Overclock.net › Forums › AMD › AMD CPUs › The Bulldozer Blog is Live
New Posts  All Forums:Forum Nav:

The Bulldozer Blog is Live - Page 36  

post #351 of 10602
I really want Bulldozer to succeed. But i find myself constantly going back and forth between belief and disbelief.

AMD's reluctance to give anything away is disheartening, what could Intel do with the knowledge anyway? It's too late to change sandy Bridge / Ivy bridge, and Intel will know all in a couple of months for future designs (not that i think Intel will be copying AMD) anyway.

I do believe AMD is losing a lot of customers to Sandy Bridge, a loss that could be stemmed if customers had something to believe in.
Purpleannex
(15 items)
 
  
CPUMotherboardGraphicsRAM
i5 2500k Z68 Extreme4gen3 Gainward GTX 470 @ 740Mhz 8GB Mushkin Blackline LV (2x4GB) DDR3 1600MHz 9... 
Hard DriveHard DriveHard DriveOptical Drive
128GB Crucial M225 SSD 2 x 500gb 500GbB samsung 500GbB samsung Samsung SH-B083L 8x BD Combo 
OSMonitorPowerCase
Windows 7 64-bit LG W2486L LED 24" 1080p Antech True power new 750W FT-02 B-W 
  hide details  
Purpleannex
(15 items)
 
  
CPUMotherboardGraphicsRAM
i5 2500k Z68 Extreme4gen3 Gainward GTX 470 @ 740Mhz 8GB Mushkin Blackline LV (2x4GB) DDR3 1600MHz 9... 
Hard DriveHard DriveHard DriveOptical Drive
128GB Crucial M225 SSD 2 x 500gb 500GbB samsung 500GbB samsung Samsung SH-B083L 8x BD Combo 
OSMonitorPowerCase
Windows 7 64-bit LG W2486L LED 24" 1080p Antech True power new 750W FT-02 B-W 
  hide details  
post #352 of 10602
Quote:
Originally Posted by JF-AMD View Post
Yes, of course I know the server performance.

But the client performance is different because things have been optimized for client workloads, so their performance profile will be different from ours.

We look at throughput, they look at speed. It is a very different world.
Do you see the game changing at the server level? Let's say Intel is able to get 33+33 gain (78%) optimally and 33+20 pessimistically (60%), that leaves AMD a little behind in the performance race either way. Now, the question becomes one of yields and manufacturing costs; can you comment on whether it's going to be easier to make a Bulldozer vs. a Sandy Bridge?

It seems quite important even to us clients, as server profits would filter back into research and lead to better products for us.
post #353 of 10602
Thread Starter 
Quote:
Originally Posted by purpleannex View Post
I really want Bulldozer to succeed. But i find myself constantly going back and forth between belief and disbelief.

AMD's reluctance to give anything away is disheartening, what could Intel do with the knowledge anyway? It's too late to change sandy Bridge / Ivy bridge, and Intel will know all in a couple of months for future designs (not that i think Intel will be copying AMD) anyway.

I do believe AMD is losing a lot of customers to Sandy Bridge, a loss that could be stemmed if customers had something to believe in.
This is pretty standard not only with our launches, but also our competitors' launches. There were no official sandybridge benchmarks until their launch.

While you believe we are losing customers to sandybridge, others may feel differently.

I have been in this business for about 20 years and I can tell you that the position that AMD is in relative to the launch dates of our product and our competitor has been played out hundreds of times, we all understand the challenges.


Quote:
Originally Posted by lonewolf371 View Post
Do you see the game changing at the server level? Let's say Intel is able to get 33+33 gain (78%) optimally and 33+20 pessimistically (60%), that leaves AMD a little behind in the performance race either way. Now, the question becomes one of yields and manufacturing costs; can you comment on whether it's going to be easier to make a Bulldozer vs. a Sandy Bridge?

It seems quite important even to us clients, as server profits would filter back into research and lead to better products for us.
OK, let's look at your assumption.

When intel went from 4 cores to 6 cores with westmere, they increased core count by 50% and increased performance by ~33%.

We have seen on the client side ~10-15% increase in performance.

Sandybridge will have 33% more cores.

If you take the old scaling (33% performance on 50% core increase) you can assume that adding 2 more cores gets them ~22% increase.

Today they are 5% behind AMD in spec int rate (x5680 vs. 6176 SE). So they have a deficit of 5%, but they get ~22% for more cores and ~15% for architecture improvments.

That comes out to ~ 32% greater than our EXISTING products, right? But bulldozer will be ~50% greater than our existing products, which nets ~18% performance advantage for AMD.

I have no idea where you are getting the 60-78% performance increases, those numbers just aren't real.

