improvements — and that’s pretty much on the mark with what we see here, given that this is one specific test, whereas Intel’s 18 percent IPC improvement is an averaged result.

But this also means that Intel’s absolute performance ranking against Whiskey Lake probably took a hit due to much lower clocks. This echoes the situation AMD ended up in with its Kaveri and Carrizo CPU families. While both of these architectures improved IPC, they traded back clock to maintain lower power targets, and the end result was largely a wash as far as performance improvements.

The implication of Intel’s 15W single-threaded slide is that we shouldn’t expect major improvements over Whiskey Lake, despite the shift from 14nm to 10nm. It’s possible that Intel has focused on improving other aspects of the chip, such as overall power consumption, rather than attempting to push performance.

Quote:Intel noted that its Ice Lake processors have passed qualification and are now shipping. Swan also said that yields are improving as the company continues to work more products through its two active 10nm foundries. The company cited continued investments in its 10nm ramp, along with investments in the following 7nm process that it says will come to market in 2021, as weighing on its operating margins.
...
Swan said that production on 10nm Ice Lake data center processors would begin in the first half of 2020, with volume production expected in the second half of that year.

Quote:Now, if you read Tom’s Hardware all the time, this may not be a big problem for you. We eat spec sheets for breakfast and save some more for lunch. But this is a big issue for the average person going and buying a new laptop. Intel should be making it more clear what you get, not less.

I reached out to ask Intel questions about its new naming convention. It started by supplying a graphic to help explain the new naming:
...
When you take the time to truly learn the new naming, there is some logic to it. But that logic assumes that customers know and understand spec sheets and will take the time to completely learn the new scheme. That’s unlikely at first.

Intel, in an attempt to simplify naming, has also complicated it. And that means it needs to find a way to educate consumers, possibly with new store signage, prominent space on its own and partner websites, and, hopefully, a lot of tech enthusiasts with patience willing to teach family and friends.

Quote:Now that we actually know what CPU performance factually looks like, we’ve got a much better basis for discussing it relative to Intel’s Whiskey Lake. Our sister site PCMag has done a thorough comparison of Ice Lake against Whiskey Lake, with the Core i7-8565U represented in multiple form factors and systems from different OEMs. That’s actually incredibly useful because it shows just how large the gap between laptops can be, and how important proper testing (and thermals) are.
...
Right off the bat, we can see that Ice Lake has some issues in a 15W envelope. The fact that the CPU’s single-threaded performance improves by 1.22x when given room to breathe in a 25W design is evidence that CPU power consumption is throttling the core badly. There’s only a 5 percent spread between the Core i7-8565U machines as far as single-thread is concerned. When we move to multi-threading, giving the CPU 1.66x more thermal headroom results in a 1.33x improvement in performance. Comparing 15W with 15W, the older Intel CPUs are all faster, particularly the HP Envy 13.

In the 25W configuration, ICL wins the benchmark overall but is only 5 percent faster than the HP Envy 13. The Ryzen 5 2500U is outperformed (PCMag did not have a Ryzen 7 to compare against or an updated 3000-series APU in a mobile system).
...
In Rise of the Tomb Raider Low, ICL can maintain 40fps at 1366×768 and 26fps at 1920×1080. Interestingly, giving the system more headroom for power took the score down, not up at 768p and held it constant in 1080p. AMD’s lower-end Vega 8 does not compete well here, and while Vega 11 would provide some additional GPU headroom, it’s unlikely to completely close the gap. Only the MX150 and MX250-equipped laptops, with Nvidia GPUs, beat out Intel’s integrated graphics.

Tom Clancy’s Rainbow Six: Siege is impressive, with equal performance between the 15W and 25W CPUs. Again, only the MX150 and MX250 exceed Intel’s integrated performance. AMD’s Vega 8 turns in playable performance at 1366×768 but doesn’t meet the minimum 30fps threshold we consider minimum for 1080p gaming.

All of the GPU figures basically follow this pattern. You’ll see AMD hold its ground better in some than others, but Intel is ahead on the whole. Vega 11 would improve these results, but likely not by enough to change the outcome in most games.
...
The third pillar is power consumption and battery life, and we don’t know yet how ICL compares on these metrics; Intel forbid testing the sample laptop for such things. Right now, Ice Lake delivers massive improvements in one area, settles for small gains to small losses in another, and offers an unknown level of improvement in the third. Gamers who want some ability to play on thin-and-lights should be the major beneficiaries of the improvements we’ve seen thus far. If this performance holds, AMD will either need to hit back at Intel on 7nm or see its long domination of the integrated mobile GPU market finally fall — which isn’t honestly a sentence I used to think I’d ever type.

