Donate!
Welcome, Guest. Please Login or Register :: View Members
Pages: 1 ... 4 5 6 7 8 ... 21
Send Topic Print
AMD & others --- Intel dominance in 2022 (Read 9739 times)
Oldfeller--FSO
Serious Thumper
ModSquad
*****
Offline

Hobby is now
"concentrated
neuropany"

Posts: 12629
Fayetteville, NC
Gender: male
Re: AMD & others --- post AMD dominance in 202
Reply #75 - 11/02/20 at 08:27:18
 

https://liliputing.com/2020/11/raspberry-pi-400-is-a-pc-in-a-keyboard-for-70-...


Raspberry Pi 400 is a PC-in-a-keyboard for $70 and up

Raspberry Pi has been selling tiny, inexpensive computers and accessories since 2012. But while Raspberry Pi hardware has become popular with enthusiasts and home users, the organization’s single-board computers were originally targeted at students, educators, and makers.

The new Raspberry Pi 400 is something different: a full-fledged computer stuffed inside a keyboard. It’s basically a modern take on the Commodore 64 and similar personal computers from decades past.

A key difference? The Raspberry Pi 400 is incredibly affordable, with prices starting at just $70.




Here’s a run-down of the new computer’s key specs:

Processor: Broadcom BCM2711 processor (4 x ARM Cortex-A72 CPU cores @ 1.8GHz
Memory: 4GB LPDDR4-3200
Wireless: Dual-band WiFi 5, Bluetooth 5.0
Ports: Gigabit Ethernet, 2 × USB 3.0 and 1 × USB 2.0,  2 × micro HDMI ports (up to 4Kp60)
GPIO: Horizontal 40-pin GPIO header
Storage: MicroSD card slot for OS and data storage
Power: 5V DC via USB connector
Keyboard: 78- or 79-key compact keyboard (UK and US English, French, Italian, German, and Spanish layouts available at launch)
Dimensions: 286 mm × 122 mm × 23 mm



And for the old Commodore 64 users out there, here is the comparison between the new Pi 400 and the 1985 Commodore 64 unit.




Back to top
 
« Last Edit: 11/04/20 at 15:27:03 by Oldfeller--FSO »  

Former Savage Owner
  IP Logged
Oldfeller--FSO
Serious Thumper
ModSquad
*****
Offline

Hobby is now
"concentrated
neuropany"

Posts: 12629
Fayetteville, NC
Gender: male
Re: AMD & others --- post AMD dominance in 202
Reply #76 - 11/03/20 at 04:30:32
 

5nm chipsets are jest a rolling out right now from both TSMC and from Samsung 5nm plants.

The Exynos 1080 is a 5nm chipset, though the exact details on the manufacturing process are not known for now. It will join the growing ranks of
5 nm chips, starting with the Apple A14 but also including the Snapdragon 875, Kirin 9000 and Samsung’s own flagship chipset (the Exynos 2100).


Each new week gives us another 5nm announcement, all with ship dates taking place this year.   This wave is early, a full half a year early in fact.   Yields are very good too, much better than 7nm yields actually so processor costs at retail should drop fairly quickly as scrap costs will be reduced.

Volume-wise TSMC is in the lead, having built run after run of Apple chipsets, some Kirin chipsets for Huawei and a few runs of Snapdragon chipsets for Qualcomm.

A couple of runs of AMD 5nm multi-layer chiplets are up next on the roster.
Back to top
 
« Last Edit: 11/17/20 at 14:02:43 by Oldfeller--FSO »  

Former Savage Owner
  IP Logged
Oldfeller--FSO
Serious Thumper
ModSquad
*****
Offline

Hobby is now
"concentrated
neuropany"

Posts: 12629
Fayetteville, NC
Gender: male
Re: AMD & others --- post AMD dominance in 202
Reply #77 - 11/03/20 at 12:25:43
 

https://liliputing.com/2020/11/arm-unveils-cortex-a78c-cpu-for-always-on-lapt...

ARM unveils Cortex-A78C CPU for always-on laptops



This 5nm design was promised to us at mid-summer by ARM for next year ---- it has arrived now and right now any of the phone boys can license this tech and build their own PC chipset.   Current design offers are 6 cores and 8 cores --- 8 cores would be a fairly good PC if matched with a good upper end Mali GPU.   THIS IS LIKELY WHAT QUALCOMM IS USING IN THEIR X-1 VERSION OF IT.

ARM Cortex-A78C has far more cache than other members of the family, and supports up to 8 “big” CPU cores on a single chip, which should offer much better multi-threaded performance than a smartphone-class Cortex-A78 chip, which would top out at 4 “big” cores and 4 “LITTLE” cores based on Cortex-A55 architecture.

According to ARM that, combined with 8MB of L3 cache memory and other improvements should lead to better performance for gaming or workloads that involve large datasets.

It’s likely that the new CPUs will be a little more power-hungry than their cousins that use a big.LITTLE design. But ARM-powered laptops already tend to get pretty long battery life, so I suspect PC makers (and customers) would be willing to sacrifice a little run time for a significant enough boost in performance.

ARM doesn’t actually manufacturer and sell its own processors, so it’ll be up to third-party companies to license the new designs and use them in upcoming laptops or other mobile devices.





It is now Nov 11 and Apple is shipping their M1 chipset at 5nm.

Overall structure looks a lot like this one.

Mediatek has announced new chipsets at TSMC's new low cost lithography stages which are at 6nm, and at 8nm and at 12nm.

People say they have the same design rules as 7nm, 10nm and 14nm so all your old designs have a potential new home at the new smaller lithography nodes.

Life going out into the future looks very hard if your name is Intel .......

