Follow Slashdot blog updates by subscribing to our blog RSS feed

 



Forgot your password?
typodupeerror

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:Uh, what? (Score 1) 89

by shaitand (#49185575) Attached to: Khronos Group Announces Vulkan To Compete Against DirectX 12
"Well... whatever. How things work in the real world is that the graphics driver generates code in the ISA of the GPU, which the GPU then executes.

We won't see LLVM-in-hardware, for the same reason we don't see Java-in-hardware. Software compilers work well, and allow for hardware that's aimed at being really fast, not at accepting some inappropriate ISA. Also, that hardware wouldn't play nice with other APIs like Direct3D."

If the ISA of the GPU is byte code what stops the Direct3D SDK from generating it? It is the byte code and not LLVM I'm suggesting be implemented in hardware. A common instruction set similar to x86 in CPU land and just like in that space it only exists as a public interface that is then translated into optimized intel or AMD underlying magic on the chip almost immediately.

Or rather, an API agnostic open specification byte code that all API's can target. The benefit is obvious, if intel, amd, and nvidia all implement native hardware support for a common instruction set it not only provides a compatibility blanket that dramatically simplifies building better API's but it also dramatically simplifies producing drivers for their hardware.

Comment: Re:Uh, what? (Score 1) 89

by shaitand (#49174589) Attached to: Khronos Group Announces Vulkan To Compete Against DirectX 12
"Especially since the bytecode is supposed to be hardware neutral, it is the compilation from bytecode that will have to do the aggresive optimizations to adapt to the target architecture."

This is a confusion in terms. Personally I blame Sun. An interpreter IS a form of compiler, it is the term used to refer compilation at run time. Which is exactly what happens here. That bytecode won't be interpreted or compiled before you open the game, therefore it is runtime compilation, therefore it is interpreting. JIT Compilation == Interpreted. The only difference between a compiler and an interpreter is when they perform compilation. What is happening here is the step happening in the sdk (compilation to bytecode) and the step happening in the graphics driver (bytecode, compiled at runtime aka interpreted, and then executed). Although both are technically compilation, classically you'd call one compilation due to all the work being done in advance and the other interpretation due to the work happening just before execution.

"building native execution of the bytecode would be fastest

Why not call this what it is? It's compilation."

I suppose if you are counting translating the machine code of the interpreter into logic gates and then physically building those gates on a wafer "compiling" that would be compilation.

As for hardware neutral, the api is a standard hardware neutral interface for developers. What difference does it make if the step which interprets the bytecode is executed as bare hardware or slower software? All software can be converted 1:1 to hardware. There are no optimizations which can be done here which wouldn't be comparable or even more efficient directly implemented in hardware. Initially it'd be a kludgy add on stealing chip die space (although not much in todays terms) but later the cards would be specifically designed to optimize the execution of that simple bytecode through the entire pipeline.

Comment: Re:Uh, what? (Score 1) 89

by shaitand (#49173627) Attached to: Khronos Group Announces Vulkan To Compete Against DirectX 12
"I can't tell if you're just being obtuse, but: the developer compiles shader language to bytecode, and the graphics driver compiles bytecode to GPU native-code. Both of these stages qualify as compilation. (They're both level-reducing language-transformations.)"

Let me put this another way. Byte code is machine code for an imaginary machine, GPU native code is machine code for an actual machine. There is no level reduction occurring when interpreting byte code, both are already machine code, there is a translation from one instruction set to another compatible instruction set. Interpreters are a form of compiler designed to run at runtime rather than well in advance, modern interpreters are JIT compilers. The JVM for instance is an interpreter.

If you start confusing the typical convention of referring to compiled vs interpreted with the fact that technically in all cases the things you are referring to are all compilers it gets confusing. There is greater specificity in saying that bytecode in this case is run through an interpreter and even more specificity in saying that the design of that interpreter is one of JIT compilation (although the term mostly exists as a form of geek marketing to avoid negative stigma of using the word interpret).

