LONDON – Nvidia Corp., best known as a supplier of graphics processor units (GPUs), has announced that it intends to build high-performance microprocessors for applications ranging from PCs and servers up to workstations and supercomputers. Nvidia (Santa Clara, Calif.) will base its designs on an architecture license from ARM Holdings plc (Cambridge, England) in what is a full-frontal attack on the world's largest chip company, Intel Corp.
Nvidia has been a long-standing licensor of ARM intellectual property but has previously made use of individual core licenses. "Project Denver," as the latest initiative is known, features an Nvidia processor running the ARM instruction set, which will be integrated with an Nvidia GPU array.
This processor stems from a strategic partnership, also announced today, under which Nvidia has obtained rights to develop its own high performance CPU cores based on ARM's future processor architecture. In addition, Nvidia has licensed ARM's current top-of-the-range Cortex-A15 processor for its future-generation Tegra mobile processors.
The news comes as Microsoft has announced that the full Windows 8 operating system will run on the ARM architecture, thereby enabling vendors of non-x86 processors to enter the Windows PC market.
"ARM is the fastest-growing CPU architecture in history," said Jen-Hsun Huang, president and chief executive officer of Nvidia, in a statement. "With Project Denver, we are designing a high-performing ARM CPU core in combination with our massively parallel GPU cores to create a new class of processor," he added.
Warren East, ARM chief executive officer said: "Nvidia is a key partner for ARM and this announcement shows the potential that partnership enables. With this architecture license, Nvidia will be at the forefront of next generation SoC design, enabling the Internet everywhere era to become a reality."
I don't agree on nVidia has much advantage on graphics for embedded market mainly for advanced UI and relative simple graphics. Imagination tech and ARM are leading this. A company knows how to build expensive Ferrari is not necessary good at building low cost efficient car like Toytota Corolla. If i remember right, nVidia is licensing Imagination Tehc core for its SoC.
Plus, i have been strongly against using 3D core to implement flash UI. What a big waste of power and resource. If UI is all you need, CPU software is more than enough for small screen. A simple 2D or 2.5D with perspective transformation will perform way better than 3D core. 3D only makes sense when game is required. Apple uses 3D graphics iPhone since iPhone has game requirement. So it is free resource for its UI. I found lots of companies start to follow Apple blindly without considering its own scenarios.
A15 has four cores per clusters but it is newly ACE AMBA4 bridge could only support two clusters now. That limits maximum 8 cores unless you don't care cache coherence or develop your own ACE AMBA4 bridge. But it is no doubt that A15 targets at server market.
Another major cause of boot times is the shear size of files/data that has to be initialised. For arguments sake, if the OS fitted in 100k it could run entirely in cache and could be loaded of 1 revolution of the hard disk. The further you depart from this ideal, the worse things become. That is the real issue with boot times
Bootup times are largely down to HDD access speeds. Putting the OS on a high performance SSD should speed up things a lot. As for the OS itself, we shall have to wait until Google merge Chrome with Android. I don't think raw Linux will take off on the desktop, but tablets might be the Trojan Horse it needs in Android form.
A deep stab at the heart of Intel. :) With Win 8 officially announced to run on ARM, Intel's dominance is finally beginning to end.
@rick & luting
I dont think other ARM Processor manufacturers like Qualcomm/Marvell/TI is poised to take over this market like nVidia, because none of them have a proper GPU which can take the load of Windows AERO other flashy UIs. Going forward majority of the OS improvements will be in the UI(MS stated it many times) and only nVidia has the technology to complement an ARM CPU for dealing with this. Other GPU manufactures like Imagination/ARM MALI will take time to catch up with nVidia to do heavy graphics processing.
Hmm is that 2 minutes from login to desktop visible, or 2 minutes from login to CPU activity more than 2%? The latter is real boot time, the former is an MS method to make people think the boot was faster than previous incarnations. Mine takes 2 minutes by the former (same as yours), but 3-4 by the latter. Still much slower than the 28MHz 68040. The only real difference is retargetable graphics and MMU support, but that can't explain the difference. Sloppy programming is more likely.
My Windows PC boots in around 2 mins. There are lot of things you can do with the bios/startup to speed/slow down your pc. For starters dump the XP and get a Win7. XP was released in 2001 IIRC and it cant even make use of all the cores in your i7 CPU.
This is an opportunity that the Silicon companies out there should be exploiting. We should be moving away from Windows as we know it and popularise the Linux fofr desktops as Android has starting doing it in mobile space. Silly they still hanker after Windows, after all the problems it loads in its innards. Patch galore and bloated code has been the hallmark of Windows OS so far. At least lets hope the Windows8 is leaner and faster.
ARM architecture is now at the threshold of breaking into the big league and who knows the next generation of us will have better choices and not end up paying our $$ for a lot of heat and buggy software.
Intel has an ARM license (the XScale was a big seller just a few years ago). In fact, that was the fastest and lowest power ARM chip for quite a while. The problem is that I'm not sure if Intel wants to get into the $1 core market (they are used to the $20 core market). Currently you can get small ARM chips for under $3! It'll be interesting to see how this market changes. NVIDIA with CUDA parallel cores could bring the desktop into the supercomputer market as long as they stay away from Microsoft and work with a linux OS running an L4 microkernel with built-in real time capability. That would be a heck of a fast PC. I sure hope they make Linux their "main" OS. This could open up a new era in desktop computing with AI, speech recognition and natural language understanding....the truly intelligent computer.
Another processor I wish people would use more is the MIPS architecture. It is easier to get to run faster than ARM and faster than the x86 processors, and I think there is an architecture with a 128-bit word.....better suited for a desktop architecture.
But these are just my preferences....time will tell....
David Patterson, known for his pioneering research that led to RAID, clusters and more, is part of a team at UC Berkeley that recently made its RISC-V processor architecture an open source hardware offering. We talk with Patterson and one of his colleagues behind the effort about the opportunities they see, what new kinds of designs they hope to enable and what it means for today’s commercial processor giants such as Intel, ARM and Imagination Technologies.