Quote:Intel is taking big strides forward with its Gen11 integrated graphics architecture. Its performance-configured variant, the Intel Iris Plus Graphics G7, featured in the Core i7-1065G7 "Ice Lake" processor, is found to beat AMD Radeon RX Vega 10 iGPU, found in the Ryzen 7 2700U processor ("Raven Ridge"), by as much as 16 percent in 3DMark 11, a staggering 23 percent in 3DMark FireStrike 1080p. Notebook Check put the two iGPUs through these, and a few game tests to derive an initial verdict that Intel's iGPU has caught up with AMD's RX Vega 10. AMD has since updated its iGPU incrementally with the "Picasso" silicon, providing it with higher clock speeds and updated display and multimedia engines.

The machines tested here are the Lenovo Ideapad S540-14API for the AMD chip, and Lenovo Yoga C940-14IIL with the i7-1065G7. The Iris Plus G7 packs 64 Gen11 execution units, while the Radeon RX Vega 10 has 640 stream processors based on the "Vega" architecture. Over in the gaming performance, and we see the Intel iGPU 2 percent faster than the RX Vega 10 at Bioshock Infinite at 1080p, 12 percent slower at Dota 2 Reborn 1080p, and 8 percent faster at XPlane 11.11.

Quote:Despite recent rumors, Intel hasn't given up on its 10nm process node for desktop chips. However, the chipmaker hasn't dropped any specific processors names into its recent statement that it would bring 10nm chips to the desktop. However, the Linux patch does seem rather convincing that Intel's 10nm desktop processors could debut with the Ice Lake architecture.

There are multiple mentions of the Ice Lake processors in the patch. Komachi believes the key to deciphering the different entries resides in the suffix. There isn't any hard evidence to back this up, though, so we should interpret the product naming scheme with caution.
...
We've already seen what mobile Ice Lake chips can do. However, it would be fascinating to see how Ice Lake performs on the desktop when it isn't confined to ultra-low TDP (thermal design power) envelopes like on the mobile parts. And who knows – maybe with some more breathing room, Intel's 10nm processors might actually surprise us.

Quote:A leaked Intel CPU has been discovered on the SiSoft database. This CPU has six cores, Hyper-Threading, and was used in a server or workstation configuration with another identical six-core for a total of 12 cores and 24 threads. What's interesting, however, is that the amount of L2 cache per core has been increased from just 256 KB on Coffee Lake CPUs, like the Core i9-9900K, to 1.25 MB. This is even more cache per core than offered by the Core i9-10980XE (1 MB) and Ice Lake mobile CPUs (512 KB).
...
The most likely possibilities are that either this is a 10nm Ice Lake, Tiger Lake, or a 14nm Rocket Lake processor. There is little information on the latter two architectures, but one Tiger Lake leak revealed it has 1.25 MB of L2 cache per core, just like this leaked CPU. That might be evidence that this is actually based on Tiger lake, but there has been no indication thus far that Tiger Lake will offer more than four cores, while Rocket Lake has been seen with eight cores. This leaked CPU also has less L3 cache than the leaked Tiger Lake CPU; because L3 caches can be quite large, it makes sense that a CPU on a less-dense node would have less L3 cache than a CPU on a denser node.
...
Given that the chips were tested in a server, that opens up the possibility that the chip is simply Ice Lake for server, which would have more L2 cache per core than Ice Lake for mobile (see Skylake vs. Skylake X).

Overall, it's hard to make any firm conclusions based on this result. The possibilities are many and the evidence is very thin. The one certainty is that this CPU is not a Skylake derivative. What isn't certain is whether or not this is 14nm Rocket Lake with a backported core, 10nm Tiger Lake, or something totally different, like Ice Lake for server.

Quote:Three new 10th generation Core "Ice Lake-U" notebook processors surfaced on Intel website with a curious new nomenclature, possibly ahead of their "Q2-2020" launch. The three follow the processor model numbering convention of 10x0NGy, where x denotes the key model differentiator, and y the iGPU tier differentiator. Among the three parts are the Core i7-1060NG7, the Core i5-1030NG7, and the Core i3-1000NG4. The i5-1060NG7 and i5-1030NG7 are 10-Watt parts and feature 4-core/8-thread "Sunny Cove" CPUs, while the i3-1000NG4 packs a 2-core/4-thread "Sunny Cove" CPU, and is rated at 9 W TDP.

