Overclock.net › Forums › Industry News › Hardware News › [AMD] Get Your Rig Ready for the AMD FX Processor
New Posts  All Forums:Forum Nav:

[AMD] Get Your Rig Ready for the AMD FX Processor - Page 24

post #231 of 401
Quote:
Originally Posted by Arni90 View Post
So what you're saying is the bad performance is caused by memory-performance in Cinebench? Or how 15.3 in Fritz chess isn't half of my 4.6GHz 2600ks 34.0 score?
All these leaks have pointed to BD being too late and too slow.

That's awesome, but it must be a little impractical to play SC2 while constantly having to watch temperatures.
Cinebench is known to be built with Intel Compiler Optimizations aimed specifically at Intel Hardware, if it is still built with ICC "unknown" then it will underperform on AMD,VIA hardware if the alternate code path fixs are not put into place.

Its massively unknown. Maybe the makers of cinebench can comment ?
post #232 of 401
What benchmarks are AMD-biased?
    
CPUMotherboardGraphicsRAM
2x intel Xeon E5-2650 Supermicro MBD-X9DR3-F-O Onboard awesomeness 8 x 8GB Kingston DDR3 1333 ECC 
Hard DriveCoolingOSMonitor
4x WD Green 2TB in RAID 10 2x Coolermaster Hyper 212 EVOs Windows Server 2012 Datacenter 3x Dell Ultrasharp U2410s 
PowerCase
Corsair AX1200 Case Labs TX10-D 
  hide details  
Reply
    
CPUMotherboardGraphicsRAM
2x intel Xeon E5-2650 Supermicro MBD-X9DR3-F-O Onboard awesomeness 8 x 8GB Kingston DDR3 1333 ECC 
Hard DriveCoolingOSMonitor
4x WD Green 2TB in RAID 10 2x Coolermaster Hyper 212 EVOs Windows Server 2012 Datacenter 3x Dell Ultrasharp U2410s 
PowerCase
Corsair AX1200 Case Labs TX10-D 
  hide details  
Reply
post #233 of 401
Quote:
Originally Posted by Oedipus View Post
What benchmarks are AMD-biased?
Linux based benchmarks

----

This isn't towards you Oedipus


AMD64 Instruction Fetch(32Bytes(2 windows so 64Bytes)) -> AMD64 Instruction Buffer(256Bytes) -> AMD64->Macro-op Decoder(4x16Bytes/4x32Bytes) -> Macro-op Buffer -> Macro-op->Micro-op Decoder(2x16Bytes) -> Execution Units

That is the path it takes time to go down that path that is "Latency"
Edited by Seronx - 10/7/11 at 8:07pm
AMD FX ~Seronx
(16 items)
 
  
CPUMotherboardGraphicsRAM
FX-9800P Acer Wasp R7 M440 SK Hynix HMA41GS6AFR8N-TF 
Hard DriveHard DriveOptical DriveCooling
KINGSTON RBU-SNS8152S3128GG2 TOSHIBA MQ01ABD100 HL-DT-ST DVDRAM GUE1N Stock 
OSMonitorKeyboardPower
Microsoft Windows 10 Home Build 14393 Viewsonic XG2401 24 Hz-144 Hz Ducky Channel Shine 3 Stock 65W 
CaseMouseMouse PadAudio
Acer Exoskeleton Steelseries Rival 300 Razer Megasoma AMD-Realtek ALC255 
  hide details  
Reply
AMD FX ~Seronx
(16 items)
 
  
CPUMotherboardGraphicsRAM
FX-9800P Acer Wasp R7 M440 SK Hynix HMA41GS6AFR8N-TF 
Hard DriveHard DriveOptical DriveCooling
KINGSTON RBU-SNS8152S3128GG2 TOSHIBA MQ01ABD100 HL-DT-ST DVDRAM GUE1N Stock 
OSMonitorKeyboardPower
Microsoft Windows 10 Home Build 14393 Viewsonic XG2401 24 Hz-144 Hz Ducky Channel Shine 3 Stock 65W 
CaseMouseMouse PadAudio
Acer Exoskeleton Steelseries Rival 300 Razer Megasoma AMD-Realtek ALC255 
  hide details  
Reply
post #234 of 401
Quote:
Originally Posted by Oedipus View Post
What benchmarks are AMD-biased?
AMD is pretty good at Truecrypt, IIRC.
GE60
(13 items)
 