Mine probably aren't right, but at least they are built on two known factors (how thier cores have traditionally scaled in their architecture and the sandybridge scaling that they just delivered.)
post #354 of 10602
I am stoked and waiting. I am ready for an update to my gear now. My aging 940 is starting to show now. I can barely get it to 3.4 Ghz, and it still fails prime95. 3 cores are defective and are getting localized heating now. Let's see what Bulldozer can do.
My System
(16 items)
 
  
CPUMotherboardGraphicsRAM
PH2 1090T Gigabyte 990FXA-UD3 Sapphire Dirt 3 6950 (have 2, but moved to a si... Samsung 30NM  
Hard DriveHard DriveHard DriveOptical Drive
180 Gb intel 330 series ssd (Windows and Programs) 750Gb Western Digital Caviar Black (Shtuff) 1Tb Hitachi Deskstar (Music, Movies, Videos) Cheap dvdrw 
CoolingOSMonitorPower
Rasa RS360 kit Windows 7 Ultimate 64bit 27 " Yamakasi 2560x1440 Rose will SilentNight 
Case
Corsair graphite 600T 
  hide details  
My System
(16 items)
 
  
CPUMotherboardGraphicsRAM
PH2 1090T Gigabyte 990FXA-UD3 Sapphire Dirt 3 6950 (have 2, but moved to a si... Samsung 30NM  
Hard DriveHard DriveHard DriveOptical Drive
180 Gb intel 330 series ssd (Windows and Programs) 750Gb Western Digital Caviar Black (Shtuff) 1Tb Hitachi Deskstar (Music, Movies, Videos) Cheap dvdrw 
CoolingOSMonitorPower
Rasa RS360 kit Windows 7 Ultimate 64bit 27 " Yamakasi 2560x1440 Rose will SilentNight 
Case
Corsair graphite 600T 
  hide details  
post #355 of 10602
JF-AMD i think you need to make a thread and get it stickied.

Rumors V Fact

In the past three days i think i can quote you five times saying those are Inaccurate numbers or something.


Quote:
Originally Posted by JF-AMD View Post
I have no idea where you are getting the 60-78% performance increases, those numbers just aren't real.
Quote:
Originally Posted by JF-AMD View Post
Don't start doing that 12% math again, it is not right. When the product is out, you will understand why.

Quote:
Originally Posted by JF-AMD View Post
This is not true.
(Well i got 3) But still. Considering you only post 4~5 times a day its a lot.
Edited by StuffStuff1 - 1/8/11 at 7:24pm
Full Of Stuff
(15 items)
 
The nEEEtBook
(13 items)
 
CPUMotherboardGraphicsRAM
AMD Phenom II 1100t X6 MSI 990XA-GD55 GTX 465 SLI Mushkin Ridge Back 
Hard DriveHard DriveOptical DriveCooling
OCZ Agility 3 Seagate 7200.12 Sony 18X DVD-ROM 48X CD-ROM SATA DVD-ROM Drive Scythe MUGEN-2 SCMG-2000 
OSMonitorKeyboardPower
Windows 7 Ultimate Planar SA2311W 3D Monitor Microsoft Keyboard PC Performance & Cooling Silencer 750W 
CaseMouseAudio
Cooler Master HAF 912 [Window Mod] OCZ BEHEMOTH Laser Mouse Realtek 5.1 Onboard 
CPUMotherboardGraphicsRAM
Intel Atom N270 AsusTek 1005HA Mobile Intel 945 Express 1GB DDR2 
Hard DriveOSMonitorKeyboard
OCZ Vertex 2 (Upgrade) Windows 7 Starter 10.1" Wide screen LED Lit Display Full Keyboard 
PowerCaseMouse
40W 19V Asus Adapter 1005HA Case Trackpad 
  hide details  
Full Of Stuff
(15 items)
 
The nEEEtBook
(13 items)
 
CPUMotherboardGraphicsRAM
AMD Phenom II 1100t X6 MSI 990XA-GD55 GTX 465 SLI Mushkin Ridge Back 
Hard DriveHard DriveOptical DriveCooling
OCZ Agility 3 Seagate 7200.12 Sony 18X DVD-ROM 48X CD-ROM SATA DVD-ROM Drive Scythe MUGEN-2 SCMG-2000 
OSMonitorKeyboardPower
Windows 7 Ultimate Planar SA2311W 3D Monitor Microsoft Keyboard PC Performance & Cooling Silencer 750W 
CaseMouseAudio
Cooler Master HAF 912 [Window Mod] OCZ BEHEMOTH Laser Mouse Realtek 5.1 Onboard 
CPUMotherboardGraphicsRAM
Intel Atom N270 AsusTek 1005HA Mobile Intel 945 Express 1GB DDR2 
Hard DriveOSMonitorKeyboard
OCZ Vertex 2 (Upgrade) Windows 7 Starter 10.1" Wide screen LED Lit Display Full Keyboard 
PowerCaseMouse
40W 19V Asus Adapter 1005HA Case Trackpad 
  hide details  
post #356 of 10602
Quote:
Originally Posted by JF-AMD View Post
OK, let's look at your assumption.

When intel went from 4 cores to 6 cores with westmere, they increased core count by 50% and increased performance by ~33%.

We have seen on the client side ~10-15% increase in performance.

Sandybridge will have 33% more cores.

If you take the old scaling (33% performance on 50% core increase) you can assume that adding 2 more cores gets them ~22% increase.

Today they are 5% behind AMD in spec int rate (x5680 vs. 6176 SE). So they have a deficit of 5%, but they get ~22% for more cores and ~15% for architecture improvments.

