Overclock.net › Forums › AMD › AMD CPUs › Don't trust those leaked benchmarks too much.
New Posts  All Forums:Forum Nav:

Don't trust those leaked benchmarks too much. - Page 7  

post #61 of 130
@radaja: could you please post the link to those quotes .... i know you quoted the guy who makes the hardwarecanucks review ... but did you quote someone else in the lot that we could take in context for ourself ??
My System
(13 items)
 
  
CPUMotherboardGraphicsRAM
FX 8120 Asus crosshair V formula 2 msi HD6870 Twin Frozr II CORSAIR Vengeance 8GB 
Hard DriveOptical DriveOSMonitor
2 SAMSUNG F4 2TB boot + 4 WD 2TB storage Lite On blu ray player win 7 sp1 oem Asus VH236H @ 1920 x 1080 
KeyboardPowerCaseMouse
logitech Media Elite Keyboard ENERMAX MAXREVO 1350W psu SILVERSTONE RAVEN RV02B-EW Matte black logitech OEM 
  hide details  
My System
(13 items)
 
  
CPUMotherboardGraphicsRAM
FX 8120 Asus crosshair V formula 2 msi HD6870 Twin Frozr II CORSAIR Vengeance 8GB 
Hard DriveOptical DriveOSMonitor
2 SAMSUNG F4 2TB boot + 4 WD 2TB storage Lite On blu ray player win 7 sp1 oem Asus VH236H @ 1920 x 1080 
KeyboardPowerCaseMouse
logitech Media Elite Keyboard ENERMAX MAXREVO 1350W psu SILVERSTONE RAVEN RV02B-EW Matte black logitech OEM 
  hide details  
post #62 of 130
I am still waiting for the official release to see how well BD works. In my mind, i cant see how AMD would make a chip that performs worse then Phenom II's. it just dosnt make sense. I am hoping that these chips are somehow not seeing full use by older bios or something. If not, ill be the first to say im wrong, but then again, ill have a chip that performs better then BD so ill be happy saying it and not need to upgrade yet lol.
post #63 of 130
Quote:
Originally Posted by Phantom123 View Post
They wouldn't go through all the trouble of rewriting and updating the kernal for both Microsoft AND Linux if it was 3%. It has to be at least 10%.
No, it does not.

It is 3%, but don't take my word for it, take the person who actually wrote the patch.

http://article.gmane.org/gmane.linux.kernel/1172226
Quote:
From: Borislav Petkov <bp <at> amd64.org>
Subject: Re: [PATCH] x86, AMD: Correct F15h IC aliasing issue
Newsgroups: gmane.linux.kernel
Date: 2011-07-27 16:42:57 GMT (10 weeks, 4 days, 23 hours and 47 minutes ago)

On Wed, Jul 27, 2011 at 11:57:45AM -0400, Avi Kivity wrote:
> Out of curiosity, what's the performance impact if the workaround is
> not enabled?

Up to 3% for a CPU-intensive style benchmark, and it can vary highly in
a microbenchmark depending on workload and compiler.

--
Regards/Gruss,
Boris.

Advanced Micro Devices GmbH
Einsteinring 24, 85609 Dornach
GM: Alberto Bozzo
Reg: Dornach, Landkreis Muenchen
HRB Nr. 43632 WEEE Registernr: 129 19551
This also isn't a 3% increase across the board, it is for SELECTIVE things.
My System
(13 items)
 
  
CPUMotherboardRAMPower
Phenom II x2 (unlocked to X4) TA890FXE 4 x G.Skill 8GB F3-12800CL9D-4GBRL Corsair 750w 
  hide details  
My System
(13 items)
 
  
CPUMotherboardRAMPower
Phenom II x2 (unlocked to X4) TA890FXE 4 x G.Skill 8GB F3-12800CL9D-4GBRL Corsair 750w 
  hide details  
post #64 of 130
I just cant believe a company would do a product that's worse than the previous one.

It has to be at least better then phenom II, i dont expect 50% better but at least 5% better per core better.

Whats the sense in making something worse than you already have and price it higher???

I waiting for a good and trusted review website i know to make my decisions.
post #65 of 130
Quote:
Originally Posted by Obakemono View Post
I have high expectations of BD, but I'm not going to run off into the Intel sunset because of some benches that are not official. I will buy BD because I want to. I could care less about benches as long as I get my monies worth out of the product I buy. What AMD has done with processors has turned the industry on it's ear and I think many are simply afraid of change. That is why there have been so many battles over the definition of the "core vs module" in numerous forums. What I loath is the Intel fanboys that insist on crashing anything related to BD or AMD for that fact because in their minds they "think" they bought the best product but are having doubts about said purchase. Posters that post just to troll knowing that what they are doing only charges the forum further are complete idiots that have no respect for anything.