  
CPUGraphicsHard DriveOS
Intel Core i5 4200M Geforce GTX760M 750GB WD Scorpio Black Windows 7 Home Premium 
MonitorKeyboardMouseMouse Pad
15.6" CM Quickfire Rapid CM Xornet Steelseries QcK+ 
  hide details  
Reply
GE60
(13 items)
 
  
CPUGraphicsHard DriveOS
Intel Core i5 4200M Geforce GTX760M 750GB WD Scorpio Black Windows 7 Home Premium 
MonitorKeyboardMouseMouse Pad
15.6" CM Quickfire Rapid CM Xornet Steelseries QcK+ 
  hide details  
Reply
post #235 of 401
Quote:
Originally Posted by Seronx View Post
Linux based benchmarks

----

This isn't towards you Oedipus


AMD64 Instruction Fetch(32Bytes(2 windows so 64Bytes)) -> AMD64 Instruction Buffer(256Bytes) -> AMD64->Macro-op Decoder(4x16Bytes/4x32Bytes) -> Macro-op Buffer -> Macro-op->Micro-op Decoder(2x16Bytes) -> Execution Units

Really ? I find that often Intel and AMD go at it pretty well in Linux benchmarks. Often Intel does edge AMD out in some ways, memory performance as of the last few generations and overall compute power. However it isn't by landslide margins. this makes sense considering that Intel can't magically make transistors that are faster and that they are also limited by all the same constraints as AMD in regards to pipeline structures etc.

I find the linux benchmarks on average produce more relevant and stable results. GCC shows no favoritism I know of towards either brand.
post #236 of 401
Quote:
Originally Posted by Seronx View Post
Linux based benchmarks

----

This isn't towards you Oedipus


AMD64 Instruction Fetch(32Bytes(2 windows so 64Bytes)) -> AMD64 Instruction Buffer(256Bytes) -> AMD64->Macro-op Decoder(4x16Bytes/4x32Bytes) -> Macro-op Buffer -> Macro-op->Micro-op Decoder(2x16Bytes) -> Execution Units

That is the path it takes time to go down that path that is "Latency"
Linux use better optimization in the OS? Why is this?
AMD Transplant
(11 items)
 
To be a NAS
(13 items)
 
Death Kühler
(14 items)
 
CPUMotherboardGraphicsRAM
965BE GA-78LMT-S2P MSI TFIII 7950 Corsair Vengence 
Hard DriveCoolingOSMonitor
Samsung 830 Noctua NH-D14 Win7 Pro FX2490HD 
PowerCaseMouse
Seasonic X660 Antec Three Hundred Saitek Rat 7 
CPUMotherboardGraphicsRAM
AMD Athlon 64 X2 4200+ Gateway GM5072 AMD HD5550 2.0 Gb 
Hard DriveMonitorKeyboardPower
Seagate Barracuda 500Gb Samsung FX2490 MS Keyboard 3000 300w generic 
Mouse
MS Intellipoint 3000 
CPUMotherboardGraphicsRAM
2500k GigaByte Z68M-D2H-B3 MSI 560 Ti TFIII Corsair Vengance 
Hard DriveCoolingOSMonitor
Samsung 830 Antec Khuler 920 Win7 HP Samsung FX2490 
KeyboardPowerCaseMouse
Microsoft Keyboard 3000 Seasonic X-660 Antec Three Hundred Microsoft Mouse 3000 
Mouse PadAudio
None - Blue Track baby Senn HD428 
  hide details  
Reply
AMD Transplant
(11 items)
 
To be a NAS
(13 items)
 
