Overclock.net › Forums › Industry News › Software News › [ZDNet] The long kiss goodbye for x86 desktop Windows
New Posts  All Forums:Forum Nav:

[ZDNet] The long kiss goodbye for x86 desktop Windows - Page 5

post #41 of 71
Quote:
Originally Posted by linkdiablo View Post

Call me crazy but I've heard that Intel despises x86 as it is pretty much like the win32 API: a bloated legacy architecture that they would've ditched decades ago if it wasn't for huge institutions (banks) that had multi-million dollars software infrastructures they would refuse to port to whatever Intel would release as a replacement. Itanium was, according to my C teacher, the potential substitute for x86 but it failed to get traction as a general purpose architecture due to x86's stronghold on the market: which would translate to Intel being Intel's most fierce competition.
I'm really curious as to wether this was crazy talk from my college teacher or if it might be a bit true.

I believe it has a lot to do with Microsoft's stronghold on the desktop market as well. x86 ensures that 20 years of Windows programs work.

If abandoning x86 means slower processors then I do not support the move at all. I wonder how many billions it would cost the industry to port everything to a different instruction set.
Po' Pimpin'
(11 items)
 
  
CPUMotherboardRAMHard Drive
i5 2500k @ stock Biostar TZ68K+ [A3] 4GB  Sandforce 1222 64GB SSD 
Optical DriveCoolingOSMonitor
LG 22x DVD-+RW  Stock Windows 7 x64 Acer S211HL 1080p 
PowerCaseMouse
600w Diablotek Linkworld Electronic Inland 
  hide details  
Reply
Po' Pimpin'
(11 items)
 
  
CPUMotherboardRAMHard Drive
i5 2500k @ stock Biostar TZ68K+ [A3] 4GB  Sandforce 1222 64GB SSD 
Optical DriveCoolingOSMonitor
LG 22x DVD-+RW  Stock Windows 7 x64 Acer S211HL 1080p 
PowerCaseMouse
600w Diablotek Linkworld Electronic Inland 
  hide details  
Reply
post #42 of 71
Quote:
Originally Posted by BizzareRide View Post

I believe it has a lot to do with Microsoft's stronghold on the desktop market as well. x86 ensures that 20 years of Windows programs work.
If abandoning x86 means slower processors then I do not support the move at all. I wonder how many billions it would cost the industry to port everything to a different instruction set.

Well, C++ really changed the world, as it made code very much more portable, C was fiarly portable but required lots of support, where as good c++ compiler, if the code was written properly, would pretty much go everywhere. minus a few quirks, but most of those are at the OS and kernel level, not the application level.

the same is true of visual basic, it should be able to move to almost any windows os platform with a suitable compiler and maybe some light patching at worst. Java etc.

There is a huge performance advantage with x86, the complexity does grant that, and this is why we really have a x86 centric world. Though MIPS with some more design, could have likely given x86 a run for its money, to many philosphical tangents by engineers likely stoppped that from happening. If ARM chips had the performance capability of x86, they'd look alot like x86 chips, and likely have damn near the same power consumption.
post #43 of 71
Quote:
Originally Posted by linkdiablo View Post

Call me crazy but I've heard that Intel despises x86 as it is pretty much like the win32 API: a bloated legacy architecture that they would've ditched decades ago if it wasn't for huge institutions (banks) that had multi-million dollars software infrastructures they would refuse to port to whatever Intel would release as a replacement. Itanium was, according to my C teacher, the potential substitute for x86 but it failed to get traction as a general purpose architecture due to x86's stronghold on the market: which would translate to Intel being Intel's most fierce competition.
I'm really curious as to wether this was crazy talk from my college teacher or if it might be a bit true.

It's true that x86 is a fairly "messy" platform. However, it is supported like no other. Compilers nowadays are so well-optimized, the messy ISA will not even matter unless you do asm programming, which is next to no one anyway. Anybody who has predicted x86 to crash and burn due to its messiness has been wrong up until now.
post #44 of 71
I'll stick with 7, and maintain that 8 should've been renamed something else. I think Microsoft should have went with two paths; one for x86/x64, and one for those who want to develop and use programs between PC's and mobile devices. x86/x64 isn't dead, far from it. I don't know why they're killing it, they can maintain an x86/x64 presence while trying to compete on the mobile/portable front.
post #45 of 71
Quote:
Originally Posted by BizzareRide View Post

1.6GHz single core Medfield chip scores 10,500 in CaffeineMark 3, Nvidia's Tegra 2 scores 7500 in the same benchmark. This is nearly a 300% increase in performance of a single Cortex A9 core.
According to this article, the A15 is a competitor to the Intel Atom and AMD Bobcat, so Intel or AMD for that matter, aren't really behind in terms of anything but adaptation. The sheer number of ARM licensees and/or corporations with stock in ARM instruction set far outweighs that of x86. This, in my opinion, is Intel's biggest challenge.
Early Medfield silicon pits the power consumption a bit high, but still in the ballpark of other SoCs such as Tegra 3. As Intel makes refinements to their production process and achieve new steppings then the power consumption will drop significantly.