Roll Eyes
Back to top
 
« Last Edit: 11/17/20 at 14:03:46 by Oldfeller--FSO »  

Former Savage Owner
  IP Logged
Oldfeller--FSO
Serious Thumper
ModSquad
*****
Offline

Hobby is now
"concentrated
neuropany"

Posts: 12629
Fayetteville, NC
Gender: male
Re: AMD & others --- post AMD dominance in 202
Reply #78 - 11/04/20 at 15:49:06
 

https://arstechnica.com/gadgets/2020/11/intel-enters-the-laptop-discrete-gpu-...

ArsTechnica is still deep diving Tiger Lake and Intel's Xe graphics, basically telling us that Intel's new hardware isn't much better than the old Intel hardware was, but the AI background cheating stuff is where all the new "Intel Magic" is coming from.

In Intel's demonstration, an Xe Max-equipped laptop used Gigapixel AI to enhance a very large, grainy photo seven times faster than a similar laptop equipped with an Nvidia MX 350 GPU could. While that was impressive, we pressed Intel for comparisons to other hardware, which an Xe Max-equipped laptop might more reasonably compete with "in the wild."

After a day or so, an Intel engineer got back to us and said we could expect an Xe Max-equipped laptop to complete Gigapixel AI workloads seven times as fast as an MX 350, five times as fast as an RTX 1650, and 1.2 times as fast as a Tiger Lake laptop with Iris Xe graphics alone.


Folks, don't allow Intel to confuse their AI tricks with their hardware's real performance, not in your minds in any case.   Intel is simply AI cheating on a scale not seen to date even from the loosest of the oriental cell phone builders.  So  a VERY LOUD Intel buyer beware alarm warning horn blast is still appropriate for Tiger Lake models right now ........    

AVOID THE TIGER LAKE GENERATION COMPLETELY  ---  Tiger Lake is based on a set of AI software tricks that has to be written into your applications which then has to use Intel driver libraries that are out on the web to get to the very latest AI driver tricks to actually use them.
  Until this happens, it is all smoke and mirrors, smoke and mirrors.


===================================================


So, let's take a deep breath here, anything that can give a 7x or 5x increase only in a certain set of tasks might seem like it could be worthwhile if it is done legitimately.   But right now it isn't being done correctly and it isn't real AT ALL right now for most commonplace software uses.

So AI can be potentially worth something, potentially worth something more than a lithography shrink for that particular set of tasks and for that particular vendor, especially for a company like Intel that simply cannot pull off a lithography shrink in any reality time anywhere near now.

BUT, the current Intel secretive black bag "Intel Marketing" trickery is still coming across as despicable and somewhat fraudulent and it seems like outright lying to the purchasing public at times the way they have done it recently .....   Especially when you read this stuff PRINTED IN BOLD TYPE ON THE CARDBOARD BOX after it gets so poorly done going through a machine builder's advertising and sales departments, done so very poorly it can sometimes reads like outright false advertising in motion.



Note how small the actual hardware improvements are compared to the AI boost given by the software designed to use Intel's AI functions (via Intel's Deep Link Media Encoders).

Let's not be totally negative ---- let's end this review on a hopeful note.

Ars Technica participated in a briefing at the end of the day and Ars had pressed away at the Intel representatives for more details ...... and Ars found out that honestly most gamers and casual content creators won’t see much benefit to getting a Tiger Lake + Iris Xe MAX laptop over getting one with plain old Iris Xe graphics (standard Intel on board graphics).

But that doesn’t mean there aren’t any advantages out there somewhere in this mess.  And it’s possible things could get better sometimes out in the future.



 
Back to top
 
« Last Edit: 11/06/20 at 14:36:27 by Oldfeller--FSO »  

Former Savage Owner
  IP Logged
Oldfeller--FSO
Serious Thumper
ModSquad
*****
Offline

Hobby is now
"concentrated
neuropany"

Posts: 12629
Fayetteville, NC
Gender: male
Re: AMD & others --- post AMD dominance in 202
Reply #79 - 11/06/20 at 12:21:23
 

https://www.anandtech.com/show/16214/amd-zen-3-ryzen-deep-dive-review-5950x-5...

This is a massive Anand Tech review of the first Ryzen 3 "x" processors from AMD that were promised to arrive around Nov. 5th after the Ryzen 3 processors and the "x" grade was announced in early October.  It is now Nov. 6th and the Anand Tech review is here as promised.  

The entire review is 30 web pages long and it is an exhaustive, exhaustive review to say the least (and if you are an Intel fan, the entire thing is totally, totally painful and demoralizing for you to read it all).   There is a scroll bar up at the top of each page on this review, as each set of the 30 sets of web pages covers just one of thirty topics or tests ......

So, the angry green She Hulk did catch up with Intel early on in the review and she simply wadded him up so tightly so he could fit into the standard Intel octagonal box along with a suitable brown stinky Intel Marketing crown that was freshly laid down on his bleeding scalpless skull personally by the angry green She Hulk.

As last glimpsed, "Intel inside the box" was still struggling a tiny bit, still twitching and weakly squeaking a tiny bit underneath his current stinky brown crown as She Hulk tucked the last flap of the octagonal box flap into place and then she carefully installed the little "Intel Inside" sticker seal over the now security sealed box flap of the (still dripping from the bottom) Intel octagonal container .......


Conclusion: AMD Has Indeed Ryzen To The Top

Coming out the other end of this review, it’s hard to believe the extent to which some of AMD’s performance numbers have grown in the last five years. Even within the Ryzen family, we can pinpoint the leaps and bounds by which AMD is now the market leader in pure x86 performance.

Let’s start with some headline numbers.

