Personal computing discussed

Search found 1755 matches

  • 1
  • 2
  • 3
  • 4
  • 5
  • 59
by chuckula
Wed Jun 20, 2018 2:58 pm
Forum: Processors
Topic: 16/0 True cores 1% faster then 16/32threads. Threadripper
Replies: 5
Views: 348

Re: 16/0 True cores 1% faster then 16/32threads. Threadripper

(only 10-11 cores used, no point going for that 32 core threadripper) :( That's when you start thinking about running two encoding jobs in parallel (if that's possible to do) and then figure out if it's actually a benefit to overall performance by using more cores or if it's actually harming perfor...
by chuckula
Tue Jun 19, 2018 7:58 am
Forum: Processors
Topic: Intel sweepstakes starts today!!
Replies: 16
Views: 833

Re: Intel sweepstakes starts today!!

Whodathunk that AMD wouldn't be in a position to give away 8086 processors, let alone the 65,391,482 you ask for =P Some of us actually want AMD to go above & beyond here! But I'll settle for AMD giving one Threadripper 1950X to each 8086K winner regardless of where that winner lives and withou...
by chuckula
Tue Jun 19, 2018 6:41 am
Forum: Processors
Topic: Intel sweepstakes starts today!!
Replies: 16
Views: 833

Re: Intel sweepstakes starts today!!

Great chance to win a 1950.... How refreshing. Disingenuous sniping from a bitter loser. Incidentally, AMD is only giving away 40 of those 1950X parts and only in the U.S. which shows just how confident they are that they'll have takers. In other words: Not really confident at all. Wake me up when ...
by chuckula
Sat Jun 16, 2018 7:39 pm
Forum: The Back Porch
Topic: Happy Father's Day Weekend
Replies: 8
Views: 1042

Re: Happy Father's Day Weekend

Very Cool!

I'm getting to grill and given how hot the weather here is I might just throw the chicken outside and let the sun do the job.
by chuckula
Fri Jun 15, 2018 8:57 am
Forum: Graphics
Topic: Nvidia Turing GTX1180 Rumors
Replies: 26
Views: 2166

Re: Nvidia Turing GTX1180 Rumors

End User wrote:
I'll believe it when I see it.

My GTX 1080 is in dire need of an upgrade. :(

Nvidia can afford to wait as they are the performance king.


May I suggest THIS UPGRADE.
by chuckula
Thu Jun 14, 2018 7:43 am
Forum: Graphics
Topic: Interesting Radeon scuttlebut...
Replies: 2
Views: 317

Re: Interesting Radeon scuttlebut...

Designing a product for a particular customer can be good if that customer is ordering enough product to make it worthwhile. Frankly I'm not sure if Apple turned out to be a big enough consumer of Vega parts to make it worthwhile considering there are Vega GPUs in only one line of rather expensive d...
by chuckula
Tue Jun 12, 2018 4:07 pm
Forum: Processors
Topic: Intel ARM -- I mean MIPS -- Chip CONFIRMED!
Replies: 18
Views: 856

Re: Intel ARM -- I mean MIPS -- Chip CONFIRMED!

derFunkenstein wrote:
Oh, sorry. Their first re-entry to the discrete market. The first RajaChip.


I'm still waiting for the press conference where they announce that the product based on the super-secret "RajaChip" codename will be named.... wait for it..... RajaChip!

#VegaStillStunsMe
by chuckula
Tue Jun 12, 2018 3:29 pm
Forum: Processors
Topic: Intel ARM -- I mean MIPS -- Chip CONFIRMED!
Replies: 18
Views: 856

Re: Intel ARM -- I mean MIPS -- Chip CONFIRMED!

While we're talking about things that Intel has confirmed, they've also confirmed the first discrete graphics products will hit in 2020: https://www.marketwatch.com/story/intel-makes-it-a-three-way-race-with-amd-and-nvidia-on-graphics-chips-2018-06-12 First there was the i740! Then there was Larrab...
by chuckula
Tue Jun 12, 2018 1:41 pm
Forum: Processors
Topic: i9 Skylake-X XCC speculation
Replies: 22
Views: 953

Re: i9 Skylake-X XCC speculation

I highly doubt that Intel is going attempt to cram a Skylake-X XCC die in a Socket 2066 package. It is cheaper and easier for them to rebrand Xeon Platnium/Gold "rejects" and let motherboard vendors deal with hassle of making customer-tier LGA3647 boards. It is essentially what AMD does w...
by chuckula
Tue Jun 12, 2018 9:28 am
Forum: Processors
Topic: i9 Skylake-X XCC speculation
Replies: 22
Views: 953

Re: i9 Skylake-X XCC speculation

Isn't AVX-512 the new hotness? I mean, as a competitive advantage. Why would Intel disable it? I'd be majorly disappointed if Intel turned off AVX-512 in HEDT parts. But go take a look at TR's benchmark suite and see what (if any) benchmarks can even try to use AVX-512 whatsoever [even inefficientl...
by chuckula
Tue Jun 12, 2018 7:48 am
Forum: Processors
Topic: Intel ARM -- I mean MIPS -- Chip CONFIRMED!
Replies: 18
Views: 856

Re: Intel ARM -- I mean MIPS -- Chip CONFIRMED!