"building native execution of the bytecode would be fastest

Why not call this what it is? It's compilation."

I'm not avoiding calling the translation compilation, as I clarified above, this is runtime compilation aka interpretation. I'm proposing that it would be faster to make the imaginary machines instruction set the instruction set physically implemented on the chip. As an intermediate but still ridiculously fast step they could add a handful of gates and perform the translation on the chip. The compiler would then be part of the SDK rather than part of the driver and you'd have compile once run everywhere shader code with the ability to hand optimize available to every developer.

It represents an excellent bit of bait to eventually get all GPU's to implement a standards based shader instruction set, much like Intel and AMD both target the same cpu instruction set.

Comment: Re:Uh, what? (Score 0) 89

by shaitand (#49173355) Attached to: Khronos Group Announces Vulkan To Compete Against DirectX 12
"No. There's no way in hell that anyone's seriously suggesting running graphics code in an interpreter. Again, it will be compiled by the graphics driver. (We could call this 'JIT compilation', but this term doesn't seem to have caught on in the context of graphics.)"

JIT compilation, An interpreter is a run time compiler, nothing more, nothing less. JIT compilation is a form of interpretation. No modern interpreter sits and converts to native code line by line during execution, they COMPILE to native code at runtime and then execute that. The only performance benefit of compilation vs interpretation is start-up time once executing compiled code is not necessarily faster. The perl interpreter is a good example. People tend to suck at writing fast perl code but someone who actually understands the language can write a perl solution that will rival or beat a C implementation for most solutions. You can compile perl implementations to native binaries and the interpreter typically compiles to an intermediate byte code, you can compile to that byte code in advance as well and run that with the interpreter in the same way you run java byte code on it's interpreter aka the java virtual machine. The only reason we do the byte code thing at all is that it's a machine code for an imaginary machine that is extremely efficient to interpret.

"Why not call this what it is? It's compilation."

Bytecode is the native machine code language of an imaginary machine, when I say native execution I mean alter the GPU to speak that machine code as it's native instruction set... in the silicon.

An interpreter is a form of compiler that is runs at runtime rather than in advance, JIT compiler is a form of interpreter design, and cloud computing is just the current evolution of clustered computing plugged into an internet connection and clusters in turn are nothing more than the distributed computing platforms built before them. You can make up new words all day long but lets stop pretending these things are NEW are not just the progressive realization of computing concepts that were invented in the 50's. Now get off my lawn.

Comment: Re:Uh, what? (Score -1) 89

by shaitand (#49171587) Attached to: Khronos Group Announces Vulkan To Compete Against DirectX 12
" an LLVM-based bytecode for its shading language to remove the need for a compiler from the graphics drivers

This removes the need for a shader language parser in the graphics driver. It still needs a compiler, unless you think the GPU is going to natively execute the bytecode."

This would do exactly the opposite. You don't compile bytecode, you compile to byte code. The entire point is that byte code is interpreted at runtime. And GPU vendors could put this in the driver but yes, building native execution of the bytecode would be fastest. Vulkan would be the one to provide a compiler.

" If you remove the compiler from a modern GPU driver, then there's very little left..."

How is that a bad thing?

Comment: Re:Cool (Score 1) 225

by shaitand (#48963521) Attached to: Facebook Will Let You Flag Content As 'False'
When discussing biblical texts it is the word typically used to describe catholic priests translating and "correcting" texts while copying them.

For example, if the Church says Jesus was tried that is a fact and it is an error on the part of this Jewish historian who forgot to include it in this historical record. Therefore the priest will do his best to correct the error while preserving the integrity of the work. He'll integrate it in his best approximation of where it goes with minimal adjustment to the original and to preserve the original tone. This way it can be the best and most accurate history.

