Overclock.net › Forums › Industry News › Hardware News › [GMANE] AMD Confirms CPU Bug
New Posts  All Forums:Forum Nav:

[GMANE] AMD Confirms CPU Bug - Page 5

post #41 of 51
Quote:
Originally Posted by Warmonger View Post

Well my point is there is no reason to write an application in assembly, when it can be done in a interpreter in less then half the time and work the same. The only time you should write something in assembly is if your writing your own drivers etc.

That was my original point as well, or at least that was my intent.
Quote:
Luckily it is rare to need assembly for anything other than learning, as most compilers will optimize code better than a human.
Foldatron
(17 items)
 
Mat
(10 items)
 
Work iMac
(9 items)
 
CPUMotherboardGraphicsGraphics
i7 950 EVGA x58 3-way SLI EVGA GTX 660ti GTX 275 
RAMHard DriveHard DriveHard Drive
3x2GB Corsair Dominator DDR3-1600 80GB Intel X25-M SSD 2TB WD Black 150GB WD Raptor 
Hard DriveOSMonitorKeyboard
2x 150GB WD V-raptor in RAID0 Win7 Home 64-bit OEM 55" LED 120hz 1080p Vizio MS Natural Ergonomic Keyboard 4000 
PowerCase
750W PC P&C Silencer CoolerMaster 690 
CPUGraphicsRAMHard Drive
Intel Core i5 2500S AMD 6770M 8GB (2x4GB) at 1333Mhz 1TB, 7200 rpm 
Optical DriveOSMonitorKeyboard
LG 8X Dual-Layer "SuperDrive" OS X Lion 27" iMac screen Mac wireless keyboard 
Mouse
Mac wireless mouse 
CPUGraphicsRAMHard Drive
i7-2600K AMD 6970M 1GB 16GB PC3-10600 DDR3 1TB 7200rpm 
Hard DriveOptical DriveOSMonitor
256GB SSD 8x DL "SuperDrive" OS X 10.7 Lion 27" 2560x1440 iMac display 
Monitor
27" Apple thunderbolt display 
  hide details  
Reply
Foldatron
(17 items)
 
Mat
(10 items)
 
Work iMac
(9 items)
 
CPUMotherboardGraphicsGraphics
i7 950 EVGA x58 3-way SLI EVGA GTX 660ti GTX 275 
RAMHard DriveHard DriveHard Drive
3x2GB Corsair Dominator DDR3-1600 80GB Intel X25-M SSD 2TB WD Black 150GB WD Raptor 
Hard DriveOSMonitorKeyboard
2x 150GB WD V-raptor in RAID0 Win7 Home 64-bit OEM 55" LED 120hz 1080p Vizio MS Natural Ergonomic Keyboard 4000 
PowerCase
750W PC P&C Silencer CoolerMaster 690 
CPUGraphicsRAMHard Drive
Intel Core i5 2500S AMD 6770M 8GB (2x4GB) at 1333Mhz 1TB, 7200 rpm 
Optical DriveOSMonitorKeyboard
LG 8X Dual-Layer "SuperDrive" OS X Lion 27" iMac screen Mac wireless keyboard 
Mouse
Mac wireless mouse 
CPUGraphicsRAMHard Drive
i7-2600K AMD 6970M 1GB 16GB PC3-10600 DDR3 1TB 7200rpm 
Hard DriveOptical DriveOSMonitor
256GB SSD 8x DL "SuperDrive" OS X 10.7 Lion 27" 2560x1440 iMac display 
Monitor
27" Apple thunderbolt display 
  hide details  
Reply
post #42 of 51
Quote:
Originally Posted by Warmonger View Post

Coming from the members who obviously don't know Assembly. I would take a look over this guide it will help you all get started learning. I also suggest you start with 16bit.

I'm learning assembly (16 bit) right now. It is extremely complicated compared to C++.
post #43 of 51
Thread Starter 
I know and have written full applications for the mips architecture..... I know what I am talking about, assembly is a nightmare to debug. Also if someone hands you their assembly and expects you to give it a once over... laugh in their face....
 