+19% IPC Gain is Confirmed at 24%

AMD quoted to us a raw IPC gain from Zen2 to Zen3 of +19%. AMD measured this with 25 workloads and both processors at 4.0 GHz, running DDR4-3600 memory. By comparison, we test with industry standard benchmarks at rated clock speeds and JEDEC supported memory, and we were able to accurately achieve that +19% number.



Compounding the generation-on-generation gains from a pre-Ryzen era, we’re seeing +114% IPC improvements, and if we look from the original Zen to Zen3, it is a ~41% gain.

In real world benchmarks, we saw an average +24% performance gain, showcasing both the increase in IPC and frequency uplift that the Ryzen 5000 parts have.

5.0 GHz Achieved on Ryzen

Turbo frequencies are often setup dependent, and because AMD uses a combination of listed turbo frequency and opportunistic boosting, the exact turbo frequency can be hard to nail down. For the top-tier Ryzen 9 5950X, AMD lists the turbo frequency as 4900 MHz for single core loading, however in very standard conditions, we were able to pass that to 5050 MHz. Diving deeper into the AGESA, this processor actually has a ‘maximum frequency’ setting of 5025 MHz. All of our Ryzen 5000 series processors offered +50-150 MHz above the listed turbo showcasing that these parts still have some headroom.





Overall Impressions of Zen 3 and Ryzen 5000

One of the exciting things about probing a new core is finding out all the little quirks and improvements that they don’t tell you about. It’s been interesting finding out how this core was put together, both from our findings and discussions AMD’s engineers.

Moving to an 8-core CCX for this generation was a no-brainer, with an easy up-tick in performance. However it is the changes in the execution units and load/store were a lot of the magic happens – increasing to peak 3 loads/cycle and 2 stores/cycle, splitting out some of the ALU/AGU work, finer grained transitions from decoder/op-cache to the micro-op queue, and pre-fetchers with more bandwidth all help to that. A lot of the instruction improvements, such as lower latency FMA and faster DIV/IDIV is going to scale well as we move into the enterprise and EPYC processors.

With AMD taking the performance crown in almost areas it is competing in, attention now rolls over to price. Having $300 as an entry level for this tier is going to sting a lot of users who would rather spend $200 or less – despite AMD having nine out of ten of Amazon’s best sellers, only two of those parts are $300 and up. There’s going to be an early adopters tax as well – one could argue that moving into Q1, when AMD is enabling 400-series motherboards, might be a better inception point for a lot of users.

Having said that, with Intel set to launch Rocket Lake at the end of Q1 next year with 8 cores, this sub-$300 market is going to be ripe for any AMD Zen3 APU to come in and take that price bracket.  Remember, AMD never launched Zen2 APUs into the consumer market, which might indicate a fast follow-on with Zen3.  Watch this space – a monolithic Zen3 APU is going to be exciting.

AMD Ryzen 5000 Series Processors

Ryzen 9 5950X      16c/32t      3400      4900      64 MB      105 W      $799
Ryzen 9 5900X      12c/24t      3700      4800      64 MB      105 W      $549
Ryzen 7 5800X      8c/16t      3800      4700      32 MB      105 W      $449
Ryzen 5 5600X      6c/12t      3700      4600      32 MB      65 W      $299*

All things considered, we’re really impressed with what AMD has achieved here. After the disillusionment of years of weaker generation-on-generation performance uplifts from the competition, AMD set a goal to beat the average ~7% IPC year-on-year gain. With +19% IPC on Zen3, Intel has no product to match AMD right now - not even Tiger Lake at 4.8 GHz - and Intel has lost that single-threaded crown.

AS SUCH, AMD now wins the total brand crown for GAMING and for content creation as AMD sweeps the top 4 spots before an Intel processor even gets a listing in the rankings.











Note please that AMD can easily break 5.0 ghz at only 105 watts of power, while Intel takes 140 watts or more to do the same upper level ghz speeds.

Also note that this is all done at a bog standard TSMC 7nm lithography level.  

Also note that with the brand new just breaking AMD 5nm chiplets that are currently being run off at TSMC there will be BRAND NEW WAVES OF AMD PROGRESS TO FOLLOW QUICKLY AFTER THIS ONE, each new wave lapping up significantly higher on the beach and lapping out fairly quickly too.



===================================================



Look for new ever higher AMD progress waves to hit the beach scheduled roughly every six months apart until every Intel marketing sandcastle is completely leveled and totally washed away (this will take place easily inside the next calendar year no less) .......

TO PROTECT THEIR CASTLE WALLS from scaling ladders,  Intel has added more height to the speed crenellations, raising them from 5.0 to up to 5.6 ghz tall .......  at 160 watts of power consumed and even bigger heat pipe cooling fins and fans to match.

This makes no difference to the AMD groundswell waves that are coming in, waves that plow into the Intel built castle walls down low, eroding sand from underneath their foundations, not by going over the tops of Intel's best hyper stacking over voltage efforts.
Back to top
 
« Last Edit: 11/11/20 at 15:18:44 by Oldfeller--FSO »  

Former Savage Owner
  IP Logged
Oldfeller--FSO
Serious Thumper
ModSquad
*****
Offline

Hobby is now
"concentrated
neuropany"

Posts: 12629
Fayetteville, NC
Gender: male
Re: AMD & others --- post AMD dominance in 202
Reply #80 - 11/09/20 at 17:22:35
 

http://linuxgizmos.com/risc-v-based-allwinner-chip-to-debut-on-13-linux-hacke...



Allwinner is building a <$13 hobby board using a RISC-V chipset.

Alibaba’s T-head subsidiary amd Allwinner have produced a single-core, RISC-V-based XuanTie C906 processor with MMU that will appear on a sandwich-style, Linux-driven, $12.50 Sipeed SBC due in two months.

