I was awarded an FPGA chip by Xilinx that I blogged about: http://msapaydin.wordpress.com They are making an effort to promote the use of Xilinx fpga's on machine learning, recently.
AMD Receives Approval for Acquisition of Xilinx
31–40 of 69 posts
Re: AMD Receives Approval for Acquisition of Xilinx
#32Why? Has Intel done anything with Altera? I’m curious. AMD’s acquisition of ATI is generally viewed as a strategic error. Does this make more sense?
> AMD’s acquisition of ATI is generally viewed as a strategic error. Historically it was (when AMD was drowning in debt from the acquisition and had no competitive processors on the timeline), but is this still true? For instance, all of the major game consoles (ps4/ps5/xbone/xbox series x/switch) use AMD boards, and as I recall, those deals lifted the company's financials quite well.
As already mentioned, not the Switch.
A few of these are pre-acquisition but the GPU's for the xbox 360, Gamecube, Wii, and Wii U were all ATI/AMD as well.
I'm sure at this point more console hardware has been AMD than any other manufacturer.
Re: AMD Receives Approval for Acquisition of Xilinx
#33Earlier quoted context omitted.
> AMD’s acquisition of ATI is generally viewed as a strategic error. Historically it was (when AMD was drowning in debt from the acquisition and had no competitive processors on the timeline), but is this still true? For instance, all of the major game consoles (ps4/ps5/xbone/xbox series x/switch) use AMD boards, and as I recall, those deals lifted the company's financials quite well.
Console deals are terrible margin - there is a reason AMD won all those deals. If you have competitive chips, you would rather use your silicon otherwise.
Terrible margin for the console manufacturer (Sony, MS, Nintendo).. do we have any evidence that they're terrible margin for component manufacturers? Presumably these consoles wouldn't be sold at a loss if the components were bargain basement as you imply?
Also if we look at the latest gen, there's some pretty cutting edge architecture and manufacturing processes used in the new xbox/playstations. Zen2 is no slouch.
Re: AMD Receives Approval for Acquisition of Xilinx
#34Earlier quoted context omitted.
What’s wrong with current state except that the chips have lead time of 52+ weeks?
The development side. Compiling and simulating your Verilog/VHDL can be done with open source software, but to put it on the FPGA itself, you generally need closed source (and sometimes paid) tools to generate the bitstreams. Contrast that with microcontrollers such as the ATMega which can be programmed from start to finish using an entirely FOSS stack - even the bootloader and programmer. And for some reason, these…
this is true in general but
1) vivado webpack edition (ie free) lets you write (and flash) a bitstream for some of the small chips. i know it at least works for the artix-7 family because i'm doing it every day lately
2) for the artix-7 (and some lattice chips) you supposedly can use OSS (https://github.com/SymbiFlow/prjxray). i haven't tried it yet but one problem i can foresee is that the OSS tools won't infer stuff like brams and dsp. in fact the symbiflow people (i think?) explicitly call this out as the part of the project that's a work in progress.
some useful links:
https://arxiv.org/abs/1903.10407
Re: AMD Receives Approval for Acquisition of Xilinx
#35Why? Has Intel done anything with Altera? I’m curious. AMD’s acquisition of ATI is generally viewed as a strategic error. Does this make more sense?
There are some interesting datacenter interconnect implications, especially around the new CXL spec.
Re: AMD Receives Approval for Acquisition of Xilinx
#36Recieved approval from the Chinese anti-trust body. Still waiting for the FTC sign-off, but that should be a rubberstamp at this point. This acquisition brings AMD up to par with Intel's market share in the chip market.
The current FTC and DoJ leadership are the most anti-trust since the (first) Roosevelt administration, it seems (nevermind that they were established after the fact, I'm being hyperbolic)
Re: AMD Receives Approval for Acquisition of Xilinx
#37Why? Has Intel done anything with Altera? I’m curious. AMD’s acquisition of ATI is generally viewed as a strategic error. Does this make more sense?
Opinions on it are definitely mixed. It's an all stock deal that was made at a very reasonable price, but 1.5 years on they are overpaying by a huge amount. Xilinx has been doing very well compared to Intel's FPGA division, so you can try to justify it, but from a shareholder perspective it's very dilutive.
Re: AMD Receives Approval for Acquisition of Xilinx
#38I was awarded an FPGA chip by Xilinx that I blogged about: http://msapaydin.wordpress.com They are making an effort to promote the use of Xilinx fpga's on machine learning, recently.
https://msapaydin.wordpress.com/2021/11/01/xilinx-and-ai/ right ?
Yes, thank you. Sorry I am on mobile, traveling and could not post the full link.
Re: AMD Receives Approval for Acquisition of Xilinx
#39If I have one wish for AMD, I wish that they would make FPGAs (and Xilinx) a more open and diverse platform like the PC. Not that the PC is perfect (there's still closed-source firmware), but any improvement to the current state of FPGAs would be welcomed.
You've struck on the fundamental problem that the FPGA industry has been trying to solve for 30+ years - how to get an FPGA into the hands of every developer, like how GPUs have propagated to be essential tools. Nobody has come up with a good answer yet. Developing for an FPGA still requires domain-specific knowledge, and because place & route (the "compile" for an FPGA) is a couple of intertwined NP-hard problems de…
You don't seem bullish on the prospects of using Vitis [0] to deploy a machine learning model to a Xilinx FPGA?
[0] https://www.xilinx.com/products/design-tools/vitis/vitis-pla...
Re: AMD Receives Approval for Acquisition of Xilinx
#40Earlier quoted context omitted.
For now they do, honestly it would make more sense to maybe consider an AMD SoC.
I would be a little surprised if they switched off of ARM. Even the Steam Deck with its custom AMD SoC is much closer to laptop specs and wattages than the switch e.g. 20w+ SoC, more than 2x battery capacity vs Switch. The switch has a lot more in common with phones than it does with other consoles or PC portables so IDK if we will see AMD SoCs with the right power profile for nintendo's needs. Nintendo could use one…
AMD has ARM licenses (IIRC, both architectural and for IP cores) and has shipped an Arm Cortex-A52 SoC in the past (Opteron A1100). If Nintendo really wanted, they might be able to order an Arm SoC from AMD directly. But yeah, going with Samsung would be far more practical.
Problem is, many existing Switch games use some nvidia-specific API (IIRC called "NVN" or whatever) instead of Vulkan.