Addlink S70 1TB NVMe M.2 SSD review
G.Skill KM360 Keyboard Review
Promo: VIP-SCDKey Games and Windows 10 / Office
Alphacool EISBAER Ex BLACK LCS review
Netgear Nighthawk AX12 Wi-Fi 6 router review
Corsair HS60 PRO Surround Headset Review
MSI Radeon RX 5700 Gaming X review
Team Group Cardea II NVMe 1 TB SSD Review
ASRock X570 Phantom Gaming ITX/TB3 review
Promo: URCDKey Autumn Sale Windows 10 Pro for $11
Lisa Su confirms Q3 launch for Ryzen, Epyc and NAVI
On an Annual Stockholders Meeting yesterday AMDs Lisa Su reconfirmed Q3 for Ryzen 3rd gen, Epyc Rome and NAVI. Q3 means from July to September. That's what, the second or third confirmation?
So once again we see a confirmation for the products to be released pretty soon, which would be the second half of this year is going to be busy with three separate product launches. AMD will soon come up with more details likely on the Computex keynote, after which there will be a "Next Horizon Gaming" live stream during the E3 gaming conference on 10 June. The products themselves will then released and on the shelves after July at the earliest.
Ryzen 7 2700X 50th Anniversary Edition Gets Laser Inscription With Lisa Su Signature - 04/25/2019 07:57 AM
In an earlier post, we already shared that AMD is preparing for the festivities of their celebration 50th anniversary beginning with a Ryzen 2700x 50th-anniversary edition to be released on or around ...
AMD President and CEO Dr. Lisa Su to Deliver COMPUTEX 2019 CEO Keynote - 04/02/2019 08:24 AM
Taiwan External Trade Development Council (TAITRA) announced today that the 2019 COMPUTEX International Press Conference will be held with a Keynote by AMD President and CEO Dr. Lisa Su. ...
Watch the AMD CES 2019 Event & CEO Dr. Lisa Su Keynote Here - 01/09/2019 06:24 PM
AMD will host a keynote presentation at CES with CEO Lisa Su, several new products are expected to be announced. We expect processor-centric products in the desktop and mobile segment, as well as log...
CES 2019: Lisa Su of Advanced Micro Devices (Interview) - 01/09/2019 09:26 AM
An interesting interview was posted by Furtune Magazine who interviewed AMDs CEO, Lisa Su. In the interview, Su talks about Spectre and Meltdown vulnerabilities that have been a "wake up c...
AMD CEO Lisa Su promises to be competitive again in high-end GPUs - 11/02/2018 10:41 AM
Things are a rough for AMDs Radeon design team, talented employees walked over towards Intel leaving quite a bit of worry in the GPU front, especially the high-end segment. We know a die shrink 7nm VE...
Fox2232
Senior Member
Posts: 9738
Joined: 2012-07-20
Senior Member
Posts: 9738
Joined: 2012-07-20
#5670349 Posted on: 05/17/2019 04:02 PM
That's baseless. AMD can't really add more transistors to GCN because only way to do it is to make CUs beefier. (As they can't put more than 64CUs there due to design limits in logic.)
If GCN could have 96CUs, they would just decrease clock by 10%, reduce voltage appropriately to lower max clock and be at same power draw as now. And it would still be smaller GPU than nVidia's counterpart that it would compete with while having much better compute than it already has.
(Here you can say that AMD made unbelievably shortsighted choice. Their 1st GCN chip already had 32CUs, that's 1/2 of maximum.)
You continue to miss the point. My point this entire time is that AMD can't add more transistors. It's design is too inefficient. That is AMD's entire problem. That is why AMD is so far behind.
That's baseless. AMD can't really add more transistors to GCN because only way to do it is to make CUs beefier. (As they can't put more than 64CUs there due to design limits in logic.)
If GCN could have 96CUs, they would just decrease clock by 10%, reduce voltage appropriately to lower max clock and be at same power draw as now. And it would still be smaller GPU than nVidia's counterpart that it would compete with while having much better compute than it already has.