In July, 2019, Chinese tech giant Alibaba Group surprised the industry with the most powerful RISC-V architecture SoC design to date: a 16-core, 2.5GHz XuanTie 910 (XT 910). Now Alibaba’s RISC-V-focused T-Head subsidiary is collaborating with Allwinner to introduce a single-core, 1GHz XuanTie C906 (RV64GCV) RISC-V processor designed to run Debian Linux. A Sipeed dev kit will arrive in the coming months for $12.50 that incorporates an Allwinner compute module built around the XuanTie C906.


Note:   better single board computers exist, notably the Raspberry Pi 4.0 units set the minimum acceptable end of all single board computing for all rational beings, which makes this one still a complete non-player.

This exists to show that a lot of Orientals are unhappy with USA and Britain still controlling their uses of computing.
Back to top
 
« Last Edit: 11/10/20 at 22:01:52 by Oldfeller--FSO »  

Former Savage Owner
  IP Logged
Oldfeller--FSO
Serious Thumper
ModSquad
*****
Offline

Hobby is now
"concentrated
neuropany"

Posts: 12629
Fayetteville, NC
Gender: male
Re: AMD & others --- post AMD dominance in 202
Reply #81 - 11/12/20 at 05:48:05
 



https://www.tomshardware.com/news/intel-now-content-to-match-tsmcs-process-te...


Intel Now Content To 'Match' TSMC's Process Technology
By Lucian Armasu December 10, 2019



This Bob Swan statement is a year old now, but it mostly rings in as completely true as what Intel is doing.    If it wasn't for black bag cheating, Intel HAS NO PROGRESS TO OFFER as the Intel 10nm only works with a bunch of black bag tricks and Intel 7nm doesn't work at all right now.

At a fireside chat with Credit Suisse at their 23rd annual technical conference, Intel’s CEO Bob Swan said that its 7nm process is expected to match TSMC’s 5nm process. He also noted that Intel's 5nm process is also expected to match TSMC’s 3nm process.   Neither of these things worked out, however.

What Swan didn’t mention is that Intel is no longer in the lead in terms of process technology and that its 7nm process is expected to arrive about a year or so later, in 2022, compared to TSMC’s 5nm which will produce device chips by the second half of 2020.

Intel's Recent Process Roadmap
When Intel announced the 22nm Tri-gate (FinFET) process, it was more than a generation ahead compared to TSMC and other third-party foundry competitors. For one, it was on a smaller 22nm process compared to others who were just moving to 28nm/32nm process nodes. And second, the switch to FinFET alone granted its own generational boost in performance and efficiency. Intel’s process leadership was uncontested for years after that.

The only exception was in mobile chips, where its 22nm FinFET Atom chip could barely match the latest high-end Arm chips on a 28nm planar node, and at a higher chip cost to boot. It’s why Intel eventually attempted to license the Atom design to Chinese fabless semiconductor companies so that they build their own “Atom” chips more cheaply on TSMC’s 28nm process.

However, that didn’t work out either, as few device makers were interested in making the trade-off compared to the Arm chips they’ve come to rely on for each device launch.

Intel then switched to 14nm, and that wasn’t a very smooth ride either. The company experienced some delays with Broadwell chips, which were the first to use the 14nm process. Intel also ended-up replacing the consumer Broadwell generation on the market with Skylake rather quickly.

The reason the switch to 14nm was quite bumpy, too, was because Intel set out to increase the chip density by 2.4x, which ended-up a little too difficult to implement, but the company succeeded in achieving that eventually.

However, instead of taking this lesson to heart, Intel attempted to increase the density even more aggressively with the 10nm process, by 2.7x. After years and years of delays, the company recently admitted that the goal was too aggressive for the company.

This is why for its move to 7nm EUV, Intel will scale back the density increase to 2.0x. The switch to an extreme ultraviolet (EUV) lithography process is difficult enough as it is. It’s also Intel’s first attempt to implement EUV, following in Samsung and TSMC’s footsteps.

From a Leader to a Follower?
Although the claims of Intel’s CEO are meant to reassure both customers and partners that the company is “still” as competitive as TSMC, this statement doesn’t come from a position of leadership in this aspect.

Even if what Intel claims is true and the process is indeed more or less equal performance, efficiency, and density-wise, the fact is that devices with chips made on TSMC’s 5nm process are expected to come out in the second half of 2020. Those devices will include the next-generation iPhones, too. Meanwhile, Intel has recently said that it will start launching 7nm chips sometime in 2021.

Intel has also fallen behind AMD in terms of having secure processors and firmware, going by the number of recent vulnerabilities (surpassing AMD 15:1). The company also says that it’s no longer interested in large market share, coincidentally in a time when AMD’s Zen 2 chips are expected to make the biggest dent in Intel’s sales, both in the consumer and data center markets in more than a decade.

Although none of this means Intel still isn’t in a much stronger position both brand and financially-wise compared to AMD and TSMC and that it can’t recover, it’s still a trend that doesn’t do Intel any favors and that Intel will have to reverse this trend before it’s too late.
Back to top
 
 

Former Savage Owner
  IP Logged
Oldfeller--FSO
Serious Thumper
ModSquad
*****
Offline

Hobby is now
"concentrated
neuropany"

Posts: 12629
Fayetteville, NC
Gender: male
Re: AMD & others --- post AMD dominance in 202
Reply #82 - 11/12/20 at 09:12:54
 

https://liliputing.com/2020/11/samsungs-first-5nm-chip-is-the-exynos-1080-for...