That comes out to ~ 32% greater than our EXISTING products, right? But bulldozer will be ~50% greater than our existing products, which nets ~18% performance advantage for AMD.

I have no idea where you are getting the 60-78% performance increases, those numbers just aren't real.

Mine probably aren't right, but at least they are built on two known factors (how thier cores have traditionally scaled in their architecture and the sandybridge scaling that they just delivered.)
I see what you mean. I got mine from this post:

Quote:
Originally Posted by JF-AMD View Post
I am in the server world, so my comments reflect servers. Take a look at MC vs. westmere today, in integer we are ~5% faster, in FP we are ~20% faster.

When they added 2 more cores to nehalem (50% more cores) they received ~33% more performance (average of FP and int). So natural scaling says that 2 more cores to SB later this year should net no more than 33% more performance, right? (straight math would say in the low 20% range, but there are other factors)

Now if I am ahead today, and I expect to get 50% more performance w/BD, where does that leave me relative to SB?

The reality is that until we actually have benchmarks and parts for both, nobody really knows for sure.
But I didn't actually consider the number of cores they were adding. My numbers required adding 50% more cores in each architecture upgrade (not used to some of the lingo), which is why they are so far off. So, long story short, you see AMD coming out ahead on the server end of things going into this summer? That's nice to hear. Hopefully you guys won't run into any manufacturing issues once demand starts to ramp up.

On a side note: if AMD has a performance advantage, how does AMD get the world to stop running on Xeons?
Edited by lonewolf371 - 1/8/11 at 8:45pm
post #357 of 10602
Thread Starter 
Well, until all parts are out, actual performance is still a question mark.

From a manufacturing standpoint client production starts first, so by the time we hit production there should be a huge number of wafers already run through the fab.
post #358 of 10602
do you think maybe bulldozer isnt as cracked up as its ment to be thats why amd is keeping it shh shh for so long, instead of leaking info of a weaker competitor..maybe? i dunno
7up
(12 items)
 
  
CPUMotherboardGraphicsGraphics
i7 4790k @ 4.7 ghz 1.275v HERO 7 GTX 780 1200Mhz @ 1.2v  GTX 780 1200Mhz @ 1.2v 
RAMHard DriveHard DriveMonitor
16GB XTREEM LV 2600Mhz C10 840 PRO 256GB Samsung 1TB F3 Asus ROG swift PG278Q 27'' 144Hz 
PowerCaseAudio
CORSAIR AX1200i Corsair 760T BLACK Asus Essence STX 
  hide details  
7up
(12 items)
 
  
CPUMotherboardGraphicsGraphics
i7 4790k @ 4.7 ghz 1.275v HERO 7 GTX 780 1200Mhz @ 1.2v  GTX 780 1200Mhz @ 1.2v 
RAMHard DriveHard DriveMonitor
16GB XTREEM LV 2600Mhz C10 840 PRO 256GB Samsung 1TB F3 Asus ROG swift PG278Q 27'' 144Hz 
PowerCaseAudio
CORSAIR AX1200i Corsair 760T BLACK Asus Essence STX 
  hide details  
post #359 of 10602
Thread Starter 
Quote:
Originally Posted by Asus11 View Post
do you think maybe bulldozer isnt as cracked up as its ment to be thats why amd is keeping it shh shh for so long, instead of leaking info of a weaker competitor..maybe? i dunno
Actually our communications cadence is usually a lot lower than this. We have been far more vocal about bulldozer than any other product that I have worked on in the last 4.5 years. Normally the comment is "we don't comment on unannounced products", evne up to the day before the launch.

If you look at how much we have blogged, how much detail we have shared, and compare it to previous launches, under your assumption we must think bulldozer will be huge.

Please note that intel didn't provide an official sandybridge benchmark until the day of the launch. What we are doing is no different and standard in the industry.
post #360 of 10602
has anybody heard anything about overclocking on these guys? really looking forward to testing them out when they come out
My System
(15 items)
 
  
CPUMotherboardGraphicsRAM
I5 2500K AsRock extreme4 p67 GTX 470 SLI 8gb Gskill 
Hard DriveOSMonitorKeyboard
Crucial 128gb,WD black 1tb, Seagate 500gb windows 7 64 bit Enterprise U2311H Razor 
PowerCaseAudioAudio
Antec HCP 1200 Corsair 800D xonar DX M-Audio BX5a 
  hide details  
My System
(15 items)
 
  
CPUMotherboardGraphicsRAM
I5 2500K AsRock extreme4 p67 GTX 470 SLI 8gb Gskill 
Hard DriveOSMonitorKeyboard
Crucial 128gb,WD black 1tb, Seagate 500gb windows 7 64 bit Enterprise U2311H Razor 
PowerCaseAudioAudio
Antec HCP 1200 Corsair 800D xonar DX M-Audio BX5a 
  hide details  
New Posts  All Forums:Forum Nav:
  Return Home
  Back to Forum: AMD CPUs
This thread is locked  
Overclock.net › Forums › AMD › AMD CPUs › The Bulldozer Blog is Live