Tragbar
(14 items)
 
 
CPUMotherboardGraphicsRAM
Ryzen 1800X Asus Crosshair VI Hero Nvidia Geforce Titan X F4-3600C15D-16GTZ 
Hard DriveHard DriveHard DriveHard Drive
Combined: 6.13 TB of space Samsung SSD 960 EVO 500GB Crucial_CT1050MX300SSD1 M4-CT128M4SSD2 
CoolingCoolingCoolingCooling
EK-Supremacy EVO White Edition PrimoChill PrimoFlex Advanced LRT EK-RES X4 250 (R2.0) Reservoir EK-CoolStream XE 360 
CoolingCoolingCoolingOS
EK-Vardar F4-120ER (2200rpm)  EK-Ekoolant EVO Liquid Coolant EK-XTOP Revo D5 PWM Pump Windows 10 Pro 
MonitorKeyboardPowerCase
Asus VG278H Ducky YOTG Keyboard Corsair AX1200 Corsair Obsidian 800D 
MouseAudioAudioAudio
Logitech G700s Schiit Gungnir Multibit Schiit Mjolnir 2 Schiit LISST 
Audio
Audeze LCD 2 - pre fazor 
CPUMotherboardGraphicsRAM
intel i7 4770K ASRock Z87E-ITX Nvidia Geforce GTX Titan X GSkill F3-2400C10D-16GTX R 
Hard DriveOptical DriveCoolingOS
Samsung 840 Pro 512GB Silverstone 12.7mm Slot Load Blu-Ray Burner Noctua NH-L12 Windows 8 Pro 
MonitorCaseAudioAudio
LG PA75U Slim LED Projector Silverstone SG08 Schiit Bifrost Schiit Asgard 2 
AudioOther
AKG Q701 Headphones Pelican 1510 Green Case  
  hide details  
Reply
 
Tragbar
(14 items)
 
 
CPUMotherboardGraphicsRAM
Ryzen 1800X Asus Crosshair VI Hero Nvidia Geforce Titan X F4-3600C15D-16GTZ 
Hard DriveHard DriveHard DriveHard Drive
Combined: 6.13 TB of space Samsung SSD 960 EVO 500GB Crucial_CT1050MX300SSD1 M4-CT128M4SSD2 
CoolingCoolingCoolingCooling
EK-Supremacy EVO White Edition PrimoChill PrimoFlex Advanced LRT EK-RES X4 250 (R2.0) Reservoir EK-CoolStream XE 360 
CoolingCoolingCoolingOS
EK-Vardar F4-120ER (2200rpm)  EK-Ekoolant EVO Liquid Coolant EK-XTOP Revo D5 PWM Pump Windows 10 Pro 
MonitorKeyboardPowerCase
Asus VG278H Ducky YOTG Keyboard Corsair AX1200 Corsair Obsidian 800D 
MouseAudioAudioAudio
Logitech G700s Schiit Gungnir Multibit Schiit Mjolnir 2 Schiit LISST 
Audio
Audeze LCD 2 - pre fazor 
CPUMotherboardGraphicsRAM
intel i7 4770K ASRock Z87E-ITX Nvidia Geforce GTX Titan X GSkill F3-2400C10D-16GTX R 
Hard DriveOptical DriveCoolingOS
Samsung 840 Pro 512GB Silverstone 12.7mm Slot Load Blu-Ray Burner Noctua NH-L12 Windows 8 Pro 
MonitorCaseAudioAudio
LG PA75U Slim LED Projector Silverstone SG08 Schiit Bifrost Schiit Asgard 2 
AudioOther
AKG Q701 Headphones Pelican 1510 Green Case  
  hide details  
Reply
post #44 of 51
Quote:
Originally Posted by rush2049 View Post

I know and have written full applications for the mips architecture..... I know what I am talking about, assembly is a nightmare to debug. Also if someone hands you their assembly and expects you to give it a once over... laugh in their face....

