Opening the Kimono: Intel Details Nehalem and Tempts with Larrabeeby Anand Lal Shimpi on March 17, 2008 5:00 PM EST
- Posted in
Nehalem supports QPI and features an integrated memory controller, as well as a large, shared, inclusive L3 cache.
Nehalem is a modular architecture, allowing Intel to ship configurations with 2 - 8 cores, some may have integrated graphics and with various memory controller configurations.
Nehalem allows for 33% more micro-ops in flight compared to Penryn (128 micro-ops vs. 96 in Penryn), this increase was achieved by simply increasing the size of the re-order window and other such buffers throughout the pipeline.
With more micro-ops in flight, Nehalem can extract greater instruction level parallelism (ILP) as well as support an increase in micro-ops thanks to each core now handling micro-ops from two threads at once.
Despite the increase in ability to support more micro-ops in flight, there have been no significant changes to the decoder or front end of Nehalem. Nehalem is still fundamentally the same 4-issue design we saw introduced with the first Core 2 microprocessors. The next time we'll see a re-evaluation of this front end will most likely be 2 years from now with the 32nm "tock" processor, codenamed Sandy Bridge.
Nehalem also improved unaligned cache access performance. In SSE there are two types of instructions: one if your data is aligned to a 16-byte cache boundary, and one if your data is unaligned. In current Core 2 based processors, the aligned instructions could execute faster than the unaligned instructions. Every now and then a compiler would produce code that used an unaligned instruction on data that was aligned with a cache boundary, resulting in a performance penalty. Nehalem fixes this case (through some circuit tricks) where unaligned instructions running on aligned data are now fast.
In many applications (e.g. video encoding) you're walking through bytes of data through a stream. If you happen to cross a cache line boundary (64-byte lines) and an instruction needs data from both sides of that boundary you encounter a latency penalty for the unaligned cache access. Nehalem significantly reduces this latency penalty, so algorithms for things like motion estimation will be sped up significantly (hence the improvement in video encode performance).
Nehalem also introduces a second level branch predictor per core. This new branch predictor augments the normal one that sits in the processor pipeline and aids it much like a L2 cache works with a L1 cache. The second level predictor has a much larger set of history data it can use to predict branches, but since its branch history table is much larger, this predictor is much slower. The first level predictor works as it always has, predicting branches as best as it can, but simultaneously the new second level predictor will also be evaluating branches. There may be cases where the first level predictor makes a prediction based on the type of branch but doesn't really have the historical data to make a highly accurate prediction, but the second level predictor can. Since it (the 2nd level predictor) has a larger history window to predict from, it has higher accuracy and can, on the fly, help catch mispredicts and correct them before a significant penalty is incurred.
The renamed return stack buffer is also a very important enhancement to Nehalem. Mispredicts in the pipeline can result in incorrect data being populated into Penryn's return stack (a data structure that keeps track of where in memory the CPU should begin executing after working on a function). A return stack with renaming support prevents corruption in the stack, so as long as the calls/returns are properly paired you'll always get the right data out of Nehalem's stack even in the event of a mispredict.
Post Your CommentPlease log in or sign up to comment.
View All Comments
dreddly - Monday, March 17, 2008 - linkAm I the only one who finds this headline offensive to women? Japan's gender relations are bad enough without another western male-dominated site using the sexualized asian women as a standard trope to talk about 'exposing' new information.
AcaClone - Tuesday, March 18, 2008 - linkWow, I am really impressed how easy some people get offended - but then I am Danish ;-)
However, your state of mind is entirely ungrounded and based on a lacking understanding of Japan - some people might get offended by such lacking knowledge about cultures. Kimonos are worn by BOTH sexes - I know for sure, as I have worn one often both when visiting and working in Japan.
dreddly - Tuesday, March 18, 2008 - linkSo would 'Up the skirt' be an equally appropriate headline?
Skirts and kilts are also worn by men, so if the image was replaced by a man in a skirt and 'Up the skirt' was the headline would it still be appropriate?
The point is that the headline and the image have nothing whatsoever to do with the accompanying article.
It is inappropriate on a technology site to equate the release of a new processor with the exposure of a asian women's body (would the reference be as titillating if it was an white north american woman?). If this was maxim, this would be a different story, but there is a long history of western society stereotyping asian women as submissive sexualized objects, that this headline yet again reproduces.
masher2 - Tuesday, March 18, 2008 - link> "would the reference be as titillating if it was an white north american woman?"
