03-01-2019, 10:00 PM
https://www.tomshardware.com/news/intel-...38246.html
Quote:Intel whipped the covers off its Xe graphics branding at its recent Architecture Day, but it doesn't represent the actual final brand names, like Radeon or GeForce. Instead, the Xe branding signifies Intel's full range of low- to high-power graphics solutions.
...
Intel's Xe line will come after Gen11 and replace the Gen12 branding. These graphics processors will scale from integrated graphics chips on processors up to discrete mid-range, enthusiast, and data center/AI cards. Intel says it will split these graphics solutions into two distinct architectures, with both integrated and discrete graphics cards for the consumer market (client), and discrete cards for the data center. Intel also disclosed that the cards would come wielding the 10nm process and arrive in 2020, which is in line with its previous projections.
...
Intel still has a lot of work to do on the enablement front, such as recruiting AIB partners, but it is possible the company will produce the new cards natively. It's hard to tell which path Intel will take, including which segments of the market it will target first. It's natural to expect Intel's freshman effort to target the mid-range enthusiast market with enticing price points, but true to its heritage, the company may also bring high-end cards based on enterprise designs to the enthusiast space, just like it does with its high-end desktop processors.
Only time will tell, but Intel has the deep pockets to take losses for the first few generations as it builds a customer base. In either case, Intel's new cards will force both AMD and Nvidia to become more competitive on pricing.
...
In a sign of things to come, Intel has increased the cadence of driver releases lately, with a heavy focus on zero-day releases. At its recent event, the company also reiterated its commitment to the software ecosystem in the graphics market, so we know the company is headed in the right direction on that front. Market-leader Nvidia employs more software engineers than hardware engineers, so success in this area is key.
Intel is also already working diligently on enabling its driver ecosystem, with the first Linux patches, 42 in fact, arriving in early 2019. The 4,000 lines of code enable support for device-local memory regions, which is key for supporting a discrete graphics card with its own onboard memory. Intel typically releases driver patches roughly a year ahead of the launch of new devices, so these updates indicate the project is well underway.
...
Both AMD and Nvidia also rely on outside fabs. Intel's fabs have been a liability lately as the company struggles with its 10nm process, but when used correctly, Intel's fabs are a tangible advantage that could give the company a leg up on its competitors. Chip packaging techniques are becoming the true differentiator in the waning light of Moore's Law, and its fair to say that the companies that produce AMD and Nvidia's GPUs (TSMC and GlobalFoundries) cannot compete with Intel's next-gen packaging technologies. At least for now.
...
There's no doubt that Intel needs to succeed in the GPU market, at least in the data center. We often look to the supercomputing realm to sniff out new trends, and the rise of GPUs in that space is explosive: in 2008 not one supercomputer used GPUs for computation, instead relying on the tried-and-true CPU, but now 80% of compute power in the top 500 supercomputers now comes from GPUs. It appears the pressure Nvidia's GPUs are putting on Intel's Xeon sales is finally having an impact: We would have never expected Intel to share a chart like the one above, which clearly shows that GPUs are part of the path forward to extending Moore's Law.