Note, this is one reason why the BIOS should be replaced by UEFI. thumb.gif

Printing "Hello World"


.....in C (UEFI) http://lwn.net/Articles/454399/
Code:
#include <efi.h>
    #include <efilib.h>

    EFI_STATUS
    efi_main (EFI_HANDLE image, EFI_SYSTEM_TABLE *systab)
    {
        SIMPLE_TEXT_OUTPUT_INTERFACE *conout;

        conout = systab->ConOut;
        uefi_call_wrapper(conout->OutputString, 2, conout, L"Hello World!\n\r");

        return EFI_SUCCESS;
    }


.....in Asembly (BIOS) http://viralpatel.net/taj/tutorial/hello_world_bootloader.php
Code:
[BITS 16]    
[ORG 0x7C00]    
                
MOV SI, HelloString 
CALL PrintString        
JMP $           


PrintCharacter: 
MOV AH, 0x0E    
MOV BH, 0x00
MOV BL, 0x07    

INT 0x10        
RET             

PrintString:    

next_character: 
MOV AL, [SI]
INC SI          
OR AL, AL       
JZ exit_function 
CALL PrintCharacter 
JMP next_character      
exit_function:  
RET     


;Data
HelloString db 'Hello World', 0 

TIMES 510 - ($ - $$) db 0       
DW 0xAA55

Edited by DuckieHo - 3/6/12 at 1:24pm
Once again...
(13 items)
 
  
CPUMotherboardGraphicsRAM
i7 920 [4.28GHz, HT] Asus P6T + Broadcom NetXtreme II VisionTek HD5850 [900/1200] + Galaxy GT240 2x4GB G.Skill Ripjaw X [1632 MHz] 
Hard DriveOSMonitorKeyboard
Intel X25-M 160GB + 3xRAID0 500GB 7200.12 Window 7 Pro 64 Acer H243H + Samsung 226BW XARMOR-U9BL  
PowerCaseMouseMouse Pad
Antec Truepower New 750W Li Lian PC-V2100 [10x120mm fans] Logitech G9 X-Trac Pro 
  hide details  
Reply
Once again...
(13 items)
 
  
CPUMotherboardGraphicsRAM
i7 920 [4.28GHz, HT] Asus P6T + Broadcom NetXtreme II VisionTek HD5850 [900/1200] + Galaxy GT240 2x4GB G.Skill Ripjaw X [1632 MHz] 
Hard DriveOSMonitorKeyboard
Intel X25-M 160GB + 3xRAID0 500GB 7200.12 Window 7 Pro 64 Acer H243H + Samsung 226BW XARMOR-U9BL  
PowerCaseMouseMouse Pad
Antec Truepower New 750W Li Lian PC-V2100 [10x120mm fans] Logitech G9 X-Trac Pro 
  hide details  
Reply
post #45 of 51
All CPUs have bugs... This isn't special. Nor was the last AMD erratum fiasco.
Lee XT
(17 items)
 
  
CPUMotherboardGraphicsRAM
AMD FX-6300 Asus M5A97 SAPPHIRE Radeon HD 7850 AMD 4GB DDR3 1333MHZ 
RAMRAMRAMHard Drive
AMD 4GB DDR3 1333MHZ AMD 4GB DDR3 1333MHZ AMD 4GB DDR3 1333MHZ OCZ Vertex 4 256GB 
CoolingOSMonitorKeyboard
Corsair H80 Windows 8.1 Pro MCE Dell P2414H WHXV7  Microsoft Generic 
PowerCaseMouseMouse Pad
Ultra 600W Limited Edition NZXT Black Steel Razer Deathadder Razer Goliath 
Audio
Realtek HD Audio 
  hide details  
Reply
Lee XT
(17 items)
 
  
CPUMotherboardGraphicsRAM
AMD FX-6300 Asus M5A97 SAPPHIRE Radeon HD 7850 AMD 4GB DDR3 1333MHZ 
RAMRAMRAMHard Drive
AMD 4GB DDR3 1333MHZ AMD 4GB DDR3 1333MHZ AMD 4GB DDR3 1333MHZ OCZ Vertex 4 256GB 
CoolingOSMonitorKeyboard
Corsair H80 Windows 8.1 Pro MCE Dell P2414H WHXV7  Microsoft Generic 
PowerCaseMouseMouse Pad
Ultra 600W Limited Edition NZXT Black Steel Razer Deathadder Razer Goliath 
Audio
Realtek HD Audio 
  hide details  
Reply
post #46 of 51
Quote:
Originally Posted by Licht View Post

All CPUs have bugs... This isn't special. Nor was the last AMD erratum fiasco.