Comment: Re:Worst idea ever. (Well, one of them). (Score 1) 168

by shaitand (#48936139) Attached to: FDA Approves Implantable Vagus Nerve Disruptor For Weight Loss
"I don't think taxpayer money should be invested in large Phase III trials (which can cost almost $1 billion) when they have a pretty low chance of succeeding. Moreover, you really do need teams of people to be competitive in today's research world - I work in a lab in academia, and there's no way you could do much drug development all by yourself."

Which is why Pharma companies are all bankrupt? No part of what I proposed involved taxpayer money or prevented working in teams. What I proposed are loans from the federal reserve on the same terms they are given to banks. The fed does not loan out tax payer money to banks, it loans out shiny newly created money at ridiculously low rates. We have an inflationary fiat currency and it actually depends on us putting new currency into circulation. Traditionally the finance industry gets all the benefits from this system. Advanced technology and especially medicine is certainly at least one obvious alternative place we could inject this money which benefits everyone in the nation.

"You absolutely shouldn't be allowed to make something that's going to go into people in a lab like you described"

I didn't actually describe a lab. Maybe you are mentally projecting your own assumption of some sort of inferior facility? Last I checked there is nothing magical about the pharma corps that makes them more capable than anyone else.

"I'm also not sure what you have against profits in general. For-profit companies aren't inherently bad, and non-profits aren't inherently good."

In general I agree. I just don't think healthcare and medicine is an appropriate for-profit industry. The costs are the same whether for-profit or non-profit. Profit has to come from somewhere and in the case of healthcare the result is higher costs which means less people benefit from the care. A for profit has an interest in maximizing profit and you maximize profit by providing as little as possible for as much as possible. This isn't in the interest of our nation. We all benefit if the health industries provide as much as possible at the lowest cost possible.

I don't propose blocking the for profit drug industry. I propose they shouldn't be allowed to use infrastructure that exists to provide an alternative to them and tie up those resources just to increase their own profits. Non-profits and partnerships still allow for teams to group together in a more established structure and work and allow for those people to profit from that work in the form of salaries in the case of a non-profit and in the system I proposed all the net profit derived from the fruits of their labor.

Comment: Step it up (Score 1) 324

by shaitand (#48870581) Attached to: What Will Google Glass 2.0 Need To Actually Succeed?
No, don't discount the importance of lower pricing. Any lower pricing they'd feasibly offer would still be quite expensive.

I need use cases. I need killer apps. I need the flavor of killer apps that let me build customized functionality without actually having to build apps. Most essentially, I need to know nothing I look at goes to Google.

People unreasonably worry about glass wearers recording them. I'm far far more concerned about Google recording via glass. I'm worried about data mining, I'm worried about facial recognition. Imagine this day. Your workplace issues glass devices for everyone. You step outside the office to have a private conversation in the parking lot. You've been a good drone on paper and face to face but criticize your direct report to some of your peers during the conversation and admit your frustration. You indicate you might start looking for something else. The next day your boss who has been monitoring your feed thinks you are buried and finally wants you to train up someone to assist you. You think, omg, finally, recognition and with that you aren't so eager to bail. Just as your help gets up to speed and there is light at the end of the tunnel they find some unrelated excuse and can you because you've just trained your replacement.

Frankly, I wouldn't be any happier about the data being used to assist "law enforcement", "catch terrorists", allow parents to monitor and "protect" their children, or "catch cheating spouses" either. I certainly wouldn't be happy if my wife was feeling frisky in a dark corner on the boardwalk and some bored night shift admin at google captured the clip and uploaded it to the web either.

Comment: Re:Size (Score 1) 324

by shaitand (#48870479) Attached to: What Will Google Glass 2.0 Need To Actually Succeed?
"So, you have no issues with people recording you when you don't know about it?

You think is OK for some Glasshole to walk into a restaurant where you are enjoying a public yet private dinner with a friend, record it and put it up on the Intertubes?"

