13.04.2015., 00:08
			
							
		 | 
		
			 
			#1057
			
		 | 
	
	| 
			
			
			
			 Premium 
			
			
			
			
			
			
			
			
				
			
			
			
				 
				Datum registracije: Jul 2012 
				Lokacija: vk+ 
				
				
					Postovi: 14,584
				 
				
				
				
				
				     
			 					
		
	 | 
	
	
	
		
		
		
		
		
		
                Je spominjalo se od starta. 
Jedna od starijih vijesti
 
Kitguru:
 
	Citiraj: 
	
	
		| 
			
				The only thing currently known about AMD’s Zen is that it will drop  clustered multi-thread (CMT) design in favour of more traditional  simultaneous multi-threaded (SMT) design. This may result in decrease of  the amount of cores inside AMD’s processors, but will increase their  efficiency.
			
		 | 
	 
	 
 
	Citiraj: 
	
	
		
			
				But if the initial rumors  are anything to go by then Zen will likely adopt an SMT style  microarchitecture which indicates that it’s quite a large core since SMT  (Simultaneous multithreading)  is usually leveraged in large CPU cores to opportunistically take  advantage of the various resources in the core and dedicate it to an  additional execution thread for added throughput. 
This adds to the area efficiency of the core design and reduces the  effect of stalls and pipeline back pressure leading to improved resource  utilization inside the core which in turn improves overall performance.
			
		 | 
	 
	 
 
	Citiraj: 
	
	
		
			
				SMT is not a new technology, but it is an approach  AMD has been reluctant to use, as opposed to the Cluster Multithreading  from Bulldozer (CMT for short). 
 In CMT, a unified front end sends instructions to  two separate integer pipelines, so that the benefits of having two full  integer pipelines would be gained while also saving die space and power  draw. 
 SMT, or Hyper-Threading as Intel calls it, can  schedule and execute two different instructions in the same clock style.  CMT should have given AMD Bulldozer an advantage, but the chip's low  efficiency killed that possibility. 
 Using SMT in Zen (though perhaps not like in  Hyper-Threading) could be a saving grace if the underlying CPU  architecture is OK with a die size increase. 15-20% performance boosts  can be achieved, as Intel has revealed repeatedly.
			
		 | 
	 
	 
 
	Citiraj: 
	
	
		
			
				Opt for Simultaneous multithreading as opposed to Cluster Multithreading:  With Bulldozer, AMD opted for an arrangement called cluster  multi-threading, or CMT. This is the strategy used by Bulldozer, in  which a unified front end issues instructions to two separate integer  pipelines. The idea behind the Bulldozer design was that AMD would gain  the benefits of having two full integer pipelines but save die space and  power consumption compared to building a conventional multi-core  design. 
 
Intel, in contrast, has long  used simultaneous multithreading (SMT), which they call Hyper-Threading,   in which two instructions from different threads can be executed in  the same clock cycle. In theory, AMD’s design could have given it an  advantage, since each core contains a full set of execution units as  opposed to SMT, where those resources are shared, but in practice  Bulldozer’s low efficiency crippled its scaling. 
The  rumor now is that AMD will include an SMT-style design with Zen. It’s  entirely possible that the company will do this — Hyper-Threading is one  example of SMT, but it’s not the only implementation — IBM,  for example, uses SMT extensively in its POWER architectures. The reason  I’m not willing to completely sign off on this rumor is that it’s a  rumor that’s dogged AMD literally since Intel introduced Hyper-Threading  15 years ago. 
 
The benefits of using SMT are  always dependent on the underlying CPU architecture, but Intel has  demonstrated that the technology is often good for a 15-20% performance  increase in exchange for a minimal die penalty. If AMD can achieve  similar results, the net effect will be quite positive.
			
		 | 
	 
	 
  
		
	
		
		
		
		
		
		
		
		
		
		
						  
				
				Zadnje izmijenjeno od: Manuel Calavera. 13.04.2015. u 00:32.
				
				
			
		
		
	
	 | 
	
		 
						
		
		
		
		 
	 | 
	
	
	
		
		
		
		
			 
		
		
		
		
		
		
			
		
		
		
	 |