texas multicore technologies revisted.

[ric 1]

I brought this up 2 years ago but it was dismissed as "middleware"...but unless BIS is writing a whole new engine from scratch perhaps it is time to rethink this course.

Best of all, SequenceL is built upon open industry standards to work with your existing methodology, training, and tools. Industry standard parallelized C++ and OpenCL output leverages all these investments while providing an easy, low risk path to modernize portions of existing programs. This also makes it quick and easy to explore if your algorithms can benefit from (GP)GPU acceleration without learning special low-level GPU languages like CUDA or OpenCL.

http://www.texasmulticoretechnologies.com/technology/sequenceL/

[Fushko 60]

"Not only does SequenceL give faster performance on multicore systems, it delivers dramatically faster time-to-market; it is typically >10X faster to write good code in SequenceL than traditional C++, Java, C#, Fortran, etc. "

Seems interesting.

[chortles 263]

So how much are they willing to work to make a single-threaded game less so?

[killzone_kid 1326]

...but unless BIS is writing a whole new engine from scratch

Does Enfusion count?

[ric 1]

Does Enfusion count?

unless the core of the engine has been gutted and written in some useful form of parallelization then the answer is no, it will suffer the same lack of ability to truly harness multi core CPU's

[chortles 263]

unless the core of the engine has been gutted and written in some useful form of parallelization then the answer is no, it will suffer the same lack of ability to truly harness multi core CPU's

Mind you, if he meant the DayZ standalone engine then no, there's no reason to expect it (as a Real Virtuality derivative that seemingly got pushed out the door) to be different in this respect -- a better question would be hope much so is the Take On Mars engine? Because that's where Bohemia is headed with the engine merge...