Would you be as offended if it were? As for your nonsense about the headline "stereotyping asian women as submissive sex objects", sounds like you have too much time on your hands to me.
The world has *real* problems. This isn't one of them. Men like women...so what? Go to any beach in the world and you'll see women intentionally exposing far more than this picture...or was suggested by the headline.
dreddly - Tuesday, March 18, 2008 - link> Would you be as offended if it were? As for your nonsense about the headline "stereotyping asian women as submissive sex objects", sounds like you have too much time on your hands to me.
My point was that the absurdity and offense would be doubly obvious. The rest of your point was a non-sequitur.
>The world has *real* problems. This isn't one of them. Men like women...so what? Go to any beach in the world and you'll see women intentionally exposing far more than this picture...or was suggested by the headline.
Then why wasn't the picture one of women on a beach - or any instance where a woman was obviously choosing to disrobe? The point is that this type of thinking breeds environments that are hostile and objectifying to women. I hope that your organization doesn't run into any litigious women down the road, because this type of thinking breeds situations ripe for lawsuits. If that isn't a 'real problem' for you, you must be better off than most...
masher2 - Wednesday, March 19, 2008 - link> "The point is that this type of thinking breeds environments that are hostile and objectifying to women"
Ah, so now a picture of a woman in a kimono is now responsible for causing rape and abuse of women? Thank god you're not a member of the movie censorship board, or we'd all be watching nothing but reruns of "Lassie" and 'The Ghost and Mr. Chicken".
> "Then why wasn't the picture one of women on a beach - or any instance where a woman was obviously choosing to disrobe?"
You believe the woman in that picture was kidnapped and forced to wear that kimono? I see, I see...interesting theory!
dreddly - Wednesday, March 19, 2008 - linkPerhaps more disturbing is the fact that you think 'hostility and objectification' EQUALS rape and abuse. I made no such implication, and you seem to be exposing a hostility towards women of your own in such a statement.
The image is irrelevant and immaterial to the article. It should be removed at that basis.
The woman on the beach would be choosing an objectification of her body. The image of the woman in the Kimono was making no such implication, and it was the accompanying headline that insinuated that idea.
If there were no other undertones, then we should all agree that a man wearing a kilt (lets say Gibson from Braveheart) could be pictured with the headline 'Up the skirt' and it would be interpreted the same way.
masher2 - Wednesday, March 19, 2008 - link> The woman on the beach would be choosing an objectification of her body. The image of the woman in the Kimono was making no such implication"
The woman in the photo chose to have her picture taken. Or are you again reverting to the wild idea she was somehow forced against her will to model?
> "The image is irrelevant and immaterial to the article"
It's a metaphor, equating Intel's openness to the intimacy generated during a sexual encounter. Get it? A valid literary technique, sadly misinterpreted by a few priggish bible-thumper wannabees.
> "you seem to be exposing a hostility towards women of your own in such a statement. "
You're seriously reaching with such nonsense.
jasongg06 - Wednesday, March 19, 2008 - link"The woman in the photo chose to have her picture taken. Or are you again reverting to the wild idea she was somehow forced against her will to model? "
The woman may have had her photo taken, but do you honestly thing it was for this article?
"It's a metaphor, equating Intel's openness to the intimacy generated during a sexual encounter. Get it? A valid literary technique, sadly misinterpreted by a few priggish bible-thumper wannabees. "
The metaphor/analogy or w/e you want to call it, was made with bad judgment and is inappropriate. Why you're still defending it, I don't know, but you should seek some help. The fact that you think stuff like this is acceptable tells us something about your character, or your lack of.
masher2 - Wednesday, March 19, 2008 - linkBut no one here has successfully advanced any argument as to *why* you believe this is objectionable. Except for a few vague mutterings about "objectification" which are wholly unconvincing,
Yes, the headline subtly interjected sex into the article context. Was it "tasteless"? I won't offer an opinion, but it certainly was not "insulting to women" -- or even worse, "all Asians". In fact, I find a comment singling out a certain race to be racist in itself.
As for my personal views on the subject, they correspond perfectly with those of feminist Camile Paglia, a woman whose been called 'the Smartest Woman in America'. Most men enjoy sex. A slightly smaller percentage of women do as well. Using a sexual metaphor to sell a story isn't in itself "objectifying" women. I saw nothing in the headline which "perpetuated any stereotypes" of submission, dominance, or sexual exploitation.
> "The woman may have had her photo taken, but do you honestly thing it was for this article? "
Why do you think it would even matter?