Intel Core i7 3960X (Sandy Bridge E) Review: Keeping the High End Alive
by Anand Lal Shimpi on November 14, 2011 3:01 AM EST- Posted in
- CPUs
- Intel
- Core i7
- Sandy Bridge
- Sandy Bridge E
The Test
To keep the review length manageable we're presenting a subset of our results here. For all benchmark results and even more comparisons be sure to use our performance comparison tool: Bench.
| Motherboard: |
ASUS P8Z68-V Pro (Intel Z68) ASUS Crosshair V Formula (AMD 990FX) Intel DX79SI (Intel X79) |
| Hard Disk: |
Intel X25-M SSD (80GB) Crucial RealSSD C300 |
| Memory: | 4 x 4GB G.Skill Ripjaws X DDR3-1600 9-9-9-20 |
| Video Card: | ATI Radeon HD 5870 (Windows 7) |
| Video Drivers: | AMD Catalyst 11.10 Beta (Windows 7) |
| Desktop Resolution: | 1920 x 1200 |
| OS: | Windows 7 x64 |
Cache and Memory Bandwidth Performance
The biggest changes from the original Sandy Bridge are the increased L3 cache size and the quad-channel memory interface. We'll first look at the impact a 15MB L3 has on latency:
| Cache/Memory Latency Comparison | ||||||
| L1 | L2 | L3 | Main Memory | |||
| AMD FX-8150 (3.6GHz) | 4 | 21 | 65 | 195 | ||
| AMD Phenom II X4 975 BE (3.6GHz) | 3 | 15 | 59 | 182 | ||
| AMD Phenom II X6 1100T (3.3GHz) | 3 | 14 | 55 | 157 | ||
| Intel Core i5 2500K (3.3GHz) | 4 | 11 | 25 | 148 | ||
| Intel Core i7 3960X (3.3GHz) | 4 | 11 | 30 | 167 | ||
Cachemem shows us a 5 cycle increase in latency. Hits in L3 can take 20% longer to get to the core that requested the data, if this is correct. For small, lightly threaded applications, you may see a slight regression in performance compared to Sandy Bridge. More likely than not however, the ~2 - 2.5x increase in L3 cache size will more than make up for the added latency. Also note that despite the large cache and thanks to its ring bus, Sandy Bridge E's L3 is still lower latency than Gulftown's.
| Memory Bandwidth Comparison - Sandra 2012.01.18.10 | |||||
| Intel Core i7 3960X (Quad Channel, DDR3-1600) | Intel Core i7 2600K (Dual Channel, DDR3-1600) | Intel Core i7 990X (Triple Channel, DDR3-1333) | |||
| Aggregate Memory Bandwidth | 37.0 GB/s | 21.2 GB/s | 19.9 GB/s | ||
Memory bandwidth is also up significantly. Populating all four channels with DDR3-1600 memory, Sandy Bridge E delivered 37GB/s of bandwidth in Sandra's memory bandwidth test. Given the 51GB/s theoretical max of this configuration and a fairly standard 20% overhead, 37GB/s is just about what we want to see here.
Facebook
Twitter
RSS
163 Comments
View All Comments
Hauk - Monday, November 14, 2011 - link
Was hoping to get 40 PCI-E lanes & 2600K performance for $300.. craptastic that they delay the 3820 till next year. Can't wait any longer, 2600K it is..medi01 - Monday, November 14, 2011 - link
Hi,why don't we see AMD cpu pricing along Intel CPU pricing?
g00ey - Monday, November 14, 2011 - link
I think it is false advertising to call the Bulldozer 8C an eight core CPU. It doesn't really have eight cores, it's actually only four cores where they have added an extra ALU inside each core. It's like doubling the core count of the i7s because of the hyperthreading (SMT) feature. The addition of ALUs is nothing but an enhanced version of hyperthreading so a Bulldozer 8C is only 4 cores, 6C is only 3 cores and 4C is only 2 cores.But AMD say; No No No, there are two computation CORES inside each MODULE.
What a BIG WAD of *BULLSHIT*!!!!!!!!!!!!!!!!!!!!!!!!!!!!
They should be thrown into jail for such fraudulent statements!!!
raddude9 - Monday, November 14, 2011 - link
Nope Mr. Troll.Bulldozer 8C can run 8 threads simultaneously. Sandy Bridge E with it's 6 multi-threaded cores can only run 6 threads at the same time, the other 6 threads have to wait.
BSMonitor - Monday, November 14, 2011 - link
Actually you are completely wrong.Hyperthreading actually allows 12 threads to fully utilize the resources of a 6 core processor.
Whereby, Bulldozer simply has double the Integer hardware. Allowing it to run 8 integer threads simulateously. So long as there are that many consecutive integer computations in a row on each thread. Beware when floating point threads start to appear. And then it crawls back to 4 cores.
raddude9 - Monday, November 14, 2011 - link
What did I say that is wrong?Hyperthreading means that each core holds the state of 2 threads. Only one thread can run at a time, usually when one thread stalls, the other thread can kick in. So, at best it can run 6 threads at once, the 6 hyperthreaded threads are waiting in the backround for their chance. But it still just runs 6 threads at once.
You are trying to mislead people with your mis-information on the Bulldozer Floating Point unit. It's FPU can run as either two independent 128bit FPUs or a single 256bit FPU. So it can run two independent Floating Point instructions at once. So, Regardless of whether Bulldozer is running Floating Point or Integer instructions, it can still run 8 threads at once.
LittleMic - Tuesday, November 15, 2011 - link
You are wrong because you are describing T1000 and T2000 CPU and not Intel with HT. Sun processor are indeed hiding memory access latency this way.Intel processors are actually scheduling micro instruction from both threads according to execution resources availabitity. It is quite old technology now so the white papers have disappeared from Intel web site, but if you have a look at
http://en.wikipedia.org/wiki/Hyper-threading
the picture on the right clearly shows that a pipeline stage can contain µ instructions coming from 2 threads
LittleMic - Tuesday, November 15, 2011 - link
No edit...Finally found "official" paper directly from Intel :
http://download.intel.com/technology/itj/2002/volu...
Have a look at page 10 that shows that all the pipeline contains instructions from both threads simultanously.
Lord 666 - Monday, November 14, 2011 - link
Anand,Have read mixed information on the release date for the 26xx series Xeons with respect to release date and architecture. Actually holding off a much needed server because have read either December or Jan.
With the socket the same, is the reviewed SB-E the same design as the new Xeons? Will there be 3D design like Ivy Bridge?
Thanks - Loyal reader for over 7 years
mwarner1 - Monday, November 14, 2011 - link
I am impressed by how much memory you had in your 386SX! My first (IBM compatible) PC was a 486DX2-50 I bought for my Software Engineering degree and it only had 4MB. This was pretty much standard for the time.