Samsung’s first 5nm chip is the Exynos 1080 for mid-range phones





The Exynos 1080 features:

1 x ARM Cortex-A78 CPU core @ 2.8 GHz
3 x ARM Cortex-A78 CPU cores @ 2.6 GHz
4 x ARM Cortex-A55 CPU cores @ 2 GHz
Mali-G78 MP10 graphics
Integrated Neural Processing Unit
Integrated 5G mode

The new Samsung Exynos 1080 processor is an octa-core processor deigned for upper mid-range smartphones, but Samsung says it will bring a 50-percent boost in single-core performance and up to a 2X improvement in multi-core performance, which could make this mid-range chip competitive with some processors designed for high-end phones and tablets.

Samsung’s new chip is also the company’s first manufactured using a 5nm EUV process.


We are looking at some significant throughput increases for Samsung 5nm chipsets ---- up to 2x multi-core and 50% for single core.

Plus wafer area savings that says each chip can have more memory and more layers and more other goodies inside, basically for no additional wafer silicon cost.   And at better yields than 7nm as well, lowering the scrap costs.

More chips per wafer and far lower scrap rates means SUBSTANTIAL COST SAVINGS to the builders, something nobody has seen for a while over there in silicon land.
Back to top
 
 

Former Savage Owner
  IP Logged
Oldfeller--FSO
Serious Thumper
ModSquad
*****
Offline

Hobby is now
"concentrated
neuropany"

Posts: 12629
Fayetteville, NC
Gender: male
Re: AMD & others --- post AMD dominance in 202
Reply #83 - 11/12/20 at 11:01:20
 

RUMOR TIME AGAIN .......


Some facts, some rumors -- all mixed together in the wok just to improve the juicy flavorful sauce .......

TSMC is building a 3.5 Billion $$$ Arizona USA facility to do high volume 5-6nm and 3-4nm lithography at up to 14 layers deep.

Apple is joining TSMC Global with a big arsed stock swap.   This is why they let the ARM deal go on past them to NVIDIA.

Intel is going to be the largest customer of the Arizona facility, even larger volume-wise than Apple and AMD added together.

Even MediaTek has neural processors hidden inside their most current designs.

3x-5x upticks in overall processing speed will come some from the lithography shrinks going down to 5nm and the rest of general progress will mostly come from AI integrations.

Microsoft needs to use Linux to utilize these new ARM features and speed levels, existing MS product lines simply can't run that stuff at full speed as MS is too tied down to the x86 past to take in all the changes.
Back to top
 
« Last Edit: 11/17/20 at 19:18:12 by Oldfeller--FSO »  

Former Savage Owner
  IP Logged
Oldfeller--FSO
Serious Thumper
ModSquad
*****
Offline

Hobby is now
"concentrated
neuropany"

Posts: 12629
Fayetteville, NC
Gender: male
Re: AMD & others --- post AMD dominance in 202
Reply #84 - 11/17/20 at 11:30:44
 

https://liliputing.com/2020/11/apple-mac-with-m1-chip-review-roundup-blazing-...

5m Apple M1 chip devices are shipping now for the holidays, and they are SIMPLY BETTER in the light laptop range than x86 based laptop chipsets from either Intel or from AMD.   Not in all cases, nor in all particulars, but M1 is better in the sub-40 watt range than x86, generally speaking.    For the first shot out of Apple's gun, this is a compelling first entry as Apple's first home grown chipset cleanly hits the mark it was aimed at.

To say it totally guts Intel Tiger Lake is an understatement ......

Apple will then build them some bigger and stronger chipsets for desktop uses, count on it.

Out of the gate, AMD and Intel are being humbled by this processor.   This will prompt a fast response from AMD, but Intel has no new bullets ready to load in any weapon that they have built out already .....  (sad but true, Intel will be mostly silent for the next year in this conflict)

Intel cannot count on their "Intel BS Black Hat Marketing Games" with AI to work against Apple as Apple has totally OS integrated all such stuff already and is currently sitting on an 11 TRILLION Operations per Second built in AI Neural Engine that has Apple Standards based support already built into all of Apple's softwares.  

AI is expected by the phone boys, it is not a "secret weapon" of any kind ....

The ARM based phone boys will shoot back sooner and more effectively than Intel can in this new laptop conflict range.







Here are some of the many many first reviews of Apple’s new Macs with M1 chips:

Macbook Air with M1
Business Insider
CNBC
CNN
Engadget
Fast Company
iMore
Gizmodo
Laptop
MacWorld
Mashable
TechCrunch
Tom’s Hardware
The Verge
Wired
WSJ

MacBook Pro with M1
Laptop
MacWorld
MKBHD (YouTube)
Pocket Lint
TechCrunch
The Verge
WSJ

Mac Mini with M1
AnandTech
TechCrunch
The Verge
General M1 reviews
Ars Technica
Six Colors

AnandTech’s Mac Mini review also has a deep dive into some of the chip details that Apple hasn’t publicly disclosed. For example, the Apple M1 processor’s four high-performance “Firestorm” CPU cores seem to be clocked at 3.2 GHz, which is a little higher than the 3 GHz speed of the Apple A14 chip used in the latest iPhones and iPads.

Power consumption seems to range from 4.2 watts at idle to about 27 watts under heavy workload. So power consumption is roughly similar to what you’d expect from a computer with a 20-24 watt TDP, as measured by other chip makers.



===================================================



But there are a few other good reasons Apple building its own ARM based chips could be good for the PC market more generally.

First, it could spur other chip makers including Intel, AMD, Qualcomm, and MediaTek to up their game. Second, it could give companies like Google and Microsoft a reason to try developing their own chips in-house to very tightly integrate hardware and software as Apple has just done.

And third? It gives developers of popular applications a reason to port their software to run natively on devices with ARM-based processors.


