Introducing Ponte Vecchio, the first commercial product based on the architectureXe Innovative - which will be tailored to all levels from server sets to ultra-cost-effective mobile products
A few years have passed since Intel announced that it plans to try its luck, and not for the first time, in parallel processing, or graphical processing if desired, thus providing a first significant competition for the Duopoly of NVIDIA and-AMD For the first time in a long time - and now this vision feels much more real than ever with revealing the technical details of a first product based on New Age architecture. ships and-Turing - Get ready to meet Xe.
Ponte Vecchio is the code name for parallel home processing accelerator Intel Which will be on the market in 2021 and will fit into the world of servers and especially to the powerful computing world (HPC) of the dreadful supercomputers - based on the future production lithography of Intel In 7 nm, for the intriguing Foveros technology that will stack several different types and uses of chips over the chassis chip Single, on fast internal EMIB links between chassis chips and a new Xe Link connectivity technology for linking different accelerators based on the CXL standard and infrastructure PCI-Express 5.0
From the official slides in the company's presentations, the chipmaker seems to be aiming for a more resilient architecture than we know NVIDIA and-AMD Today - there will be no basic processing cluster that is identical across all products with a defined number of processing units, cache and scheduling units, but different Chiplet units that are tailored to different performance and are connected to separate cache chips according to the requirement in each field. More similar to the Zen 2 general processor architecture AMD, Than other products in the field.
Ponte Vecchio probably won't be the first product based on the architectureXe In the market (we should see its applications in the home market as early as next year), but it is the first to receive any technical detail right now - and also a testament to the intended power and flexibility of the technology that can also fit into the groundbreaking Exascale systems.
Intel did not disclose performance data from Ponte Vecchio units, making it difficult to compare the venture to products we now know from competitors - but data on the expected array for the mighty Aurora supercomputer to be launched at the US Government Department of Energy's 2021 National Laboratory has enabled some Very rough calculations that give us a particularly promising anchor point.
With the promise of maximum breakthrough performance at ExaFLOPs (quintillion floating point calculations per second) based on about 15,000 Ponte Vecchio accelerators, an estimate of about 60TeraFLOPS (about 60 trillion floating point per second processing) is evaluated Such a standard 32 bit exactly - this compares to the performance of some 15TeraFLOPS similar top accelerators of NVIDIA and-AMD Right now.
It's a huge leap to be treated with healthy skepticism (the computer in question hasn't been built after all, and a lot of things can change in a year and a half or two in the world of computing and hardware), but this is a first testament to the fact that Xe's X Intel Competitive products are expected to be competitive in the first generation - seemingly without a few years of trial and error until they can catch up to years of gaps.
Expect more details and data about Xe And various products that will be based on it in the near future!