Intel's Haswell Architecture Analyzed: Building a New PC and a New Intel
by Anand Lal Shimpi on October 5, 2012 2:45 AM ESTTSX
Johan did a great job explaining Haswell's Transactional Synchronization eXtensions (TSX), so I won't go into as much depth here. The basic premise is simple, although the implementation is quite complex.
It's easy to demand well threaded applications from software vendors, but actually implementing code that scales well across unlimited threads isn't easy. Parallelizing truly independent tasks is the low hanging fruit, but it's the tasks that all access the same data structure that can create problems. With multiple cores accessing the same data structure, running independent of one another, there's the risk of two different cores writing to the same part of the same structure. Only one set of data can be right, but dealing with this concurrent access problem can get hairy.
The simplest way to deal with it is simply to lock the entire data structure as soon as one core starts accessing it and only allow that one core write access until it's done. Other cores are given access to the data structure, but serially, not in parallel to avoid any data integrity issues.
This is by far the easiest way to deal with the problem of multiple threads accessing the same data structure, however it also prevents any performance scaling across multiple threads/cores. As focused as Intel is on increasing single threaded performance, a lot of die area goes wasted if applications don't scale well with more cores.
Software developers can instead choose to implement more fine grained locking of data structures, however doing so obviously increases the complexity of their code.
Haswell's TSX instructions allow the developer to shift much of the complexity of managing locks to the CPU. Using the new Hardware Lock Elision and its XAQUIRE/XRELEASE instructions, Haswell developers can mark a section of code for transactional execution. Haswell will then execute the code as if no hardware locks were in place and if it completes without issues the CPU will commit all writes to memory and enjoy the performance benefits. If two or more threads attempt to write to the same area in memory, the process is aborted and code re-executed traditionally with locks. The XAQUIRE/XRELEASE instructions decode to no-ops on earlier architectures so backwards compatibility isn't a problem.
Like most new instructions, it's going to take a while for Haswell's TSX to take off as we'll need to see significant adoption of Haswell platforms as well as developers embracing the new instructions. TSX does stand to show improvements in performance anywhere from client to server performance if implemented however, this is definitely one to watch for and be excited about.
Haswell also continues improvements in virtualization performance, including big decreases to guest/host transition times.
245 Comments
View All Comments
Spunjji - Thursday, October 18, 2012 - link
Fuckwit.nirmalv - Sunday, October 7, 2012 - link
Anandtech being a hardware site,its more inclined to keenly flow hardware devices with new architecture and innovations. iphone brings in1, A new A7 chip design and a novel 3 core graphics core
2, A new 3 microphone parabolic sound receiving design(which likely will become the new standard)
3, A new sim tray design(which will also likely become the new standard)
4, New sony BSI stacked sensor (the 13 mpx version will likely be the rage next year).
5, The first time that we have a 32 nm LTE chip which will give all day usage.
6, New thinner screen with incorporated touch panel and 100 % RGB
I am not sure about samsung but can anyone enlighten me about S3's technical achievements?
nirmalv - Sunday, October 7, 2012 - link
Sorry make that a 28 nm LTE basebandcenthar - Sunday, October 7, 2012 - link
99.998% of iPhone users just don't care about that. Really they don't.Geeks like me who do, are too damn smart to sell our souls to the such a god damned, locked down and closed system to even bother to care.
Magik_Breezy - Sunday, October 14, 2012 - link
2nd thatSpunjji - Thursday, October 18, 2012 - link
3rdCaptainDoug - Tuesday, October 23, 2012 - link
4th,solipsism - Tuesday, October 9, 2012 - link
Of course a company that releases one device per product category per year as well as one with the greatest mindshare is going to have more articles.But what happens when you add up all Samsung phones against all Apple phones in a given year?
What happens when you don't count the small blogs that only detail a small aspect of a secretive product but count the total words to get a better feel for the effort spent per company's market segment?
I bet you'll find that AT spends a lot more time covering Samsung's phones than Apple's.
Spunjji - Thursday, October 18, 2012 - link
This. I generally trust their editorial, but the focus on Apple prevails. One just has to read accordingly.Kepe - Friday, October 5, 2012 - link
Also look at any other Apple product review. They are all ridiculously in-depth with analysis about almost every single component in the product. Macbook Pro with Retina Display got 18 pages, the 3rd gen iPad got 21 pages. Don't get me wrong, I like a proper review with everything analyzed, but it's only the Apple products that get these huge reviews. But compared to those massive Apple reviews, it's like all other products are just glanced over in a hurry. The new Razer Blade got 9 pages. Asus Transformer Pad Infinity got 8 pages.