Podcast #444 - ASUS Motherboard, NVIDIA Quadro, AMD ReLive, DDR5

Subject: Editorial | April 6, 2017 - 12:57 AM |
Tagged: Z270E, windows 10, relive, podcast, pascal, NVIDA, Mad Catz, Imagination Technologies, ddr5, asus, amd

PC Perspective Podcast #444 - 04/6/17

Join us for an ASUS Z270 Motherboard, NVIDIA Quadro, AMD ReLive, DDR5 and more!

You can subscribe to us through iTunes and you can still access it directly through the RSS page HERE.

The URL for the podcast is: http://pcper.com/podcast - Share with your friends!

Hosts: Jeremy Hellstrom, Josh Walrath, Allyn Malventano, Ken Addison

Program length: 1:05:50
 
Podcast topics of discussion:
  1. Week in Review:
  2. News items of interest:
  3. Hardware/Software Picks of the Week
    1. Jeremy: ASUS GTX 1080 8GB ROG STRIX, CAN or US
  4. Closing/outro

Source:

April 6, 2017 | 07:49 PM - Posted by Anonymous (not verified)

Looks like some more Ryzen(Radeon RX480 GPU) testing is going on against the GTX 1060, Ryzen 7 1800X against the 7700k.

"Does Ryzen Perform Better with AMD GPUs?

Is That Even Possible? We Give It a Go"

http://www.techspot.com/article/1374-amd-ryzen-with-amd-gpu/

April 6, 2017 | 07:59 PM - Posted by Anonymous (not verified)

P.S. The Ryzen 7 1800x and 7700K are clocked the same, they are trying to test if Ryzen performs better with AMD GPUs. So this is not a Ryzen against the 7700K sort of contest, it's more of a looking at the GPUs performance with Ryzen sort of testing and how that may differ between Nvidia's and AMD GPUs and their respective Nvidia and AMD GPUs' driver/API software stacks.

April 6, 2017 | 11:54 PM - Posted by Anonymous (not verified)

Relating to Apple designing their own gpu, there seems to be some evidence that their gpus already share only the fixed function hardware with imagination gpus. This was covered by David Kanter in the article titled "A Look At Apple's Custom GPU for the Iphone" from October 25 2016 (don't know about pcper's links in comments policy so i just wrote the title)

April 7, 2017 | 01:00 PM - Posted by Anonymous (not verified)

Well Apple better not be using any Unified Shaders without working up some IP licensing from AMD, Nvidia, or Imagination Technologies/others that may have any Rights to some Unified Shader patented ideas. Because even if your in-house clean sheet GPU design happens to use any Unified Shader design, the very idea of creating any unified shader implementation is patented. So Apple will have to license that patented Idea from any that may have been grated patents for Unified Shaders by the USPTO. Ditto for any other GPU design Ideas that any GPU designer/maker was awarded a patent for by the USPTO.

And it's damn near impossible to even work up a clean sheet GPU design that does not infringe on some current GPU designer’s/maker’s GPU patent portfolios!

Apple can design its own GPUs till the cows come home, but those designs can not be legally sold if they make use of any patnted ideas that others hold the patent rights to. Apple will have to license some IP to be able to legally sell its in-house GPU designs in any markets that legally inforce patent/trade laws. That's what Intel has to do for Intel's very own in-house GPU designs, and Intel licenses those patent rights from Nvidia currently.

April 6, 2017 | 11:54 PM - Posted by Anonymous (not verified)

Relating to Apple designing their own gpu, there seems to be some evidence that their gpus already share only the fixed function hardware with imagination gpus. This was covered by David Kanter in the article titled "A Look At Apple's Custom GPU for the Iphone" from October 25 2016 (don't know about pcper's links in comments policy so i just wrote the title)

April 8, 2017 | 04:04 PM - Posted by Anonymous (not verified)

WTF is this, DX12 in the GPU's command processor of the GPU(1) !!!

A graohics API built into the GPU's Commannd Processor, well that has one Hell of an positive affect on -->Latency<--- BIG TIME!

I Hope that this can be done on discrete GPUs, because that has even more potential Positive -->Latency<--- implication for discrete graphics if the graphcs API is in the GPU's command processor. I'd love to see discrete GPUs that could load up the Graphics API into the GPU's command processor and not have to worry about the extra latency inducing hopps over PCIe or even video memory up into the GPU's cache levels latency. This technology has to be looked at closely for it's implications across the entire PCgaming market and not just the console market.

"However, potentially the most exciting aspect surrounding the CPU revamp doesn't actually relate to the processor blocks at all, but rather to the GPU command processor - the piece of hardware that receives instructions from the CPU, piping them through to the graphics core.