Tegra 2 is the slowest of the A9s, My SGSII with Cyanogenmod7 at stock gets 8846. Tegra3 is also already matching it at a 300Mhz lower clock speed.

My SGSII with a 200Mhz OC also gets 10303 (Proof)...Like I said, Medfield is not that fast compared to current generation chips, let alone next-generation chips which it actually will compete against.

As for the power consumption, it's at 3.6w but said to scale down to 2.6w in future, iirc? Even at 2.6w it still uses more power than Tegra3 when both are pegged...And with Tegra3s companion core, I'd bet it uses more power while you're doing tasks like watching movies, listening to music, etc.

I can't find it anywhere, but is it even a dual core? If not, then (Even considering hard to make MP code) Tegra3 could double its score, at least...

Edit: ATDuy.jpg That's at 1.6Ghz, same clock speed as Medfield.
Quote:
Originally Posted by SCollins View Post

there are some things that x86 just does better, and powerful instructions is one of them. Its the reason x86 won the instruction ISA war where it mattered.

That was more due to the IBM PC and the low-price of the 8088 compared to the other competing CPUs, no-one who programs assembly likes x86 at all.
People bought the IBM PC because it was cheap, or one of the clones and then wanted to keep their programs working...It's a cycle.
Edited by Brutuz - 2/20/12 at 2:31pm
    
CPUMotherboardGraphicsRAM
Intel Core i5 3570k @ 4.5Ghz ASRock Z77 Pro3 Powercolor Radeon HD7950 3GB @ 1150/1350 4x4GB G.Skill Ares 2000Mhz CL9 
Hard DriveHard DriveHard DriveHard Drive
Samsung 840 250GB Western Digital Black 1TB WD1002FAEX Seagate Barracuda 3TB ST3000DM001 Samsung Spinpoint EcoGreen 2TB 
Optical DriveCoolingCoolingCooling
Pioneer DVR-220LBKS Noctua NH-D14 Scythe Gentle Typhoon 1850rpm Corsair AF140 Quiet Edition 
CoolingOSMonitorMonitor
Arcitc Cooling Acclero Twin Turbo II Arch Linux x86-64, amdgpu BenQ G2220HD BenQ G2020HD 
KeyboardPowerCaseMouse
Ducky Shine III Year of the Snake, Cherry Blue Silverstone Strider Plus 600w CoolerMaster CM690 II Black and White SteelSeries Sensei Professional 
Mouse PadAudioOther
Artisan Hien Mid Japan Black Large ASUS Xonar DX NZXT Sentry Mesh 30w Fan Controller 
  hide details  
Reply
    
CPUMotherboardGraphicsRAM
Intel Core i5 3570k @ 4.5Ghz ASRock Z77 Pro3 Powercolor Radeon HD7950 3GB @ 1150/1350 4x4GB G.Skill Ares 2000Mhz CL9 
Hard DriveHard DriveHard DriveHard Drive
Samsung 840 250GB Western Digital Black 1TB WD1002FAEX Seagate Barracuda 3TB ST3000DM001 Samsung Spinpoint EcoGreen 2TB 
Optical DriveCoolingCoolingCooling
Pioneer DVR-220LBKS Noctua NH-D14 Scythe Gentle Typhoon 1850rpm Corsair AF140 Quiet Edition 
CoolingOSMonitorMonitor
Arcitc Cooling Acclero Twin Turbo II Arch Linux x86-64, amdgpu BenQ G2220HD BenQ G2020HD 
KeyboardPowerCaseMouse
Ducky Shine III Year of the Snake, Cherry Blue Silverstone Strider Plus 600w CoolerMaster CM690 II Black and White SteelSeries Sensei Professional 
Mouse PadAudioOther
Artisan Hien Mid Japan Black Large ASUS Xonar DX NZXT Sentry Mesh 30w Fan Controller 
  hide details  
Reply
post #46 of 71
Windows 3.0= Good
Windows 95 = Bad
Windows 98 = Good
Millenium Edition = Bad,
XP = Good,
Vista = Bad,
Windows 7 = Good,
Windows 8 = Bad (probably)

It's how Microsoft operates.
Low Tide
(12 items)
 