(Here you can say that AMD made unbelievably shortsighted choice. Their 1st GCN chip already had 32CUs, that's 1/2 of maximum.)
ttnuagmada
Senior Member
Posts: 121
Joined: 2015-05-18
Senior Member
Posts: 121
Joined: 2015-05-18
#5670353 Posted on: 05/17/2019 04:07 PM
That's baseless. AMD can't really add more transistors to GCN because only way to do it is to make CUs beefier. (As they can't put more than 64CUs there due to design limits in logic.)
If GCN could have 96CUs, they would just decrease clock by 10%, reduce voltage appropriately to lower max clock and be at same power draw as now. And it would still be smaller GPU than nVidia's counterpart that it would compete with while having much better compute than it already has.
(Here you can say that AMD made unbelievably shortsighted choice. Their 1st GCN chip already had 32CUs, that's 1/2 of maximum.)
I'm afraid it doesn't work that way, as a quick glance at any perf/watt chart from a techpowerup review will clearly show you. AMD would need 400w at a minimum to make exactly what you described.
That's baseless. AMD can't really add more transistors to GCN because only way to do it is to make CUs beefier. (As they can't put more than 64CUs there due to design limits in logic.)
If GCN could have 96CUs, they would just decrease clock by 10%, reduce voltage appropriately to lower max clock and be at same power draw as now. And it would still be smaller GPU than nVidia's counterpart that it would compete with while having much better compute than it already has.
(Here you can say that AMD made unbelievably shortsighted choice. Their 1st GCN chip already had 32CUs, that's 1/2 of maximum.)
I'm afraid it doesn't work that way, as a quick glance at any perf/watt chart from a techpowerup review will clearly show you. AMD would need 400w at a minimum to make exactly what you described.
Fox2232
Senior Member
Posts: 9738
Joined: 2012-07-20
Senior Member
Posts: 9738
Joined: 2012-07-20
#5670358 Posted on: 05/17/2019 04:23 PM
Same way as any other AMD's GPU being sold at unreasonably clock and voltage.
According to TPU database Fury nano is just 10% slower (1080p) than Fury X while Nano has 175W TDP and tiny cooler and Fury X has 300W TDP and integrated liquid cooling.
Same way as I was able to reduce power draw of any AMD's GCN card by good 25~30% with minimal performance loss or gain if I tuned memory timings and clock.
Sacrificing clock and reduced voltage will get you very far. Have you ever seen AMD's Zen based APUs with Vega iGPU? Looks like you did not. Kind of funny if you look at their performance at 15/35/65/95W. There's really not that big of an difference.
I'm afraid it doesn't work that way, as a quick glance at any perf/watt chart from a techpowerup review will clearly show you. AMD would need 400w at a minimum to make exactly what you described.
Same way as any other AMD's GPU being sold at unreasonably clock and voltage.
According to TPU database Fury nano is just 10% slower (1080p) than Fury X while Nano has 175W TDP and tiny cooler and Fury X has 300W TDP and integrated liquid cooling.
Same way as I was able to reduce power draw of any AMD's GCN card by good 25~30% with minimal performance loss or gain if I tuned memory timings and clock.
Sacrificing clock and reduced voltage will get you very far. Have you ever seen AMD's Zen based APUs with Vega iGPU? Looks like you did not. Kind of funny if you look at their performance at 15/35/65/95W. There's really not that big of an difference.
ttnuagmada
Senior Member
Posts: 121
Joined: 2015-05-18
Senior Member
Posts: 121
Joined: 2015-05-18
#5670361 Posted on: 05/17/2019 04:44 PM
Same way as any other AMD's GPU being sold at unreasonably clock and voltage.
According to TPU database Fury nano is just 10% slower (1080p) than Fury X while Nano has 175W TDP and tiny cooler and Fury X has 300W TDP and integrated liquid cooling.
Same way as I was able to reduce power draw of any AMD's GCN card by good 25~30% with minimal performance loss or gain if I tuned memory timings and clock.
Sacrificing clock and reduced voltage will get you very far. Have you ever seen AMD's Zen based APUs with Vega iGPU? Looks like you did not. Kind of funny if you look at their performance at 15/35/65/95W. There's really not that big of an difference.