To be fair, the Phenom I TLB erratum was a had more possible stability/performance impact than this one though.
Once again...
(13 items)
 
  
CPUMotherboardGraphicsRAM
i7 920 [4.28GHz, HT] Asus P6T + Broadcom NetXtreme II VisionTek HD5850 [900/1200] + Galaxy GT240 2x4GB G.Skill Ripjaw X [1632 MHz] 
Hard DriveOSMonitorKeyboard
Intel X25-M 160GB + 3xRAID0 500GB 7200.12 Window 7 Pro 64 Acer H243H + Samsung 226BW XARMOR-U9BL  
PowerCaseMouseMouse Pad
Antec Truepower New 750W Li Lian PC-V2100 [10x120mm fans] Logitech G9 X-Trac Pro 
  hide details  
Reply
Once again...
(13 items)
 
  
CPUMotherboardGraphicsRAM
i7 920 [4.28GHz, HT] Asus P6T + Broadcom NetXtreme II VisionTek HD5850 [900/1200] + Galaxy GT240 2x4GB G.Skill Ripjaw X [1632 MHz] 
Hard DriveOSMonitorKeyboard
Intel X25-M 160GB + 3xRAID0 500GB 7200.12 Window 7 Pro 64 Acer H243H + Samsung 226BW XARMOR-U9BL  
PowerCaseMouseMouse Pad
Antec Truepower New 750W Li Lian PC-V2100 [10x120mm fans] Logitech G9 X-Trac Pro 
  hide details  
Reply
post #47 of 51
Quote:
Originally Posted by DuckieHo View Post

To be fair, the Phenom I TLB erratum was a had more possible stability/performance impact than this one though.

I read a few articles on it and no one who I read about trying was actually able to reproduce it in a real world scenario. The whole thing was blown totally out of proportion.
Lee XT
(17 items)
 
  
CPUMotherboardGraphicsRAM
AMD FX-6300 Asus M5A97 SAPPHIRE Radeon HD 7850 AMD 4GB DDR3 1333MHZ 
RAMRAMRAMHard Drive
AMD 4GB DDR3 1333MHZ AMD 4GB DDR3 1333MHZ AMD 4GB DDR3 1333MHZ OCZ Vertex 4 256GB 
CoolingOSMonitorKeyboard
Corsair H80 Windows 8.1 Pro MCE Dell P2414H WHXV7  Microsoft Generic 
PowerCaseMouseMouse Pad
Ultra 600W Limited Edition NZXT Black Steel Razer Deathadder Razer Goliath 
Audio
Realtek HD Audio 
  hide details  
Reply
Lee XT
(17 items)
 
  
CPUMotherboardGraphicsRAM
AMD FX-6300 Asus M5A97 SAPPHIRE Radeon HD 7850 AMD 4GB DDR3 1333MHZ 
RAMRAMRAMHard Drive
AMD 4GB DDR3 1333MHZ AMD 4GB DDR3 1333MHZ AMD 4GB DDR3 1333MHZ OCZ Vertex 4 256GB 
CoolingOSMonitorKeyboard
Corsair H80 Windows 8.1 Pro MCE Dell P2414H WHXV7  Microsoft Generic 
PowerCaseMouseMouse Pad
Ultra 600W Limited Edition NZXT Black Steel Razer Deathadder Razer Goliath 
Audio
Realtek HD Audio 
  hide details  
Reply
post #48 of 51
Quote:
Originally Posted by Licht View Post

I read a few articles on it and no one who I read about trying was actually able to reproduce it in a real world scenario. The whole thing was blown totally out of proportion.

Who and how were they testing?

The TLB erratum was that a heavily loaded K9-based CPU could fault while using L3. Consumer workloads may never load a CPU hard and long enough for this to be an issue. However, the enterprise users could and they could not just disable/control L3 usage. This particular erratum is specific to a single instruction. There is a workaround for this issue.... but there was not one for the TLB one. Then AMD released a fixed which hurt performance.... and they were already losing the performance race at that time.
Once again...
(13 items)
 
  
CPUMotherboardGraphicsRAM
i7 920 [4.28GHz, HT] Asus P6T + Broadcom NetXtreme II VisionTek HD5850 [900/1200] + Galaxy GT240 2x4GB G.Skill Ripjaw X [1632 MHz] 
Hard DriveOSMonitorKeyboard
Intel X25-M 160GB + 3xRAID0 500GB 7200.12 Window 7 Pro 64 Acer H243H + Samsung 226BW XARMOR-U9BL  
PowerCaseMouseMouse Pad
Antec Truepower New 750W Li Lian PC-V2100 [10x120mm fans] Logitech G9 X-Trac Pro 
  hide details  
Reply
Once again...
(13 items)
 