Death Kühler
(14 items)
 
CPUMotherboardGraphicsRAM
965BE GA-78LMT-S2P MSI TFIII 7950 Corsair Vengence 
Hard DriveCoolingOSMonitor
Samsung 830 Noctua NH-D14 Win7 Pro FX2490HD 
PowerCaseMouse
Seasonic X660 Antec Three Hundred Saitek Rat 7 
CPUMotherboardGraphicsRAM
AMD Athlon 64 X2 4200+ Gateway GM5072 AMD HD5550 2.0 Gb 
Hard DriveMonitorKeyboardPower
Seagate Barracuda 500Gb Samsung FX2490 MS Keyboard 3000 300w generic 
Mouse
MS Intellipoint 3000 
CPUMotherboardGraphicsRAM
2500k GigaByte Z68M-D2H-B3 MSI 560 Ti TFIII Corsair Vengance 
Hard DriveCoolingOSMonitor
Samsung 830 Antec Khuler 920 Win7 HP Samsung FX2490 
KeyboardPowerCaseMouse
Microsoft Keyboard 3000 Seasonic X-660 Antec Three Hundred Microsoft Mouse 3000 
Mouse PadAudio
None - Blue Track baby Senn HD428 
  hide details  
Reply
post #237 of 401
Quote:
Originally Posted by Nocturin View Post
Linux use better optimization in the OS? Why is this?
Linux benchmarks show more parity then many commercial synthetics, could be due to compiler and optimization differences. Linux is likely less tuned to each CPU arch then in the world of the Windows and Intel compiler.
post #238 of 401
Quote:
Originally Posted by SCollins View Post
I find the linux benchmarks on average produce more relevant and stable results. GCC shows no favoritism I know of towards either brand.
Thanks SCollins quote mined
AMD FX ~Seronx
(16 items)
 
  
CPUMotherboardGraphicsRAM
FX-9800P Acer Wasp R7 M440 SK Hynix HMA41GS6AFR8N-TF 
Hard DriveHard DriveOptical DriveCooling
KINGSTON RBU-SNS8152S3128GG2 TOSHIBA MQ01ABD100 HL-DT-ST DVDRAM GUE1N Stock 
OSMonitorKeyboardPower
Microsoft Windows 10 Home Build 14393 Viewsonic XG2401 24 Hz-144 Hz Ducky Channel Shine 3 Stock 65W 
CaseMouseMouse PadAudio
Acer Exoskeleton Steelseries Rival 300 Razer Megasoma AMD-Realtek ALC255 
  hide details  
Reply
AMD FX ~Seronx
(16 items)
 
  
CPUMotherboardGraphicsRAM
FX-9800P Acer Wasp R7 M440 SK Hynix HMA41GS6AFR8N-TF 
Hard DriveHard DriveOptical DriveCooling
KINGSTON RBU-SNS8152S3128GG2 TOSHIBA MQ01ABD100 HL-DT-ST DVDRAM GUE1N Stock 
OSMonitorKeyboardPower
Microsoft Windows 10 Home Build 14393 Viewsonic XG2401 24 Hz-144 Hz Ducky Channel Shine 3 Stock 65W 
CaseMouseMouse PadAudio
Acer Exoskeleton Steelseries Rival 300 Razer Megasoma AMD-Realtek ALC255 
  hide details  
Reply
post #239 of 401
Quote:
That makes most benchmarks Intel biased then,why aren't there more sources bringing up the continued use of ICC?
part of the settlement between AMD and Intel was for AMD to keep quiet about the issue. some people don't know/care that they basically have not stopped this compiler optimization business and anandtech staff pretty much defends/supports it.
post #240 of 401
Quote:
Originally Posted by wuttz View Post
any benchmark that uses intel tools is biased.
I remember reading something like 99.9% of all programs are compiled with Intel compilers.
Quote:
Originally Posted by Seronx View Post
FMA and XOP it does miracles particularly 256bit FMAs
Is there any guarantee todays games and programs will take advantage of these instruction sets?
Why would anyone buy something that will be great in a year, when they can buy something that's great now?
Quote:
Originally Posted by Heavy MG View Post
Keep laughing,but BD failing to be competitive isn't good for anyone.
That makes most benchmarks Intel biased then,why aren't there more sources bringing up the continued use of ICC?
This!
BD needs to be competetive for us, if not we'll end up with 10% faster than last gen i3s for 600$
Quote:
Originally Posted by SCollins View Post
If it can produce the desired performance metric in a given power envelope, the clock speed is irrelevant.

