Please create an account to participate in the Slashdot moderation system


Forgot your password?

Slashdot videos: Now with more Slashdot!

  • View

  • Discuss

  • Share

We've improved Slashdot's video section; now you can view our video interviews, product close-ups and site visits with all the usual Slashdot options to comment, share, etc. No more walled garden! It's a work in progress -- we hope you'll check it out (Learn more about the recent updates).


Comment: Re:Wow (Score 1) 223

by warrior (#41513527) Attached to: AMD Trinity APUs Stack Up Well To Intel's Core 3
Just curious, I'm an engineer at AMD, albeit on the CPU cores/cache memory side. I work on the transistors, so I can't really comment on our GPU drivers (although I work with the GPU team from time to time as there is some commonality between CPU cache memory design and GPU shader memories, so I can vouch for the hardware being excellent, at least the SRAM). I use the AMD binary drivers under linux and they're rock solid. I wonder if the issues are specific to DirectX?

Comment: This is about energy efficiency, not GHz (Score 1) 286

by warrior (#39187055) Attached to: AMD's Piledriver To Hit 4GHz+ With Resonant Clock Mesh
Too bad the article is lacking on the technical details. This is about energy efficiency, not GHz. They have hit 4GHz and higher with a traditional clock mesh. The point here is that they hit 4GHz with a resonant clock mesh. What this means is that instead of charging and discharging the huge capacitor that is the clock grid every cycle using only FETs connected to VDD and VSS (traditional digital logic), there is an LC tank circuit that is resonating with the clock grid. The power rails still do some of the charging and discharging of the grid, but now some of the energy comes from the oscillator. I have seen the paper, the distributed LC tank is pretty cool. The technical achievement is that they got this to run at 4GHz while keeping the skew between clock grid points as low as a traditional mesh (had the skew increased, the max frequency of the processor would go down). They claim reduced clock power of 25%. Given that clock power is roughly half the power of a core, that's a 12% power reduction overall, pretty impressive. It's also really cool that the whole thing is on-die - they made the inductors out of back-end wires on the CPU die itself, no additional components on the package so no increased cost.

Comment: Re:Reading List (Score 2) 446

by warrior (#38893353) Attached to: Ask Slashdot: Transitioning From 'Hacker' To 'Engineer'?
I would also add "The Art of UNIX Programming" to that list. This book isn't just about programming in UNIX. It is more about the philosophy behind UNIX, which in turn describes properties of any sustainable software system.

It can be found online here:

One of my favorite parts is on transparency and discoverability:

17% Smaller DES S-box Circuits Found 45

Posted by Soulskill
from the still-bigger-than-a-breadbox dept.
solardiz writes "DES is still in use, brute-force key search remains the most effective attack on it, and it is an attractive building block for certain applications (the key size may be increased e.g. with 3DES). Openwall researchers, with funding from Rapid7, came up with 17% shorter Boolean expressions representing the DES S-boxes. Openwall's John the Ripper 1.7.8 tests over 20 million combinations against DES-based crypt(3) per second on a Core i7-2600K 3.4 GHz, which roughly corresponds to a DES encryption speed of 33 Gbps."

Comment: Re:Processor use (Score 1) 129

by warrior (#35068590) Attached to: Julia Meets HTML5
Exactly. This is why the "application" is a bad idea. I understand the goal of moving "heavy lifting" to the cloud and having "thin" clients. However, it appears that the "thin" client envisioned here is a machine that parses and interprets lots and lots of text. It's so inefficient and wasteful. As a hardware designer, we keep making mobile devices more powerful and energy efficient all so lazy programmers can throw steaming piles of crap onto the devices. It's a hack on top of a hack on top of a hack. Some sort of binary protocol where minimal bytes are passed between server and client is needed here.

Comment: Re:He's right (Score 1) 357

by warrior (#32903560) Attached to: SugarCRM 6 Released, But Is It Open Source?
You are free to do that. Some, such as corporate customers or those just concerned about security, may want the original binaries as compiled by the company that is selling them. As snowgirl pointed out, you are not free to take those binaries and redistribute them at will.

I like this. This is the type of open source business model that I think a lot of people have been looking for. We want our software to be open. We also want to feed ourselves and our families.

"Pay no attention to the man behind the curtain." -- The Wizard Of Oz