  
CPUMotherboardGraphicsRAM
i7 920 [4.28GHz, HT] Asus P6T + Broadcom NetXtreme II VisionTek HD5850 [900/1200] + Galaxy GT240 2x4GB G.Skill Ripjaw X [1632 MHz] 
Hard DriveOSMonitorKeyboard
Intel X25-M 160GB + 3xRAID0 500GB 7200.12 Window 7 Pro 64 Acer H243H + Samsung 226BW XARMOR-U9BL  
PowerCaseMouseMouse Pad
Antec Truepower New 750W Li Lian PC-V2100 [10x120mm fans] Logitech G9 X-Trac Pro 
  hide details  
Reply
post #49 of 51
Quote:
Originally Posted by rush2049 View Post

That there is assembly.... its what all compiled code gets compiled to.....
Quote:
Originally Posted by lordikon View Post

Haven't read the source yet, do they show more than just the disassembly? Honestly if you can cause that same set of assembly instructions then it may not matter which language you use, so long as it gets optimized into that exact form. You could always use straight assembly as well, of course.
Regardless, this looks like a minor edge-case, not sure how it will affect other programs. Hopefully they can patch this somehow, bugs like this are the kind that crop up causing really strange behavior that is completely mind-numbing to track down, especially considering how much work it was for him to get them a reproduction case and how much time it took for them to confirm it was even a hardware problem.
Quote:
Originally Posted by lordikon View Post

This. Assembly is difficult to learn no matter what language you choose to start with. Luckily it is rare to need assembly for anything other than learning, as most compilers will optimize code better than a human. Unless you're programming a compiler, then you're just screwed. tongue.gif

Assembly isn't the all ends, that's machine code. Assembly is (more or less) what a compiler builds too, but to say every language gets optimized to the same code is...... Well you have Java, which runs on a JVM, which runs on top of another computer. Java never hits assembly, the jvm converts it to machine code and runs it. Honestly, even assembly is compiled. Nothing gets compiled with the exact same instructions unless you use the exact same version of GCC. if you use GCC vs the Intel compiler your going to get what would be considered close to the exact same code but it's not. it all depends on what your building it on, and what code your building it from/for.

[ugh] too tipsy to really have planned this response, or it's just my normal brain being terribly awful. I edit a lot, it's a bad habit, anywho.

Though when you get into specific cpu calls, there are functions that all code will end up calling. Now I'm not saying all code ends up the same but eventually you have to have all code call the same functions for the cpu. It's like cars, well most cars. They all are designed differently but lets face it, the standard V (or even straight) engines work the same. You have to have the bare functions universal, well at least for now I'm pretty certain we have too. wink.gif I'm just correcting the idea that all code gets compiled the same. That's wrong, as there are many things that can alter.
Edited by mushroomboy - 3/6/12 at 10:15pm
Current Rig
(14 items)
 
  
CPUMotherboardGraphicsRAM
FX-8350 4.6GHz@1.44v GA-990FXA-UD3 R4.0 HD 7950 (1100/1450) 8G Muskin DDR3 1866@8CLS 
Hard DriveOptical DriveOSMonitor
1TB WD LiteOn DVD-RW DL Linux/Windows 19" Phillips TV 1080p 
PowerCaseMouseMouse Pad
OCZ 600W Generic Junk Logitech MX400 Generic Junk 
Audio
SBL 5.1 
  hide details  
Reply
Current Rig
(14 items)
 
  
CPUMotherboardGraphicsRAM
FX-8350 4.6GHz@1.44v GA-990FXA-UD3 R4.0 HD 7950 (1100/1450) 8G Muskin DDR3 1866@8CLS 
Hard DriveOptical DriveOSMonitor
1TB WD LiteOn DVD-RW DL Linux/Windows 19" Phillips TV 1080p 
PowerCaseMouseMouse Pad
OCZ 600W Generic Junk Logitech MX400 Generic Junk 
Audio
SBL 5.1 
  hide details  
Reply
post #50 of 51
Quote:
Originally Posted by mushroomboy View Post