Any of these happening is a blow to Intel, make no mistake about it.   The age of "Intel on x86 total dominance" is jest about over.    

Intel will become relatively a smaller and smaller player with many many new competitors constantly popping up and egging each other on continuously, starting right now. today.
Back to top
 
« Last Edit: 11/23/20 at 07:37:36 by Oldfeller--FSO »  

Former Savage Owner
  IP Logged
Oldfeller--FSO
Serious Thumper
ModSquad
*****
Offline

Hobby is now
"concentrated
neuropany"

Posts: 12629
Fayetteville, NC
Gender: male
Re: AMD & others --- post AMD dominance in 202
Reply #85 - 11/18/20 at 18:19:48
 

https://liliputing.com/2020/11/lilbits-porting-apps-to-arm.html


Rapid progress adapting software to use the Apple M1 Chipset and all of its capabilities.

Apple has published AI specifications to use the 11 trillion operations per second Neural Processor that is part of all M1 chipsets.

This isn't a secret and it isn't the Black Ops thing like Intel is trying to do it.   As such, the future belongs to Apple's relatively open system of calls and requirements.  

Being relatively open, Apple puts pressure on Intel to come in out of their Black Ops secrecy and to publish what their AI requires out of an OS or out of an individual software program to actually use the AI boosts that are in the Intel processors and the large number of associated daughterboard chipsets.

Until this happens, Intel customers are paying a significant price bump to buy a complex daughter board mounted AI system that right now only Intel can utilize for certain benchmark tests ........

The list of companies jumping on the Apple Silicon bandwagon is growing. Google just released a version of Chrome for Apple’s new computers with M1 processors, and Mozilla is developing a version of Firefox that will support the new chips as well.

Meanwhile, Adobe’s recent move to release a beta version of Photoshop for both macOS Big Sur devices with Apple M1 chips and Windows on ARM has had an unintended side effect – at least one developer who has loaded Windows 10 onto an old Microsoft Lumia smartphone can now run Photoshop on a phone.

Google releases Apple Silicon-optimized version of Chrome for Mac
Google releases a new version of Chrome for macOS that’s optimized for the Apple Silicon chips in the new MacBook Air, MacBook pro, and Mac Mini.
Pre-release Firefox for Apple Silicon [Mozilla]
And Mozilla is working on a version of Firefox that will do the same.

Tab throttling and more performance improvements in Chrome 87 [Chromium Blog]
Chrome 87 will actively manage your browser tab resource usage to balance performance and power usage – extending battery life while maintaining responsiveness. Back/forward cache will also improve page load speeds when you hit the back or forward button.
Google Pay reimagined: pay, save, manage expenses and more [Google]
Google unveils new Google Pay for Android and iOS (US-only at first), with money management/insights features, support for person-to-person, group, and business payments and collections, and more. Plex mobile-first bank accounts are coming next year.

Meet the Microsoft Pluton processor – The security chip designed for the future of Windows PCs [Microsoft]
Microsoft introduces Pluton security processor. It will eventually replace TPM in upcoming PCs with AMD, Intel, and Qualcomm chips, offers protection from speculative execution attacks, and can receive updates through Windows Update.

Huawei to sell Honor brand to consortium of agents and dealers in bid to save its supply chain [Reuters]
Huawei’s been under pressure due to US trade sanctions that have limited the company’s ability to acquire components for its devices. It’s unclear whether this new ownership structure will help the Honor sub-brand at all
Purism’s Librem 5 Linux smartphone is now shipping [Linux Smartphones]
Three years after announcing plans to build a Linux smartphone with an emphasis on free and open source software, privacy, and security, Purism is now starting to ship the mass production version of the Librem 5 to customers.



Photoshop on a Lumia phone running Windows on ARM [@imbushuo]
Not only does Photoshop now run on Mac and Windows computers with ARM-based processors… but folks who have shoehorned Windows on ARM onto phones for some reason or other can try using it on those too.
Also, screen rotation is now working on that Lumia phone with Windows on ARM [@imbushuo]

Speaking of running Windows 10 on phones, now it looks like you can do that and easily switch between portrait and landscape.


https://www.codeweavers.com/blog/jwhite/2020/11/18/okay-im-on-the-bandwagon-a...

This is the Code Weavers guy burbling in Apple-speak that he's got it working already.

Okay, I'm on the bandwagon - Apple Silicon is officially cool
by Jeremy White

The new Apple Silicon-based Macs have dropped and the reviews are very positive. They've delivered faster machines that use less power, and they run CrossOver 20 brilliantly!

We have a range of the new systems on order. But we got impatient and discovered that our local Best Buy had the cheapest Macbook Air in stock, so we bought it and loaded CrossOver 20.0.2 onto it.

We also installed the beta version of Big Sur 11.1, because we know it has some critical fixes to Rosetta. After we did that, we were able to fire up CrossOver and install and run a wide range of Windows applications. We got Quicken to work:

the desktop version of Among Us, where you can actually use your mouse,

and we were even able to have a satisfying session of Team Fortress 2:

That's incredible when you consider that we're on literally the cheapest Apple Silicon device you can buy - one that gets thermally throttled and is missing a GPU core.

I can't tell you how cool that is; there is so much emulation going on under the covers. Imagine - a 32-bit Windows Intel binary, running in a 32-to-64 bridge in Wine / CrossOver on top of macOS, on an ARM CPU that is emulating x86 - and it works! This is just so cool.

Now it isn't perfect; Team Fortress 2 showed some lag. I think we've got some work to do on that front.

But I can't get Brian to stop playing Witcher 3...

