When we first reported that AMD would be calling its now current-gen processors Ryzen, the name just didn't stick at first - but here we are, with a slew of Ryzen processors that are starting to make Intel squirm.
But according to a new trademark filing, it looks like AMD is working on new products called Kyzen, Aragon, Pharos, Promethean, Zenso, and CoreAmp. All of these product names were trademarked in March, with a few of them already released. What can we expect from these new, interestingly named AMD products?
Well, Kyzen sounds just like Ryzen - so maybe this is a new CPU from AMD, or maybe even a new APU. I have a 'cryo' feel from Kyzen, so maybe we're looking at a heavily overclockable Ryzen processor that will be released as Kyzen? Who knows. Next up we have Aragon - very Lord of the Rings. Promethean will most likely end up as a chipset, as AMD named their Ryzen chipset Promontory - with Promethean being very close to that.
Intel is preparing its 10C/20T processor to directly compete against AMD's Ryzen 7 1800X and their upcoming ThreadRipper CPUs that will feature 16C/32T of CPU power, but Intel could have it in the bag with its Core i9-7900X.
According to new benchmarks, the Core i9-7900X will be clocked at 3.3/4.3GHz for base/boost, respectively. This is a huge deal for Skylake-X, as the IPC performance at 4.3GHz and 10C/20T of power should pummel every other CPU into dust. Better yet, SiSoft's benchmark picked up the CPU as 4.0GHz base clock and 4.5GHz boost, which would be absolutely insane - especially for a 10-core processor.
We should expect 13.75MB of L3 cache, 1MB L2 cache per core (10MB total), and a 175W TDP for the upcoming Core i9-7900X. We should expect Intel to unleash its new Skylake-X parts at Computex next week, alongside the new X299 chipset and a slew of new motherboards.
Intel has been on the CPU offensive since AMD launched their new Ryzen platform, and now we're hearing about their next-gen Xeon Scalable Platform, otherwise known as Cascade Lake.
Cascade Lake was shown off during the SAP Sapphire conference, with Intel teasing that its next-gen platform will arrive in 2018. Cascade Lake-SP is the Skylake-SP refresh, with Intel tapping the 14nm+ node. Cascade Lake will support up to a mammoth 6TB of Optane DIMMs, which is a huge plus for Intel.
Intel has teased: "Intel persistent memory will allow users to improve system performance dramatically by putting more data closer to the processor on nonvolatile media, and do it in an affordable manner. This will truly be a game-changer when it comes to the way applications and systems are designed".
The next-gen Cascade Lake CPUs will be capable of being thrown into 4-socket configurations, supporting up to 3TB of Optane DIMMs, while the 8-socket systems will support up to 6TB of Optane goodness.
Google has just unveiled its second-generation tensor processor, something that packs 45 TFLOPs of performance per chip, with four of them placed onto a tensor processor unit (TPU) module for a total of 180 TFLOPs.
The massively powerful systems are built for machine learning and artificial intelligence, and Google is pushing it into the cloud with their TPU-based computational powerhouse systems to be made available to Google Cloud Compute later this year. Google's first-gen Tensor processors were already 15-30x more powerful, and a huge 30-80x more power efficient than CPUs and GPUs for these types of workloads.
These new TPUs are "optimized for both workloads, allowing the same chips to be used for both training and making inferences. Each card has its own high-speed interconnects, and 64 of the cards can be linked into what Google calls a pod, with 11.5 petaflops total; one petaflops is 1015 floating point operations per second", reports Ars Technica.
AMD is really kicking Intel in the shins with its Ryzen CPU family, teasing that it's next-gen ThreadRipper processor will be launching in Summer 2017 - and will be officially detailed at Computex.
ThreadRipper will feature up to 16C/32T of CPU performance, with AMD "targeting the world's fastest ultra-premium desktop systems in an all-new HEDT platform".
I reached out to Founder & Principal Analyst of Moor Insights & Strategy, Patrick Moorhead, where he told us: "AMD's Threadripper willl be unique in the market and could easily garner over $1,000. I don't expect Intel to follow tit for tat, thread to thread, but rather on other merits like single core performance".
I totally agree, especially with Patrick's comments for AMD hitting the $1000+ price point with ThreadRipper. It will push Intel to react, which is probably why we're hearing about Intel's upcoming Core i9 range with up to 12C/24T of performance at up to a blistering 4.5GHz with their purported Turbo Boost 3.0 technology. It's an exciting time to be a technology enthusiast, that's for sure.
AMD has just announced the name of its Naples platform datacenter CPUs, with the company revealing their next-gen Epyc CPU that will feature up to 32C/64T.