  
CPUMotherboardGraphicsRAM
i5-3570K @ 4.7GHz Asus P8Z77-V Pro EVGA GTX 670 FTW 8GB G. Skill 2133MHz 
Hard DriveCoolingOSMonitor
Samsung 850 Pro 256GB Prolimatech Megahalems Rev. C Windows X Samsung T240HD 
KeyboardPowerCaseAudio
Ducky DK9008G2 Red Corsair TX850W V1 Corsair Carbide 300R X-Fi XtremeGamer 
  hide details  
Reply
Low Tide
(12 items)
 
  
CPUMotherboardGraphicsRAM
i5-3570K @ 4.7GHz Asus P8Z77-V Pro EVGA GTX 670 FTW 8GB G. Skill 2133MHz 
Hard DriveCoolingOSMonitor
Samsung 850 Pro 256GB Prolimatech Megahalems Rev. C Windows X Samsung T240HD 
KeyboardPowerCaseAudio
Ducky DK9008G2 Red Corsair TX850W V1 Corsair Carbide 300R X-Fi XtremeGamer 
  hide details  
Reply
post #47 of 71
Quote:
Originally Posted by losttsol View Post

Windows 3.0= Good
Windows 95 = Bad
Windows 98 = Good
Millenium Edition = Bad,
XP = Good,
Vista = Bad,
Windows 7 = Good,
Windows 8 = Bad (probably)
It's how Microsoft operates.


Windows 3.1 = Good
Windows 95 = Bad, Good after SR2
Windows 98 = Bad, Good after SE
Windows ME = Bad
Windows 2000 = Bad, good after SP2
Windows XP = Bad, good after SP1
Windows Vitsa = Bad, good after SP1
Windows 7 = Vista SP2, so just good.

I wish people would stop spreading the good-bad cycle crap.
    
CPUMotherboardGraphicsRAM
Intel Core i5 3570k @ 4.5Ghz ASRock Z77 Pro3 Powercolor Radeon HD7950 3GB @ 1150/1350 4x4GB G.Skill Ares 2000Mhz CL9 
Hard DriveHard DriveHard DriveHard Drive
Samsung 840 250GB Western Digital Black 1TB WD1002FAEX Seagate Barracuda 3TB ST3000DM001 Samsung Spinpoint EcoGreen 2TB 
Optical DriveCoolingCoolingCooling
Pioneer DVR-220LBKS Noctua NH-D14 Scythe Gentle Typhoon 1850rpm Corsair AF140 Quiet Edition 
CoolingOSMonitorMonitor
Arcitc Cooling Acclero Twin Turbo II Arch Linux x86-64, amdgpu BenQ G2220HD BenQ G2020HD 
KeyboardPowerCaseMouse
Ducky Shine III Year of the Snake, Cherry Blue Silverstone Strider Plus 600w CoolerMaster CM690 II Black and White SteelSeries Sensei Professional 
Mouse PadAudioOther
Artisan Hien Mid Japan Black Large ASUS Xonar DX NZXT Sentry Mesh 30w Fan Controller 
  hide details  
Reply
    
CPUMotherboardGraphicsRAM
Intel Core i5 3570k @ 4.5Ghz ASRock Z77 Pro3 Powercolor Radeon HD7950 3GB @ 1150/1350 4x4GB G.Skill Ares 2000Mhz CL9 
Hard DriveHard DriveHard DriveHard Drive
Samsung 840 250GB Western Digital Black 1TB WD1002FAEX Seagate Barracuda 3TB ST3000DM001 Samsung Spinpoint EcoGreen 2TB 
Optical DriveCoolingCoolingCooling
Pioneer DVR-220LBKS Noctua NH-D14 Scythe Gentle Typhoon 1850rpm Corsair AF140 Quiet Edition 
CoolingOSMonitorMonitor
Arcitc Cooling Acclero Twin Turbo II Arch Linux x86-64, amdgpu BenQ G2220HD BenQ G2020HD 
KeyboardPowerCaseMouse
Ducky Shine III Year of the Snake, Cherry Blue Silverstone Strider Plus 600w CoolerMaster CM690 II Black and White SteelSeries Sensei Professional 
Mouse PadAudioOther
Artisan Hien Mid Japan Black Large ASUS Xonar DX NZXT Sentry Mesh 30w Fan Controller 
  hide details  
Reply
post #48 of 71
I must say, this is surprising for Microsoft!
post #49 of 71
Windows 8 will fully support the win32 API. If people even bothered to read the article it says only ARM builds of Windows 8 won't support native win32 binarys. Every single program you use on Windows 7 should still work on Windows 8.
Main Rig
(14 items)
 
Linux Rig
(10 items)
 