It's not over until the NDA lifts. PERIOD!!!!!!!!!!
i agree with some of what you said,but not all.i too will buy BD regardless of how it performs,mainly because i think its going to be fun to OC and thats all i do with hardware,so my view is i never really care what benchmarks say.i buy from both camps because i love OCing new hardware,hell i also go back and forth between generations,like one week i might buy a i7-920 setup to play with and then sell it and grab a E8400+EP45-UD3P because its a fun Ocing platform,then sell it and grab an i7-870 or a Phenom II and then sell it and grab a REX and E8600 or do a total downgrade due to money and use a Phenom 9650 like i had a few months ago. the past two years i must have gone through at least 20 cpus and and maybe 10- 15 platforms.so my perspective isnt like someone who upgrade once or twice every two years.and i am 100% confident that BD will sell very well and benchers at HWbot will make good use of these and be very popular,no mater how BD performs.
plus if the price is under $250 for all FX cpu's,average user will buy no mater what

but as to the intel fanboys in BD threads,i do think they can be annoying,but i also think blind AMD defenders are too.it takes two to tango and destroy threads,do you know what i mean
Quote:
Originally Posted by Fr0sty View Post
@radaja: could you please post the link to those quotes .... i know you quoted the guy who makes the hardwarecanucks review ... but did you quote someone else in the lot that we could take in context for ourself ??
i PMed you

Quote:
Originally Posted by Erick View Post
I just cant believe a company would do a product that's worse than the previous one.
It has to be at least better then phenom II, i dont expect 50% better but at least 5% better per core better.
Whats the sense in making something worse than you already have and price it higher???
I waiting for a good and trusted review website i know to make my decisions.
well im sure if it turns out to be true AMD didnt do it on purpose,think about how difficult it is to do a new uarch and then look at how hard it is to do a node shrink,AMD did both at the same time a new innovated uarch on an unmature 32nm process,add gatefirst and you can imaginge how easy unknown problem might arise,even intel avoids this because its just so risky.if problems did arise then AMD would have to make the best of it and still release BD.the good news if this is a new uarch that AMD can build upon and tweak and make better,something they couldnt do with the last gen,it was on its last legs in terms of improvements
Edited by radaja - 10/10/11 at 9:49am
    
CPUMotherboardGraphicsRAM
AMD A6-3650 8.32GHz so close Gigabyte A75M-UD2H sapphire HD3450 2x2GB DDR3-1600 
Hard DriveOptical DriveOSMonitor
western digital 320GB ASUS DRW-24B1ST DVD Microsoft Windows 7 Ultimate x64 ASUS LED 23.6" MS246H 
PowerCase
Corsair 400W cardboard box w/lots of holes for fans 
  hide details  
    
CPUMotherboardGraphicsRAM
AMD A6-3650 8.32GHz so close Gigabyte A75M-UD2H sapphire HD3450 2x2GB DDR3-1600 
Hard DriveOptical DriveOSMonitor
western digital 320GB ASUS DRW-24B1ST DVD Microsoft Windows 7 Ultimate x64 ASUS LED 23.6" MS246H 
PowerCase
Corsair 400W cardboard box w/lots of holes for fans 
  hide details  
post #66 of 130
All that I am looking for is a good "price to performance to power usage" for a new folding machine.

my i7 920 is killing me $ wise at the end of the month, so I stopped folding the last two months. :-(

Anyone else with me? Or am I crazy?
post #67 of 130
Quote:
Originally Posted by Dan17z View Post
All that I am looking for is a good "price to performance to power usage" for a new folding machine.

my i7 920 is killing me $ wise at the end of the month, so I stopped folding the last two months. :-(

Anyone else with me? Or am I crazy?
It seems that BD systems will require more juice than what their old AM3 boards used.
Maybe they will come out with a version that uses less power sometime in the future.
My System
(13 items)
 
  
CPUMotherboardRAMPower
Phenom II x2 (unlocked to X4) TA890FXE 4 x G.Skill 8GB F3-12800CL9D-4GBRL Corsair 750w 
  hide details  
My System
(13 items)
 
  
CPUMotherboardRAMPower
Phenom II x2 (unlocked to X4) TA890FXE 4 x G.Skill 8GB F3-12800CL9D-4GBRL Corsair 750w 
  hide details  
post #68 of 130
Quote:
Originally Posted by radaja View Post
well im sure if it turns out to be true AMD didnt do it on purpose,think about how difficult it is to do a new uarch and then look at how hard it is to do a node shrink,AMD did both at the same time a new innovated uarch on an unmature 32nm process,add gatefirst and you can imaginge how easy unknown problem might arise,even intel avoids this because its just so risky.if problems did arise then AMD would have to make the best of it and still release BD.the good news if this is a new uarch that AMD can build upon and tweak and make better,something they couldnt do with the last gen,it was on its last legs in terms of improvements
I sure hope after some tweaks its better than it seems right now, from what i have read about the architecture it seems to pretty innovative, and it can really shiny.