Quote:A lot of excitement surrounds Intel's looming Xeon Ice Lake-SP chips, as they will be the first non-mobile CPUs to represent the chipmaker's 10nm process node. As spotted today by @TUM_APISAK, a fresh pair of 28-core chips have landed on the Geekbench 4 benchmark and could offer a glimpse of what to expect from Ice Lake-SP.
...
The Intel system from the Geekbench 4 submissions is equipped with two 28-core Ice Lake-SP processors, totaling up to 56 cores and 112 threads. Each chip reportedly features a 1.5 GHz base clock, a maximum clock speed of 3.19 GHz and 42MB of L3 cache. The base clock speed appears to be a lot lower than the base clock on a previously leaked 24-core Ice Lake-SP. However, it's normal to see models with higher core counts come with lower clock speeds. In any event, the Ice Lake-SP samples in the submission could be engineering samples, and Intel hasn't confirmed them, so take the values with a grain of salt.

The EPYC 7442 (codename Rome) is one of AMD's multiple 64-core monsters. The chip is the second fastest SKU, only lagging behind the EPYC 7H12. The EPYC 7442 checks in with 64 cores and 128 threads with a base clock of 2.25 GHz base clock and 3.4 GHz boost clock. There is also a whopping 256MB of L3 cache on the processor too.

It should be noted that the Geekbench 4 submissions are from distinct systems with different hardware and operating systems under unknown testing environments. It's also uncertain if the reported clock speeds are the final specifications for the Ice Lake-SP chips. Furthermore, Geekbench 4.1 and later has a liking for the AVX-512, which Ice Lake-SP exploits and AMD evidently lacks.

Based on the numbers provided, however, the EPYC 7442 performed up to 28.4% faster than the pair of Xeon Ice Lake-SP processors in the single-core test. This was to be expected, considering that the EPYC 7742 obviously has higher clock speeds. On the multi-core test, the dual Ice Lake-SP processors surpassed the EPYC 7442 by up to 7.3%.

Intel is slated to ship Ice Lake-SP by the end of this year. Notwithstanding, the processors might not be widely available until next year.

On the consumer side, Intel has confirmed that its desktop 10nm processors won't come to the market until the second half of 2021.

Quote:Intel 10 nm products have seen massive delays over the years, and Intel has built many IPs on the new node, however, not many of them have seen the light of the day due to problems the company has experienced with the manufacturing of the new node. That has caused delays in product shipments in the past, meaning that the time for 10 nm is just ahead. According to the latest DigiTimes Taiwan report, we have information that Intel is going to delay its Ice Lake-SP server processors manufactured on a 10 nm node. And it is going to be a whole quarter late according to the report. Instead of launching in Q4 this year, we can expect to see new processors in Q1 of 2021. It is yet unknown whatever the launch will happen at the beginning of Q1 or its end, however, we will report on it as we hear more information.

Update: DigiTimes has also released another report regarding server shipments. It is reported that server vendors are decelerating the shipments as they are making fewer orders in Q4 to wait for the new Intel CPUs. Judging by this move, the demand for these new processors is going to be rather high and the supply chain is preparing slowly for it.

Quote:Intel today unveiled the suite of new security features for the upcoming 3rd generation Intel Xeon Scalable platform, code-named "Ice Lake." Intel is doubling down on its Security First Pledge, bringing its pioneering and proven Intel Software Guard Extension (Intel SGX) to the full spectrum of Ice Lake platforms, along with new features that include Intel Total Memory Encryption (Intel TME), Intel Platform Firmware Resilience (Intel PFR) and new cryptographic accelerators to strengthen the platform and improve the overall confidentiality and integrity of data.

Quote:Today, in the latest GeekBench 5 submission by ASUS, we have discovered something rather interesting. Intel's Ice Lake-SP processors were rumored to arrive with up to 28 cores and 56 threads at maximum, on a single chip. That was due to the 10 nm process used to make these chips, with suspicions that the yield of the node was not good enough to make any higher core count parts. Thanks to the GB5 listing, discovered by Leakbench on Twitter, the Intel Ice Lake-SP CPU engineering sample appeared with an amazing 36 cores with 72 threads. This is supposedly Intel's efforts to try and match the 64 cores and 128 threads of AMD's EPYC "Rome" CPUs, which are winning many server applications due to their performance.

Quote:Intel highlighted the company's focus on execution of core products and showcased the company's broader portfolio, in addition to sharing more on what's coming in the year ahead. As part of its disclosures, Intel announced the recent production of its 3rd Gen Intel Xeon Scalable processors (code-named "Ice Lake") with volume ramp taking place during the first quarter of 2021. Intel's 10 nm Xeon Scalable processors feature architectural and platform innovations that boost performance, security and operational efficiency within data centers.