No, I'm not okay with it. But the restaurant is already recording me. The other patrons in the restaurant already have the capability to record me as well without it looking like they are doing anything more than playing with their phone. On top of that there are already glasses cams, lapel cams, hat cams, and pen cams to name a few.

Potentially, every person in the restaurant has that capability already and everyone at the table is likely carrying a device that can be used to record the conversation. Hell, there is a pretty good chance there is crap installed on your phone that gives your employer the ability to remotely activate the camera and microphone on YOUR phone to do the same and almost certainly apps you've voluntarily installed that carry those capabilities and probably even got you to click through an agreement giving them permission. The same with the camera and microphone on your company issued laptop as well.

At most google glass is giving someone a device that lets them flip on and point the camera a little more quickly when something interesting comes up to take a picture of. Otherwise, I don't see anything new here with glass vs cell phones and security cams. I also don't see glass users as somehow being more or less innately trustworthy than random staff and patrons at your restaurant or work place.

P.S. If you don't think your employer can/does do this, think again. They almost certainly do especially if a technology company. You can't actually trust any blocker that you install to prevent it but some of those blocker apps will monitor and detect when other apps grab your phone mic/cam and differentiate between the app simply securing the resource and actually activating it. You might be surprised.

Comment: Re:My political lea\nings (Score 1) 225

by shaitand (#48868513) Attached to: Facebook Will Let You Flag Content As 'False'
"Have you ever read the drivel from infowars and prisonplanet?"

No. And my comment shouldn't be taken as advocating anything from those sources.

"The fact that some conspiracies are real does not imply that all posited conspiracy theories are."

The fact that some conspiracies are not real does not imply that all posited conspiracy theories are not.

I'm not defending the particular flavor of nut job you are referencing. It is the phrase "paranoid conspiracy theorist" that triggers me. Pre-CIA disclosures, snowden, and wikileaks barrage educated individuals generally came from a number of assumptions about government conspiracies that resulted in immediately labeling anyone who speculated overt deception and/or conspiracy on the part of government/state/police sources as a paranoid conspiracy theorist. As a consequence, the only people who could safely advocate such opinions publicly WERE nut jobs. I've argued against this providing sane and rational skepticism prior to the aforementioned disclosures and leaks and advocate the same now.

When it comes to government and the global banking system an incredibly healthy portion of what was posited by nut jobs turned out to be true. Frankly, most of what has come out was actually probable if you were viewing those sources with appropriate skepticism in the first place.

Here is a conspiracy for you. I find it highly suspect that nut jobs are the only ones who posit overt deception on the part of government that are given significant media and television coverage. A great way to divert suspicion is to throw out a few foaming at the mouth lunatics and bury obvious suspicious elements within their drivel. Then associate anyone who repeats those suspicious elements with those lunatics. See any history channel show that eventually devolves into the ancient aliens guy. See opera episodes that put militia extremists on stage along side KKK members and neo-nazi's after waco.

Comment: Re:My political lea\nings (Score 1) 225

by shaitand (#48866557) Attached to: Facebook Will Let You Flag Content As 'False'
The government has admitted they were in fact behind the UFO sightings, area 51 is real, the NSA really is illegally reading all your communications without warrants, they really are backdooring all your software, the FBI really is intercepting cell communications in mass and says it doesn't need a warrant if the interception device is on public property, and the US really did have death squads killing civilians in Iraq and Afghanistan...

I didn't realize we still tied conspiracy theorist with paranoid anymore. For the most part, it's people who do so as a knee jerk reaction who have proven to be wrong.

Comment: Re:Not "like Slashdot" (Score 1) 225

by shaitand (#48866455) Attached to: Facebook Will Let You Flag Content As 'False'
"However once in a while a truly new piece of information may come out to inspire further investigation, and shouldn't be shut down so quickly because it doesn't immediately fit our world view."

While true, consider the forum. FB is a place for keeping in touch with friends and family not a news outlet.

core error - bus dumped

Working...