AMD CEO Lisa Su unveiled Epyc on stage, offering 32C/64T of CPU performance, 8 memory channels, and 128 PCIe 3.0 lanes per CPU socket. We will have more news as it breaks.
We've been hearing a few rumors on Intel's next-gen Core i9 family of processors, but now we have benchmarks of the new Core i9-7920X which rocks a 12C/24T design.
Intel's upcoming Core i9-7920X will reportedly feature 12C/24T with somewhere around 4GHz boost CPU clocks, with 16.5MB of L3 cache, 44 PCIe lanes, and 140W TDP. This chip was benchmarked against Intel's 10C/20T offering in the Core i9-7900X with its 3.3/4.0GHz base/boost clocks with 13.75MB of L3 cache, and the same PCIe lanes and TDP.
I put all of the scores into one of our benchmark templates, so you can see the scores in a much easier to understand way. As you can see the Core i9-7920X really is a monster, with the multi-core test score pushing 1760, leaving the Core i7-6950X in its rear view mirror, and the AMD Ryzen 7 1800X in its dust.
Even the 10C/20T chip in the Core i9-7900X doesn't do too well, with less performance than the current-gen Core i7-6950X @ 3.5GHz. The 7900X might be at its base 3.3GHz frequency, and the 7920X at 3.3GHz, which would explain these scores. The full 4.5GHz clocks on these Core i9 beasts might be scary good.
We have been hearing about this silent monster that AMD has with 16C/32T of CPU performance, something that has been referred to as ThreadRipper and is launching in June. Now we're hearing that AMD will have 10/12/14/16 core versions, meaning we'll have CPUs with 10C/20T, 12C/24T, 14C/28T, and 16C/32T.
ThreadRipper will be compatible with a modified version of AMD's current SP3 socket, something that's codenamed SP3r2, and was designed for AMD's upcoming Naples server platform. AMD's new Whitehaven platform will provide quad-channel DDR4 with 44 PCIe lanes for multi-GPU users, enthusiasts and workstation users.
Better yet, we know the names of AMD's new ThreadRipper processors with a rather large purported list of Ryzen 9 processors.
ThreadRipper 16C/32T: Ryzen 9 1998X/1998
The new HEDT chips will be led by the flagship Ryzen 9 1998X and Ryzen 9 1998, offering 16C/32T at 3.5GHz base and 3.9GHz boost CPU clocks, while coming in with a 155W TDP - 5W less than Intel's next-gen Core i7-7920X which is a 12C/24T part. The Ryzen 9 1998 on the other hand will retain the 16C/32T power, but at 3.2/3.6GHz for base/boost clocks, respectively - on the same 155W TDP.
Intel first launched its Itanium processor back in 2001, with chipzilla hoping its 64-bit processor would destroy the x86 dominance over the decades before it - but yeah, that didn't happen and now Intel has killed Itanium.
Before it's officially dead, Intel has pushed out a final Itanium 9700 series processor family that are the end of a failed era. Itanium co-creator HP and its enterprise arm HPE will be the last major customer of Itanium processors, with its Integrity i6 servers to receive the improved hardware, but other than that - Itanium is dead.
Itanium launched with a huge marketing campaign where Intel expected its exciting (at least at the time) 64-bit processor to take a huge chunk out of the massive wave of x86, aiming for high-end servers and workstations before cloud computing was even a thing. The first Itanium processors were power hungry, and then AMD decided it would launch consumer 64-bit processors in x86 form, disrupting Intel's plans.
Fast forward to 2017, and AMD is once again disrupting Intel's slowly moving and now tick-tock-less CPU plans with Ryzen, offering 8C/16T of processing power to consumers for under half of what Intel tries to shake you down for. This is why we're hearing so damn much about new processors with monstrous core counts, from both sides of the CPU business - AMD with their upcoming Naples platform, Starship rocking 48C/96T, and even a new 16C/32T consumer/prosumer Ryzen processor.
According to DigiTimes, a Taiwanese technology rumor website, Apple has already placed orders with TSMC (Taiwan Semiconductor Manufacturing Company) for their new iPhone 8 processors.
While we still don't actually know whether or not Apple will call their new phone the iPhone 7S or iPhone 8, DigiTimes is already claiming to know that TSMC has taken orders from Apple for their newest phone using TSMC's upcoming 10nm process.
Currently, TSMC only produces chips for most of their clients at 16nm, while they introduced only this week their new 12nm process for NVIDIA's Volta GPUs. It seems that 10nm will be used for phones primarily because Apple is accompanied by HiSilicon and Mediatek as additional customers for TSMC's upcoming 10nm process.