"We essentially moved Direct3D 12," says Goossen. "We built that into the command processor of the GPU and what that means is that, for all the high frequency API invocations that the games do, they'll all natively implemented in the logic of the command processor - and what this means is that our communication from the game to the GPU is super-efficient."

Processing draw calls - effectively telling the graphics hardware what to draw - is one of the most important tasks the CPU carries out. It can suck up a lot of processor resources, a pipeline that traditionally takes thousands - perhaps hundreds of thousands - of CPU instructions. With Scorpio's hardware offload, any draw call can be executed with just 11 instructions, and just nine for a state change.

"It's a massive win for us and for the developers who've adopted D3D12 on Xbox, they've told us they've been able to cut their CPU rendering overhead by half, which is pretty amazing because now the driver portion of that is such a tiny fraction," adds Goossen.

[UPDATE 7/4/17 20:44: Microsoft's Andrew Goossen has been in touch to clarify that D3D12 support at the hardware level is actually a part of the existing Xbox One and Xbox One S too. "Scorpio builds on the Command Processor capability present in the original Xbox One," we're told. "Our implementation of D3D12 supports all Xbox Ones, and games have already shipped that use it. When a game using D3D12 starts up, we reprogram the GPU's Command Processor front-end. The 50 per cent CPU rendering overhead improvement was reported by shipping games. The amount of win is dependent on the game engine and content, and not all games will see that size of improvement. Scorpio's Command Processor provides additional capability and programmability beyond what Xbox One/Xbox One S can do. We plan to take advantage of this in the future."] " (1)

(1)

"Inside the next Xbox: Project Scorpio tech revealed

Digital Foundry has the specs, has seen it running, and has talked to the people who built it."

http://www.eurogamer.net/articles/digitalfoundry-2017-project-scorpio-te...

April 8, 2017 | 07:20 PM - Posted by Anonymous (not verified)

How may this[see below] relates(?) to the Xbox and its GCN based IP, and that GPU command procesor able to have its own DX 12 API functionality. This goes back into AMD's AMD's 3rd generation products also with that hardware scheduler IP.

Vega prpbably will have an updated version of these hardware schedulers(with a brain/AI) with updatable micro-code for processing/implementing API calls in micro-code.

"A single Graphics Command Processor up front is still responsible for dispatching graphics queues to the Shader Engines. So too are the Asynchronous Compute Engines tasked with handling compute queues. Only now AMD says its command processing logic consists of four ACEs instead of eight, with two Hardware Scheduler units in place for prioritized queues, temporal/spatial resource management and offloading CPU kernel mode driver scheduling tasks. These aren’t separate or new blocks per se, but rather an optional mode the existing pipelines can run in. Dave Nalasco, senior technology manager for graphics at AMD, helps clarify their purpose:

"The HWS (Hardware Workgroup/Wavefront Schedulers) are essentially ACE pipelines that are configured without dispatch controllers. Their job is to offload the CPU by handling the scheduling of user/driver queues on the available hardware queue slots. They are microcode-programmable processors that can implement a variety of scheduling policies. We used them to implement the Quick Response Queue and CU Reservation features in Polaris, and we were able to port those changes to third-generation GCN products with driver updates." " (1)

(1)

"AMD Radeon RX 480 8GB Review"

http://www.tomshardware.com/reviews/amd-radeon-rx-480-polaris-10,4616.html

April 11, 2017 | 12:41 AM - Posted by Anonymous (not verified)

Intel's buggy Puma 6 chpisets rates a lawsuit for Arris. And Arris' QA/QC was MIA causing many needless gaiming "You are Dead" episodes.
.
.
.

"The complaint, filed in the Northern California District Court, accuses the vendor of violating four California state consumer protection laws and seeks relief for folks in the Golden State who purchased an Arris SURFboard SB6190 modem since its launch in late 2015.

According to the complaint, Arris violated state laws on misleading advertising and unfair competition, as well as consumer protection and warranty laws, when it advertised and sold the SURFboard cable modems as "gigabit" home internet boxes.

As covered in detail by El Reg in December, the Arris SB6190 was among home gateways using a buggy Intel Puma 6 chipset that was prone to high latency under certain circumstances. This chipset caused the SB6190 – and other DOCSIS 3.0 cable modems using Intel's silicon – to suffer from jittery connectivity that ruined online gaming and other latency-sensitive apps." (1)

(1)

"Intel's buggy Puma 6 chipset earns Arris a gigabit-modem lawsuit

Laggy silicon at heart of broadband boxes lands gateway maker in court"

http://www.theregister.co.uk/2017/04/11/intel_puma_6_arris/