Let's hope it happens.
post #69 of 130
Big surprise coming. That's my intuition. Only time will tell.
    
CPUMotherboardGraphicsRAM
INTEL ASUS XFX  SAMSUNG 
Hard DriveOptical DriveCoolingOS
WD/ST LG KUHLER WINDOWS 
MonitorKeyboardPowerCase
LG/SAMSUNG IBM MODEL M CORSAIR THERMALTAKE 
MouseMouse PadAudio
MS INTELLIMOUSE EXPLORER 3.0 REGULAR LARGE PAD ONBOARD but it USED TO BE A XONAR DG  
  hide details  
    
CPUMotherboardGraphicsRAM
INTEL ASUS XFX  SAMSUNG 
Hard DriveOptical DriveCoolingOS
WD/ST LG KUHLER WINDOWS 
MonitorKeyboardPowerCase
LG/SAMSUNG IBM MODEL M CORSAIR THERMALTAKE 
MouseMouse PadAudio
MS INTELLIMOUSE EXPLORER 3.0 REGULAR LARGE PAD ONBOARD but it USED TO BE A XONAR DG  
  hide details  
post #70 of 130
Quote:
Originally Posted by Obakemono View Post
I have high expectations of BD, but I'm not going to run off into the Intel sunset because of some benches that are not official. I will buy BD because I want to. I could care less about benches as long as I get my monies worth out of the product I buy. What AMD has done with processors has turned the industry on it's ear and I think many are simply afraid of change. That is why there have been so many battles over the definition of the "core vs module" in numerous forums. What I loath is the Intel fanboys that insist on crashing anything related to BD or AMD for that fact because in their minds they "think" they bought the best product but are having doubts about said purchase. Posters that post just to troll knowing that what they are doing only charges the forum further are complete idiots that have no respect for anything.

It's not over until the NDA lifts. PERIOD!!!!!!!!!!
^^this.
Quote:
Originally Posted by KobaltRock View Post
No, it does not.

It is 3%, but don't take my word for it, take the person who actually wrote the patch.

http://article.gmane.org/gmane.linux.kernel/1172226

Quote:
From: Borislav Petkov <bp <at> amd64.org>
Subject: Re: [PATCH] x86, AMD: Correct F15h IC aliasing issue
Newsgroups: gmane.linux.kernel
Date: 2011-07-27 16:42:57 GMT (10 weeks, 4 days, 23 hours and 47 minutes ago)

On Wed, Jul 27, 2011 at 11:57:45AM -0400, Avi Kivity wrote:
> Out of curiosity, what's the performance impact if the workaround is
> not enabled?

Up to 3% for a CPU-intensive style benchmark, and it can vary highly in
a microbenchmark depending on workload and compiler
.

--
Regards/Gruss,
Boris.

Advanced Micro Devices GmbH
Einsteinring 24, 85609 Dornach
GM: Alberto Bozzo
Reg: Dornach, Landkreis Muenchen
HRB Nr. 43632 WEEE Registernr: 129 19551
This also isn't a 3% increase across the board, it is for SELECTIVE things.
Exactly. For the longest time, Intel's have performed "better" simply due to the compiler used. It's not that the competing CPU's were slower, it's that the programs tested were optimized for and by intel's compiler. And they were also artificially programmed to stifle competitors products to make them perform worse.
Black Box
(16 items)
 
  
CPUMotherboardGraphicsRAM
i7 3770k Asus P8Z77-Vpro Evga 780 Classified Crucial Ballistix 
Hard DriveHard DriveOptical DriveCooling
A-Data 128GB SSD Samsung Spinpoint F3 1TB Pioneer BDR-207DBK Corsair H80 
OSMonitorKeyboardPower
Win 7 pro 64 Hannspree 25" 1080p LCD 2ms Razer Lycosa PC Power & Cooling 760w 
CaseMouseMouse PadAudio
Corsair 550D MX 518 Allsop Creative XFi Xtreme music 
  hide details  
Black Box
(16 items)
 
  
CPUMotherboardGraphicsRAM
i7 3770k Asus P8Z77-Vpro Evga 780 Classified Crucial Ballistix 
Hard DriveHard DriveOptical DriveCooling
A-Data 128GB SSD Samsung Spinpoint F3 1TB Pioneer BDR-207DBK Corsair H80 
OSMonitorKeyboardPower
Win 7 pro 64 Hannspree 25" 1080p LCD 2ms Razer Lycosa PC Power & Cooling 760w 
CaseMouseMouse PadAudio
Corsair 550D MX 518 Allsop Creative XFi Xtreme music 
  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 › Don't trust those leaked benchmarks too much.