Chuckaluphagus wrote:
Ok, I'm chuckling here, but seriously: do you need a hobby?


In this case, I actually used "CONFIRMED" accurately! That's my hobby!
by chuckula
Tue Jun 12, 2018 7:47 am
Forum: Processors
Topic: i9 Skylake-X XCC speculation
Replies: 22
Views: 953

Re: i9 Skylake-X XCC speculation

Incidentally, the newest unfounded speculation is that these parts will completely disable AVX-512 support. As for the package, it's certainly possible for Intel to push LGA-3647 into the HEDT market, but I did an estimate and there's roughly 1400mm^2 of space under the heatspreader on an LGA-2066 (...
by chuckula
Tue Jun 12, 2018 7:36 am
Forum: Processors
Topic: Intel ARM -- I mean MIPS -- Chip CONFIRMED!
Replies: 18
Views: 856

Intel ARM -- I mean MIPS -- Chip CONFIRMED!

Looks like those dinosaurs at Intel finally realized the asteroid is coming for them!
Behold the Intel MIPS interAptiv SoC GRX500 family.

Given the complete failure of its x86 product line and inability to manufacture real chips, Intel sees MIPS as the way forward.

THANKS ARM!
by chuckula
Sat Jun 09, 2018 11:10 am
Forum: Processors
Topic: i9 Skylake-X XCC speculation
Replies: 22
Views: 953

Re: i9 Skylake-X XCC speculation

I'd be surprised if it boots successfully! Krogoth said: Here is what I suspect it will end-up being based what we already know about Purely platform. While the demo system used was a Purley motherboard I wouldn't be surprised if the commercial product ends up on the LGA-2011 platform. The same chip...
by chuckula
Fri Jun 08, 2018 11:43 pm
Forum: Processors
Topic: Intel's 28-core HEDT part was overclocked - CONFIRMED
Replies: 8
Views: 482

Re: Intel's 28-core HEDT part was overclocked - CONFIRMED

Maybe some people were so happy to see intel come out with an amd slayer that they suspended their belief in physics. Why does Intel need an "AMD Slayer" Last time I checked AMD needs to double its core count to try to overtake Intel's 2017 model that beats it in Blender in both performan...
by chuckula
Fri Jun 08, 2018 7:08 pm
Forum: Processors
Topic: Intel's 28-core HEDT part was overclocked - CONFIRMED
Replies: 8
Views: 482

Re: Intel's 28-core HEDT part was overclocked - CONFIRMED

You can't use that word! That's OUR word!

Having said that... maybe a few people didn't think the chip was overclocked but nobody ever thought it was 10nm so it's great Anand dispelled rumors that didn't exist in the first place. #TheyNeverConfirmedItWasn'tReallyThreadripperInDisguise
by chuckula
Fri Jun 08, 2018 2:15 pm
Forum: General Hardware
Topic: Oak Ridge flops 200 Quadrillion times a second
Replies: 17
Views: 726

Re: Oak Ridge flops 200 Quadrillion times a second

Can't be any good, those 43 TFLOP servers with only 25 GB/s bandwidth to fabric are clearly going to be bandwidth starved at 142 MB/s out-of-box bandwidth per CPU thread, I think the designers forgot about scaling :wink: Very funny but something tells me those Voltas wouldn't be so fast if you took...
by chuckula
Fri Jun 08, 2018 1:32 pm
Forum: General Hardware
Topic: Oak Ridge flops 200 Quadrillion times a second
Replies: 17
Views: 726

Re: Oak Ridge flops 200 Quadrillion times a second

Was wondering why Oak Ridge gets the big iron. Then I realized; less radiation induced errors that close to sea level. Actually Oak Ridge was the cite of Uranium enrichment and nuclear weapons manufacturing back in the day, although I know that the manufacturing process isn't supposed to release mu...
by chuckula
Fri Jun 08, 2018 1:06 pm
Forum: General Hardware
Topic: Oak Ridge flops 200 Quadrillion times a second
Replies: 17
Views: 726

Oak Ridge flops 200 Quadrillion times a second

The top 500 list is publishing soon and there's a new #1: https://ornl.gov/news/ornl-launches-summit-supercomputer Oak Ridge dropped some coin to get 4,608 Power9 CPU nodes that each have 6 (count-em 6) Volta V100 cards to push 200 Petaflops. The article also talks about how the system can get 3.3 E...
by chuckula
Fri Jun 08, 2018 10:50 am
Forum: Processors
Topic: 16 core CPUs with a single RAM channel are AWESOME
Replies: 38
Views: 1657

Re: 16 core CPUs with a single RAM channel are AWESOME

Ok, to simplify Topinio's wall-o-text that doesn't get the very easy to understand premise: Some workloads which are CPU-bound and not memory-bound will perform better when CPUs with more performance come along; some workloads which are memory-bound and not CPU-bound won't. This should be obvious, a...
by chuckula
Thu Jun 07, 2018 9:34 pm
Forum: The Back Porch
Topic: What are you listening to RIGHT NOW?
Replies: 3832
Views: 555326

Re: What are you listening to RIGHT NOW?