Ahh, of course, the ol "undervolting is an AMD only feature" argument. ignoring the fact that literally all semiconductors behave the same way, and that the reason they all mostly run at higher volts than they need, is because there are always a few that can't. AMD owners are just obsessed with it due to their dumpster tier efficiency at stock settings. Both of my 1080ti's will do 1800mhz at 800mv. Undervolting is not AMD specific.
Same way as any other AMD's GPU being sold at unreasonably clock and voltage.
According to TPU database Fury nano is just 10% slower (1080p) than Fury X while Nano has 175W TDP and tiny cooler and Fury X has 300W TDP and integrated liquid cooling.
Same way as I was able to reduce power draw of any AMD's GCN card by good 25~30% with minimal performance loss or gain if I tuned memory timings and clock.
Sacrificing clock and reduced voltage will get you very far. Have you ever seen AMD's Zen based APUs with Vega iGPU? Looks like you did not. Kind of funny if you look at their performance at 15/35/65/95W. There's really not that big of an difference.
Ahh, of course, the ol "undervolting is an AMD only feature" argument. ignoring the fact that literally all semiconductors behave the same way, and that the reason they all mostly run at higher volts than they need, is because there are always a few that can't. AMD owners are just obsessed with it due to their dumpster tier efficiency at stock settings. Both of my 1080ti's will do 1800mhz at 800mv. Undervolting is not AMD specific.
vbetts
Moderator
Posts: 14686
Joined: 2006-07-04
Moderator
Posts: 14686
Joined: 2006-07-04
#5670363 Posted on: 05/17/2019 04:53 PM
Although to be fair, compared to how much AMD cards ship with a higher voltages than needed compared to Nvidia is quite high to the point where if you have an AMD gpu you almost have to tune the voltage for it to be reasonable. Nvidia cards out the box IMO at least have reasonable voltages where you do not need to tune them at all.
Not sure how undervolting is on Turing, but at least with cards like the Radeon VII can be undervolted to be competitive in power draw compared to the competition.
Ahh, of course, the ol "undervolting is an AMD only feature" argument. ignoring the fact that literally all semiconductors behave the same way, and that the reason they all mostly run at higher volts than they need, is because there are always a few that can't. AMD owners are just obsessed with it due to their dumpster tier efficiency at stock settings. Both of my 1080ti's will do 1800mhz at 800mv. Undervolting is not AMD specific.
Although to be fair, compared to how much AMD cards ship with a higher voltages than needed compared to Nvidia is quite high to the point where if you have an AMD gpu you almost have to tune the voltage for it to be reasonable. Nvidia cards out the box IMO at least have reasonable voltages where you do not need to tune them at all.
Not sure how undervolting is on Turing, but at least with cards like the Radeon VII can be undervolted to be competitive in power draw compared to the competition.
Fox2232
Senior Member
Posts: 9738
Joined: 2012-07-20
Senior Member
Posts: 9738
Joined: 2012-07-20
#5670364 Posted on: 05/17/2019 04:56 PM
After making such post, I would have think that you already know voltage requirements and current increase for reaching last 5~10% of achievable clock. So, why it is so hard for you to understand that actual downclock of 10% on GPU which can't be really overclocked more than 5% yields quite different results than undervolting nVidia's GPU which can be OCed by 15% or more.
Ahh, of course, the ol "undervolting is an AMD only feature" argument. ignoring the fact that literally all semiconductors behave the same way, and that the reason they all mostly run at higher volts than they need, is because there are always a few that can't. AMD owners are just obsessed with it due to their dumpster tier efficiency at stock settings. Both of my 1080ti's will do 1800mhz at 800mv. Undervolting is not AMD specific.
After making such post, I would have think that you already know voltage requirements and current increase for reaching last 5~10% of achievable clock. So, why it is so hard for you to understand that actual downclock of 10% on GPU which can't be really overclocked more than 5% yields quite different results than undervolting nVidia's GPU which can be OCed by 15% or more.
Click here to post a comment for this news story on the message forum.
Senior Member
Posts: 121
Joined: 2015-05-18
You continue to miss the point. My point this entire time is that AMD can't add more transistors. It's design is too inefficient. That is AMD's entire problem. That is why AMD is so far behind.