IPS is the end of the saga, IPC just factor heavily into IPS.

and still, we have NO IDEA what real bulldozer core performance is like because we have no real hardware with which to test. Leaks could be anything, we have no capability to verify the validity.
I agree, if BD could hit 15GHz on air and still keep cool, needing 6GHz to match SB-performance at 3GHz wouldn't mean anything.
Yes, we have no benchmarks. Though there is a large trends towards BD being crap in every leak we see, which means that we're either seeing some really old ES and AMD has magically pulled 30-40% more IPS from BD or we won't get the amazing chip the market so desperately needs.
Quote:
Originally Posted by wuttz View Post
unfortunately, bentmarks have unrealistic IPC. this is why bentmarks are misleading.
Why does all reviews use these benchmarks if they are so biased?
Edited by Arni90 - 10/7/11 at 8:18pm
Main rig
(21 items)
 
Alienware M14x
(11 items)
 
 
CPUMotherboardGraphicsRAM
i7-2600k P8Z68-V PRO 2x HD 7970 16GB 1600 MHz 
Hard DriveHard DriveHard DriveCooling
180GB SSD 2TB Green spinpoint F3 1TB EK Supreme HF 
CoolingCoolingCoolingCooling
MCP355 2x Coolgate 240mm XSPC Dual-bay res Scythe Gentle Typhoon 
CoolingOSMonitorKeyboard
2x EK-FC7970 Windows 7 XL2410T Qpad MK-80 
PowerCaseMouseAudio
Corsair AX850 Corsair C70 Arctic White Steelseries Xai ASUS Xonar DX 
CPUMotherboardGraphicsGraphics
i7-3720QM Alienware M14x motherboard Nvidia Geforce GT 650M Intel HD Graphics 4000 
RAMHard DriveOptical DriveCooling
6GB 1600MHz CL11 Seagate momentus 500GB 7200RPM DVD Alienwarer M14x leafblower 
OSMonitorKeyboard
Windows 7 Home Premium 1600x900 Alienware bling 
  hide details  
Reply
Main rig
(21 items)
 
Alienware M14x
(11 items)
 
 
CPUMotherboardGraphicsRAM
i7-2600k P8Z68-V PRO 2x HD 7970 16GB 1600 MHz 
Hard DriveHard DriveHard DriveCooling
180GB SSD 2TB Green spinpoint F3 1TB EK Supreme HF 
CoolingCoolingCoolingCooling
MCP355 2x Coolgate 240mm XSPC Dual-bay res Scythe Gentle Typhoon 
CoolingOSMonitorKeyboard
2x EK-FC7970 Windows 7 XL2410T Qpad MK-80 
PowerCaseMouseAudio
Corsair AX850 Corsair C70 Arctic White Steelseries Xai ASUS Xonar DX 
CPUMotherboardGraphicsGraphics
i7-3720QM Alienware M14x motherboard Nvidia Geforce GT 650M Intel HD Graphics 4000 
RAMHard DriveOptical DriveCooling
6GB 1600MHz CL11 Seagate momentus 500GB 7200RPM DVD Alienwarer M14x leafblower 
OSMonitorKeyboard
Windows 7 Home Premium 1600x900 Alienware bling 
  hide details  
Reply
New Posts  All Forums:Forum Nav:
  Return Home
  Back to Forum: Hardware News
Overclock.net › Forums › Industry News › Hardware News › [AMD] Get Your Rig Ready for the AMD FX Processor