JustAnEngineer wrote:
The Outfield - Your Love


Drunk.
At a Karaoke Bar.
by chuckula
Thu Jun 07, 2018 9:08 pm
Forum: Processors
Topic: 16 core CPUs with a single RAM channel are AWESOME
Replies: 38
Views: 1657

Re: 16 core CPUs with a single RAM channel are AWESOME

I don't see how this helps, or what the problem is here? What you seem to argue, which to me seems weird to get into it over, is that these bandwidths being equivalent to 3.2 GB/s and 4.3 GB/s per core if all cores are trying to do RAM RW at the same time is a Big Problem . But if you want to apply...
by chuckula
Thu Jun 07, 2018 7:12 pm
Forum: Processors
Topic: 16 core CPUs with a single RAM channel are AWESOME
Replies: 38
Views: 1657

Re: 16 core CPUs with a single RAM channel are AWESOME

HBM2 sounds interesting but in its current incarnations it's great for GPUs (high bandwidth) but not so great for CPUs (too much latency even if there is a lot of bandwidth). HBM/HBM2 are pretty comparable for latency...and they are both measurably faster than DRAM due to various factors (proximity...
by chuckula
Thu Jun 07, 2018 2:49 pm
Forum: The Back Porch
Topic: Nasa to make Major Martian Announcement
Replies: 17
Views: 631

Re: Nasa to make Major Martian Announcement

K-L-Waster wrote:
All these spurious suggestions.

They found Waldo, of course. Duh...


And here I thought it was all those missing socks.
by chuckula
Thu Jun 07, 2018 12:25 pm
Forum: The Back Porch
Topic: Nasa to make Major Martian Announcement
Replies: 17
Views: 631

Nasa to make Major Martian Announcement

Read all about it here . Catch the live-stream here [Bonus! Will I.Am is on before the Mars stuff! And now you know why they have to pay the Russians to put people in orbit]. And no, it probably isn't aliens. My guess is something about finding water erosion that confirms Mars once had flowing river...
by chuckula
Thu Jun 07, 2018 9:44 am
Forum: Processors
Topic: 16 core CPUs with a single RAM channel are AWESOME
Replies: 38
Views: 1657

Re: 16 core CPUs with a single RAM channel are AWESOME

I don't see how this helps, or what the problem is here? Has anyone made a 16C CPU with a single-channel memory controller? I guess there are server builds where someone has put in only 1 DIMM, and there are workloads where that could be awesome as well as cost-effective (but probably not in the bi...
by chuckula
Thu Jun 07, 2018 8:15 am
Forum: Processors
Topic: One memory channel per die THANK YOU AMD!
Replies: 35
Views: 1255

Re: One memory channel per die THANK YOU AMD!

So, you continue to reckon you'll see that thing launch as a part with 5GHz on 28C as a default turbo option? Where did I say that a stock-clocked HEDT chip would be running an all-core 5GHz Turbo with no overclocking? I think your koolaid drinking has gone to your head. Maybe you should go back to...
by chuckula
Thu Jun 07, 2018 7:08 am
Forum: Processors
Topic: One memory channel per die THANK YOU AMD!
Replies: 35
Views: 1255

Re: One memory channel per die THANK YOU AMD!

Its vapourware Chuck. Vapourware. Same as the critical thinking portion of your nugget! Good, then since you are such a cocky little teenager you'll have no problem coughing up the money to buy me one this year since they clearly won't be on sale and you won't go bankrupt. I'm sure these chips are ...
by chuckula
Wed Jun 06, 2018 8:20 pm
Forum: Processors
Topic: 16 core CPUs with a single RAM channel are AWESOME
Replies: 38
Views: 1657

Re: 16 core CPUs with a single RAM channel are AWESOME

this topic doesn't seem very serious either Oh, it's deadly serious assuming Lisa Su didn't flat-out lie at the end of AMD's webcast yesterday. Which, unlike the AMD fansquad around here, I actually watched live. People tend to forget that I take technology, but not myself, seriously. The story com...
by chuckula
Wed Jun 06, 2018 8:01 pm
Forum: Processors
Topic: 16 core CPUs with a single RAM channel are AWESOME
Replies: 38
Views: 1657

Re: 16 core CPUs with a single RAM channel are AWESOME

Mikael33 wrote:
How do I downvote this?


You can't. But I do note that you don't have an argument as to why it's wrong, so you really should be asking why you can't downvote reality.
  • 1
  • 2
  • 3
  • 4
  • 5
  • 59