Assembly isn't the all ends, that's machine code. Assembly is (more or less) what a compiler builds too, but to say every language gets optimized to the same code is...... Well you have Java, which runs on a JVM, which runs on top of another computer. Java never hits assembly, the jvm converts it to machine code and runs it. Honestly, even assembly is compiled. Nothing gets compiled with the exact same instructions unless you use the exact same version of GCC. if you use GCC vs the Intel compiler your going to get what would be considered close to the exact same code but it's not. it all depends on what your building it on, and what code your building it from/for.
[ugh] too tipsy to really have planned this response, or it's just my normal brain being terribly awful. I edit a lot, it's a bad habit, anywho.
Though when you get into specific cpu calls, there are functions that all code will end up calling. Now I'm not saying all code ends up the same but eventually you have to have all code call the same functions for the cpu. It's like cars, well most cars. They all are designed differently but lets face it, the standard V (or even straight) engines work the same. You have to have the bare functions universal, well at least for now I'm pretty certain we have too. wink.gif I'm just correcting the idea that all code gets compiled the same. That's wrong, as there are many things that can alter.

Good explanation. I was just trying to keep it simple, as most people on OCN aren't programmers.
Foldatron
(17 items)
 
Mat
(10 items)
 
Work iMac
(9 items)
 
CPUMotherboardGraphicsGraphics
i7 950 EVGA x58 3-way SLI EVGA GTX 660ti GTX 275 
RAMHard DriveHard DriveHard Drive
3x2GB Corsair Dominator DDR3-1600 80GB Intel X25-M SSD 2TB WD Black 150GB WD Raptor 
Hard DriveOSMonitorKeyboard
2x 150GB WD V-raptor in RAID0 Win7 Home 64-bit OEM 55" LED 120hz 1080p Vizio MS Natural Ergonomic Keyboard 4000 
PowerCase
750W PC P&C Silencer CoolerMaster 690 
CPUGraphicsRAMHard Drive
Intel Core i5 2500S AMD 6770M 8GB (2x4GB) at 1333Mhz 1TB, 7200 rpm 
Optical DriveOSMonitorKeyboard
LG 8X Dual-Layer "SuperDrive" OS X Lion 27" iMac screen Mac wireless keyboard 
Mouse
Mac wireless mouse 
CPUGraphicsRAMHard Drive
i7-2600K AMD 6970M 1GB 16GB PC3-10600 DDR3 1TB 7200rpm 
Hard DriveOptical DriveOSMonitor
256GB SSD 8x DL "SuperDrive" OS X 10.7 Lion 27" 2560x1440 iMac display 
Monitor
27" Apple thunderbolt display 
  hide details  
Reply
Foldatron
(17 items)
 
Mat
(10 items)
 
Work iMac
(9 items)
 
CPUMotherboardGraphicsGraphics
i7 950 EVGA x58 3-way SLI EVGA GTX 660ti GTX 275 
RAMHard DriveHard DriveHard Drive
3x2GB Corsair Dominator DDR3-1600 80GB Intel X25-M SSD 2TB WD Black 150GB WD Raptor 
Hard DriveOSMonitorKeyboard
2x 150GB WD V-raptor in RAID0 Win7 Home 64-bit OEM 55" LED 120hz 1080p Vizio MS Natural Ergonomic Keyboard 4000 
PowerCase
750W PC P&C Silencer CoolerMaster 690 
CPUGraphicsRAMHard Drive
Intel Core i5 2500S AMD 6770M 8GB (2x4GB) at 1333Mhz 1TB, 7200 rpm 
Optical DriveOSMonitorKeyboard
LG 8X Dual-Layer "SuperDrive" OS X Lion 27" iMac screen Mac wireless keyboard 
Mouse
Mac wireless mouse 
CPUGraphicsRAMHard Drive
i7-2600K AMD 6970M 1GB 16GB PC3-10600 DDR3 1TB 7200rpm 
Hard DriveOptical DriveOSMonitor
256GB SSD 8x DL "SuperDrive" OS X 10.7 Lion 27" 2560x1440 iMac display 
Monitor
27" Apple thunderbolt display 
  hide details  
Reply
New Posts  All Forums:Forum Nav:
  Return Home
  Back to Forum: Hardware News
Overclock.net › Forums › Industry News › Hardware News › [GMANE] AMD Confirms CPU Bug