Cheers,

Jeremy
Back to top
 
« Last Edit: 11/23/20 at 04:54:17 by Oldfeller--FSO »  

Former Savage Owner
  IP Logged
Oldfeller--FSO
Serious Thumper
ModSquad
*****
Offline

Hobby is now
"concentrated
neuropany"

Posts: 12629
Fayetteville, NC
Gender: male
Re: AMD & others --- post AMD dominance in 202
Reply #86 - 11/21/20 at 21:35:40
 

https://youtu.be/xNNTXd85VXo      This quick video review is worth watching.


OK, same-same model comparison showing that the state of art Intel processor Mac can't keep up on any head to head test against the much lower current draw M1 Apple Mac.  

The Intel based Mac gets HOT, blows a whole lot of hot fan air ..... and the cool running M1 Apple Mac does not even kick its fan on,  even though it is noticeably faster getting the tests done (and yes, it is emulating to do that on some of the tests, but it is emulating quicker than Intel can even run naturally).

"The fans have not kicked on once with the M1 Mac during this entire test series"


===================================================


I would say AMD needs to change its focus away from Intel and focus on their real competition, which is the AI equipped (11 trillion ops per second neural processing) ARM based computer chipsets.  

Yes, with the Apple M1 Mac simply being the first of these ARM 5nm chipsets to ship to the buying public that is complete with a decent neural processor.   ARM has all this stuff sitting there ready to license and trust me, the phone boys will buy into it.

Focusing anything on Intel is wasting precious development dollars and critical development time as Intel is doing ABSOLUTELY NOTHING meaningful right now, completely zero progress and pursuing totally zero real world wins.

Lastly, on the subject of AI and all the neural processor stuff, Apple does it very very well, much much better than Intel can.  

Next, the larger "outside of Apple" software world already has all the neural libraries and AI drivers and files and support stuff already out there to make their Apple related products sing right along, whereas Intel is having a very hard time even getting started outside of Intel itself.

(it is very tough to keep all the lies and BS secret games going if others are involved  ......)

Back to top
 
« Last Edit: 11/27/20 at 19:49:17 by Oldfeller--FSO »  

Former Savage Owner
  IP Logged
Oldfeller--FSO
Serious Thumper
ModSquad
*****
Offline

Hobby is now
"concentrated
neuropany"

Posts: 12629
Fayetteville, NC
Gender: male
Re: AMD & others --- post AMD dominance in 202
Reply #87 - 11/24/20 at 00:51:01
 

https://www.ftc.gov/sites/default/files/documents/cases/091216intelcmpt.pdf

In 2009 Intel was enjoined by the FCC specifically to not do the things that Intel is currently doing again, big time.

Trump's administration may have turned a blind eye to this activity by defunding the FCC, but Biden's administration is likely not to ignore Intel's activities any further.

If you open the pdf and read it, it is EXACTLY what Intel is up to all over again .....
Back to top
 
« Last Edit: 11/28/20 at 06:26:37 by Oldfeller--FSO »  

Former Savage Owner
  IP Logged
Oldfeller--FSO
Serious Thumper
ModSquad
*****
Offline

Hobby is now
"concentrated
neuropany"

Posts: 12629
Fayetteville, NC
Gender: male
Re: AMD & others --- post AMD dominance in 202
Reply #88 - 11/24/20 at 13:41:45
 

Intel busted a gut recently, lying profusely to set themselves up as the ultimate benchmark for "gaming performance"

Now, everyone else is now using Intel to prove they are better than "x86 as was in the past" and by golly they ACTUALLY MEAN it this time around  .......  and they can prove it by like to like same model comparisons.   Intel blows a lot of hot air around, and performs poorly compared to the new stuff from AMD and APPLE.


===================================================


Intel is now trying to brag that they made up the specs for a 10 core Intel processor (but they were unable to get their first runs to work right as Intel had to laser off several non-functional cores in testing) thus making up some dodgy poorly performing 8 core chipsets with some odd chipset designations.   The successful ones that came out as 10 core chipsets didn't perform one whit better than the dodgy 8 core cut downs, and actually didn't do much better than their 6 core predecessors.

Faced with ever increasing post sorting scrap rates, Intel would have to make up a 14 core layout to yield 10-12 "meets spec" cores, or else they will do the standard old style Intel reaction plan yet again, which is to jack the final spec limits wide open so that everything "passes" Intel final test bench inspection as it is is.   LOOK FOR THE OLD "YOU CAN'T DO ANYTHING TO TEST BENCH THE PERFORMANCE SPECS ON YOUR OWN INDIVIDUAL CHIPSET" MISLEADING INTEL BULLSHITE TO GET TROTTED OUT AGAIN TO COVER INTEL'S DECISION TO SHIP OUT THEIR IN-PROCESS SCRAP ON TO THEIR END USERS.


===================================================


Look to see AMD to make themselves up a separate neural chiplet, large, powerful, distinct and easily produced by the wafer load.   Look to see the AMD APU "all on the same chip silicon" go away at 5nm and smaller, as using AMD's chiplet construction methods means FAR LESS SCRAP and waste are created at each new generation time.

Look to see other chipset manufacturers start to copy the chiplet idea, as it leads to faster six month generation cycles with significant improvement levels at each level.
Back to top
 
« Last Edit: 11/28/20 at 06:29:09 by Oldfeller--FSO »  

Former Savage Owner
  IP Logged
Oldfeller--FSO
Serious Thumper
ModSquad
*****
Offline

Hobby is now
"concentrated
neuropany"

Posts: 12629
Fayetteville, NC
Gender: male
Re: AMD & others --- post AMD dominance in 202
Reply #89 - 11/26/20 at 14:22:55
 

https://www.cnx-software.com/2020/11/26/rockchip-rk3588-specifications-reveal...