 
CPUMotherboardGraphicsRAM
Athlon II x3 450 Biostar A880GZ PowerColor HD 4650 DDR3 4GB Samsung MV-3V2G3/US 
Hard DriveOptical DriveCoolingOS
Samsung 830 128GB (Pending) ASUS DRW-24B1ST Stock Windows 8 Enterprise x64 
KeyboardPowerCaseMouse
Logitech Classic 200 300w Hipro a1410n HP 1000 DPI 
Mouse PadAudio
Standard Realtek ALC662 
CPUMotherboardGraphicsRAM
AMD Sempron 3000+ ASUS A7V8X-LA VIA KM400A 2GB DDR 333 
Hard DriveOptical DriveCoolingOS
40GB Seagate Barracuda 7200.7 Samsung Writemaster Stock ASUS Ubuntu 12.04 
PowerCase
Hipro 250W SR1500NX 
  hide details  
Reply
Main Rig
(14 items)
 
Linux Rig
(10 items)
 
 
CPUMotherboardGraphicsRAM
Athlon II x3 450 Biostar A880GZ PowerColor HD 4650 DDR3 4GB Samsung MV-3V2G3/US 
Hard DriveOptical DriveCoolingOS
Samsung 830 128GB (Pending) ASUS DRW-24B1ST Stock Windows 8 Enterprise x64 
KeyboardPowerCaseMouse
Logitech Classic 200 300w Hipro a1410n HP 1000 DPI 
Mouse PadAudio
Standard Realtek ALC662 
CPUMotherboardGraphicsRAM
AMD Sempron 3000+ ASUS A7V8X-LA VIA KM400A 2GB DDR 333 
Hard DriveOptical DriveCoolingOS
40GB Seagate Barracuda 7200.7 Samsung Writemaster Stock ASUS Ubuntu 12.04 
PowerCase
Hipro 250W SR1500NX 
  hide details  
Reply
post #50 of 71
Quote:
Originally Posted by Brutuz View Post

Tegra 2 is the slowest of the A9s, My SGSII with Cyanogenmod7 at stock gets 8846. Tegra3 is also already matching it at a 300Mhz lower clock speed.
My SGSII with a 200Mhz OC also gets 10303 (Proof)...Like I said, Medfield is not that fast compared to current generation chips, let alone next-generation chips which it actually will compete against.
As for the power consumption, it's at 3.6w but said to scale down to 2.6w in future, iirc? Even at 2.6w it still uses more power than Tegra3 when both are pegged...And with Tegra3s companion core, I'd bet it uses more power while you're doing tasks like watching movies, listening to music, etc.
I can't find it anywhere, but is it even a dual core? If not, then (Even considering hard to make MP code) Tegra3 could double its score, at least...
That was more due to the IBM PC and the low-price of the 8088 compared to the other competing CPUs, no-one who programs assembly likes x86 at all.
People bought the IBM PC because it was cheap, or one of the clones and then wanted to keep their programs working...It's a cycle.

Intel won because it had the fastest CISC chips at the time (and CISC part was viewed as important due to RAM costs).

Since that time, Intel and AMD have moved to a RISC architecture with a CISC decoder (note: many ARM instructions are *very* CISC-like making the whole ARM-is-better-because-they-are-RISC somewhat untrue). I don't think that ARM has the huge advantage that most people believe to to have. Current ARM chips only achieve good energy efficiency when the can get a job done quickly and go back to idle (and Medfield idle power consumption is on par with current A9 chips). The next generation of ARM chips will increase power consumption. Some manufacturers are trying to partially negate this with big-little, but the max TDP won't change. If AMD decides to die-shrink Brazos (there was talk that a die-shrink was abandoned, but AMDs current talk of sticking with 28nm for a while seems to make that somewhat doubtful), then the AMD chip will likely beat A15 in most every metric.

OT: What was Nvidia thinking when they moved to quad-core? A dual-core (and companion-core) with a larger GPU would have provided similar performance for 99% of phone/tablet tasks while fewer cores would have provided possibility for higher clocks and much-needed GPU improvements (the improvements in Tegra3 weren't enough to keep up with the competition). Further, how does Nvidia expect Tegra3 to compete with Qualcomm S4 processors releasing 1H of this year (or all the A15 designs hitting a little later)? Even now, a knowledgeable purchaser (rather than buying a Transformer Prime) would be money ahead waiting for a S4-based tablet (after S4, there are few performance improvements for the next couple of years).
New Posts  All Forums:Forum Nav:
  Return Home
  Back to Forum: Software News
Overclock.net › Forums › Industry News › Software News › [ZDNet] The long kiss goodbye for x86 desktop Windows