"These new synchronization extensions are useful in shared-memory multithreaded applications that employ lock-based synchronization mechanisms. Thanks to TSX, specially written applications will run faster on multi-core/multi-threaded chips.
Intel TSX provides a set of instruction set extensions that allow programmers to specify regions of code for transactional synchronization. Programmers can use these extensions to achieve the performance of fine-grain locking while actually programming using coarse-grain locks. With transactional synchronization, the hardware can determine dynamically whether threads need to serialize through lock-protected critical sections, and perform serialization only when required. This lets the processor expose and exploit concurrency that would otherwise be hidden due to dynamically unnecessary synchronization."
Source: here
More: info
Will "Haswell" TSX instructions help chess program
Moderators: hgm, Rebel, chrisw
-
- Posts: 638
- Joined: Thu Aug 30, 2007 8:23 pm
- Location: San Juan, Puerto Rico
-
- Posts: 20943
- Joined: Mon Feb 27, 2006 7:30 pm
- Location: Birmingham, AL
Re: Will "Haswell" TSX instructions help chess pro
My initial thought is "no". Chess programs do not share memory in the same way as other types of computations. In fact, we have to avoid it because each thread needs its own board and stuff to conduct its own private search...tano-urayoan wrote:"These new synchronization extensions are useful in shared-memory multithreaded applications that employ lock-based synchronization mechanisms. Thanks to TSX, specially written applications will run faster on multi-core/multi-threaded chips.
Intel TSX provides a set of instruction set extensions that allow programmers to specify regions of code for transactional synchronization. Programmers can use these extensions to achieve the performance of fine-grain locking while actually programming using coarse-grain locks. With transactional synchronization, the hardware can determine dynamically whether threads need to serialize through lock-protected critical sections, and perform serialization only when required. This lets the processor expose and exploit concurrency that would otherwise be hidden due to dynamically unnecessary synchronization."
Source: here
More: info
It won't hurt, and might, on occasion, make something slightly more efficient. But no huge gain.