Yesterday EE Times posted some interesting information that they had gleaned at ISSCC. AMD released a paper describing the design process and advances they were able to achieve with the Zen architecture manufactured on Samsung’s/GF’s 14nm FinFETT process. AMD went over some of the basic measurements at the transistor scale and how it compares to what Intel currently has on their latest 14nm process.
The first thing that jumps out is that AMD claimes that their 4 core/8 thread x86 core is about 10% smaller than what Intel has with one of their latest CPUs. We assume it is either Kaby Lake or Skylake. AMD did not exactly go over exactly what they were counting when looking at the cores because there are some significant differences between the two architectures. We are not sure if that 44mm sq. figure includes the L3 cache or the L2 caches. My guess is that it probably includes L2 cache but not L3. I could be easily wrong here.
Going down the table we see that AMD and Samsung/GF are able to get their SRAM sizes down smaller than what Intel is able to do. AMD has double the amount of L2 cache per core, but it is only about 60% larger than Intel’s 256 KB L2. AMD also has a much smaller L3 cache as well than Intel. Both are 8 MB units but AMD comes in at 16 mm sq. while Intel is at 19.1 mm sq. There will be differences in how AMD and Intel set up these caches, and until we see L3 performance comparisons we cannot assume too much.
(Image courtesy of ISSCC)
In some of the basic measurements of the different processes we see that Intel has advantages throughout. This is not surprising as Intel has been well known to push process technology beyond what others are able to do. In theory their products will have denser logic throughout, including the SRAM cells. When looking at this information we wonder how AMD has been able to make their cores and caches smaller. Part of that is due to the likely setup of cache control and access.
One of the most likely culprits of this smaller size is that the less advanced FPU/SSE/AVX units that AMD has in Zen. They support AVX-256, but it has to be done in double the cycles. They can do single cycle AVX-128, but Intel’s throughput is much higher than what AMD can achieve. AVX is not the end-all, be-all but it is gaining in importance in high performance computing and editing applications. David Kanter in his article covering the architecture explicitly said that AMD made this decision to lower the die size and power constraints for this product.
Ryzen will undoubtedly be a pretty large chip overall once both modules and 16 MB of L3 cache are put together. My guess would be in the 220 mm sq. range, but again that is only a guess once all is said and done (northbridge, southbridge, PCI-E controllers, etc.). What is perhaps most interesting of it all is that AMD has a part that on the surface is very close to the Broadwell-E based Intel i7 chips. The i7-6900K runs at 3.2 to 3.7 GHz, features 8 cores and 16 threads, and around 20 MB of L2/L3 cache. AMD’s top end looks to run at 3.6 GHz, features the same number of cores and threads, and has 20 MB of L2/L3 cache. The Intel part is rated at 140 watts TDP while the AMD part will have a max of 95 watts TDP.
If Ryzen is truly competitive in this top end space (with a price to undercut Intel, yet not destroy their own margins) then AMD is going to be in a good position for the rest of this year. We will find out exactly what is coming our way next month, but all indications point to Ryzen being competitive in overall performance while being able to undercut Intel in TDPs for comparable cores/threads. We are counting down the days…