Rockchip RK3588 specifications revealed – 8K video, 6 TOPS NPU, PCIe 3.0, up to 32GB RAM

Rockchip RK3588 is one of the most anticipated processors for the year on this side of the Internet with the octa-core processor features four Cortex-A76 cores, four Cortex-A55 cores, an NPU, and 8K video decoding support.

The roadmap shows an expected launch date in Q3/Q4 2020, but sadly the release date will be pushed back in the future. Having said that, the Rockchip Developer Conference (RKDC) is now taking place, and the company has put up a poster that reveals a bit more about the processor.

Rockchip RK3588 specifications

That means we now have some more detailed Rockchip RK3588 specifications available now.

CPU – 4x Cortex-A76 and 4x Cortex-A55 cores in dynamIQ configuration
GPU – Arm Mali “Odin” MP4 GPU
AI Accelerator – 6 TOPS NPU 3.0 (Neural Processing Unit)
VPU – 8Kp60 video decoding support, 8Kp30 encoding support
Memory I/F – LPDDR4x/LPDDR5 up to 32GB
Storage – eMMC 5.1, SDIO, SATA 3.0 (multiplexed with PCIe 2.0)
Video Output
Dual HDMI 2.1 / eDP up to 8Kp60 or 4Kp120
Dual DisplayPort up to 4Kp60
Dual MIPI DSI output
Up to four independent displays
Camera – 48M (2x 24M) ISP with HDR and 3D NR support; multi-camera input
Audio – Microphone array support
Networking – Dual Gigabit Ethernet
USB – 2x USB 3.1 Type-C, 2x USB 2.0
PCIe – 4-lane PCIe 3.0, and 3x PCIe 2.0 (multiplexed with SATA)
Manufacturing process – 8nm LP
RK3588 Rockchip-Developer Conference 2020

The company will provide support for Android, Linux, and a “domestic OS”. We should note that the GPU has changed from “Natt” family to “Odin” family. Rockchip is unable to disclose the GPU name as it’s a new GPU family that has yet to be announced by ARM. We were informed that Rockchip designed its own NPU IP for RK3588, and did not use a third-party design like VeriSilicon NPU IP.  

Rockchip will likely eventually adopt whichever NPU IP vendor winds up the winner out of the first 3-4 candidates out here at this time.   Not enough is in use to call out a "best vendor" at this point in time.

RK3588 specifications are pretty impressive, and the processor will be found in Arm computers, smart displays, edge computing & AIoT solutions, Arm servers, high-performance tablets, network video recorders, virtual reality headsets, and applications requiring multiple cameras and displays. We should however note that RK3588 sadly lacks UFS support, and relies on the slower eMMC 5.1 flash interface for storage. The launch is now scheduled for Q2/Q3 2021.



Rockchip represents the typical low end ARM SOC lapping up into something that can easily run a chromebook, a Linux laptop or an "intensive use" tablet with keyboard.

This also acts to raise the performance bar for Mediatek's low end processors, a general low end competitive move upwards which is always a good thing.   See this Mediatek roll up to show up in AMAZON Fire Tablets next year.

Notice that ARM provides the designs of neural processing units (AI cores) which all of these chipsets now incorporate as Android provides for this use model (and has for 5 years now).   All of the phone boys have neural processors and use the newer smaller lithography cores available to them now as well as pre-proven out canned computer processor layouts direct from ARM that they can have build in volume at TSMC.

What Intel struggles to incorporate now is NOT NEW --- the PC people are all playing catch up to the phone boys on ARM technology uses yet again.

AI gives full multiples of better software performance but only where it is fully implemented in the surrounding larger software world.

AI will be important in the next few years as hardware increases are now down to the <20% level per generation, a situation which says the big bang for the buck comes from the 6 to 11 trillion instructions per second neural processors, not the standard lithography shrinks.

AMD is behind in this AI race, and is playing catch up going forward.   AMD has arguably the best AI partner out of the lot for their AI partner.



===================================================



https://liliputing.com/2020/11/lilbits-windows-on-apple-silicon-android-apps-...

Apple Silicon is fast.  Macs with Apple M1 chips outperform just about every other Tiger Lake laptop on the market by >20% in most benchmarks, while still consuming less power. Even Mac apps that were designed to run on x86 chips run faster on the new Macs than they do on equivalent models with Intel processors.

But what if you want to run a different operating system? Apple’s Craig Federighi recently told Ars Technica that it’s up to Microsoft to decide whether to support Apple’s new hardware. Previous-gen Macs with Intel processors had a feature called Boot Camp which allowed users to install Windows on their Apple computers and dual boot, choosing which operating system to run at launch.


Right now Apple M1 has a slamming lead over any laptop chipset out there.   Ranking runs Apple M1 up by 25% to either AMD or Intel.   Intel has NOTHING in the pipeline for the next 1 1/2 years while AMD can put out a competitive laptop product as soon as TSMC runs their lots of chipsets.

There will be 1-2 Apple vs AMD bouts before the ARM phone boys begin selling their 8 core A-78c product, which may bump past AMD for a short period of time.

Then the entire match up becomes "who can implement their AI better and cover more of their general software space" while doing so.    Apple has the advantage here as they have already put their support out there and ENFORCED all of Apple software space to switch over to it.

Back to top
 
« Last Edit: 12/01/20 at 02:48:50 by Oldfeller--FSO »  

Former Savage Owner
  IP Logged
Pages: 1 ... 4 5 6 7 8 ... 21
Send Topic Print


« Home

 
« Home
SuzukiSavage.com
03/29/24 at 08:53:30



General CategoryThe Cafe › AMD & others --- Intel dominance in 2022


SuzukiSavage.com » Powered by YaBB 2.2!
YaBB © 2000-2007. All Rights Reserved.